main: version 0.8.0

This should speed up testing.

.circleci/config.yml

@@ -44,20 +44,14 @@ commands:
     steps:
       - restore_cache:
           keys:
-            - llvm-source-8-v3
+            - llvm-source-8-v5
       - run:
           name: "Fetch LLVM source"
           command: make llvm-source
       - save_cache:
-          key: llvm-source-8-v3
+          key: llvm-source-8-v5
           paths:
-            - llvm
-  smoketest:
-    steps:
-      - run: make smoketest
-  smoketest-no-avr:
-    steps:
-      - run: make smoketest-no-avr
+            - llvm-project
   test-linux:
     steps:
       - checkout
@@ -67,18 +61,19 @@ commands:
       - install-node
       - restore_cache:
           keys:
-            - go-cache-{{ checksum "Gopkg.lock" }}-{{ .Environment.CIRCLE_PREVIOUS_BUILD_NUM }}
-            - go-cache-{{ checksum "Gopkg.lock" }}
+            - go-cache-v2-{{ checksum "go.mod" }}-{{ .Environment.CIRCLE_PREVIOUS_BUILD_NUM }}
+            - go-cache-v2-{{ checksum "go.mod" }}
       - llvm-source-linux
       - run: go install .
-      - run: go test -v
+      - run: go test -v ./transform .
       - run: make gen-device -j4
-      - smoketest
+      - run: make smoketest RISCV=0
       - save_cache:
-          key: go-cache-{{ checksum "Gopkg.lock" }}-{{ .Environment.CIRCLE_BUILD_NUM }}
+          key: go-cache-v2-{{ checksum "go.mod" }}-{{ .Environment.CIRCLE_BUILD_NUM }}
           paths:
             - ~/.cache/go-build
             - ~/.cache/tinygo
+            - /go/pkg/mod
       - run: make fmt-check
   build-linux:
     steps:
@@ -101,12 +96,12 @@ commands:
       - install-node
       - restore_cache:
           keys:
-            - go-cache-{{ checksum "Gopkg.lock" }}-{{ .Environment.CIRCLE_PREVIOUS_BUILD_NUM }}
-            - go-cache-{{ checksum "Gopkg.lock" }}
+            - go-cache-v2-{{ checksum "go.mod" }}-{{ .Environment.CIRCLE_PREVIOUS_BUILD_NUM }}
+            - go-cache-v2-{{ checksum "go.mod" }}
       - llvm-source-linux
       - restore_cache:
           keys:
-            - llvm-build-8-linux-v5
+            - llvm-build-8-linux-v7
       - run:
           name: "Build LLVM"
           command: |
@@ -124,7 +119,7 @@ commands:
               make llvm-build
             fi
       - save_cache:
-          key: llvm-build-8-linux-v5
+          key: llvm-build-8-linux-v7
           paths:
             llvm-build
       - run:
@@ -144,10 +139,11 @@ commands:
       - store_artifacts:
           path: /tmp/tinygo.linux-amd64.tar.gz
       - save_cache:
-          key: go-cache-{{ checksum "Gopkg.lock" }}-{{ .Environment.CIRCLE_BUILD_NUM }}
+          key: go-cache-v2-{{ checksum "go.mod" }}-{{ .Environment.CIRCLE_BUILD_NUM }}
           paths:
             - ~/.cache/go-build
             - ~/.cache/tinygo
+            - /go/pkg/mod
       - run:
           name: "Extract release tarball"
           command: |
@@ -155,7 +151,12 @@ commands:
             tar -C ~/lib -xf /tmp/tinygo.linux-amd64.tar.gz
             ln -s ~/lib/tinygo/bin/tinygo /go/bin/tinygo
             tinygo version
-      - smoketest
+      - run:
+          name: "Download SiFive GNU toolchain"
+          command: |
+            curl -O https://static.dev.sifive.com/dev-tools/riscv64-unknown-elf-gcc-8.2.0-2019.05.3-x86_64-linux-ubuntu14.tar.gz
+            sudo tar -C /usr/local --strip-components=1 -xf riscv64-unknown-elf-gcc-8.2.0-2019.05.3-x86_64-linux-ubuntu14.tar.gz
+      - run: make smoketest
   build-macos:
     steps:
       - checkout
@@ -169,17 +170,21 @@ commands:
             HOMEBREW_NO_AUTO_UPDATE=1 brew install qemu
       - restore_cache:
           keys:
-            - llvm-source-8-macos-v3
+            - go-cache-macos-v2-{{ checksum "go.mod" }}-{{ .Environment.CIRCLE_PREVIOUS_BUILD_NUM }}
+            - go-cache-macos-v2-{{ checksum "go.mod" }}
+      - restore_cache:
+          keys:
+            - llvm-source-8-macos-v5
       - run:
           name: "Fetch LLVM source"
           command: make llvm-source
       - save_cache:
-          key: llvm-source-8-macos-v3
+          key: llvm-source-8-macos-v5
           paths:
-            - llvm
+            - llvm-project
       - restore_cache:
           keys:
-            - llvm-build-8-macos-v4
+            - llvm-build-8-macos-v6
       - run:
           name: "Build LLVM"
           command: |
@@ -191,7 +196,7 @@ commands:
               make llvm-build
             fi
       - save_cache:
-          key: llvm-build-8-macos-v4
+          key: llvm-build-8-macos-v6
           paths:
             llvm-build
       - run:
@@ -215,23 +220,34 @@ commands:
             tar -C /usr/local/opt -xf /tmp/tinygo.darwin-amd64.tar.gz
             ln -s /usr/local/opt/tinygo/bin/tinygo /usr/local/bin/tinygo
             tinygo version
-      - smoketest-no-avr
+      - run:
+          name: "Download SiFive GNU toolchain"
+          command: |
+            curl -O https://static.dev.sifive.com/dev-tools/riscv64-unknown-elf-gcc-8.2.0-2019.05.3-x86_64-apple-darwin.tar.gz
+            sudo tar -C /usr/local --strip-components=1 -xf riscv64-unknown-elf-gcc-8.2.0-2019.05.3-x86_64-apple-darwin.tar.gz
+      - run: make smoketest AVR=0
+      - save_cache:
+          key: go-cache-macos-v2-{{ checksum "go.mod" }}-{{ .Environment.CIRCLE_BUILD_NUM }}
+          paths:
+            - ~/.cache/go-build
+            - ~/.cache/tinygo
+            - /go/pkg/mod
 
 
 jobs:
   test-llvm8-go111:
     docker:
-      - image: circleci/golang:1.11
+      - image: circleci/golang:1.11-stretch
     steps:
       - test-linux
   test-llvm8-go112:
     docker:
-      - image: circleci/golang:1.12
+      - image: circleci/golang:1.12-stretch
     steps:
       - test-linux
   build-linux:
     docker:
-      - image: circleci/golang:1.12
+      - image: circleci/golang:1.12-stretch
     steps:
       - build-linux
   build-macos:

.gitignore

@@ -5,10 +5,12 @@ src/device/avr/*.ld
 src/device/avr/*.s
 src/device/nrf/*.go
 src/device/nrf/*.s
-src/device/stm32/*.go
-src/device/stm32/*.s
 src/device/sam/*.go
 src/device/sam/*.s
+src/device/sifive/*.go
+src/device/sifive/*.s
+src/device/stm32/*.go
+src/device/stm32/*.s
 vendor
 llvm
 llvm-build

.gitmodules

@@ -9,7 +9,7 @@
 	url = https://github.com/avr-rust/avr-mcu.git
 [submodule "lib/cmsis-svd"]
 	path = lib/cmsis-svd
-	url = https://github.com/posborne/cmsis-svd
+	url = https://github.com/tinygo-org/cmsis-svd
 [submodule "lib/compiler-rt"]
 	path = lib/compiler-rt
 	url = https://github.com/llvm-mirror/compiler-rt.git

BUILDING.md

@@ -16,7 +16,6 @@ LLVM, Clang and LLD are quite light on dependencies, requiring only standard
 build tools to be built. Go is of course necessary to build TinyGo itself.
 
   * Go (1.11+)
-  * [dep](https://golang.github.io/dep/)
   * Standard build tools (gcc/clang)
   * git
   * CMake
@@ -27,16 +26,20 @@ on a different system like Mac.
 
 ## Download the source
 
-The first step is to download the TinyGo sources. Then, inside the directory,
-perform these steps:
+The first step is to download the TinyGo sources (use `--recursive` if you clone
+the git repository). Then, inside the directory, download the LLVM source:
 
-    dep ensure -vendor-only # download Go dependencies
-    make llvm-source        # download LLVM
+    make llvm-source
 
 You can also store LLVM outside of the TinyGo root directory by setting the
 `LLVM_BUILDDIR`, `CLANG_SRC` and `LLD_SRC` make variables, but that is not
 covered by this guide.
 
+TinyGo uses Go modules, so if you clone TinyGo inside your GOPATH (and are using
+Go below 1.13), make sure that Go modules are enabled:
+
+    export GO111MODULE=on
+
 ## Build LLVM, Clang, LLD
 
 Before starting the build, you may want to set the following environment

CHANGELOG.md

@@ -1,3 +1,99 @@
+0.8.0
+---
+* **command line**
+  - fix parsing of beta Go versions
+  - check the major/minor installed version of Go before compiling
+  - validate `-target` flag better to not panic on an invalid target
+* **compiler**
+  - implement full slice expression: `s[:2:4]`
+  - fix a crash when storing a linked list in an interface
+  - fix comparing struct types by making type IDs more unique
+  - fix some bugs in IR generation
+  - add support for linked lists in reflect data
+  - implement `[]rune` to string conversion
+  - implement support for `go` on func values
+* **standard library**
+  - `reflect`: add support for named types
+  - `reflect`: add support for `t.Bits()`
+  - `reflect`: add basic support for `t.AssignableTo()`
+  - `reflect`: implement `t.Align()`
+  - `reflect`: add support for struct types
+  - `reflect`: fix bug in `v.IsNil` and `v.Pointer` for addressable values
+  - `reflect`: implement support for array types
+  - `reflect`: implement `t.Comparable()`
+  - `runtime`: implement stack-based scheduler
+  - `runtime`: fix bug in the sleep queue of the scheduler
+  - `runtime`: implement `memcpy` for Cortex-M
+  - `testing`: implement stub `testing.B` struct
+  - `testing`: add common test logging methods such as Errorf/Fatalf/Printf
+* **targets**
+  - `386`: add support for linux/386 syscalls
+  - `atsamd21`: make SPI pins configurable so that multiple SPI ports can be
+    used
+  - `atsamd21`: correct issue with invalid first reading coming from ADC
+  - `atsamd21`: add support for reset-to-bootloader using 1200baud over USB-CDC
+  - `atsamd21`: make pin selection more flexible for peripherals
+  - `atsamd21`: fix minimum delay in `time.Sleep`
+  - `atsamd51`: fix minimum delay in `time.Sleep`
+  - `nrf`: improve SPI write-only speed, by making use of double buffering
+  - `stm32f103`: fix SPI frequency selection
+  - `stm32f103`: add machine.Pin.Get method for reading GPIO values
+  - `stm32f103`: allow board specific UART usage
+  - `nucleo-f103rb`: add support for NUCLEO-F103RB board
+  - `itsybitsy-m4`: add support for this board with a SAMD51 family chip
+  - `cortex-m`: add support for `arm.SystemReset()`
+  - `gameboy-advance`: add initial support for the GameBoy Advance
+  - `wasm`: add `//go:wasm-module` magic comment to set the wasm module name
+  - `wasm`: add syscall/js.valueSetIndex support
+  - `wasm`: add syscall/js.valueInvoke support
+
+0.7.1
+---
+* **targets**
+  - `atsamd21`: add support for the `-port` flag in the flash subcommand
+
+0.7.0
+---
+* **command line**
+  - try more locations to find Clang built-in headers
+  - add support for `tinygo test`
+  - build current directory if no package is specified
+  - support custom .json target spec with `-target` flag
+  - use zversion.go to detect version of GOROOT version
+  - make initial heap size configurable for some targets (currently WebAssembly
+    only)
+* **cgo**
+  - add support for bitfields using generated getters and setters
+  - add support for anonymous structs
+* **compiler**
+  - show an error instead of panicking on duplicate function definitions
+  - allow packages like github.com/tinygo-org/tinygo/src/\* by aliasing it
+  - remove `//go:volatile` support  
+    It has been replaced with the runtime/volatile package.
+  - allow poiners in map keys
+  - support non-constant syscall numbers
+  - implement non-blocking selects
+  - add support for the `-tags` flag
+  - add support for `string` to `[]rune` conversion
+  - implement a portable conservative garbage collector (with support for wasm)
+  - add the `//go:noinline` pragma
+* **standard library**
+  - `os`: add `os.Exit` and `syscall.Exit`
+  - `os`: add several stubs
+  - `runtime`: fix heap corruption in conservative GC
+  - `runtime`: add support for math intrinsics where supported, massively
+    speeding up some benchmarks
+  - `testing`: add basic support for testing
+* **targets**
+  - add support for a generic target that calls `__tinygo_*` functions for
+    peripheral access
+  - `arduino-nano33`: add support for this board
+  - `hifive1`: add support for this RISC-V board
+  - `reelboard`: add e-paper pins
+  - `reelboard`: add `PowerSupplyActive` to enable voltage for on-board devices
+  - `wasm`: put the stack at the start of linear memory, to detect stack
+    overflows
+
 0.6.0
 ---
 * **command line**

CONTRIBUTING.md

@@ -16,12 +16,16 @@ Please open a Github issue with your problem, and we will be happy to assist.
 
 We probably have not implemented it yet. Please take a look at our [Roadmap](https://github.com/tinygo-org/tinygo/wiki/Roadmap). Your pull request adding the functionality to TinyGo would be greatly appreciated.
 
+Please open a Github issue. We want to help, and also make sure that there is no duplications of efforts. Sometimes what you need is already being worked on by someone else.
+
 A long tail of small (and large) language features haven't been implemented yet. In almost all cases, the compiler will show a `todo:` error from `compiler/compiler.go` when you try to use it. You can try implementing it, or open a bug report with a small code sample that fails to compile.
 
 ### Some specific hardware you want to use does not appear to be in TinyGo
 
 As above, we probably have not implemented it yet. Your contribution adding the hardware support to TinyGo would be greatly appreciated.
 
+Please start by opening a Github issue. We want to help you to help us to help you.
+
 Lots of targets/boards are still unsupported. Adding an architecture often requires a few compiler changes, but if the architecture is supported you can try implementing support for a new chip or board in `src/runtime`. For details, see [this wiki entry on adding archs/chips/boards](https://github.com/tinygo-org/tinygo/wiki/Adding-a-new-board).
 
 Microcontrollers have lots of peripherals (I2C, SPI, ADC, etc.) and many don't have an implementation yet in the `machine` package. Adding support for new peripherals is very useful.

CONTRIBUTORS

@@ -0,0 +1,17 @@
+# This is the official list of TinyGo authors for copyright purposes.
+#
+# This file is not actively maintained.
+# To be included, send a change adding the individual or
+# company who owns a contribution's copyright.
+#
+# Names should be added to this file as one of
+#     Organization's name
+#     Individual's name <submission email address>
+#     Individual's name <submission email address> <email2> <emailN>
+#
+# Please keep the list sorted.
+
+Ayke van Laethem <aykevanlaethem@gmail.com>
+Daniel Esteban <conejo@conejo.me>
+Loon, LLC.
+Ron Evans <ron@hybridgroup.com>

Dockerfile

@@ -1,34 +1,31 @@
-# TinyGo base stage just installs LLVM 8 and the TinyGo compiler itself.
-FROM golang:latest AS tinygo-base
+# TinyGo base stage installs Go 1.12, LLVM 8 and the TinyGo compiler itself.
+FROM golang:1.12 AS tinygo-base
 
 RUN wget -O- https://apt.llvm.org/llvm-snapshot.gpg.key| apt-key add - && \
-    echo "deb http://apt.llvm.org/stretch/ llvm-toolchain-stretch-8 main" >> /etc/apt/sources.list && \
+    echo "deb http://apt.llvm.org/buster/ llvm-toolchain-buster-8 main" >> /etc/apt/sources.list && \
     apt-get update && \
     apt-get install -y llvm-8-dev libclang-8-dev git
 
-RUN wget -O- https://raw.githubusercontent.com/golang/dep/master/install.sh | sh
-
-COPY . /go/src/github.com/tinygo-org/tinygo
+COPY . /tinygo
 
 # remove submodules directories and re-init them to fix any hard-coded paths
 # after copying the tinygo directory in the previous step.
-RUN cd /go/src/github.com/tinygo-org/tinygo/ && \
+RUN cd /tinygo/ && \
     rm -rf ./lib/* && \
     git submodule update --init --recursive --force
 
-RUN cd /go/src/github.com/tinygo-org/tinygo/ && \
-    dep ensure --vendor-only && \
-    go install /go/src/github.com/tinygo-org/tinygo/
+RUN cd /tinygo/ && \
+    go install /tinygo/
 
 # tinygo-wasm stage installs the needed dependencies to compile TinyGo programs for WASM.
 FROM tinygo-base AS tinygo-wasm
 
 COPY --from=tinygo-base /go/bin/tinygo /go/bin/tinygo
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/src /go/src/github.com/tinygo-org/tinygo/src
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/targets /go/src/github.com/tinygo-org/tinygo/targets
+COPY --from=tinygo-base /tinygo/src /tinygo/src
+COPY --from=tinygo-base /tinygo/targets /tinygo/targets
 
 RUN wget -O- https://apt.llvm.org/llvm-snapshot.gpg.key| apt-key add - && \
-    echo "deb http://apt.llvm.org/stretch/ llvm-toolchain-stretch-8 main" >> /etc/apt/sources.list && \
+    echo "deb http://apt.llvm.org/buster/ llvm-toolchain-buster-8 main" >> /etc/apt/sources.list && \
     apt-get update && \
     apt-get install -y libllvm8 lld-8
 
@@ -36,13 +33,13 @@ RUN wget -O- https://apt.llvm.org/llvm-snapshot.gpg.key| apt-key add - && \
 FROM tinygo-base AS tinygo-avr
 
 COPY --from=tinygo-base /go/bin/tinygo /go/bin/tinygo
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/src /go/src/github.com/tinygo-org/tinygo/src
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/targets /go/src/github.com/tinygo-org/tinygo/targets
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/Makefile /go/src/github.com/tinygo-org/tinygo/
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/tools /go/src/github.com/tinygo-org/tinygo/tools
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/lib /go/src/github.com/tinygo-org/tinygo/lib
+COPY --from=tinygo-base /tinygo/src /tinygo/src
+COPY --from=tinygo-base /tinygo/targets /tinygo/targets
+COPY --from=tinygo-base /tinygo/Makefile /tinygo/
+COPY --from=tinygo-base /tinygo/tools /tinygo/tools
+COPY --from=tinygo-base /tinygo/lib /tinygo/lib
 
-RUN cd /go/src/github.com/tinygo-org/tinygo/ && \
+RUN cd /tinygo/ && \
     apt-get update && \
     apt-get install -y apt-utils python3 make binutils-avr gcc-avr avr-libc && \
     make gen-device-avr && \
@@ -54,13 +51,13 @@ RUN cd /go/src/github.com/tinygo-org/tinygo/ && \
 FROM tinygo-base AS tinygo-arm
 
 COPY --from=tinygo-base /go/bin/tinygo /go/bin/tinygo
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/src /go/src/github.com/tinygo-org/tinygo/src
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/targets /go/src/github.com/tinygo-org/tinygo/targets
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/Makefile /go/src/github.com/tinygo-org/tinygo/
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/tools /go/src/github.com/tinygo-org/tinygo/tools
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/lib /go/src/github.com/tinygo-org/tinygo/lib
+COPY --from=tinygo-base /tinygo/src /tinygo/src
+COPY --from=tinygo-base /tinygo/targets /tinygo/targets
+COPY --from=tinygo-base /tinygo/Makefile /tinygo/
+COPY --from=tinygo-base /tinygo/tools /tinygo/tools
+COPY --from=tinygo-base /tinygo/lib /tinygo/lib
 
-RUN cd /go/src/github.com/tinygo-org/tinygo/ && \
+RUN cd /tinygo/ && \
     apt-get update && \
     apt-get install -y apt-utils python3 make clang-8 && \
     make gen-device-nrf && make gen-device-stm32 && \
@@ -71,11 +68,11 @@ RUN cd /go/src/github.com/tinygo-org/tinygo/ && \
 # tinygo-all stage installs the needed dependencies to compile TinyGo programs for all platforms.
 FROM tinygo-wasm AS tinygo-all
 
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/Makefile /go/src/github.com/tinygo-org/tinygo/
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/tools /go/src/github.com/tinygo-org/tinygo/tools
-COPY --from=tinygo-base /go/src/github.com/tinygo-org/tinygo/lib /go/src/github.com/tinygo-org/tinygo/lib
+COPY --from=tinygo-base /tinygo/Makefile /tinygo/
+COPY --from=tinygo-base /tinygo/tools /tinygo/tools
+COPY --from=tinygo-base /tinygo/lib /tinygo/lib
 
-RUN cd /go/src/github.com/tinygo-org/tinygo/ && \
+RUN cd /tinygo/ && \
     apt-get update && \
     apt-get install -y apt-utils python3 make clang-8 binutils-avr gcc-avr avr-libc && \
     make gen-device && \

Gopkg.lock

@@ -1,51 +0,0 @@
-# This file is autogenerated, do not edit; changes may be undone by the next 'dep ensure'.
-
-
-[[projects]]
-  branch = "master"
-  digest = "1:06519a2ec1d59040eaccec40206f9d0b59dc662db2a032f974d6d6b9a2bcb839"
-  name = "github.com/blakesmith/ar"
-  packages = ["."]
-  pruneopts = "UT"
-  revision = "8bd4349a67f2533b078dbc524689d15dba0f4659"
-
-[[projects]]
-  branch = "master"
-  digest = "1:00b45e06c7843541372fc17d982242bd6adfc2fc382b6f2e9ef9ce53d87a50b9"
-  name = "github.com/marcinbor85/gohex"
-  packages = ["."]
-  pruneopts = "UT"
-  revision = "7a43cd876e46e0f6ddc553f10f91731a78e6e949"
-
-[[projects]]
-  branch = "master"
-  digest = "1:ba70784a3deee74c0ca3c87bcac3c2f93d3b2d27d8f237b768c358b45ba47da8"
-  name = "golang.org/x/tools"
-  packages = [
-    "go/ast/astutil",
-    "go/ssa",
-    "go/types/typeutil",
-  ]
-  pruneopts = "UT"
-  revision = "8dcc6e70cdefe9a82236b6e195e4f4e2108fcb9f"
-
-[[projects]]
-  branch = "llvm8"
-  digest = "1:bf5539bdf6b3cc3ec1e45926db05d81180da11ce722fa1edcce3f0b4e1967da5"
-  name = "tinygo.org/x/go-llvm"
-  packages = ["."]
-  pruneopts = "UT"
-  revision = "7707ae5d1261a8929edea7336c8087ca8b520d8d"
-
-[solve-meta]
-  analyzer-name = "dep"
-  analyzer-version = 1
-  input-imports = [
-    "github.com/blakesmith/ar",
-    "github.com/marcinbor85/gohex",
-    "golang.org/x/tools/go/ast/astutil",
-    "golang.org/x/tools/go/ssa",
-    "tinygo.org/x/go-llvm",
-  ]
-  solver-name = "gps-cdcl"
-  solver-version = 1

Gopkg.toml

@@ -1,11 +0,0 @@
-[[constraint]]
-  branch = "llvm8"
-  name = "tinygo.org/x/go-llvm"
-
-[[constraint]]
-  branch = "master"
-  name = "golang.org/x/tools"
-
-[prune]
-  go-tests = true
-  unused-packages = true

Makefile

@@ -3,12 +3,12 @@
 all: tinygo
 tinygo: build/tinygo
 
-.PHONY: all tinygo build/tinygo test llvm-build llvm-source clean fmt gen-device gen-device-nrf gen-device-avr
-
 # Default build and source directories, as created by `make llvm-build`.
 LLVM_BUILDDIR ?= llvm-build
-CLANG_SRC ?= llvm/tools/clang
-LLD_SRC ?= llvm/tools/lld
+CLANG_SRC ?= llvm-project/clang
+LLD_SRC ?= llvm-project/lld
+
+.PHONY: all tinygo build/tinygo test $(LLVM_BUILDDIR) llvm-source clean fmt gen-device gen-device-nrf gen-device-avr
 
 LLVM_COMPONENTS = all-targets analysis asmparser asmprinter bitreader bitwriter codegen core coroutines debuginfodwarf executionengine instrumentation interpreter ipo irreader linker lto mc mcjit objcarcopts option profiledata scalaropts support target
 
@@ -18,15 +18,17 @@ ifeq ($(UNAME_S),Linux)
     END_GROUP = -Wl,--end-group
 endif
 
-CLANG_LIBS = $(START_GROUP) $(abspath $(LLVM_BUILDDIR))/lib/libclang.a -lclangAnalysis -lclangARCMigrate -lclangAST -lclangASTMatchers -lclangBasic -lclangCodeGen -lclangCrossTU -lclangDriver -lclangDynamicASTMatchers -lclangEdit -lclangFormat -lclangFrontend -lclangFrontendTool -lclangHandleCXX -lclangHandleLLVM -lclangIndex -lclangLex -lclangParse -lclangRewrite -lclangRewriteFrontend -lclangSema -lclangSerialization -lclangStaticAnalyzerCheckers -lclangStaticAnalyzerCore -lclangStaticAnalyzerFrontend -lclangTooling -lclangToolingASTDiff -lclangToolingCore -lclangToolingInclusions -lclangToolingRefactor $(END_GROUP) -lstdc++
+CLANG_LIBS = $(START_GROUP) $(abspath $(LLVM_BUILDDIR))/lib/libclang.a -lclangAnalysis -lclangARCMigrate -lclangAST -lclangASTMatchers -lclangBasic -lclangCodeGen -lclangCrossTU -lclangDriver -lclangDynamicASTMatchers -lclangEdit -lclangFormat -lclangFrontend -lclangFrontendTool -lclangHandleCXX -lclangHandleLLVM -lclangIndex -lclangLex -lclangParse -lclangRewrite -lclangRewriteFrontend -lclangSema -lclangSerialization -lclangStaticAnalyzerCheckers -lclangStaticAnalyzerCore -lclangStaticAnalyzerFrontend -lclangTooling -lclangToolingASTDiff -lclangToolingCore -lclangToolingInclusions $(END_GROUP) -lstdc++
 
 LLD_LIBS = $(START_GROUP) -llldCOFF -llldCommon -llldCore -llldDriver -llldELF -llldMachO -llldMinGW -llldReaderWriter -llldWasm -llldYAML $(END_GROUP)
 
 
 # For static linking.
-CGO_CPPFLAGS=$(shell $(LLVM_BUILDDIR)/bin/llvm-config --cppflags) -I$(abspath $(CLANG_SRC))/include -I$(abspath $(LLD_SRC))/include
-CGO_CXXFLAGS=-std=c++11
-CGO_LDFLAGS=-L$(LLVM_BUILDDIR)/lib $(CLANG_LIBS) $(LLD_LIBS) $(shell $(LLVM_BUILDDIR)/bin/llvm-config --ldflags --libs --system-libs $(LLVM_COMPONENTS))
+ifneq ("$(wildcard $(LLVM_BUILDDIR)/bin/llvm-config)","")
+    CGO_CPPFLAGS=$(shell $(LLVM_BUILDDIR)/bin/llvm-config --cppflags) -I$(abspath $(CLANG_SRC))/include -I$(abspath $(LLD_SRC))/include
+    CGO_CXXFLAGS=-std=c++11
+    CGO_LDFLAGS=-L$(LLVM_BUILDDIR)/lib $(CLANG_LIBS) $(LLD_LIBS) $(shell $(LLVM_BUILDDIR)/bin/llvm-config --ldflags --libs --system-libs $(LLVM_COMPONENTS))
+endif
 
 
 clean:
@@ -38,7 +40,8 @@ fmt:
 fmt-check:
 	@unformatted=$$(gofmt -l $(FMT_PATHS)); [ -z "$$unformatted" ] && exit 0; echo "Unformatted:"; for fn in $$unformatted; do echo "  $$fn"; done; exit 1
 
-gen-device: gen-device-avr gen-device-nrf gen-device-sam gen-device-stm32
+
+gen-device: gen-device-avr gen-device-nrf gen-device-sam gen-device-sifive gen-device-stm32
 
 gen-device-avr:
 	./tools/gen-device-avr.py lib/avr/packs/atmega src/device/avr/
@@ -53,42 +56,43 @@ gen-device-sam:
 	./tools/gen-device-svd.py lib/cmsis-svd/data/Atmel/ src/device/sam/ --source=https://github.com/posborne/cmsis-svd/tree/master/data/Atmel
 	go fmt ./src/device/sam
 
+gen-device-sifive:
+	./tools/gen-device-svd.py lib/cmsis-svd/data/SiFive-Community/ src/device/sifive/ --source=https://github.com/AdaCore/svd2ada/tree/master/CMSIS-SVD/SiFive-Community
+	go fmt ./src/device/sifive
+
 gen-device-stm32:
 	./tools/gen-device-svd.py lib/cmsis-svd/data/STMicro/ src/device/stm32/ --source=https://github.com/posborne/cmsis-svd/tree/master/data/STMicro
 	go fmt ./src/device/stm32
 
 
 # Get LLVM sources.
-llvm/README.txt:
-	git clone -b release_80 https://github.com/llvm-mirror/llvm.git llvm
-llvm/tools/clang/README.txt:
-	git clone -b release_80 https://github.com/llvm-mirror/clang.git llvm/tools/clang
-llvm/tools/lld/README.md:
-	git clone -b release_80 https://github.com/llvm-mirror/lld.git llvm/tools/lld
-llvm-source: llvm/README.txt llvm/tools/clang/README.txt llvm/tools/lld/README.md
+llvm-project/README.md:
+	git clone -b release/8.x https://github.com/llvm/llvm-project
+llvm-source: llvm-project/README.md
 
 # Configure LLVM.
-llvm-build/build.ninja: llvm-source
-	mkdir -p llvm-build; cd llvm-build; cmake -G Ninja ../llvm "-DLLVM_TARGETS_TO_BUILD=X86;ARM;AArch64;WebAssembly" "-DLLVM_EXPERIMENTAL_TARGETS_TO_BUILD=AVR" -DCMAKE_BUILD_TYPE=Release -DLLVM_ENABLE_ASSERTIONS=OFF -DLIBCLANG_BUILD_STATIC=ON -DLLVM_ENABLE_TERMINFO=OFF -DLLVM_ENABLE_ZLIB=OFF
+TINYGO_SOURCE_DIR=$(shell pwd)
+$(LLVM_BUILDDIR)/build.ninja: llvm-source
+	mkdir -p $(LLVM_BUILDDIR); cd $(LLVM_BUILDDIR); cmake -G Ninja $(TINYGO_SOURCE_DIR)/llvm-project/llvm "-DLLVM_TARGETS_TO_BUILD=X86;ARM;AArch64;WebAssembly" "-DLLVM_EXPERIMENTAL_TARGETS_TO_BUILD=AVR;RISCV" -DCMAKE_BUILD_TYPE=Release -DLLVM_ENABLE_ASSERTIONS=OFF -DLIBCLANG_BUILD_STATIC=ON -DLLVM_ENABLE_TERMINFO=OFF -DLLVM_ENABLE_ZLIB=OFF -DLLVM_ENABLE_PROJECTS="clang;lld" -DLLVM_TOOL_CLANG_TOOLS_EXTRA_BUILD=OFF
 
 # Build LLVM.
-llvm-build: llvm-build/build.ninja
-	cd llvm-build; ninja
+$(LLVM_BUILDDIR): $(LLVM_BUILDDIR)/build.ninja
+	cd $(LLVM_BUILDDIR); ninja
 
 
 # Build the Go compiler.
 build/tinygo:
-	@if [ ! -f llvm-build/bin/llvm-config ]; then echo "Fetch and build LLVM first by running:\n  make llvm-source\n  make llvm-build"; exit 1; fi
+	@if [ ! -f "$(LLVM_BUILDDIR)/bin/llvm-config" ]; then echo "Fetch and build LLVM first by running:"; echo "  make llvm-source"; echo "  make $(LLVM_BUILDDIR)"; exit 1; fi
 	CGO_CPPFLAGS="$(CGO_CPPFLAGS)" CGO_CXXFLAGS="$(CGO_CXXFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" go build -o build/tinygo -tags byollvm .
 
 test:
-	CGO_CPPFLAGS="$(CGO_CPPFLAGS)" CGO_CXXFLAGS="$(CGO_CXXFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" go test -v -tags byollvm .
+	CGO_CPPFLAGS="$(CGO_CPPFLAGS)" CGO_CXXFLAGS="$(CGO_CXXFLAGS)" CGO_LDFLAGS="$(CGO_LDFLAGS)" go test -v -tags byollvm ./transform .
 
-.PHONY: smoketest smoketest-no-avr
-smoketest: smoketest-no-avr
-	tinygo build -size short -o test.elf -target=arduino             examples/blinky1
-	tinygo build -size short -o test.elf -target=digispark           examples/blinky1
-smoketest-no-avr:
+tinygo-test:
+	cd tests/tinygotest && tinygo test
+
+.PHONY: smoketest
+smoketest:
 	# test all examples
 	tinygo build -size short -o test.elf -target=pca10040            examples/blinky1
 	tinygo build -size short -o test.elf -target=pca10040            examples/adc
@@ -104,7 +108,7 @@ smoketest-no-avr:
 	tinygo build -size short -o test.elf -target=pca10040            examples/serial
 	tinygo build -size short -o test.elf -target=pca10040            examples/test
 	# test all targets/boards
-	tinygo build             -o test.elf                             examples/blinky2 # TODO: re-enable -size flag with MachO support
+	tinygo build             -o test.wasm -tags=pca10040             examples/blinky2
 	tinygo build -size short -o test.elf -target=microbit            examples/echo
 	tinygo build -size short -o test.elf -target=nrf52840-mdk        examples/blinky1
 	tinygo build -size short -o test.elf -target=pca10031            examples/blinky1
@@ -120,6 +124,16 @@ smoketest-no-avr:
 	tinygo build -size short -o test.elf -target=stm32f4disco        examples/blinky1
 	tinygo build -size short -o test.elf -target=stm32f4disco        examples/blinky2
 	tinygo build -size short -o test.elf -target=circuitplay-express examples/i2s
+	tinygo build -size short -o test.elf -target=gameboy-advance     examples/gba-display
+	tinygo build -size short -o test.elf -target=itsybitsy-m4        examples/blinky1
+	tinygo build -size short -o test.elf -target=nucleo-f103rb       examples/blinky1
+ifneq ($(AVR), 0)
+	tinygo build -size short -o test.elf -target=arduino             examples/blinky1
+	tinygo build -size short -o test.elf -target=digispark           examples/blinky1
+endif
+ifneq ($(RISCV), 0)
+	tinygo build -size short -o test.elf -target=hifive1b            examples/blinky1
+endif
 	tinygo build             -o wasm.wasm -target=wasm               examples/wasm/export
 	tinygo build             -o wasm.wasm -target=wasm               examples/wasm/main
 

README.md

@@ -2,7 +2,7 @@
 
 [![CircleCI](https://circleci.com/gh/tinygo-org/tinygo/tree/dev.svg?style=svg)](https://circleci.com/gh/tinygo-org/tinygo/tree/dev)
 
-TinyGo is a Go compiler intended for use in small places such as microcontrollers, WebAssembly (WASM), and command-line tools.
+TinyGo is a Go compiler intended for use in small places such as microcontrollers, WebAssembly (Wasm), and command-line tools.
 
 It reuses libraries used by the [Go language tools](https://golang.org/pkg/go/) alongside [LLVM](http://llvm.org) to provide an alternative way to compile programs written in the Go programming language.
 
@@ -43,15 +43,19 @@ See the [getting started instructions](https://tinygo.org/getting-started/) for
 
 You can compile TinyGo programs for microcontrollers, WebAssembly and Linux.
 
-The following 14 microcontroller boards are currently supported:
+The following 18 microcontroller boards are currently supported:
 
 * [Adafruit Circuit Playground Express](https://www.adafruit.com/product/3333)
 * [Adafruit Feather M0](https://www.adafruit.com/product/2772)
 * [Adafruit ItsyBitsy M0](https://www.adafruit.com/product/3727)
+* [Adafruit ItsyBitsy M4](https://www.adafruit.com/product/3800)
 * [Adafruit Trinket M0](https://www.adafruit.com/product/3500)
+* [Arduino Nano33 IoT](https://store.arduino.cc/nano-33-iot)
 * [Arduino Uno](https://store.arduino.cc/arduino-uno-rev3)
 * [BBC micro:bit](https://microbit.org/)
+* [Game Boy Advance](https://en.wikipedia.org/wiki/Game_Boy_Advance)
 * [ST Micro STM32F103XX "Bluepill"](http://wiki.stm32duino.com/index.php?title=Blue_Pill)
+* [ST Micro "Nucleo F103RB"](https://www.st.com/en/evaluation-tools/nucleo-f103rb.html)
 * [ST Micro STM32F407 "Discovery"](https://www.st.com/en/evaluation-tools/stm32f4discovery.html)
 * [Digispark](http://digistump.com/products/1)
 * [Nordic Semiconductor PCA10031](https://www.nordicsemi.com/eng/Products/nRF51-Dongle)

cgo/cgo.go

@@ -36,6 +36,7 @@ type cgoPackage struct {
 	typedefs        map[string]*typedefInfo
 	elaboratedTypes map[string]*elaboratedTypeInfo
 	enums           map[string]enumInfo
+	anonStructNum   int
 }
 
 // constantInfo stores some information about a CGo constant found by libclang
@@ -68,8 +69,20 @@ type typedefInfo struct {
 // elaboratedTypeInfo contains some information about an elaborated type
 // (struct, union) found in the C AST.
 type elaboratedTypeInfo struct {
-	typeExpr ast.Expr
+	typeExpr  *ast.StructType
+	pos       token.Pos
+	bitfields []bitfieldInfo
+}
+
+// bitfieldInfo contains information about a single bitfield in a struct. It
+// keeps information about the start, end, and the special (renamed) base field
+// of this bitfield.
+type bitfieldInfo struct {
+	field    *ast.Field
+	name     string
 	pos      token.Pos
+	startBit int64
+	endBit   int64 // may be 0 meaning "until the end of the field"
 }
 
 // enumInfo contains information about an enum in the C.
@@ -581,10 +594,299 @@ func (p *cgoPackage) addElaboratedTypes() {
 		}
 		obj.Decl = typeSpec
 		gen.Specs = append(gen.Specs, typeSpec)
+		// If this struct has bitfields, create getters for them.
+		for _, bitfield := range typ.bitfields {
+			p.createBitfieldGetter(bitfield, typeName)
+			p.createBitfieldSetter(bitfield, typeName)
+		}
 	}
 	p.generated.Decls = append(p.generated.Decls, gen)
 }
 
+// createBitfieldGetter creates a bitfield getter function like the following:
+//
+//     func (s *C.struct_foo) bitfield_b() byte {
+//         return (s.__bitfield_1 >> 5) & 0x1
+//     }
+func (p *cgoPackage) createBitfieldGetter(bitfield bitfieldInfo, typeName string) {
+	// The value to return from the getter.
+	// Not complete: this is just an expression to get the complete field.
+	var result ast.Expr = &ast.SelectorExpr{
+		X: &ast.Ident{
+			NamePos: bitfield.pos,
+			Name:    "s",
+			Obj:     nil,
+		},
+		Sel: &ast.Ident{
+			NamePos: bitfield.pos,
+			Name:    bitfield.field.Names[0].Name,
+		},
+	}
+	if bitfield.startBit != 0 {
+		// Shift to the right by .startBit so that fields that come before are
+		// shifted off.
+		result = &ast.BinaryExpr{
+			X:     result,
+			OpPos: bitfield.pos,
+			Op:    token.SHR,
+			Y: &ast.BasicLit{
+				ValuePos: bitfield.pos,
+				Kind:     token.INT,
+				Value:    strconv.FormatInt(bitfield.startBit, 10),
+			},
+		}
+	}
+	if bitfield.endBit != 0 {
+		// Mask off the high bits so that fields that come after this field are
+		// masked off.
+		and := (uint64(1) << uint64(bitfield.endBit-bitfield.startBit)) - 1
+		result = &ast.BinaryExpr{
+			X:     result,
+			OpPos: bitfield.pos,
+			Op:    token.AND,
+			Y: &ast.BasicLit{
+				ValuePos: bitfield.pos,
+				Kind:     token.INT,
+				Value:    "0x" + strconv.FormatUint(and, 16),
+			},
+		}
+	}
+
+	// Create the getter function.
+	getter := &ast.FuncDecl{
+		Recv: &ast.FieldList{
+			Opening: bitfield.pos,
+			List: []*ast.Field{
+				&ast.Field{
+					Names: []*ast.Ident{
+						&ast.Ident{
+							NamePos: bitfield.pos,
+							Name:    "s",
+							Obj: &ast.Object{
+								Kind: ast.Var,
+								Name: "s",
+								Decl: nil,
+							},
+						},
+					},
+					Type: &ast.StarExpr{
+						Star: bitfield.pos,
+						X: &ast.Ident{
+							NamePos: bitfield.pos,
+							Name:    typeName,
+							Obj:     nil,
+						},
+					},
+				},
+			},
+			Closing: bitfield.pos,
+		},
+		Name: &ast.Ident{
+			NamePos: bitfield.pos,
+			Name:    "bitfield_" + bitfield.name,
+		},
+		Type: &ast.FuncType{
+			Func: bitfield.pos,
+			Params: &ast.FieldList{
+				Opening: bitfield.pos,
+				Closing: bitfield.pos,
+			},
+			Results: &ast.FieldList{
+				List: []*ast.Field{
+					&ast.Field{
+						Type: bitfield.field.Type,
+					},
+				},
+			},
+		},
+		Body: &ast.BlockStmt{
+			Lbrace: bitfield.pos,
+			List: []ast.Stmt{
+				&ast.ReturnStmt{
+					Return: bitfield.pos,
+					Results: []ast.Expr{
+						result,
+					},
+				},
+			},
+			Rbrace: bitfield.pos,
+		},
+	}
+	p.generated.Decls = append(p.generated.Decls, getter)
+}
+
+// createBitfieldSetter creates a bitfield setter function like the following:
+//
+//     func (s *C.struct_foo) set_bitfield_b(value byte) {
+//         s.__bitfield_1 = s.__bitfield_1 ^ 0x60 | ((value & 1) << 5)
+//     }
+//
+// Or the following:
+//
+//     func (s *C.struct_foo) set_bitfield_c(value byte) {
+//         s.__bitfield_1 = s.__bitfield_1 & 0x3f | (value << 6)
+//     }
+func (p *cgoPackage) createBitfieldSetter(bitfield bitfieldInfo, typeName string) {
+	// The full field with all bitfields.
+	var field ast.Expr = &ast.SelectorExpr{
+		X: &ast.Ident{
+			NamePos: bitfield.pos,
+			Name:    "s",
+			Obj:     nil,
+		},
+		Sel: &ast.Ident{
+			NamePos: bitfield.pos,
+			Name:    bitfield.field.Names[0].Name,
+		},
+	}
+	// The value to insert into the field.
+	var valueToInsert ast.Expr = &ast.Ident{
+		NamePos: bitfield.pos,
+		Name:    "value",
+	}
+
+	if bitfield.endBit != 0 {
+		// Make sure the value is in range with a mask.
+		valueToInsert = &ast.BinaryExpr{
+			X:     valueToInsert,
+			OpPos: bitfield.pos,
+			Op:    token.AND,
+			Y: &ast.BasicLit{
+				ValuePos: bitfield.pos,
+				Kind:     token.INT,
+				Value:    "0x" + strconv.FormatUint((uint64(1)<<uint64(bitfield.endBit-bitfield.startBit))-1, 16),
+			},
+		}
+		// Create a mask for the AND NOT operation.
+		mask := ((uint64(1) << uint64(bitfield.endBit-bitfield.startBit)) - 1) << uint64(bitfield.startBit)
+		// Zero the bits in the field that will soon be inserted.
+		field = &ast.BinaryExpr{
+			X:     field,
+			OpPos: bitfield.pos,
+			Op:    token.AND_NOT,
+			Y: &ast.BasicLit{
+				ValuePos: bitfield.pos,
+				Kind:     token.INT,
+				Value:    "0x" + strconv.FormatUint(mask, 16),
+			},
+		}
+	} else { // bitfield.endBit == 0
+		// We don't know exactly how many high bits should be zeroed. So we do
+		// something different: keep the low bits with a mask and OR the new
+		// value with it.
+		mask := (uint64(1) << uint64(bitfield.startBit)) - 1
+		// Extract the lower bits.
+		field = &ast.BinaryExpr{
+			X:     field,
+			OpPos: bitfield.pos,
+			Op:    token.AND,
+			Y: &ast.BasicLit{
+				ValuePos: bitfield.pos,
+				Kind:     token.INT,
+				Value:    "0x" + strconv.FormatUint(mask, 16),
+			},
+		}
+	}
+
+	// Bitwise OR with the new value (after the new value has been shifted).
+	field = &ast.BinaryExpr{
+		X:     field,
+		OpPos: bitfield.pos,
+		Op:    token.OR,
+		Y: &ast.BinaryExpr{
+			X:     valueToInsert,
+			OpPos: bitfield.pos,
+			Op:    token.SHL,
+			Y: &ast.BasicLit{
+				ValuePos: bitfield.pos,
+				Kind:     token.INT,
+				Value:    strconv.FormatInt(bitfield.startBit, 10),
+			},
+		},
+	}
+
+	// Create the setter function.
+	setter := &ast.FuncDecl{
+		Recv: &ast.FieldList{
+			Opening: bitfield.pos,
+			List: []*ast.Field{
+				&ast.Field{
+					Names: []*ast.Ident{
+						&ast.Ident{
+							NamePos: bitfield.pos,
+							Name:    "s",
+							Obj: &ast.Object{
+								Kind: ast.Var,
+								Name: "s",
+								Decl: nil,
+							},
+						},
+					},
+					Type: &ast.StarExpr{
+						Star: bitfield.pos,
+						X: &ast.Ident{
+							NamePos: bitfield.pos,
+							Name:    typeName,
+							Obj:     nil,
+						},
+					},
+				},
+			},
+			Closing: bitfield.pos,
+		},
+		Name: &ast.Ident{
+			NamePos: bitfield.pos,
+			Name:    "set_bitfield_" + bitfield.name,
+		},
+		Type: &ast.FuncType{
+			Func: bitfield.pos,
+			Params: &ast.FieldList{
+				Opening: bitfield.pos,
+				List: []*ast.Field{
+					&ast.Field{
+						Names: []*ast.Ident{
+							&ast.Ident{
+								NamePos: bitfield.pos,
+								Name:    "value",
+								Obj:     nil,
+							},
+						},
+						Type: bitfield.field.Type,
+					},
+				},
+				Closing: bitfield.pos,
+			},
+		},
+		Body: &ast.BlockStmt{
+			Lbrace: bitfield.pos,
+			List: []ast.Stmt{
+				&ast.AssignStmt{
+					Lhs: []ast.Expr{
+						&ast.SelectorExpr{
+							X: &ast.Ident{
+								NamePos: bitfield.pos,
+								Name:    "s",
+								Obj:     nil,
+							},
+							Sel: &ast.Ident{
+								NamePos: bitfield.pos,
+								Name:    bitfield.field.Names[0].Name,
+							},
+						},
+					},
+					TokPos: bitfield.pos,
+					Tok:    token.ASSIGN,
+					Rhs: []ast.Expr{
+						field,
+					},
+				},
+			},
+			Rbrace: bitfield.pos,
+		},
+	}
+	p.generated.Decls = append(p.generated.Decls, setter)
+}
+
 // addEnumTypes adds C enums to the AST. For example, the following C code:
 //
 //     enum option {

cgo/libclang.go

@@ -51,6 +51,7 @@ CXSourceRange tinygo_clang_getCursorExtent(GoCXCursor c);
 CXTranslationUnit tinygo_clang_Cursor_getTranslationUnit(GoCXCursor c);
 long long tinygo_clang_getEnumConstantDeclValue(GoCXCursor c);
 CXType tinygo_clang_getEnumDeclIntegerType(GoCXCursor c);
+unsigned tinygo_clang_Cursor_isBitField(GoCXCursor c);
 
 int tinygo_clang_globals_visitor(GoCXCursor c, GoCXCursor parent, CXClientData client_data);
 int tinygo_clang_struct_visitor(GoCXCursor c, GoCXCursor parent, CXClientData client_data);
@@ -512,78 +513,48 @@ func (p *cgoPackage) makeASTType(typ C.CXType, pos token.Pos) ast.Expr {
 	case C.CXType_Record:
 		cursor := C.tinygo_clang_getTypeDeclaration(typ)
 		name := getString(C.tinygo_clang_getCursorSpelling(cursor))
-		var cgoName string
-		switch C.tinygo_clang_getCursorKind(cursor) {
-		case C.CXCursor_StructDecl:
-			cgoName = "struct_" + name
-		case C.CXCursor_UnionDecl:
-			cgoName = "union_" + name
-		default:
-			panic("unknown record declaration")
-		}
-		if _, ok := p.elaboratedTypes[cgoName]; !ok {
-			p.elaboratedTypes[cgoName] = nil // predeclare (to avoid endless recursion)
-			fieldList := &ast.FieldList{
-				Opening: pos,
-				Closing: pos,
+		if name == "" {
+			// Anonymous record, probably inside a typedef.
+			typeExpr, bitfieldList := p.makeASTRecordType(cursor, pos)
+			if bitfieldList != nil {
+				// This struct has bitfields, so we have to declare it as a
+				// named type (for bitfield getters/setters to work).
+				p.anonStructNum++
+				cgoName := "struct_" + strconv.Itoa(p.anonStructNum)
+				p.elaboratedTypes[cgoName] = &elaboratedTypeInfo{
+					typeExpr:  typeExpr,
+					pos:       pos,
+					bitfields: bitfieldList,
+				}
+				return &ast.Ident{
+					NamePos: pos,
+					Name:    "C." + cgoName,
+				}
 			}
-			ref := storedRefs.Put(struct {
-				fieldList *ast.FieldList
-				pkg       *cgoPackage
-			}{fieldList, p})
-			defer storedRefs.Remove(ref)
-			C.tinygo_clang_visitChildren(cursor, C.CXCursorVisitor(C.tinygo_clang_struct_visitor), C.CXClientData(ref))
+			return typeExpr
+		} else {
+			var cgoName string
 			switch C.tinygo_clang_getCursorKind(cursor) {
 			case C.CXCursor_StructDecl:
-				p.elaboratedTypes[cgoName] = &elaboratedTypeInfo{
-					typeExpr: &ast.StructType{
-						Struct: pos,
-						Fields: fieldList,
-					},
-					pos: pos,
-				}
+				cgoName = "struct_" + name
 			case C.CXCursor_UnionDecl:
-				if len(fieldList.List) > 1 {
-					// Insert a special field at the front (of zero width) as a
-					// marker that this is struct is actually a union. This is done
-					// by giving the field a name that cannot be expressed directly
-					// in Go.
-					// Other parts of the compiler look at the first element in a
-					// struct (of size > 2) to know whether this is a union.
-					// Note that we don't have to insert it for single-element
-					// unions as they're basically equivalent to a struct.
-					unionMarker := &ast.Field{
-						Type: &ast.StructType{
-							Struct: pos,
-						},
-					}
-					unionMarker.Names = []*ast.Ident{
-						&ast.Ident{
-							NamePos: pos,
-							Name:    "C union",
-							Obj: &ast.Object{
-								Kind: ast.Var,
-								Name: "C union",
-								Decl: unionMarker,
-							},
-						},
-					}
-					fieldList.List = append([]*ast.Field{unionMarker}, fieldList.List...)
-				}
-				p.elaboratedTypes[cgoName] = &elaboratedTypeInfo{
-					typeExpr: &ast.StructType{
-						Struct: pos,
-						Fields: fieldList,
-					},
-					pos: pos,
-				}
+				cgoName = "union_" + name
 			default:
-				panic("unreachable")
+				panic("unknown record declaration")
+			}
+			if _, ok := p.elaboratedTypes[cgoName]; !ok {
+				p.elaboratedTypes[cgoName] = nil // predeclare (to avoid endless recursion)
+				typeExpr, bitfieldList := p.makeASTRecordType(cursor, pos)
+				p.elaboratedTypes[cgoName] = &elaboratedTypeInfo{
+					typeExpr:  typeExpr,
+					pos:       pos,
+					bitfields: bitfieldList,
+				}
+			}
+			return &ast.Ident{
+				NamePos: pos,
+				Name:    "C." + cgoName,
 			}
-		}
-		return &ast.Ident{
-			NamePos: pos,
-			Name:    "C." + cgoName,
 		}
 	case C.CXType_Enum:
 		cursor := C.tinygo_clang_getTypeDeclaration(typ)
@@ -629,25 +600,143 @@ func (p *cgoPackage) makeASTType(typ C.CXType, pos token.Pos) ast.Expr {
 	}
 }
 
+// makeASTRecordType parses a C record (struct or union) and translates it into
+// a Go struct type. Unions are implemented by setting the first field to a
+// zero-lengt "C union" field, which cannot be written in Go directly.
+func (p *cgoPackage) makeASTRecordType(cursor C.GoCXCursor, pos token.Pos) (*ast.StructType, []bitfieldInfo) {
+	fieldList := &ast.FieldList{
+		Opening: pos,
+		Closing: pos,
+	}
+	var bitfieldList []bitfieldInfo
+	inBitfield := false
+	bitfieldNum := 0
+	ref := storedRefs.Put(struct {
+		fieldList    *ast.FieldList
+		pkg          *cgoPackage
+		inBitfield   *bool
+		bitfieldNum  *int
+		bitfieldList *[]bitfieldInfo
+	}{fieldList, p, &inBitfield, &bitfieldNum, &bitfieldList})
+	defer storedRefs.Remove(ref)
+	C.tinygo_clang_visitChildren(cursor, C.CXCursorVisitor(C.tinygo_clang_struct_visitor), C.CXClientData(ref))
+	switch C.tinygo_clang_getCursorKind(cursor) {
+	case C.CXCursor_StructDecl:
+		return &ast.StructType{
+			Struct: pos,
+			Fields: fieldList,
+		}, bitfieldList
+	case C.CXCursor_UnionDecl:
+		if bitfieldList != nil {
+			// This is valid C... but please don't do this.
+			p.errors = append(p.errors, scanner.Error{
+				Pos: p.fset.PositionFor(pos, true),
+				Msg: fmt.Sprintf("bitfield in a union is not supported"),
+			})
+		}
+		if len(fieldList.List) > 1 {
+			// Insert a special field at the front (of zero width) as a
+			// marker that this is struct is actually a union. This is done
+			// by giving the field a name that cannot be expressed directly
+			// in Go.
+			// Other parts of the compiler look at the first element in a
+			// struct (of size > 2) to know whether this is a union.
+			// Note that we don't have to insert it for single-element
+			// unions as they're basically equivalent to a struct.
+			unionMarker := &ast.Field{
+				Type: &ast.StructType{
+					Struct: pos,
+				},
+			}
+			unionMarker.Names = []*ast.Ident{
+				&ast.Ident{
+					NamePos: pos,
+					Name:    "C union",
+					Obj: &ast.Object{
+						Kind: ast.Var,
+						Name: "C union",
+						Decl: unionMarker,
+					},
+				},
+			}
+			fieldList.List = append([]*ast.Field{unionMarker}, fieldList.List...)
+		}
+		return &ast.StructType{
+			Struct: pos,
+			Fields: fieldList,
+		}, bitfieldList
+	default:
+		panic("unknown record declaration")
+	}
+}
+
 //export tinygo_clang_struct_visitor
 func tinygo_clang_struct_visitor(c, parent C.GoCXCursor, client_data C.CXClientData) C.int {
 	passed := storedRefs.Get(unsafe.Pointer(client_data)).(struct {
-		fieldList *ast.FieldList
-		pkg       *cgoPackage
+		fieldList    *ast.FieldList
+		pkg          *cgoPackage
+		inBitfield   *bool
+		bitfieldNum  *int
+		bitfieldList *[]bitfieldInfo
 	})
 	fieldList := passed.fieldList
 	p := passed.pkg
+	inBitfield := passed.inBitfield
+	bitfieldNum := passed.bitfieldNum
+	bitfieldList := passed.bitfieldList
 	if C.tinygo_clang_getCursorKind(c) != C.CXCursor_FieldDecl {
 		panic("expected field inside cursor")
 	}
 	name := getString(C.tinygo_clang_getCursorSpelling(c))
+	if name == "" {
+		// Assume this is a bitfield of 0 bits.
+		// Warning: this is not necessarily true!
+		return C.CXChildVisit_Continue
+	}
 	typ := C.tinygo_clang_getCursorType(c)
+	pos := p.getCursorPosition(c)
 	field := &ast.Field{
 		Type: p.makeASTType(typ, p.getCursorPosition(c)),
 	}
+	offsetof := int64(C.clang_Type_getOffsetOf(C.tinygo_clang_getCursorType(parent), C.CString(name)))
+	alignOf := int64(C.clang_Type_getAlignOf(typ) * 8)
+	bitfieldOffset := offsetof % alignOf
+	if bitfieldOffset != 0 {
+		if C.tinygo_clang_Cursor_isBitField(c) != 1 {
+			panic("expected a bitfield")
+		}
+		if !*inBitfield {
+			*bitfieldNum++
+		}
+		bitfieldName := "__bitfield_" + strconv.Itoa(*bitfieldNum)
+		prevField := fieldList.List[len(fieldList.List)-1]
+		if !*inBitfield {
+			// The previous element also was a bitfield, but wasn't noticed
+			// then. Add it now.
+			*inBitfield = true
+			*bitfieldList = append(*bitfieldList, bitfieldInfo{
+				field:    prevField,
+				name:     prevField.Names[0].Name,
+				startBit: 0,
+				pos:      prevField.Names[0].NamePos,
+			})
+			prevField.Names[0].Name = bitfieldName
+			prevField.Names[0].Obj.Name = bitfieldName
+		}
+		prevBitfield := &(*bitfieldList)[len(*bitfieldList)-1]
+		prevBitfield.endBit = bitfieldOffset
+		*bitfieldList = append(*bitfieldList, bitfieldInfo{
+			field:    prevField,
+			name:     name,
+			startBit: bitfieldOffset,
+			pos:      pos,
+		})
+		return C.CXChildVisit_Continue
+	}
+	*inBitfield = false
 	field.Names = []*ast.Ident{
 		&ast.Ident{
-			NamePos: p.getCursorPosition(c),
+			NamePos: pos,
 			Name:    name,
 			Obj: &ast.Object{
 				Kind: ast.Var,

cgo/libclang_stubs.c

@@ -64,3 +64,7 @@ long long tinygo_clang_getEnumConstantDeclValue(CXCursor c) {
 CXType tinygo_clang_getEnumDeclIntegerType(CXCursor c) {
 	return clang_getEnumDeclIntegerType(c);
 }
+
+unsigned tinygo_clang_Cursor_isBitField(CXCursor c) {
+	return clang_Cursor_isBitField(c);
+}

commands.go

@@ -37,6 +37,7 @@ func execCommand(cmdNames []string, args ...string) error {
 				// this command was not found, try the next
 				continue
 			}
+			return err
 		}
 		return nil
 	}

compiler/asserts.go

@@ -56,7 +56,7 @@ func (c *Compiler) emitLookupBoundsCheck(frame *Frame, arrayLen, index llvm.Valu
 // normal meaning) and for creating a new slice, where 'capacity' means the
 // biggest possible slice capacity, 'low' means len and 'high' means cap. The
 // logic is the same in both cases.
-func (c *Compiler) emitSliceBoundsCheck(frame *Frame, capacity, low, high llvm.Value, lowType, highType *types.Basic) {
+func (c *Compiler) emitSliceBoundsCheck(frame *Frame, capacity, low, high, max llvm.Value, lowType, highType, maxType *types.Basic) {
 	if frame.fn.IsNoBounds() {
 		// The //go:nobounds pragma was added to the function to avoid bounds
 		// checking.
@@ -71,6 +71,9 @@ func (c *Compiler) emitSliceBoundsCheck(frame *Frame, capacity, low, high llvm.V
 	if high.Type().IntTypeWidth() > capacityType.IntTypeWidth() {
 		capacityType = high.Type()
 	}
+	if max.Type().IntTypeWidth() > capacityType.IntTypeWidth() {
+		capacityType = max.Type()
+	}
 	if capacityType != capacity.Type() {
 		capacity = c.builder.CreateZExt(capacity, capacityType, "")
 	}
@@ -90,6 +93,13 @@ func (c *Compiler) emitSliceBoundsCheck(frame *Frame, capacity, low, high llvm.V
 			high = c.builder.CreateSExt(high, capacityType, "")
 		}
 	}
+	if max.Type().IntTypeWidth() < capacityType.IntTypeWidth() {
+		if maxType.Info()&types.IsUnsigned != 0 {
+			max = c.builder.CreateZExt(max, capacityType, "")
+		} else {
+			max = c.builder.CreateSExt(max, capacityType, "")
+		}
+	}
 
 	faultBlock := c.ctx.AddBasicBlock(frame.fn.LLVMFn, "slice.outofbounds")
 	nextBlock := c.ctx.AddBasicBlock(frame.fn.LLVMFn, "slice.next")
@@ -97,8 +107,10 @@ func (c *Compiler) emitSliceBoundsCheck(frame *Frame, capacity, low, high llvm.V
 
 	// Now do the bounds check: low > high || high > capacity
 	outOfBounds1 := c.builder.CreateICmp(llvm.IntUGT, low, high, "slice.lowhigh")
-	outOfBounds2 := c.builder.CreateICmp(llvm.IntUGT, high, capacity, "slice.highcap")
-	outOfBounds := c.builder.CreateOr(outOfBounds1, outOfBounds2, "slice.outofbounds")
+	outOfBounds2 := c.builder.CreateICmp(llvm.IntUGT, high, max, "slice.highmax")
+	outOfBounds3 := c.builder.CreateICmp(llvm.IntUGT, max, capacity, "slice.maxcap")
+	outOfBounds := c.builder.CreateOr(outOfBounds1, outOfBounds2, "slice.lowmax")
+	outOfBounds = c.builder.CreateOr(outOfBounds, outOfBounds3, "slice.lowcap")
 	c.builder.CreateCondBr(outOfBounds, faultBlock, nextBlock)
 
 	// Fail: this is a nil pointer, exit with a panic.

compiler/calls.go

@@ -38,7 +38,7 @@ func (c *Compiler) createCall(fn llvm.Value, args []llvm.Value, name string) llv
 }
 
 // Expand an argument type to a list that can be used in a function call
-// paramter list.
+// parameter list.
 func (c *Compiler) expandFormalParamType(t llvm.Type) []llvm.Type {
 	switch t.TypeKind() {
 	case llvm.StructTypeKind:
@@ -163,7 +163,7 @@ func (c *Compiler) collapseFormalParamInternal(t llvm.Type, fields []llvm.Value)
 	switch t.TypeKind() {
 	case llvm.StructTypeKind:
 		if len(c.flattenAggregateType(t)) <= MaxFieldsPerParam {
-			value := c.getZeroValue(t)
+			value := llvm.ConstNull(t)
 			for i, subtyp := range t.StructElementTypes() {
 				structField, remaining := c.collapseFormalParamInternal(subtyp, fields)
 				fields = remaining

compiler/channel.go

@@ -4,6 +4,7 @@ package compiler
 // or pseudo-operations that are lowered during goroutine lowering.
 
 import (
+	"fmt"
 	"go/types"
 
 	"golang.org/x/tools/go/ssa"
@@ -12,11 +13,22 @@ import (
 
 // emitMakeChan returns a new channel value for the given channel type.
 func (c *Compiler) emitMakeChan(expr *ssa.MakeChan) (llvm.Value, error) {
-	chanType := c.mod.GetTypeByName("runtime.channel")
-	size := c.targetData.TypeAllocSize(chanType)
+	chanType := c.getLLVMType(expr.Type())
+	size := c.targetData.TypeAllocSize(chanType.ElementType())
 	sizeValue := llvm.ConstInt(c.uintptrType, size, false)
 	ptr := c.createRuntimeCall("alloc", []llvm.Value{sizeValue}, "chan.alloc")
-	ptr = c.builder.CreateBitCast(ptr, llvm.PointerType(chanType, 0), "chan")
+	ptr = c.builder.CreateBitCast(ptr, chanType, "chan")
+	// Set the elementSize field
+	elementSizePtr := c.builder.CreateGEP(ptr, []llvm.Value{
+		llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+		llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+	}, "")
+	elementSize := c.targetData.TypeAllocSize(c.getLLVMType(expr.Type().(*types.Chan).Elem()))
+	if elementSize > 0xffff {
+		return ptr, c.makeError(expr.Pos(), fmt.Sprintf("element size is %d bytes, which is bigger than the maximum of %d bytes", elementSize, 0xffff))
+	}
+	elementSizeValue := llvm.ConstInt(c.ctx.Int16Type(), elementSize, false)
+	c.builder.CreateStore(elementSizeValue, elementSizePtr)
 	return ptr, nil
 }
 
@@ -33,8 +45,7 @@ func (c *Compiler) emitChanSend(frame *Frame, instr *ssa.Send) {
 
 	// Do the send.
 	coroutine := c.createRuntimeCall("getCoroutine", nil, "")
-	valueSize := llvm.ConstInt(c.uintptrType, c.targetData.TypeAllocSize(chanValue.Type()), false)
-	c.createRuntimeCall("chanSend", []llvm.Value{coroutine, ch, valueAllocaCast, valueSize}, "")
+	c.createRuntimeCall("chanSend", []llvm.Value{coroutine, ch, valueAllocaCast}, "")
 
 	// End the lifetime of the alloca.
 	// This also works around a bug in CoroSplit, at least in LLVM 8:
@@ -53,13 +64,12 @@ func (c *Compiler) emitChanRecv(frame *Frame, unop *ssa.UnOp) llvm.Value {
 
 	// Do the receive.
 	coroutine := c.createRuntimeCall("getCoroutine", nil, "")
-	valueSize := llvm.ConstInt(c.uintptrType, c.targetData.TypeAllocSize(valueType), false)
-	c.createRuntimeCall("chanRecv", []llvm.Value{coroutine, ch, valueAllocaCast, valueSize}, "")
+	c.createRuntimeCall("chanRecv", []llvm.Value{coroutine, ch, valueAllocaCast}, "")
 	received := c.builder.CreateLoad(valueAlloca, "chan.received")
 	c.emitLifetimeEnd(valueAllocaCast, valueAllocaSize)
 
 	if unop.CommaOk {
-		commaOk := c.createRuntimeCall("getTaskPromiseData", []llvm.Value{coroutine}, "chan.commaOk.wide")
+		commaOk := c.createRuntimeCall("getTaskStateData", []llvm.Value{coroutine}, "chan.commaOk.wide")
 		commaOk = c.builder.CreateTrunc(commaOk, c.ctx.Int1Type(), "chan.commaOk")
 		tuple := llvm.Undef(c.ctx.StructType([]llvm.Type{valueType, c.ctx.Int1Type()}, false))
 		tuple = c.builder.CreateInsertValue(tuple, received, 0, "")
@@ -72,8 +82,157 @@ func (c *Compiler) emitChanRecv(frame *Frame, unop *ssa.UnOp) llvm.Value {
 
 // emitChanClose closes the given channel.
 func (c *Compiler) emitChanClose(frame *Frame, param ssa.Value) {
-	valueType := c.getLLVMType(param.Type().(*types.Chan).Elem())
-	valueSize := llvm.ConstInt(c.uintptrType, c.targetData.TypeAllocSize(valueType), false)
 	ch := c.getValue(frame, param)
-	c.createRuntimeCall("chanClose", []llvm.Value{ch, valueSize}, "")
+	c.createRuntimeCall("chanClose", []llvm.Value{ch}, "")
+}
+
+// emitSelect emits all IR necessary for a select statements. That's a
+// non-trivial amount of code because select is very complex to implement.
+func (c *Compiler) emitSelect(frame *Frame, expr *ssa.Select) llvm.Value {
+	if len(expr.States) == 0 {
+		// Shortcuts for some simple selects.
+		llvmType := c.getLLVMType(expr.Type())
+		if expr.Blocking {
+			// Blocks forever:
+			//     select {}
+			c.createRuntimeCall("deadlock", nil, "")
+			return llvm.Undef(llvmType)
+		} else {
+			// No-op:
+			//     select {
+			//     default:
+			//     }
+			retval := llvm.Undef(llvmType)
+			retval = c.builder.CreateInsertValue(retval, llvm.ConstInt(c.intType, 0xffffffffffffffff, true), 0, "")
+			return retval // {-1, false}
+		}
+	}
+
+	// This code create a (stack-allocated) slice containing all the select
+	// cases and then calls runtime.chanSelect to perform the actual select
+	// statement.
+	// Simple selects (blocking and with just one case) are already transformed
+	// into regular chan operations during SSA construction so we don't have to
+	// optimize such small selects.
+
+	// Go through all the cases. Create the selectStates slice and and
+	// determine the receive buffer size and alignment.
+	recvbufSize := uint64(0)
+	recvbufAlign := 0
+	hasReceives := false
+	var selectStates []llvm.Value
+	chanSelectStateType := c.getLLVMRuntimeType("chanSelectState")
+	for _, state := range expr.States {
+		ch := c.getValue(frame, state.Chan)
+		selectState := llvm.ConstNull(chanSelectStateType)
+		selectState = c.builder.CreateInsertValue(selectState, ch, 0, "")
+		switch state.Dir {
+		case types.RecvOnly:
+			// Make sure the receive buffer is big enough and has the correct alignment.
+			llvmType := c.getLLVMType(state.Chan.Type().(*types.Chan).Elem())
+			if size := c.targetData.TypeAllocSize(llvmType); size > recvbufSize {
+				recvbufSize = size
+			}
+			if align := c.targetData.ABITypeAlignment(llvmType); align > recvbufAlign {
+				recvbufAlign = align
+			}
+			hasReceives = true
+		case types.SendOnly:
+			// Store this value in an alloca and put a pointer to this alloca
+			// in the send state.
+			sendValue := c.getValue(frame, state.Send)
+			alloca := c.createEntryBlockAlloca(sendValue.Type(), "select.send.value")
+			c.builder.CreateStore(sendValue, alloca)
+			ptr := c.builder.CreateBitCast(alloca, c.i8ptrType, "")
+			selectState = c.builder.CreateInsertValue(selectState, ptr, 1, "")
+		default:
+			panic("unreachable")
+		}
+		selectStates = append(selectStates, selectState)
+	}
+
+	// Create a receive buffer, where the received value will be stored.
+	recvbuf := llvm.Undef(c.i8ptrType)
+	if hasReceives {
+		allocaType := llvm.ArrayType(c.ctx.Int8Type(), int(recvbufSize))
+		recvbufAlloca := c.builder.CreateAlloca(allocaType, "select.recvbuf.alloca")
+		recvbufAlloca.SetAlignment(recvbufAlign)
+		recvbuf = c.builder.CreateGEP(recvbufAlloca, []llvm.Value{
+			llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+			llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+		}, "select.recvbuf")
+	}
+
+	// Create the states slice (allocated on the stack).
+	statesAllocaType := llvm.ArrayType(chanSelectStateType, len(selectStates))
+	statesAlloca := c.builder.CreateAlloca(statesAllocaType, "select.states.alloca")
+	for i, state := range selectStates {
+		// Set each slice element to the appropriate channel.
+		gep := c.builder.CreateGEP(statesAlloca, []llvm.Value{
+			llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+			llvm.ConstInt(c.ctx.Int32Type(), uint64(i), false),
+		}, "")
+		c.builder.CreateStore(state, gep)
+	}
+	statesPtr := c.builder.CreateGEP(statesAlloca, []llvm.Value{
+		llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+		llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+	}, "select.states")
+	statesLen := llvm.ConstInt(c.uintptrType, uint64(len(selectStates)), false)
+
+	// Convert the 'blocking' flag on this select into a LLVM value.
+	blockingInt := uint64(0)
+	if expr.Blocking {
+		blockingInt = 1
+	}
+	blockingValue := llvm.ConstInt(c.ctx.Int1Type(), blockingInt, false)
+
+	// Do the select in the runtime.
+	results := c.createRuntimeCall("chanSelect", []llvm.Value{
+		recvbuf,
+		statesPtr, statesLen, statesLen, // []chanSelectState
+		blockingValue,
+	}, "")
+
+	// The result value does not include all the possible received values,
+	// because we can't load them in advance. Instead, the *ssa.Extract
+	// instruction will treat a *ssa.Select specially and load it there inline.
+	// Store the receive alloca in a sidetable until we hit this extract
+	// instruction.
+	if frame.selectRecvBuf == nil {
+		frame.selectRecvBuf = make(map[*ssa.Select]llvm.Value)
+	}
+	frame.selectRecvBuf[expr] = recvbuf
+
+	return results
+}
+
+// getChanSelectResult returns the special values from a *ssa.Extract expression
+// when extracting a value from a select statement (*ssa.Select). Because
+// *ssa.Select cannot load all values in advance, it does this later in the
+// *ssa.Extract expression.
+func (c *Compiler) getChanSelectResult(frame *Frame, expr *ssa.Extract) llvm.Value {
+	if expr.Index == 0 {
+		// index
+		value := c.getValue(frame, expr.Tuple)
+		index := c.builder.CreateExtractValue(value, expr.Index, "")
+		if index.Type().IntTypeWidth() < c.intType.IntTypeWidth() {
+			index = c.builder.CreateSExt(index, c.intType, "")
+		}
+		return index
+	} else if expr.Index == 1 {
+		// comma-ok
+		value := c.getValue(frame, expr.Tuple)
+		return c.builder.CreateExtractValue(value, expr.Index, "")
+	} else {
+		// Select statements are (index, ok, ...) where ... is a number of
+		// received values, depending on how many receive statements there
+		// are. They are all combined into one alloca (because only one
+		// receive can proceed at a time) so we'll get that alloca, bitcast
+		// it to the correct type, and dereference it.
+		recvbuf := frame.selectRecvBuf[expr.Tuple.(*ssa.Select)]
+		typ := llvm.PointerType(c.getLLVMType(expr.Type()), 0)
+		ptr := c.builder.CreateBitCast(recvbuf, typ, "")
+		return c.builder.CreateLoad(ptr, "")
+	}
 }

compiler/check.go

@@ -0,0 +1,128 @@
+package compiler
+
+// This file implements a set of sanity checks for the IR that is generated.
+// It can catch some mistakes that LLVM's verifier cannot.
+
+import (
+	"errors"
+	"fmt"
+
+	"tinygo.org/x/go-llvm"
+)
+
+func (c *Compiler) checkType(t llvm.Type, checked map[llvm.Type]struct{}, specials map[llvm.TypeKind]llvm.Type) {
+	if t.IsNil() {
+		panic(t)
+	}
+
+	// prevent infinite recursion for self-referential types
+	if _, ok := checked[t]; ok {
+		return
+	}
+	checked[t] = struct{}{}
+
+	// check for any context mismatches
+	switch {
+	case t.Context() == c.ctx:
+		// this is correct
+	case t.Context() == llvm.GlobalContext():
+		// somewhere we accidentally used the global context instead of a real context
+		panic(fmt.Errorf("type %q uses global context", t.String()))
+	default:
+		// we used some other context by accident
+		panic(fmt.Errorf("type %q uses context %v instead of the main context %v", t.Context(), c.ctx))
+	}
+
+	// if this is a composite type, check the components of the type
+	switch t.TypeKind() {
+	case llvm.VoidTypeKind, llvm.LabelTypeKind, llvm.TokenTypeKind, llvm.MetadataTypeKind:
+		// there should only be one of any of these
+		if s, ok := specials[t.TypeKind()]; !ok {
+			specials[t.TypeKind()] = t
+		} else if s != t {
+			panic(fmt.Errorf("duplicate special type %q: %v and %v", t.TypeKind().String(), t, s))
+		}
+	case llvm.FloatTypeKind, llvm.DoubleTypeKind, llvm.X86_FP80TypeKind, llvm.FP128TypeKind, llvm.PPC_FP128TypeKind:
+		// floating point numbers are primitives - nothing to recurse
+	case llvm.IntegerTypeKind:
+		// integers are primitives - nothing to recurse
+	case llvm.FunctionTypeKind:
+		// check arguments and return(s)
+		for _, v := range t.ParamTypes() {
+			c.checkType(v, checked, specials)
+		}
+		c.checkType(t.ReturnType(), checked, specials)
+	case llvm.StructTypeKind:
+		// check all elements
+		for _, v := range t.StructElementTypes() {
+			c.checkType(v, checked, specials)
+		}
+	case llvm.ArrayTypeKind:
+		// check element type
+		c.checkType(t.ElementType(), checked, specials)
+	case llvm.PointerTypeKind:
+		// check underlying type
+		c.checkType(t.ElementType(), checked, specials)
+	case llvm.VectorTypeKind:
+		// check element type
+		c.checkType(t.ElementType(), checked, specials)
+	}
+}
+
+func (c *Compiler) checkValue(v llvm.Value, types map[llvm.Type]struct{}, specials map[llvm.TypeKind]llvm.Type) {
+	// check type
+	c.checkType(v.Type(), types, specials)
+}
+
+func (c *Compiler) checkInstruction(inst llvm.Value, types map[llvm.Type]struct{}, specials map[llvm.TypeKind]llvm.Type) {
+	// check value properties
+	c.checkValue(inst, types, specials)
+
+	// check operands
+	for i := 0; i < inst.OperandsCount(); i++ {
+		c.checkValue(inst.Operand(i), types, specials)
+	}
+}
+
+func (c *Compiler) checkBasicBlock(bb llvm.BasicBlock, types map[llvm.Type]struct{}, specials map[llvm.TypeKind]llvm.Type) {
+	// check basic block value and type
+	c.checkValue(bb.AsValue(), types, specials)
+
+	// check instructions
+	for inst := bb.FirstInstruction(); !inst.IsNil(); inst = llvm.NextInstruction(inst) {
+		c.checkInstruction(inst, types, specials)
+	}
+}
+
+func (c *Compiler) checkFunction(fn llvm.Value, types map[llvm.Type]struct{}, specials map[llvm.TypeKind]llvm.Type) {
+	// check function value and type
+	c.checkValue(fn, types, specials)
+
+	// check basic blocks
+	for bb := fn.FirstBasicBlock(); !bb.IsNil(); bb = llvm.NextBasicBlock(bb) {
+		c.checkBasicBlock(bb, types, specials)
+	}
+}
+
+func (c *Compiler) checkModule() {
+	// check for any context mismatches
+	switch {
+	case c.mod.Context() == c.ctx:
+		// this is correct
+	case c.mod.Context() == llvm.GlobalContext():
+		// somewhere we accidentally used the global context instead of a real context
+		panic(errors.New("module uses global context"))
+	default:
+		// we used some other context by accident
+		panic(fmt.Errorf("module uses context %v instead of the main context %v", c.mod.Context(), c.ctx))
+	}
+
+	types := map[llvm.Type]struct{}{}
+	specials := map[llvm.TypeKind]llvm.Type{}
+	for fn := c.mod.FirstFunction(); !fn.IsNil(); fn = llvm.NextFunction(fn) {
+		c.checkFunction(fn, types, specials)
+	}
+	for g := c.mod.FirstGlobal(); !g.IsNil(); g = llvm.NextGlobal(g) {
+		c.checkValue(g, types, specials)
+	}
+}

compiler/compiler.go

@@ -3,6 +3,7 @@ package compiler
 import (
 	"errors"
 	"fmt"
+	"go/ast"
 	"go/build"
 	"go/constant"
 	"go/token"
@@ -26,6 +27,24 @@ func init() {
 	llvm.InitializeAllAsmPrinters()
 }
 
+// The TinyGo import path.
+const tinygoPath = "github.com/tinygo-org/tinygo"
+
+// functionsUsedInTransform is a list of function symbols that may be used
+// during TinyGo optimization passes so they have to be marked as external
+// linkage until all TinyGo passes have finished.
+var functionsUsedInTransforms = []string{
+	"runtime.alloc",
+	"runtime.free",
+	"runtime.sleepTask",
+	"runtime.sleepCurrentTask",
+	"runtime.setTaskStatePtr",
+	"runtime.getTaskStatePtr",
+	"runtime.activateTask",
+	"runtime.scheduler",
+	"runtime.startGoroutine",
+}
+
 // Configure the compiler.
 type Config struct {
 	Triple        string   // LLVM target triple, e.g. x86_64-unknown-linux-gnu (empty string means default)
@@ -34,15 +53,24 @@ type Config struct {
 	GOOS          string   //
 	GOARCH        string   //
 	GC            string   // garbage collection strategy
-	PanicStrategy string   // panic strategy ("abort" or "trap")
+	Scheduler     string   // scheduler implementation ("coroutines" or "tasks")
+	PanicStrategy string   // panic strategy ("print" or "trap")
 	CFlags        []string // cflags to pass to cgo
 	LDFlags       []string // ldflags to pass to cgo
+	ClangHeaders  string   // Clang built-in header include path
 	DumpSSA       bool     // dump Go SSA, for compiler debugging
+	VerifyIR      bool     // run extra checks on the IR
 	Debug         bool     // add debug symbols for gdb
 	GOROOT        string   // GOROOT
 	TINYGOROOT    string   // GOROOT for TinyGo
 	GOPATH        string   // GOPATH, like `go env GOPATH`
 	BuildTags     []string // build tags for TinyGo (empty means {Config.GOOS/Config.GOARCH})
+	TestConfig    TestConfig
+}
+
+type TestConfig struct {
+	CompileTestBinary bool
+	// TODO: Filter the test functions to run, include verbose flag, etc
 }
 
 type Compiler struct {
@@ -63,6 +91,7 @@ type Compiler struct {
 	interfaceInvokeWrappers []interfaceInvokeWrapper
 	ir                      *ir.Program
 	diagnostics             []error
+	astComments             map[string]*ast.CommentGroup
 }
 
 type Frame struct {
@@ -79,6 +108,7 @@ type Frame struct {
 	deferFuncs        map[*ir.Function]int
 	deferInvokeFuncs  map[string]int
 	deferClosureFuncs map[*ir.Function]int
+	selectRecvBuf     map[*ssa.Select]llvm.Value
 }
 
 type Phi struct {
@@ -154,11 +184,21 @@ func (c *Compiler) TargetData() llvm.TargetData {
 
 // selectGC picks an appropriate GC strategy if none was provided.
 func (c *Compiler) selectGC() string {
-	gc := c.GC
-	if gc == "" {
-		gc = "dumb"
+	if c.GC != "" {
+		return c.GC
 	}
-	return gc
+	return "conservative"
+}
+
+// selectScheduler picks an appropriate scheduler for the target if none was
+// given.
+func (c *Compiler) selectScheduler() string {
+	if c.Scheduler != "" {
+		// A scheduler was specified in the target description.
+		return c.Scheduler
+	}
+	// Fall back to coroutines, which are supported everywhere.
+	return "coroutines"
 }
 
 // Compile the given package path or .go file path. Return an error when this
@@ -177,6 +217,7 @@ func (c *Compiler) Compile(mainPath string) []error {
 	if err != nil {
 		return []error{err}
 	}
+	buildTags := append([]string{"tinygo", "gc." + c.selectGC(), "scheduler." + c.selectScheduler()}, c.BuildTags...)
 	lprogram := &loader.Program{
 		Build: &build.Context{
 			GOARCH:      c.GOARCH,
@@ -186,7 +227,7 @@ func (c *Compiler) Compile(mainPath string) []error {
 			CgoEnabled:  true,
 			UseAllFiles: false,
 			Compiler:    "gc", // must be one of the recognized compilers
-			BuildTags:   append([]string{"tinygo", "gc." + c.selectGC()}, c.BuildTags...),
+			BuildTags:   buildTags,
 		},
 		OverlayBuild: &build.Context{
 			GOARCH:      c.GOARCH,
@@ -196,24 +237,31 @@ func (c *Compiler) Compile(mainPath string) []error {
 			CgoEnabled:  true,
 			UseAllFiles: false,
 			Compiler:    "gc", // must be one of the recognized compilers
-			BuildTags:   append([]string{"tinygo", "gc." + c.selectGC()}, c.BuildTags...),
+			BuildTags:   buildTags,
 		},
-		ShouldOverlay: func(path string) bool {
+		OverlayPath: func(path string) string {
+			// Return the (overlay) import path when it should be overlaid, and
+			// "" if it should not.
+			if strings.HasPrefix(path, tinygoPath+"/src/") {
+				// Avoid issues with packages that are imported twice, one from
+				// GOPATH and one from TINYGOPATH.
+				path = path[len(tinygoPath+"/src/"):]
+			}
 			switch path {
-			case "machine", "os", "reflect", "runtime", "runtime/volatile", "sync":
-				return true
+			case "machine", "os", "reflect", "runtime", "runtime/volatile", "sync", "testing":
+				return path
 			default:
 				if strings.HasPrefix(path, "device/") || strings.HasPrefix(path, "examples/") {
-					return true
+					return path
 				} else if path == "syscall" {
 					for _, tag := range c.BuildTags {
-						if tag == "avr" || tag == "cortexm" || tag == "darwin" {
-							return true
+						if tag == "baremetal" || tag == "darwin" {
+							return path
 						}
 					}
 				}
 			}
-			return false
+			return ""
 		},
 		TypeChecker: types.Config{
 			Sizes: &StdSizes{
@@ -222,10 +270,12 @@ func (c *Compiler) Compile(mainPath string) []error {
 				MaxAlign: int64(c.targetData.PrefTypeAlignment(c.i8ptrType)),
 			},
 		},
-		Dir:        wd,
-		TINYGOROOT: c.TINYGOROOT,
-		CFlags:     c.CFlags,
+		Dir:          wd,
+		TINYGOROOT:   c.TINYGOROOT,
+		CFlags:       c.CFlags,
+		ClangHeaders: c.ClangHeaders,
 	}
+
 	if strings.HasSuffix(mainPath, ".go") {
 		_, err = lprogram.ImportFile(mainPath)
 		if err != nil {
@@ -237,12 +287,13 @@ func (c *Compiler) Compile(mainPath string) []error {
 			return []error{err}
 		}
 	}
+
 	_, err = lprogram.Import("runtime", "")
 	if err != nil {
 		return []error{err}
 	}
 
-	err = lprogram.Parse()
+	err = lprogram.Parse(c.TestConfig.CompileTestBinary)
 	if err != nil {
 		return []error{err}
 	}
@@ -265,39 +316,7 @@ func (c *Compiler) Compile(mainPath string) []error {
 
 	var frames []*Frame
 
-	// Declare all named struct types.
-	for _, t := range c.ir.NamedTypes {
-		if named, ok := t.Type.Type().(*types.Named); ok {
-			if _, ok := named.Underlying().(*types.Struct); ok {
-				t.LLVMType = c.ctx.StructCreateNamed(named.Obj().Pkg().Path() + "." + named.Obj().Name())
-			}
-		}
-	}
-
-	// Define all named struct types.
-	for _, t := range c.ir.NamedTypes {
-		if named, ok := t.Type.Type().(*types.Named); ok {
-			if st, ok := named.Underlying().(*types.Struct); ok {
-				llvmType := c.getLLVMType(st)
-				t.LLVMType.StructSetBody(llvmType.StructElementTypes(), false)
-			}
-		}
-	}
-
-	// Declare all globals.
-	for _, g := range c.ir.Globals {
-		typ := g.Type().(*types.Pointer).Elem()
-		llvmType := c.getLLVMType(typ)
-		global := c.mod.NamedGlobal(g.LinkName())
-		if global.IsNil() {
-			global = llvm.AddGlobal(c.mod, llvmType, g.LinkName())
-		}
-		g.LLVMGlobal = global
-		if !g.IsExtern() {
-			global.SetLinkage(llvm.InternalLinkage)
-			global.SetInitializer(c.getZeroValue(llvmType))
-		}
-	}
+	c.loadASTComments(lprogram)
 
 	// Declare all functions.
 	for _, f := range c.ir.Functions {
@@ -345,13 +364,15 @@ func (c *Compiler) Compile(mainPath string) []error {
 	// would be optimized away.
 	realMain := c.mod.NamedFunction(c.ir.MainPkg().Pkg.Path() + ".main")
 	realMain.SetLinkage(llvm.ExternalLinkage) // keep alive until goroutine lowering
-	c.mod.NamedFunction("runtime.alloc").SetLinkage(llvm.ExternalLinkage)
-	c.mod.NamedFunction("runtime.free").SetLinkage(llvm.ExternalLinkage)
-	c.mod.NamedFunction("runtime.sleepTask").SetLinkage(llvm.ExternalLinkage)
-	c.mod.NamedFunction("runtime.setTaskPromisePtr").SetLinkage(llvm.ExternalLinkage)
-	c.mod.NamedFunction("runtime.getTaskPromisePtr").SetLinkage(llvm.ExternalLinkage)
-	c.mod.NamedFunction("runtime.activateTask").SetLinkage(llvm.ExternalLinkage)
-	c.mod.NamedFunction("runtime.scheduler").SetLinkage(llvm.ExternalLinkage)
+
+	// Make sure these functions are kept in tact during TinyGo transformation passes.
+	for _, name := range functionsUsedInTransforms {
+		fn := c.mod.NamedFunction(name)
+		if fn.IsNil() {
+			continue
+		}
+		fn.SetLinkage(llvm.ExternalLinkage)
+	}
 
 	// Load some attributes
 	getAttr := func(attrName string) llvm.Attribute {
@@ -371,6 +392,15 @@ func (c *Compiler) Compile(mainPath string) []error {
 	// See emitNilCheck in asserts.go.
 	c.mod.NamedFunction("runtime.isnil").AddAttributeAtIndex(1, nocapture)
 
+	// This function is necessary for tracking pointers on the stack in a
+	// portable way (see gc.go). Indicate to the optimizer that the only thing
+	// we'll do is read the pointer.
+	trackPointer := c.mod.NamedFunction("runtime.trackPointer")
+	if !trackPointer.IsNil() {
+		trackPointer.AddAttributeAtIndex(1, nocapture)
+		trackPointer.AddAttributeAtIndex(1, readonly)
+	}
+
 	// Memory copy operations do not capture pointers, even though some weird
 	// pointer arithmetic is happening in the Go implementation.
 	for _, fnName := range []string{"runtime.memcpy", "runtime.memmove"} {
@@ -403,6 +433,22 @@ func (c *Compiler) Compile(mainPath string) []error {
 	return c.diagnostics
 }
 
+// getRuntimeType obtains a named type from the runtime package and returns it
+// as a Go type.
+func (c *Compiler) getRuntimeType(name string) types.Type {
+	return c.ir.Program.ImportedPackage("runtime").Type(name).Type()
+}
+
+// getLLVMRuntimeType obtains a named type from the runtime package and returns
+// it as a LLVM type, creating it if necessary. It is a shorthand for
+// getLLVMType(getRuntimeType(name)).
+func (c *Compiler) getLLVMRuntimeType(name string) llvm.Type {
+	return c.getLLVMType(c.getRuntimeType(name))
+}
+
+// getLLVMType creates and returns a LLVM type for a Go type. In the case of
+// named struct types (or Go types implemented as named LLVM structs such as
+// strings) it also creates it first if necessary.
 func (c *Compiler) getLLVMType(goType types.Type) llvm.Type {
 	switch typ := goType.(type) {
 	case *types.Array:
@@ -431,7 +477,7 @@ func (c *Compiler) getLLVMType(goType types.Type) llvm.Type {
 		case types.Complex128:
 			return c.ctx.StructType([]llvm.Type{c.ctx.DoubleType(), c.ctx.DoubleType()}, false)
 		case types.String, types.UntypedString:
-			return c.mod.GetTypeByName("runtime._string")
+			return c.getLLVMRuntimeType("_string")
 		case types.Uintptr:
 			return c.uintptrType
 		case types.UnsafePointer:
@@ -440,16 +486,23 @@ func (c *Compiler) getLLVMType(goType types.Type) llvm.Type {
 			panic("unknown basic type: " + typ.String())
 		}
 	case *types.Chan:
-		return llvm.PointerType(c.mod.GetTypeByName("runtime.channel"), 0)
+		return llvm.PointerType(c.getLLVMRuntimeType("channel"), 0)
 	case *types.Interface:
-		return c.mod.GetTypeByName("runtime._interface")
+		return c.getLLVMRuntimeType("_interface")
 	case *types.Map:
-		return llvm.PointerType(c.mod.GetTypeByName("runtime.hashmap"), 0)
+		return llvm.PointerType(c.getLLVMRuntimeType("hashmap"), 0)
 	case *types.Named:
-		if _, ok := typ.Underlying().(*types.Struct); ok {
-			llvmType := c.mod.GetTypeByName(typ.Obj().Pkg().Path() + "." + typ.Obj().Name())
+		if st, ok := typ.Underlying().(*types.Struct); ok {
+			// Structs are a special case. While other named types are ignored
+			// in LLVM IR, named structs are implemented as named structs in
+			// LLVM. This is because it is otherwise impossible to create
+			// self-referencing types such as linked lists.
+			llvmName := typ.Obj().Pkg().Path() + "." + typ.Obj().Name()
+			llvmType := c.mod.GetTypeByName(llvmName)
 			if llvmType.IsNil() {
-				panic("underlying type not found: " + typ.Obj().Pkg().Path() + "." + typ.Obj().Name())
+				llvmType = c.ctx.StructCreateNamed(llvmName)
+				underlying := c.getLLVMType(st)
+				llvmType.StructSetBody(underlying.StructElementTypes(), false)
 			}
 			return llvmType
 		}
@@ -511,42 +564,6 @@ func (c *Compiler) getLLVMType(goType types.Type) llvm.Type {
 	}
 }
 
-// Return a zero LLVM value for any LLVM type. Setting this value as an
-// initializer has the same effect as setting 'zeroinitializer' on a value.
-// Sadly, I haven't found a way to do it directly with the Go API but this works
-// just fine.
-func (c *Compiler) getZeroValue(typ llvm.Type) llvm.Value {
-	switch typ.TypeKind() {
-	case llvm.ArrayTypeKind:
-		subTyp := typ.ElementType()
-		subVal := c.getZeroValue(subTyp)
-		vals := make([]llvm.Value, typ.ArrayLength())
-		for i := range vals {
-			vals[i] = subVal
-		}
-		return llvm.ConstArray(subTyp, vals)
-	case llvm.FloatTypeKind, llvm.DoubleTypeKind:
-		return llvm.ConstFloat(typ, 0.0)
-	case llvm.IntegerTypeKind:
-		return llvm.ConstInt(typ, 0, false)
-	case llvm.PointerTypeKind:
-		return llvm.ConstPointerNull(typ)
-	case llvm.StructTypeKind:
-		types := typ.StructElementTypes()
-		vals := make([]llvm.Value, len(types))
-		for i, subTyp := range types {
-			vals[i] = c.getZeroValue(subTyp)
-		}
-		if typ.StructName() != "" {
-			return llvm.ConstNamedStruct(typ, vals)
-		} else {
-			return c.ctx.ConstStruct(vals, false)
-		}
-	default:
-		panic("unknown LLVM zero inititializer: " + typ.String())
-	}
-}
-
 // Is this a pointer type of some sort? Can be unsafe.Pointer or any *T pointer.
 func isPointer(typ types.Type) bool {
 	if _, ok := typ.(*types.Pointer); ok {
@@ -769,6 +786,11 @@ func (c *Compiler) parseFuncDecl(f *ir.Function) *Frame {
 	// External/exported functions may not retain pointer values.
 	// https://golang.org/cmd/cgo/#hdr-Passing_pointers
 	if f.IsExported() {
+		// Set the wasm-import-module attribute if the function's module is set.
+		if f.Module() != "" {
+			wasmImportModuleAttr := c.ctx.CreateStringAttribute("wasm-import-module", f.Module())
+			frame.fn.LLVMFn.AddFunctionAttr(wasmImportModuleAttr)
+		}
 		nocaptureKind := llvm.AttributeKindID("nocapture")
 		nocapture := c.ctx.CreateEnumAttribute(nocaptureKind, 0)
 		for i, typ := range paramTypes {
@@ -826,7 +848,8 @@ func (c *Compiler) parseFunc(frame *Frame) {
 		fmt.Printf("\nfunc %s:\n", frame.fn.Function)
 	}
 	if !frame.fn.LLVMFn.IsDeclaration() {
-		panic("function is already defined: " + frame.fn.LLVMFn.Name())
+		c.addError(frame.fn.Pos(), "function is already defined:"+frame.fn.LLVMFn.Name())
+		return
 	}
 	if !frame.fn.IsExported() {
 		frame.fn.LLVMFn.SetLinkage(llvm.InternalLinkage)
@@ -842,6 +865,10 @@ func (c *Compiler) parseFunc(frame *Frame) {
 		// Add LLVM inline hint to functions with //go:inline pragma.
 		inline := c.ctx.CreateEnumAttribute(llvm.AttributeKindID("inlinehint"), 0)
 		frame.fn.LLVMFn.AddFunctionAttr(inline)
+	case ir.InlineNone:
+		// Add LLVM attribute to always avoid inlining this function.
+		noinline := c.ctx.CreateEnumAttribute(llvm.AttributeKindID("noinline"), 0)
+		frame.fn.LLVMFn.AddFunctionAttr(noinline)
 	}
 
 	// Add debug info, if needed.
@@ -994,42 +1021,56 @@ func (c *Compiler) parseInstr(frame *Frame, instr ssa.Instruction) {
 			frame.locals[instr] = llvm.Undef(c.getLLVMType(instr.Type()))
 		} else {
 			frame.locals[instr] = value
+			if len(*instr.Referrers()) != 0 && c.needsStackObjects() {
+				c.trackExpr(frame, instr, value)
+			}
 		}
 	case *ssa.DebugRef:
 		// ignore
 	case *ssa.Defer:
 		c.emitDefer(frame, instr)
 	case *ssa.Go:
-		if instr.Call.IsInvoke() {
-			c.addError(instr.Pos(), "todo: go on method receiver")
-			return
-		}
-		callee := instr.Call.StaticCallee()
-		if callee == nil {
-			c.addError(instr.Pos(), "todo: go on non-direct function (function pointer, etc.)")
-			return
-		}
-		calleeFn := c.ir.GetFunction(callee)
-
-		// Mark this function as a 'go' invocation and break invalid
-		// interprocedural optimizations. For example, heap-to-stack
-		// transformations are not sound as goroutines can outlive their parent.
-		calleeType := calleeFn.LLVMFn.Type()
-		calleeValue := c.builder.CreateBitCast(calleeFn.LLVMFn, c.i8ptrType, "")
-		calleeValue = c.createRuntimeCall("makeGoroutine", []llvm.Value{calleeValue}, "")
-		calleeValue = c.builder.CreateBitCast(calleeValue, calleeType, "")
-
 		// Get all function parameters to pass to the goroutine.
 		var params []llvm.Value
 		for _, param := range instr.Call.Args {
 			params = append(params, c.getValue(frame, param))
 		}
-		if !calleeFn.IsExported() {
-			params = append(params, llvm.Undef(c.i8ptrType)) // context parameter
-			params = append(params, llvm.Undef(c.i8ptrType)) // parent coroutine handle
-		}
 
-		c.createCall(calleeValue, params, "")
+		// Start a new goroutine.
+		if callee := instr.Call.StaticCallee(); callee != nil {
+			// Static callee is known. This makes it easier to start a new
+			// goroutine.
+			calleeFn := c.ir.GetFunction(callee)
+			if !calleeFn.IsExported() && c.selectScheduler() != "tasks" {
+				// For coroutine scheduling, this is only required when calling
+				// an external function.
+				// For tasks, because all params are stored in a single object,
+				// no unnecessary parameters should be stored anyway.
+				params = append(params, llvm.Undef(c.i8ptrType))            // context parameter
+				params = append(params, llvm.ConstPointerNull(c.i8ptrType)) // parent coroutine handle
+			}
+			c.emitStartGoroutine(calleeFn.LLVMFn, params)
+		} else if !instr.Call.IsInvoke() {
+			// This is a function pointer.
+			// At the moment, two extra params are passed to the newly started
+			// goroutine:
+			//   * The function context, for closures.
+			//   * The parent handle (for coroutines) or the function pointer
+			//     itself (for tasks).
+			funcPtr, context := c.decodeFuncValue(c.getValue(frame, instr.Call.Value), instr.Call.Value.Type().(*types.Signature))
+			params = append(params, context) // context parameter
+			switch c.selectScheduler() {
+			case "coroutines":
+				params = append(params, llvm.ConstPointerNull(c.i8ptrType)) // parent coroutine handle
+			case "tasks":
+				params = append(params, funcPtr)
+			default:
+				panic("unknown scheduler type")
+			}
+			c.emitStartGoroutine(funcPtr, params)
+		} else {
+			c.addError(instr.Pos(), "todo: go on interface call")
+		}
 	case *ssa.If:
 		cond := c.getValue(frame, instr.Cond)
 		block := instr.Block()
@@ -1056,7 +1097,7 @@ func (c *Compiler) parseInstr(frame *Frame, instr ssa.Instruction) {
 			c.builder.CreateRet(c.getValue(frame, instr.Results[0]))
 		} else {
 			// Multiple return values. Put them all in a struct.
-			retVal := c.getZeroValue(frame.fn.LLVMFn.Type().ElementType().ReturnType())
+			retVal := llvm.ConstNull(frame.fn.LLVMFn.Type().ElementType().ReturnType())
 			for i, result := range instr.Results {
 				val := c.getValue(frame, result)
 				retVal = c.builder.CreateInsertValue(retVal, val, i, "")
@@ -1075,12 +1116,7 @@ func (c *Compiler) parseInstr(frame *Frame, instr ssa.Instruction) {
 			// nothing to store
 			return
 		}
-		store := c.builder.CreateStore(llvmVal, llvmAddr)
-		valType := instr.Addr.Type().Underlying().(*types.Pointer).Elem()
-		if c.ir.IsVolatile(valType) {
-			// Volatile store, for memory-mapped registers.
-			store.SetVolatile(true)
-		}
+		c.builder.CreateStore(llvmVal, llvmAddr)
 	default:
 		c.addError(instr.Pos(), "unknown instruction: "+instr.String())
 	}
@@ -1283,11 +1319,11 @@ func (c *Compiler) parseCall(frame *Frame, instr *ssa.CallCommon) (llvm.Value, e
 	if fn := instr.StaticCallee(); fn != nil {
 		name := fn.RelString(nil)
 		switch {
-		case name == "device/arm.ReadRegister":
-			return c.emitReadRegister(instr.Args)
-		case name == "device/arm.Asm" || name == "device/avr.Asm":
+		case name == "device/arm.ReadRegister" || name == "device/riscv.ReadRegister":
+			return c.emitReadRegister(name, instr.Args)
+		case name == "device/arm.Asm" || name == "device/avr.Asm" || name == "device/riscv.Asm":
 			return c.emitAsm(instr.Args)
-		case name == "device/arm.AsmFull" || name == "device/avr.AsmFull":
+		case name == "device/arm.AsmFull" || name == "device/avr.AsmFull" || name == "device/riscv.AsmFull":
 			return c.emitAsmFull(frame, instr)
 		case strings.HasPrefix(name, "device/arm.SVCall"):
 			return c.emitSVCall(frame, instr.Args)
@@ -1327,10 +1363,7 @@ func (c *Compiler) parseCall(frame *Frame, instr *ssa.CallCommon) (llvm.Value, e
 		value := c.getValue(frame, instr.Value)
 		// This is a func value, which cannot be called directly. We have to
 		// extract the function pointer and context first from the func value.
-		funcPtr, context, err := c.decodeFuncValue(value, instr.Value.Type().Underlying().(*types.Signature))
-		if err != nil {
-			return llvm.Value{}, err
-		}
+		funcPtr, context := c.decodeFuncValue(value, instr.Value.Type().Underlying().(*types.Signature))
 		c.emitNilCheck(frame, funcPtr, "fpcall")
 		return c.parseFunctionCall(frame, instr.Args, funcPtr, context, false), nil
 	}
@@ -1350,9 +1383,9 @@ func (c *Compiler) getValue(frame *Frame, expr ssa.Value) llvm.Value {
 		}
 		return c.createFuncValue(fn.LLVMFn, llvm.Undef(c.i8ptrType), fn.Signature)
 	case *ssa.Global:
-		value := c.ir.GetGlobal(expr).LLVMGlobal
+		value := c.getGlobal(expr)
 		if value.IsNil() {
-			c.addError(expr.Pos(), "global not found: "+c.ir.GetGlobal(expr).LinkName())
+			c.addError(expr.Pos(), "global not found: "+expr.RelString(nil))
 			return llvm.Undef(c.getLLVMType(expr.Type()))
 		}
 		return value
@@ -1385,7 +1418,6 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 				// Size would be truncated if truncated to uintptr.
 				return llvm.Value{}, c.makeError(expr.Pos(), fmt.Sprintf("value is too big (%v bytes)", size))
 			}
-			// TODO: escape analysis
 			sizeValue := llvm.ConstInt(c.uintptrType, size, false)
 			buf := c.createRuntimeCall("alloc", []llvm.Value{sizeValue}, expr.Comment)
 			buf = c.builder.CreateBitCast(buf, llvm.PointerType(typ, 0), "")
@@ -1393,7 +1425,7 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 		} else {
 			buf := c.createEntryBlockAlloca(typ, expr.Comment)
 			if c.targetData.TypeAllocSize(typ) != 0 {
-				c.builder.CreateStore(c.getZeroValue(typ), buf) // zero-initialize var
+				c.builder.CreateStore(llvm.ConstNull(typ), buf) // zero-initialize var
 			}
 			return buf, nil
 		}
@@ -1449,9 +1481,11 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 		x := c.getValue(frame, expr.X)
 		return c.parseConvert(expr.X.Type(), expr.Type(), x, expr.Pos())
 	case *ssa.Extract:
+		if _, ok := expr.Tuple.(*ssa.Select); ok {
+			return c.getChanSelectResult(frame, expr), nil
+		}
 		value := c.getValue(frame, expr.Tuple)
-		result := c.builder.CreateExtractValue(value, expr.Index, "")
-		return result, nil
+		return c.builder.CreateExtractValue(value, expr.Index, ""), nil
 	case *ssa.Field:
 		value := c.getValue(frame, expr.X)
 		if s := expr.X.Type().Underlying().(*types.Struct); s.NumFields() > 2 && s.Field(0).Name() == "C union" {
@@ -1627,10 +1661,11 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 		}
 
 		// Bounds checking.
-		c.emitSliceBoundsCheck(frame, maxSize, sliceLen, sliceCap, expr.Len.Type().(*types.Basic), expr.Cap.Type().(*types.Basic))
+		lenType := expr.Len.Type().(*types.Basic)
+		capType := expr.Cap.Type().(*types.Basic)
+		c.emitSliceBoundsCheck(frame, maxSize, sliceLen, sliceCap, sliceCap, lenType, capType, capType)
 
 		// Allocate the backing array.
-		// TODO: escape analysis
 		sliceCapCast, err := c.parseConvert(expr.Cap.Type(), types.Typ[types.Uintptr], sliceCap, expr.Pos())
 		if err != nil {
 			return llvm.Value{}, err
@@ -1690,43 +1725,22 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 		var iteratorType llvm.Type
 		switch typ := expr.X.Type().Underlying().(type) {
 		case *types.Basic: // string
-			iteratorType = c.mod.GetTypeByName("runtime.stringIterator")
+			iteratorType = c.getLLVMRuntimeType("stringIterator")
 		case *types.Map:
-			iteratorType = c.mod.GetTypeByName("runtime.hashmapIterator")
+			iteratorType = c.getLLVMRuntimeType("hashmapIterator")
 		default:
 			panic("unknown type in range: " + typ.String())
 		}
 		it, _, _ := c.createTemporaryAlloca(iteratorType, "range.it")
-		c.builder.CreateStore(c.getZeroValue(iteratorType), it)
+		c.builder.CreateStore(llvm.ConstNull(iteratorType), it)
 		return it, nil
 	case *ssa.Select:
-		if len(expr.States) == 0 {
-			// Shortcuts for some simple selects.
-			llvmType := c.getLLVMType(expr.Type())
-			if expr.Blocking {
-				// Blocks forever:
-				//     select {}
-				c.createRuntimeCall("deadlockStub", nil, "")
-				return llvm.Undef(llvmType), nil
-			} else {
-				// No-op:
-				//     select {
-				//     default:
-				//     }
-				retval := llvm.Undef(llvmType)
-				retval = c.builder.CreateInsertValue(retval, llvm.ConstInt(c.intType, 0xffffffffffffffff, true), 0, "")
-				return retval, nil // {-1, false}
-			}
-		}
-		return llvm.Value{}, c.makeError(expr.Pos(), "unimplemented: "+expr.String())
+		return c.emitSelect(frame, expr), nil
 	case *ssa.Slice:
-		if expr.Max != nil {
-			return llvm.Value{}, c.makeError(expr.Pos(), "todo: full slice expressions (with max): "+expr.Type().String())
-		}
 		value := c.getValue(frame, expr.X)
 
-		var lowType, highType *types.Basic
-		var low, high llvm.Value
+		var lowType, highType, maxType *types.Basic
+		var low, high, max llvm.Value
 
 		if expr.Low != nil {
 			lowType = expr.Low.Type().Underlying().(*types.Basic)
@@ -1757,6 +1771,20 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 			highType = types.Typ[types.Uintptr]
 		}
 
+		if expr.Max != nil {
+			maxType = expr.Max.Type().Underlying().(*types.Basic)
+			max = c.getValue(frame, expr.Max)
+			if max.Type().IntTypeWidth() < c.uintptrType.IntTypeWidth() {
+				if maxType.Info()&types.IsUnsigned != 0 {
+					max = c.builder.CreateZExt(max, c.uintptrType, "")
+				} else {
+					max = c.builder.CreateSExt(max, c.uintptrType, "")
+				}
+			}
+		} else {
+			maxType = types.Typ[types.Uintptr]
+		}
+
 		switch typ := expr.X.Type().Underlying().(type) {
 		case *types.Pointer: // pointer to array
 			// slice an array
@@ -1765,25 +1793,31 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 			if high.IsNil() {
 				high = llvmLen
 			}
+			if max.IsNil() {
+				max = llvmLen
+			}
 			indices := []llvm.Value{
 				llvm.ConstInt(c.ctx.Int32Type(), 0, false),
 				low,
 			}
 
-			c.emitSliceBoundsCheck(frame, llvmLen, low, high, lowType, highType)
+			c.emitSliceBoundsCheck(frame, llvmLen, low, high, max, lowType, highType, maxType)
 
 			// Truncate ints bigger than uintptr. This is after the bounds
 			// check so it's safe.
+			if c.targetData.TypeAllocSize(low.Type()) > c.targetData.TypeAllocSize(c.uintptrType) {
+				low = c.builder.CreateTrunc(low, c.uintptrType, "")
+			}
 			if c.targetData.TypeAllocSize(high.Type()) > c.targetData.TypeAllocSize(c.uintptrType) {
 				high = c.builder.CreateTrunc(high, c.uintptrType, "")
 			}
-			if c.targetData.TypeAllocSize(low.Type()) > c.targetData.TypeAllocSize(c.uintptrType) {
-				low = c.builder.CreateTrunc(low, c.uintptrType, "")
+			if c.targetData.TypeAllocSize(max.Type()) > c.targetData.TypeAllocSize(c.uintptrType) {
+				max = c.builder.CreateTrunc(max, c.uintptrType, "")
 			}
 
 			sliceLen := c.builder.CreateSub(high, low, "slice.len")
 			slicePtr := c.builder.CreateInBoundsGEP(value, indices, "slice.ptr")
-			sliceCap := c.builder.CreateSub(llvmLen, low, "slice.cap")
+			sliceCap := c.builder.CreateSub(max, low, "slice.cap")
 
 			slice := c.ctx.ConstStruct([]llvm.Value{
 				llvm.Undef(slicePtr.Type()),
@@ -1803,8 +1837,11 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 			if high.IsNil() {
 				high = oldLen
 			}
+			if max.IsNil() {
+				max = oldCap
+			}
 
-			c.emitSliceBoundsCheck(frame, oldCap, low, high, lowType, highType)
+			c.emitSliceBoundsCheck(frame, oldCap, low, high, max, lowType, highType, maxType)
 
 			// Truncate ints bigger than uintptr. This is after the bounds
 			// check so it's safe.
@@ -1814,10 +1851,13 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 			if c.targetData.TypeAllocSize(high.Type()) > c.targetData.TypeAllocSize(c.uintptrType) {
 				high = c.builder.CreateTrunc(high, c.uintptrType, "")
 			}
+			if c.targetData.TypeAllocSize(max.Type()) > c.targetData.TypeAllocSize(c.uintptrType) {
+				max = c.builder.CreateTrunc(max, c.uintptrType, "")
+			}
 
 			newPtr := c.builder.CreateInBoundsGEP(oldPtr, []llvm.Value{low}, "")
 			newLen := c.builder.CreateSub(high, low, "")
-			newCap := c.builder.CreateSub(oldCap, low, "")
+			newCap := c.builder.CreateSub(max, low, "")
 			slice := c.ctx.ConstStruct([]llvm.Value{
 				llvm.Undef(newPtr.Type()),
 				llvm.Undef(c.uintptrType),
@@ -1833,13 +1873,18 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 				return llvm.Value{}, c.makeError(expr.Pos(), "unknown slice type: "+typ.String())
 			}
 			// slice a string
+			if expr.Max != nil {
+				// This might as well be a panic, as the frontend should have
+				// handled this already.
+				return llvm.Value{}, c.makeError(expr.Pos(), "slicing a string with a max parameter is not allowed by the spec")
+			}
 			oldPtr := c.builder.CreateExtractValue(value, 0, "")
 			oldLen := c.builder.CreateExtractValue(value, 1, "")
 			if high.IsNil() {
 				high = oldLen
 			}
 
-			c.emitSliceBoundsCheck(frame, oldLen, low, high, lowType, highType)
+			c.emitSliceBoundsCheck(frame, oldLen, low, high, high, lowType, highType, maxType)
 
 			// Truncate ints bigger than uintptr. This is after the bounds
 			// check so it's safe.
@@ -1852,7 +1897,7 @@ func (c *Compiler) parseExpr(frame *Frame, expr ssa.Value) (llvm.Value, error) {
 
 			newPtr := c.builder.CreateInBoundsGEP(oldPtr, []llvm.Value{low}, "")
 			newLen := c.builder.CreateSub(high, low, "")
-			str := llvm.Undef(c.mod.GetTypeByName("runtime._string"))
+			str := llvm.Undef(c.getLLVMRuntimeType("_string"))
 			str = c.builder.CreateInsertValue(str, newPtr, 0, "")
 			str = c.builder.CreateInsertValue(str, newLen, 1, "")
 			return str, nil
@@ -2231,7 +2276,7 @@ func (c *Compiler) parseConst(prefix string, expr *ssa.Const) llvm.Value {
 			global.SetUnnamedAddr(true)
 			zero := llvm.ConstInt(c.ctx.Int32Type(), 0, false)
 			strPtr := c.builder.CreateInBoundsGEP(global, []llvm.Value{zero, zero}, "")
-			strObj := llvm.ConstNamedStruct(c.mod.GetTypeByName("runtime._string"), []llvm.Value{strPtr, strLen})
+			strObj := llvm.ConstNamedStruct(c.getLLVMRuntimeType("_string"), []llvm.Value{strPtr, strLen})
 			return strObj
 		} else if typ.Kind() == types.UnsafePointer {
 			if !expr.IsNil() {
@@ -2269,12 +2314,12 @@ func (c *Compiler) parseConst(prefix string, expr *ssa.Const) llvm.Value {
 		if expr.Value != nil {
 			panic("expected nil chan constant")
 		}
-		return c.getZeroValue(c.getLLVMType(expr.Type()))
+		return llvm.ConstNull(c.getLLVMType(expr.Type()))
 	case *types.Signature:
 		if expr.Value != nil {
 			panic("expected nil signature constant")
 		}
-		return c.getZeroValue(c.getLLVMType(expr.Type()))
+		return llvm.ConstNull(c.getLLVMType(expr.Type()))
 	case *types.Interface:
 		if expr.Value != nil {
 			panic("expected nil interface constant")
@@ -2284,7 +2329,7 @@ func (c *Compiler) parseConst(prefix string, expr *ssa.Const) llvm.Value {
 			llvm.ConstInt(c.uintptrType, 0, false),
 			llvm.ConstPointerNull(c.i8ptrType),
 		}
-		return llvm.ConstNamedStruct(c.mod.GetTypeByName("runtime._interface"), fields)
+		return llvm.ConstNamedStruct(c.getLLVMRuntimeType("_interface"), fields)
 	case *types.Pointer:
 		if expr.Value != nil {
 			panic("expected nil pointer constant")
@@ -2309,7 +2354,7 @@ func (c *Compiler) parseConst(prefix string, expr *ssa.Const) llvm.Value {
 			panic("non-nil map constant")
 		}
 		llvmType := c.getLLVMType(typ)
-		return c.getZeroValue(llvmType)
+		return llvm.ConstNull(llvmType)
 	default:
 		panic("unknown constant: " + expr.String())
 	}
@@ -2381,6 +2426,8 @@ func (c *Compiler) parseConvert(typeFrom, typeTo types.Type, value llvm.Value, p
 				switch typeFrom.Elem().(*types.Basic).Kind() {
 				case types.Byte:
 					return c.createRuntimeCall("stringFromBytes", []llvm.Value{value}, ""), nil
+				case types.Rune:
+					return c.createRuntimeCall("stringFromRunes", []llvm.Value{value}, ""), nil
 				default:
 					return llvm.Value{}, c.makeError(pos, "todo: convert to string: "+typeFrom.String())
 				}
@@ -2467,8 +2514,10 @@ func (c *Compiler) parseConvert(typeFrom, typeTo types.Type, value llvm.Value, p
 		switch elemType.Kind() {
 		case types.Byte:
 			return c.createRuntimeCall("stringToBytes", []llvm.Value{value}, ""), nil
+		case types.Rune:
+			return c.createRuntimeCall("stringToRunes", []llvm.Value{value}, ""), nil
 		default:
-			return llvm.Value{}, c.makeError(pos, "todo: convert from string: "+elemType.String())
+			panic("unexpected type in string to slice conversion")
 		}
 
 	default:
@@ -2494,18 +2543,18 @@ func (c *Compiler) parseUnOp(frame *Frame, unop *ssa.UnOp) (llvm.Value, error) {
 			return llvm.Value{}, c.makeError(unop.Pos(), "todo: unknown type for negate: "+unop.X.Type().Underlying().String())
 		}
 	case token.MUL: // *x, dereference pointer
-		valType := unop.X.Type().Underlying().(*types.Pointer).Elem()
+		unop.X.Type().Underlying().(*types.Pointer).Elem()
 		if c.targetData.TypeAllocSize(x.Type().ElementType()) == 0 {
 			// zero-length data
-			return c.getZeroValue(x.Type().ElementType()), nil
+			return llvm.ConstNull(x.Type().ElementType()), nil
 		} else if strings.HasSuffix(unop.X.String(), "$funcaddr") {
 			// CGo function pointer. The cgo part has rewritten CGo function
 			// pointers as stub global variables of the form:
 			//     var C.add unsafe.Pointer
 			// Instead of a load from the global, create a bitcast of the
 			// function pointer itself.
-			global := c.ir.GetGlobal(unop.X.(*ssa.Global))
-			name := global.LinkName()[:len(global.LinkName())-len("$funcaddr")]
+			globalName := c.getGlobalInfo(unop.X.(*ssa.Global)).linkName
+			name := globalName[:len(globalName)-len("$funcaddr")]
 			fn := c.mod.NamedFunction(name)
 			if fn.IsNil() {
 				return llvm.Value{}, c.makeError(unop.Pos(), "cgo function not found: "+name)
@@ -2514,10 +2563,6 @@ func (c *Compiler) parseUnOp(frame *Frame, unop *ssa.UnOp) (llvm.Value, error) {
 		} else {
 			c.emitNilCheck(frame, x, "deref")
 			load := c.builder.CreateLoad(x, "")
-			if c.ir.IsVolatile(valType) {
-				// Volatile load, for memory-mapped registers.
-				load.SetVolatile(true)
-			}
 			return load, nil
 		}
 	case token.XOR: // ^x, toggle all bits in integer
@@ -2668,7 +2713,7 @@ func (c *Compiler) ExternalInt64AsPtr() error {
 			// correct calling convention.
 			fn.SetLinkage(llvm.InternalLinkage)
 			fn.SetUnnamedAddr(true)
-			entryBlock := llvm.AddBasicBlock(externalFn, "entry")
+			entryBlock := c.ctx.AddBasicBlock(externalFn, "entry")
 			c.builder.SetInsertPointAtEnd(entryBlock)
 			var callParams []llvm.Value
 			if fnType.ReturnType() == int64Type {

compiler/defer.go

@@ -29,7 +29,7 @@ func (c *Compiler) deferInitFunc(frame *Frame) {
 	frame.deferClosureFuncs = make(map[*ir.Function]int)
 
 	// Create defer list pointer.
-	deferType := llvm.PointerType(c.mod.GetTypeByName("runtime._defer"), 0)
+	deferType := llvm.PointerType(c.getLLVMRuntimeType("_defer"), 0)
 	frame.deferPtr = c.builder.CreateAlloca(deferType, "deferPtr")
 	c.builder.CreateStore(llvm.ConstPointerNull(deferType), frame.deferPtr)
 }
@@ -122,7 +122,7 @@ func (c *Compiler) emitDefer(frame *Frame, instr *ssa.Defer) {
 
 	// Make a struct out of the collected values to put in the defer frame.
 	deferFrameType := c.ctx.StructType(valueTypes, false)
-	deferFrame := c.getZeroValue(deferFrameType)
+	deferFrame := llvm.ConstNull(deferFrameType)
 	for i, value := range values {
 		deferFrame = c.builder.CreateInsertValue(deferFrame, value, i, "")
 	}
@@ -130,6 +130,9 @@ func (c *Compiler) emitDefer(frame *Frame, instr *ssa.Defer) {
 	// Put this struct in an alloca.
 	alloca := c.builder.CreateAlloca(deferFrameType, "defer.alloca")
 	c.builder.CreateStore(deferFrame, alloca)
+	if c.needsStackObjects() {
+		c.trackPointer(alloca)
+	}
 
 	// Push it on top of the linked list by replacing deferPtr.
 	allocaCast := c.builder.CreateBitCast(alloca, next.Type(), "defer.alloca.cast")
@@ -154,10 +157,10 @@ func (c *Compiler) emitRunDefers(frame *Frame) {
 	//     }
 
 	// Create loop.
-	loophead := llvm.AddBasicBlock(frame.fn.LLVMFn, "rundefers.loophead")
-	loop := llvm.AddBasicBlock(frame.fn.LLVMFn, "rundefers.loop")
-	unreachable := llvm.AddBasicBlock(frame.fn.LLVMFn, "rundefers.default")
-	end := llvm.AddBasicBlock(frame.fn.LLVMFn, "rundefers.end")
+	loophead := c.ctx.AddBasicBlock(frame.fn.LLVMFn, "rundefers.loophead")
+	loop := c.ctx.AddBasicBlock(frame.fn.LLVMFn, "rundefers.loop")
+	unreachable := c.ctx.AddBasicBlock(frame.fn.LLVMFn, "rundefers.default")
+	end := c.ctx.AddBasicBlock(frame.fn.LLVMFn, "rundefers.end")
 	c.builder.CreateBr(loophead)
 
 	// Create loop head:
@@ -189,7 +192,7 @@ func (c *Compiler) emitRunDefers(frame *Frame) {
 		// Create switch case, for example:
 		//     case 0:
 		//         // run first deferred call
-		block := llvm.AddBasicBlock(frame.fn.LLVMFn, "rundefers.callback")
+		block := c.ctx.AddBasicBlock(frame.fn.LLVMFn, "rundefers.callback")
 		sw.AddCase(llvm.ConstInt(c.uintptrType, uint64(i), false), block)
 		c.builder.SetInsertPointAtEnd(block)
 		switch callback := callback.(type) {
@@ -200,7 +203,7 @@ func (c *Compiler) emitRunDefers(frame *Frame) {
 			}
 
 			// Get the real defer struct type and cast to it.
-			valueTypes := []llvm.Type{c.uintptrType, llvm.PointerType(c.mod.GetTypeByName("runtime._defer"), 0), c.i8ptrType}
+			valueTypes := []llvm.Type{c.uintptrType, llvm.PointerType(c.getLLVMRuntimeType("_defer"), 0), c.i8ptrType}
 			for _, arg := range callback.Args {
 				valueTypes = append(valueTypes, c.getLLVMType(arg.Type()))
 			}
@@ -231,7 +234,7 @@ func (c *Compiler) emitRunDefers(frame *Frame) {
 			// Direct call.
 
 			// Get the real defer struct type and cast to it.
-			valueTypes := []llvm.Type{c.uintptrType, llvm.PointerType(c.mod.GetTypeByName("runtime._defer"), 0)}
+			valueTypes := []llvm.Type{c.uintptrType, llvm.PointerType(c.getLLVMRuntimeType("_defer"), 0)}
 			for _, param := range callback.Params {
 				valueTypes = append(valueTypes, c.getLLVMType(param.Type()))
 			}
@@ -260,7 +263,7 @@ func (c *Compiler) emitRunDefers(frame *Frame) {
 		case *ssa.MakeClosure:
 			// Get the real defer struct type and cast to it.
 			fn := c.ir.GetFunction(callback.Fn.(*ssa.Function))
-			valueTypes := []llvm.Type{c.uintptrType, llvm.PointerType(c.mod.GetTypeByName("runtime._defer"), 0)}
+			valueTypes := []llvm.Type{c.uintptrType, llvm.PointerType(c.getLLVMRuntimeType("_defer"), 0)}
 			params := fn.Signature.Params()
 			for i := 0; i < params.Len(); i++ {
 				valueTypes = append(valueTypes, c.getLLVMType(params.At(i).Type()))

compiler/func-lowering.go

@@ -51,7 +51,7 @@ func (c *Compiler) LowerFuncValues() {
 	}
 
 	// Find all func values used in the program with their signatures.
-	funcValueWithSignaturePtr := llvm.PointerType(c.mod.GetTypeByName("runtime.funcValueWithSignature"), 0)
+	funcValueWithSignaturePtr := llvm.PointerType(c.getLLVMRuntimeType("funcValueWithSignature"), 0)
 	signatures := map[string]*funcSignatureInfo{}
 	for global := c.mod.FirstGlobal(); !global.IsNil(); global = llvm.NextGlobal(global) {
 		if global.Type() != funcValueWithSignaturePtr {
@@ -152,11 +152,11 @@ func (c *Compiler) LowerFuncValues() {
 				// There are multiple functions used in a func value that
 				// implement this signature.
 				// What we'll do is transform the following:
-				//     rawPtr := runtime.getFuncPtr(fn)
-				//     if func.rawPtr == nil {
+				//     rawPtr := runtime.getFuncPtr(func.ptr)
+				//     if rawPtr == nil {
 				//         runtime.nilPanic()
 				//     }
-				//     result := func.rawPtr(...args, func.context)
+				//     result := rawPtr(...args, func.context)
 				// into this:
 				//     if false {
 				//         runtime.nilPanic()
@@ -175,95 +175,111 @@ func (c *Compiler) LowerFuncValues() {
 
 				// Remove some casts, checks, and the old call which we're going
 				// to replace.
-				var funcCall llvm.Value
-				for _, inttoptr := range getUses(getFuncPtrCall) {
-					if inttoptr.IsAIntToPtrInst().IsNil() {
+				for _, callIntPtr := range getUses(getFuncPtrCall) {
+					if !callIntPtr.IsACallInst().IsNil() && callIntPtr.CalledValue().Name() == "runtime.makeGoroutine" {
+						for _, inttoptr := range getUses(callIntPtr) {
+							if inttoptr.IsAIntToPtrInst().IsNil() {
+								panic("expected a inttoptr")
+							}
+							for _, use := range getUses(inttoptr) {
+								c.addFuncLoweringSwitch(funcID, use, c.emitStartGoroutine, functions)
+								use.EraseFromParentAsInstruction()
+							}
+							inttoptr.EraseFromParentAsInstruction()
+						}
+						callIntPtr.EraseFromParentAsInstruction()
+						continue
+					}
+					if callIntPtr.IsAIntToPtrInst().IsNil() {
 						panic("expected inttoptr")
 					}
-					for _, ptrUse := range getUses(inttoptr) {
+					for _, ptrUse := range getUses(callIntPtr) {
 						if !ptrUse.IsABitCastInst().IsNil() {
 							for _, bitcastUse := range getUses(ptrUse) {
-								if bitcastUse.IsACallInst().IsNil() || bitcastUse.CalledValue().Name() != "runtime.isnil" {
+								if bitcastUse.IsACallInst().IsNil() || bitcastUse.CalledValue().IsAFunction().IsNil() {
+									panic("expected a call instruction")
+								}
+								switch bitcastUse.CalledValue().Name() {
+								case "runtime.isnil":
+									bitcastUse.ReplaceAllUsesWith(llvm.ConstInt(c.ctx.Int1Type(), 0, false))
+									bitcastUse.EraseFromParentAsInstruction()
+								default:
 									panic("expected a call to runtime.isnil")
 								}
-								bitcastUse.ReplaceAllUsesWith(llvm.ConstInt(c.ctx.Int1Type(), 0, false))
-								bitcastUse.EraseFromParentAsInstruction()
 							}
-							ptrUse.EraseFromParentAsInstruction()
-						} else if !ptrUse.IsACallInst().IsNil() && ptrUse.CalledValue() == inttoptr {
-							if !funcCall.IsNil() {
-								panic("multiple calls on a single runtime.getFuncPtr")
-							}
-							funcCall = ptrUse
+						} else if !ptrUse.IsACallInst().IsNil() && ptrUse.CalledValue() == callIntPtr {
+							c.addFuncLoweringSwitch(funcID, ptrUse, func(funcPtr llvm.Value, params []llvm.Value) llvm.Value {
+								return c.builder.CreateCall(funcPtr, params, "")
+							}, functions)
 						} else {
 							panic("unexpected getFuncPtrCall")
 						}
+						ptrUse.EraseFromParentAsInstruction()
 					}
-				}
-				if funcCall.IsNil() {
-					panic("expected exactly one call use of a runtime.getFuncPtr")
-				}
-
-				// The block that cannot be reached with correct funcValues (to
-				// help the optimizer).
-				c.builder.SetInsertPointBefore(funcCall)
-				defaultBlock := llvm.AddBasicBlock(funcCall.InstructionParent().Parent(), "func.default")
-				c.builder.SetInsertPointAtEnd(defaultBlock)
-				c.builder.CreateUnreachable()
-
-				// Create the switch.
-				c.builder.SetInsertPointBefore(funcCall)
-				sw := c.builder.CreateSwitch(funcID, defaultBlock, len(functions)+1)
-
-				// Split right after the switch. We will need to insert a few
-				// basic blocks in this gap.
-				nextBlock := c.splitBasicBlock(sw, llvm.NextBasicBlock(sw.InstructionParent()), "func.next")
-
-				// The 0 case, which is actually a nil check.
-				nilBlock := llvm.InsertBasicBlock(nextBlock, "func.nil")
-				c.builder.SetInsertPointAtEnd(nilBlock)
-				c.createRuntimeCall("nilPanic", nil, "")
-				c.builder.CreateUnreachable()
-				sw.AddCase(llvm.ConstInt(c.uintptrType, 0, false), nilBlock)
-
-				// Gather the list of parameters for every call we're going to
-				// make.
-				callParams := make([]llvm.Value, funcCall.OperandsCount()-1)
-				for i := range callParams {
-					callParams[i] = funcCall.Operand(i)
-				}
-
-				// If the call produces a value, we need to get it using a PHI
-				// node.
-				phiBlocks := make([]llvm.BasicBlock, len(functions))
-				phiValues := make([]llvm.Value, len(functions))
-				for i, fn := range functions {
-					// Insert a switch case.
-					bb := llvm.InsertBasicBlock(nextBlock, "func.call"+strconv.Itoa(fn.id))
-					c.builder.SetInsertPointAtEnd(bb)
-					result := c.builder.CreateCall(fn.funcPtr, callParams, "")
-					c.builder.CreateBr(nextBlock)
-					sw.AddCase(llvm.ConstInt(c.uintptrType, uint64(fn.id), false), bb)
-					phiBlocks[i] = bb
-					phiValues[i] = result
-				}
-				// Create the PHI node so that the call result flows into the
-				// next block (after the split). This is only necessary when the
-				// call produced a value.
-				if funcCall.Type().TypeKind() != llvm.VoidTypeKind {
-					c.builder.SetInsertPointBefore(nextBlock.FirstInstruction())
-					phi := c.builder.CreatePHI(funcCall.Type(), "")
-					phi.AddIncoming(phiValues, phiBlocks)
-					funcCall.ReplaceAllUsesWith(phi)
-				}
-
-				// Finally, remove the old instructions.
-				funcCall.EraseFromParentAsInstruction()
-				for _, inttoptr := range getUses(getFuncPtrCall) {
-					inttoptr.EraseFromParentAsInstruction()
+					callIntPtr.EraseFromParentAsInstruction()
 				}
 				getFuncPtrCall.EraseFromParentAsInstruction()
 			}
 		}
 	}
 }
+
+// addFuncLoweringSwitch creates a new switch on a function ID and inserts calls
+// to the newly created direct calls. The funcID is the number to switch on,
+// call is the call instruction to replace, and createCall is the callback that
+// actually creates the new call. By changing createCall to something other than
+// c.builder.CreateCall, instead of calling a function it can start a new
+// goroutine for example.
+func (c *Compiler) addFuncLoweringSwitch(funcID, call llvm.Value, createCall func(funcPtr llvm.Value, params []llvm.Value) llvm.Value, functions funcWithUsesList) {
+	// The block that cannot be reached with correct funcValues (to help the
+	// optimizer).
+	c.builder.SetInsertPointBefore(call)
+	defaultBlock := c.ctx.AddBasicBlock(call.InstructionParent().Parent(), "func.default")
+	c.builder.SetInsertPointAtEnd(defaultBlock)
+	c.builder.CreateUnreachable()
+
+	// Create the switch.
+	c.builder.SetInsertPointBefore(call)
+	sw := c.builder.CreateSwitch(funcID, defaultBlock, len(functions)+1)
+
+	// Split right after the switch. We will need to insert a few basic blocks
+	// in this gap.
+	nextBlock := c.splitBasicBlock(sw, llvm.NextBasicBlock(sw.InstructionParent()), "func.next")
+
+	// The 0 case, which is actually a nil check.
+	nilBlock := c.ctx.InsertBasicBlock(nextBlock, "func.nil")
+	c.builder.SetInsertPointAtEnd(nilBlock)
+	c.createRuntimeCall("nilPanic", nil, "")
+	c.builder.CreateUnreachable()
+	sw.AddCase(llvm.ConstInt(c.uintptrType, 0, false), nilBlock)
+
+	// Gather the list of parameters for every call we're going to make.
+	callParams := make([]llvm.Value, call.OperandsCount()-1)
+	for i := range callParams {
+		callParams[i] = call.Operand(i)
+	}
+
+	// If the call produces a value, we need to get it using a PHI
+	// node.
+	phiBlocks := make([]llvm.BasicBlock, len(functions))
+	phiValues := make([]llvm.Value, len(functions))
+	for i, fn := range functions {
+		// Insert a switch case.
+		bb := c.ctx.InsertBasicBlock(nextBlock, "func.call"+strconv.Itoa(fn.id))
+		c.builder.SetInsertPointAtEnd(bb)
+		result := createCall(fn.funcPtr, callParams)
+		c.builder.CreateBr(nextBlock)
+		sw.AddCase(llvm.ConstInt(c.uintptrType, uint64(fn.id), false), bb)
+		phiBlocks[i] = bb
+		phiValues[i] = result
+	}
+	// Create the PHI node so that the call result flows into the
+	// next block (after the split). This is only necessary when the
+	// call produced a value.
+	if call.Type().TypeKind() != llvm.VoidTypeKind {
+		c.builder.SetInsertPointBefore(nextBlock.FirstInstruction())
+		phi := c.builder.CreatePHI(call.Type(), "")
+		phi.AddIncoming(phiValues, phiBlocks)
+		call.ReplaceAllUsesWith(phi)
+	}
+}

compiler/func.go

@@ -32,10 +32,15 @@ const (
 // funcImplementation picks an appropriate func value implementation for the
 // target.
 func (c *Compiler) funcImplementation() funcValueImplementation {
-	if c.GOARCH == "wasm" {
+	// Always pick the switch implementation, as it allows the use of blocking
+	// inside a function that is used as a func value.
+	switch c.selectScheduler() {
+	case "coroutines":
 		return funcValueSwitch
-	} else {
+	case "tasks":
 		return funcValueDoubleword
+	default:
+		panic("unknown scheduler type")
 	}
 }
 
@@ -48,11 +53,11 @@ func (c *Compiler) createFuncValue(funcPtr, context llvm.Value, sig *types.Signa
 		// Closure is: {context, function pointer}
 		funcValueScalar = funcPtr
 	case funcValueSwitch:
-		sigGlobal := c.getFuncSignature(sig)
+		sigGlobal := c.getTypeCode(sig)
 		funcValueWithSignatureGlobalName := funcPtr.Name() + "$withSignature"
 		funcValueWithSignatureGlobal := c.mod.NamedGlobal(funcValueWithSignatureGlobalName)
 		if funcValueWithSignatureGlobal.IsNil() {
-			funcValueWithSignatureType := c.mod.GetTypeByName("runtime.funcValueWithSignature")
+			funcValueWithSignatureType := c.getLLVMRuntimeType("funcValueWithSignature")
 			funcValueWithSignature := llvm.ConstNamedStruct(funcValueWithSignatureType, []llvm.Value{
 				llvm.ConstPtrToInt(funcPtr, c.uintptrType),
 				sigGlobal,
@@ -73,22 +78,6 @@ func (c *Compiler) createFuncValue(funcPtr, context llvm.Value, sig *types.Signa
 	return funcValue
 }
 
-// getFuncSignature returns a global for identification of a particular function
-// signature. It is used in runtime.funcValueWithSignature and in calls to
-// getFuncPtr.
-func (c *Compiler) getFuncSignature(sig *types.Signature) llvm.Value {
-	typeCodeName := getTypeCodeName(sig)
-	sigGlobalName := "reflect/types.type:" + typeCodeName
-	sigGlobal := c.mod.NamedGlobal(sigGlobalName)
-	if sigGlobal.IsNil() {
-		sigGlobal = llvm.AddGlobal(c.mod, c.ctx.Int8Type(), sigGlobalName)
-		sigGlobal.SetInitializer(llvm.Undef(c.ctx.Int8Type()))
-		sigGlobal.SetGlobalConstant(true)
-		sigGlobal.SetLinkage(llvm.InternalLinkage)
-	}
-	return sigGlobal
-}
-
 // extractFuncScalar returns some scalar that can be used in comparisons. It is
 // a cheap operation.
 func (c *Compiler) extractFuncScalar(funcValue llvm.Value) llvm.Value {
@@ -103,14 +92,14 @@ func (c *Compiler) extractFuncContext(funcValue llvm.Value) llvm.Value {
 
 // decodeFuncValue extracts the context and the function pointer from this func
 // value. This may be an expensive operation.
-func (c *Compiler) decodeFuncValue(funcValue llvm.Value, sig *types.Signature) (funcPtr, context llvm.Value, err error) {
+func (c *Compiler) decodeFuncValue(funcValue llvm.Value, sig *types.Signature) (funcPtr, context llvm.Value) {
 	context = c.builder.CreateExtractValue(funcValue, 0, "")
 	switch c.funcImplementation() {
 	case funcValueDoubleword:
 		funcPtr = c.builder.CreateExtractValue(funcValue, 1, "")
 	case funcValueSwitch:
 		llvmSig := c.getRawFuncType(sig)
-		sigGlobal := c.getFuncSignature(sig)
+		sigGlobal := c.getTypeCode(sig)
 		funcPtr = c.createRuntimeCall("getFuncPtr", []llvm.Value{funcValue, sigGlobal}, "")
 		funcPtr = c.builder.CreateIntToPtr(funcPtr, llvmSig, "")
 	default:
@@ -126,7 +115,7 @@ func (c *Compiler) getFuncType(typ *types.Signature) llvm.Type {
 		rawPtr := c.getRawFuncType(typ)
 		return c.ctx.StructType([]llvm.Type{c.i8ptrType, rawPtr}, false)
 	case funcValueSwitch:
-		return c.mod.GetTypeByName("runtime.funcValue")
+		return c.getLLVMRuntimeType("funcValue")
 	default:
 		panic("unimplemented func value variant")
 	}

compiler/gc.go

@@ -0,0 +1,471 @@
+package compiler
+
+// This file provides IR transformations necessary for precise and portable
+// garbage collectors.
+
+import (
+	"go/token"
+	"math/big"
+
+	"golang.org/x/tools/go/ssa"
+	"tinygo.org/x/go-llvm"
+)
+
+// needsStackObjects returns true if the compiler should insert stack objects
+// that can be traced by the garbage collector.
+func (c *Compiler) needsStackObjects() bool {
+	if c.selectGC() != "conservative" {
+		return false
+	}
+	for _, tag := range c.BuildTags {
+		if tag == "baremetal" {
+			return false
+		}
+	}
+
+	return true
+}
+
+// trackExpr inserts pointer tracking intrinsics for the GC if the expression is
+// one of the expressions that need this.
+func (c *Compiler) trackExpr(frame *Frame, expr ssa.Value, value llvm.Value) {
+	// There are uses of this expression, Make sure the pointers
+	// are tracked during GC.
+	switch expr := expr.(type) {
+	case *ssa.Alloc, *ssa.MakeChan, *ssa.MakeMap:
+		// These values are always of pointer type in IR.
+		c.trackPointer(value)
+	case *ssa.Call, *ssa.Convert, *ssa.MakeClosure, *ssa.MakeInterface, *ssa.MakeSlice, *ssa.Next:
+		if !value.IsNil() {
+			c.trackValue(value)
+		}
+	case *ssa.Select:
+		if alloca, ok := frame.selectRecvBuf[expr]; ok {
+			if alloca.IsAUndefValue().IsNil() {
+				c.trackPointer(alloca)
+			}
+		}
+	case *ssa.UnOp:
+		switch expr.Op {
+		case token.MUL:
+			// Pointer dereference.
+			c.trackValue(value)
+		case token.ARROW:
+			// Channel receive operator.
+			// It's not necessary to look at commaOk here, because in that
+			// case it's just an aggregate and trackValue will extract the
+			// pointer in there (if there is one).
+			c.trackValue(value)
+		}
+	}
+}
+
+// trackValue locates pointers in a value (possibly an aggregate) and tracks the
+// individual pointers
+func (c *Compiler) trackValue(value llvm.Value) {
+	typ := value.Type()
+	switch typ.TypeKind() {
+	case llvm.PointerTypeKind:
+		c.trackPointer(value)
+	case llvm.StructTypeKind:
+		if !typeHasPointers(typ) {
+			return
+		}
+		numElements := typ.StructElementTypesCount()
+		for i := 0; i < numElements; i++ {
+			subValue := c.builder.CreateExtractValue(value, i, "")
+			c.trackValue(subValue)
+		}
+	case llvm.ArrayTypeKind:
+		if !typeHasPointers(typ) {
+			return
+		}
+		numElements := typ.ArrayLength()
+		for i := 0; i < numElements; i++ {
+			subValue := c.builder.CreateExtractValue(value, i, "")
+			c.trackValue(subValue)
+		}
+	}
+}
+
+// trackPointer creates a call to runtime.trackPointer, bitcasting the poitner
+// first if needed. The input value must be of LLVM pointer type.
+func (c *Compiler) trackPointer(value llvm.Value) {
+	if value.Type() != c.i8ptrType {
+		value = c.builder.CreateBitCast(value, c.i8ptrType, "")
+	}
+	c.createRuntimeCall("trackPointer", []llvm.Value{value}, "")
+}
+
+// typeHasPointers returns whether this type is a pointer or contains pointers.
+// If the type is an aggregate type, it will check whether there is a pointer
+// inside.
+func typeHasPointers(t llvm.Type) bool {
+	switch t.TypeKind() {
+	case llvm.PointerTypeKind:
+		return true
+	case llvm.StructTypeKind:
+		for _, subType := range t.StructElementTypes() {
+			if typeHasPointers(subType) {
+				return true
+			}
+		}
+		return false
+	case llvm.ArrayTypeKind:
+		if typeHasPointers(t.ElementType()) {
+			return true
+		}
+		return false
+	default:
+		return false
+	}
+}
+
+// makeGCStackSlots converts all calls to runtime.trackPointer to explicit
+// stores to stack slots that are scannable by the GC.
+func (c *Compiler) makeGCStackSlots() bool {
+	// Check whether there are allocations at all.
+	alloc := c.mod.NamedFunction("runtime.alloc")
+	if alloc.IsNil() {
+		// Nothing to. Make sure all remaining bits and pieces for stack
+		// chains are neutralized.
+		for _, call := range getUses(c.mod.NamedFunction("runtime.trackPointer")) {
+			call.EraseFromParentAsInstruction()
+		}
+		stackChainStart := c.mod.NamedGlobal("runtime.stackChainStart")
+		if !stackChainStart.IsNil() {
+			stackChainStart.SetInitializer(llvm.ConstNull(stackChainStart.Type().ElementType()))
+			stackChainStart.SetGlobalConstant(true)
+		}
+	}
+
+	trackPointer := c.mod.NamedFunction("runtime.trackPointer")
+	if trackPointer.IsNil() || trackPointer.FirstUse().IsNil() {
+		return false // nothing to do
+	}
+
+	// Look at *all* functions to see whether they are free of function pointer
+	// calls.
+	// This takes less than 5ms for ~100kB of WebAssembly but would perhaps be
+	// faster when written in C++ (to avoid the CGo overhead).
+	funcsWithFPCall := map[llvm.Value]struct{}{}
+	n := 0
+	for fn := c.mod.FirstFunction(); !fn.IsNil(); fn = llvm.NextFunction(fn) {
+		n++
+		if _, ok := funcsWithFPCall[fn]; ok {
+			continue // already found
+		}
+		done := false
+		for bb := fn.FirstBasicBlock(); !bb.IsNil() && !done; bb = llvm.NextBasicBlock(bb) {
+			for call := bb.FirstInstruction(); !call.IsNil() && !done; call = llvm.NextInstruction(call) {
+				if call.IsACallInst().IsNil() {
+					continue // only looking at calls
+				}
+				called := call.CalledValue()
+				if !called.IsAFunction().IsNil() {
+					continue // only looking for function pointers
+				}
+				funcsWithFPCall[fn] = struct{}{}
+				markParentFunctions(funcsWithFPCall, fn)
+				done = true
+			}
+		}
+	}
+
+	// Determine which functions need stack objects. Many leaf functions don't
+	// need it: it only causes overhead for them.
+	// Actually, in one test it was only able to eliminate stack object from 12%
+	// of functions that had a call to runtime.trackPointer (8 out of 68
+	// functions), so this optimization is not as big as it may seem.
+	allocatingFunctions := map[llvm.Value]struct{}{} // set of allocating functions
+
+	// Work from runtime.alloc and trace all parents to check which functions do
+	// a heap allocation (and thus which functions do not).
+	markParentFunctions(allocatingFunctions, alloc)
+
+	// Also trace all functions that call a function pointer.
+	for fn := range funcsWithFPCall {
+		// Assume that functions that call a function pointer do a heap
+		// allocation as a conservative guess because the called function might
+		// do a heap allocation.
+		allocatingFunctions[fn] = struct{}{}
+		markParentFunctions(allocatingFunctions, fn)
+	}
+
+	// Collect some variables used below in the loop.
+	stackChainStart := c.mod.NamedGlobal("runtime.stackChainStart")
+	if stackChainStart.IsNil() {
+		panic("stack chain start not found!")
+	}
+	stackChainStartType := stackChainStart.Type().ElementType()
+	stackChainStart.SetInitializer(llvm.ConstNull(stackChainStartType))
+
+	// Iterate until runtime.trackPointer has no uses left.
+	for use := trackPointer.FirstUse(); !use.IsNil(); use = trackPointer.FirstUse() {
+		// Pick the first use of runtime.trackPointer.
+		call := use.User()
+		if call.IsACallInst().IsNil() {
+			panic("expected runtime.trackPointer use to be a call")
+		}
+
+		// Pick the parent function.
+		fn := call.InstructionParent().Parent()
+
+		if _, ok := allocatingFunctions[fn]; !ok {
+			// This function nor any of the functions it calls (recursively)
+			// allocate anything from the heap, so it will not trigger a garbage
+			// collection cycle. Thus, it does not need to track local pointer
+			// values.
+			// This is a useful optimization but not as big as you might guess,
+			// as described above (it avoids stack objects for ~12% of
+			// functions).
+			call.EraseFromParentAsInstruction()
+			continue
+		}
+
+		// Find all calls to runtime.trackPointer in this function.
+		var calls []llvm.Value
+		var returns []llvm.Value
+		for bb := fn.FirstBasicBlock(); !bb.IsNil(); bb = llvm.NextBasicBlock(bb) {
+			for inst := bb.FirstInstruction(); !inst.IsNil(); inst = llvm.NextInstruction(inst) {
+				switch inst.InstructionOpcode() {
+				case llvm.Call:
+					if inst.CalledValue() == trackPointer {
+						calls = append(calls, inst)
+					}
+				case llvm.Ret:
+					returns = append(returns, inst)
+				}
+			}
+		}
+
+		// Determine what to do with each call.
+		var allocas, pointers []llvm.Value
+		for _, call := range calls {
+			ptr := call.Operand(0)
+			call.EraseFromParentAsInstruction()
+			if ptr.IsAInstruction().IsNil() {
+				continue
+			}
+
+			// Some trivial optimizations.
+			if ptr.IsAInstruction().IsNil() {
+				continue
+			}
+			switch ptr.InstructionOpcode() {
+			case llvm.PHI, llvm.GetElementPtr:
+				// These values do not create new values: the values already
+				// existed locally in this function so must have been tracked
+				// already.
+				continue
+			case llvm.ExtractValue, llvm.BitCast:
+				// These instructions do not create new values, but their
+				// original value may not be tracked. So keep tracking them for
+				// now.
+				// With more analysis, it should be possible to optimize a
+				// significant chunk of these away.
+			case llvm.Call, llvm.Load, llvm.IntToPtr:
+				// These create new values so must be stored locally. But
+				// perhaps some of these can be fused when they actually refer
+				// to the same value.
+			default:
+				// Ambiguous. These instructions are uncommon, but perhaps could
+				// be optimized if needed.
+			}
+
+			if !ptr.IsAAllocaInst().IsNil() {
+				if typeHasPointers(ptr.Type().ElementType()) {
+					allocas = append(allocas, ptr)
+				}
+			} else {
+				pointers = append(pointers, ptr)
+			}
+		}
+
+		if len(allocas) == 0 && len(pointers) == 0 {
+			// This function does not need to keep track of stack pointers.
+			continue
+		}
+
+		// Determine the type of the required stack slot.
+		fields := []llvm.Type{
+			stackChainStartType, // Pointer to parent frame.
+			c.uintptrType,       // Number of elements in this frame.
+		}
+		for _, alloca := range allocas {
+			fields = append(fields, alloca.Type().ElementType())
+		}
+		for _, ptr := range pointers {
+			fields = append(fields, ptr.Type())
+		}
+		stackObjectType := c.ctx.StructType(fields, false)
+
+		// Create the stack object at the function entry.
+		c.builder.SetInsertPointBefore(fn.EntryBasicBlock().FirstInstruction())
+		stackObject := c.builder.CreateAlloca(stackObjectType, "gc.stackobject")
+		initialStackObject := llvm.ConstNull(stackObjectType)
+		numSlots := (c.targetData.TypeAllocSize(stackObjectType) - c.targetData.TypeAllocSize(c.i8ptrType)*2) / uint64(c.targetData.ABITypeAlignment(c.uintptrType))
+		numSlotsValue := llvm.ConstInt(c.uintptrType, numSlots, false)
+		initialStackObject = llvm.ConstInsertValue(initialStackObject, numSlotsValue, []uint32{1})
+		c.builder.CreateStore(initialStackObject, stackObject)
+
+		// Update stack start.
+		parent := c.builder.CreateLoad(stackChainStart, "")
+		gep := c.builder.CreateGEP(stackObject, []llvm.Value{
+			llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+			llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+		}, "")
+		c.builder.CreateStore(parent, gep)
+		stackObjectCast := c.builder.CreateBitCast(stackObject, stackChainStartType, "")
+		c.builder.CreateStore(stackObjectCast, stackChainStart)
+
+		// Replace all independent allocas with GEPs in the stack object.
+		for i, alloca := range allocas {
+			gep := c.builder.CreateGEP(stackObject, []llvm.Value{
+				llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+				llvm.ConstInt(c.ctx.Int32Type(), uint64(2+i), false),
+			}, "")
+			alloca.ReplaceAllUsesWith(gep)
+			alloca.EraseFromParentAsInstruction()
+		}
+
+		// Do a store to the stack object after each new pointer that is created.
+		for i, ptr := range pointers {
+			c.builder.SetInsertPointBefore(llvm.NextInstruction(ptr))
+			gep := c.builder.CreateGEP(stackObject, []llvm.Value{
+				llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+				llvm.ConstInt(c.ctx.Int32Type(), uint64(2+len(allocas)+i), false),
+			}, "")
+			c.builder.CreateStore(ptr, gep)
+		}
+
+		// Make sure this stack object is popped from the linked list of stack
+		// objects at return.
+		for _, ret := range returns {
+			c.builder.SetInsertPointBefore(ret)
+			c.builder.CreateStore(parent, stackChainStart)
+		}
+	}
+
+	return true
+}
+
+func (c *Compiler) addGlobalsBitmap() bool {
+	if c.mod.NamedGlobal("runtime.trackedGlobalsStart").IsNil() {
+		return false // nothing to do: no GC in use
+	}
+
+	var trackedGlobals []llvm.Value
+	var trackedGlobalTypes []llvm.Type
+	for global := c.mod.FirstGlobal(); !global.IsNil(); global = llvm.NextGlobal(global) {
+		if global.IsDeclaration() {
+			continue
+		}
+		typ := global.Type().ElementType()
+		ptrs := c.getPointerBitmap(typ, global.Name())
+		if ptrs.BitLen() == 0 {
+			continue
+		}
+		trackedGlobals = append(trackedGlobals, global)
+		trackedGlobalTypes = append(trackedGlobalTypes, typ)
+	}
+
+	globalsBundleType := c.ctx.StructType(trackedGlobalTypes, false)
+	globalsBundle := llvm.AddGlobal(c.mod, globalsBundleType, "tinygo.trackedGlobals")
+	globalsBundle.SetLinkage(llvm.InternalLinkage)
+	globalsBundle.SetUnnamedAddr(true)
+	initializer := llvm.Undef(globalsBundleType)
+	for i, global := range trackedGlobals {
+		initializer = llvm.ConstInsertValue(initializer, global.Initializer(), []uint32{uint32(i)})
+		gep := llvm.ConstGEP(globalsBundle, []llvm.Value{
+			llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+			llvm.ConstInt(c.ctx.Int32Type(), uint64(i), false),
+		})
+		global.ReplaceAllUsesWith(gep)
+		global.EraseFromParentAsGlobal()
+	}
+	globalsBundle.SetInitializer(initializer)
+
+	trackedGlobalsStart := llvm.ConstPtrToInt(globalsBundle, c.uintptrType)
+	c.mod.NamedGlobal("runtime.trackedGlobalsStart").SetInitializer(trackedGlobalsStart)
+
+	alignment := c.targetData.PrefTypeAlignment(c.i8ptrType)
+	trackedGlobalsLength := llvm.ConstInt(c.uintptrType, c.targetData.TypeAllocSize(globalsBundleType)/uint64(alignment), false)
+	c.mod.NamedGlobal("runtime.trackedGlobalsLength").SetInitializer(trackedGlobalsLength)
+
+	bitmapBytes := c.getPointerBitmap(globalsBundleType, "globals bundle").Bytes()
+	bitmapValues := make([]llvm.Value, len(bitmapBytes))
+	for i, b := range bitmapBytes {
+		bitmapValues[len(bitmapBytes)-i-1] = llvm.ConstInt(c.ctx.Int8Type(), uint64(b), false)
+	}
+	bitmapArray := llvm.ConstArray(c.ctx.Int8Type(), bitmapValues)
+	bitmapNew := llvm.AddGlobal(c.mod, bitmapArray.Type(), "runtime.trackedGlobalsBitmap.tmp")
+	bitmapOld := c.mod.NamedGlobal("runtime.trackedGlobalsBitmap")
+	bitmapOld.ReplaceAllUsesWith(llvm.ConstBitCast(bitmapNew, bitmapOld.Type()))
+	bitmapNew.SetInitializer(bitmapArray)
+	bitmapNew.SetName("runtime.trackedGlobalsBitmap")
+
+	return true // the IR was changed
+}
+
+func (c *Compiler) getPointerBitmap(typ llvm.Type, name string) *big.Int {
+	alignment := c.targetData.PrefTypeAlignment(c.i8ptrType)
+	switch typ.TypeKind() {
+	case llvm.IntegerTypeKind, llvm.FloatTypeKind, llvm.DoubleTypeKind:
+		return big.NewInt(0)
+	case llvm.PointerTypeKind:
+		return big.NewInt(1)
+	case llvm.StructTypeKind:
+		ptrs := big.NewInt(0)
+		for i, subtyp := range typ.StructElementTypes() {
+			subptrs := c.getPointerBitmap(subtyp, name)
+			if subptrs.BitLen() == 0 {
+				continue
+			}
+			offset := c.targetData.ElementOffset(typ, i)
+			if offset%uint64(alignment) != 0 {
+				panic("precise GC: global contains unaligned pointer: " + name)
+			}
+			subptrs.Lsh(subptrs, uint(offset)/uint(alignment))
+			ptrs.Or(ptrs, subptrs)
+		}
+		return ptrs
+	case llvm.ArrayTypeKind:
+		subtyp := typ.ElementType()
+		subptrs := c.getPointerBitmap(subtyp, name)
+		ptrs := big.NewInt(0)
+		if subptrs.BitLen() == 0 {
+			return ptrs
+		}
+		elementSize := c.targetData.TypeAllocSize(subtyp)
+		for i := 0; i < typ.ArrayLength(); i++ {
+			ptrs.Lsh(ptrs, uint(elementSize)/uint(alignment))
+			ptrs.Or(ptrs, subptrs)
+		}
+		return ptrs
+	default:
+		panic("unknown type kind of global: " + name)
+	}
+}
+
+// markParentFunctions traverses all parent function calls (recursively) and
+// adds them to the set of marked functions. It only considers function calls:
+// any other uses of such a function is ignored.
+func markParentFunctions(marked map[llvm.Value]struct{}, fn llvm.Value) {
+	worklist := []llvm.Value{fn}
+	for len(worklist) != 0 {
+		fn := worklist[len(worklist)-1]
+		worklist = worklist[:len(worklist)-1]
+		for _, use := range getUses(fn) {
+			if use.IsACallInst().IsNil() || use.CalledValue() != fn {
+				// Not the parent function.
+				continue
+			}
+			parent := use.InstructionParent().Parent()
+			if _, ok := marked[parent]; !ok {
+				marked[parent] = struct{}{}
+				worklist = append(worklist, parent)
+			}
+		}
+	}
+}

compiler/goroutine-lowering.go

@@ -1,5 +1,16 @@
 package compiler
 
+// This file implements lowering for the goroutine scheduler. There are two
+// scheduler implementations, one based on tasks (like RTOSes and the main Go
+// runtime) and one based on a coroutine compiler transformation. The task based
+// implementation requires very little work from the compiler but is not very
+// portable (in particular, it is very hard if not impossible to support on
+// WebAssembly). The coroutine based one requires a lot of work by the compiler
+// to implement, but can run virtually anywhere with a single scheduler
+// implementation.
+//
+// The below description is for the coroutine based scheduler.
+//
 // This file lowers goroutine pseudo-functions into coroutines scheduled by a
 // scheduler at runtime. It uses coroutine support in LLVM for this
 // transformation: https://llvm.org/docs/Coroutines.html
@@ -62,7 +73,7 @@ package compiler
 //         llvm.suspend(hdl)                       // suspend point
 //         println("some other operation")
 //         var i *int                              // allocate space on the stack for the return value
-//         runtime.setTaskPromisePtr(hdl, &i)      // store return value alloca in our coroutine promise
+//         runtime.setTaskStatePtr(hdl, &i)        // store return value alloca in our coroutine promise
 //         bar(hdl)                                // await, pass a continuation (hdl) to bar
 //         llvm.suspend(hdl)                       // suspend point, wait for the callee to re-activate
 //         println("done", *i)
@@ -106,10 +117,69 @@ type asyncFunc struct {
 	unreachableBlock llvm.BasicBlock
 }
 
-// LowerGoroutines is a pass called during optimization that transforms the IR
-// into one where all blocking functions are turned into goroutines and blocking
-// calls into await calls.
+// LowerGoroutines performs some IR transformations necessary to support
+// goroutines. It does something different based on whether it uses the
+// coroutine or the tasks implementation of goroutines, and whether goroutines
+// are necessary at all.
 func (c *Compiler) LowerGoroutines() error {
+	switch c.selectScheduler() {
+	case "coroutines":
+		return c.lowerCoroutines()
+	case "tasks":
+		return c.lowerTasks()
+	default:
+		panic("unknown scheduler type")
+	}
+}
+
+// lowerTasks starts the main goroutine and then runs the scheduler.
+// This is enough compiler-level transformation for the task-based scheduler.
+func (c *Compiler) lowerTasks() error {
+	uses := getUses(c.mod.NamedFunction("runtime.callMain"))
+	if len(uses) != 1 || uses[0].IsACallInst().IsNil() {
+		panic("expected exactly 1 call of runtime.callMain, check the entry point")
+	}
+	mainCall := uses[0]
+
+	realMain := c.mod.NamedFunction(c.ir.MainPkg().Pkg.Path() + ".main")
+	if len(getUses(c.mod.NamedFunction("runtime.startGoroutine"))) != 0 {
+		// Program needs a scheduler. Start main.main as a goroutine and start
+		// the scheduler.
+		realMainWrapper := c.createGoroutineStartWrapper(realMain)
+		c.builder.SetInsertPointBefore(mainCall)
+		zero := llvm.ConstInt(c.uintptrType, 0, false)
+		c.createRuntimeCall("startGoroutine", []llvm.Value{realMainWrapper, zero}, "")
+		c.createRuntimeCall("scheduler", nil, "")
+		sleep := c.mod.NamedFunction("time.Sleep")
+		if !sleep.IsNil() {
+			sleep.ReplaceAllUsesWith(c.mod.NamedFunction("runtime.sleepCurrentTask"))
+		}
+	} else {
+		// Program doesn't need a scheduler. Call main.main directly.
+		c.builder.SetInsertPointBefore(mainCall)
+		params := []llvm.Value{
+			llvm.Undef(c.i8ptrType), // unused context parameter
+			llvm.Undef(c.i8ptrType), // unused coroutine handle
+		}
+		c.createCall(realMain, params, "")
+		// runtime.Goexit isn't needed so let it be optimized away by
+		// globalopt.
+		c.mod.NamedFunction("runtime.Goexit").SetLinkage(llvm.InternalLinkage)
+	}
+	mainCall.EraseFromParentAsInstruction()
+
+	// main.main was set to external linkage during IR construction. Set it to
+	// internal linkage to enable interprocedural optimizations.
+	realMain.SetLinkage(llvm.InternalLinkage)
+
+	return nil
+}
+
+// lowerCoroutines transforms the IR into one where all blocking functions are
+// turned into goroutines and blocking calls into await calls. It also makes
+// sure that the first coroutine is started and the coroutine scheduler will be
+// run.
+func (c *Compiler) lowerCoroutines() error {
 	needsScheduler, err := c.markAsyncFunctions()
 	if err != nil {
 		return err
@@ -144,12 +214,6 @@ func (c *Compiler) LowerGoroutines() error {
 	// main.main was set to external linkage during IR construction. Set it to
 	// internal linkage to enable interprocedural optimizations.
 	realMain.SetLinkage(llvm.InternalLinkage)
-	c.mod.NamedFunction("runtime.alloc").SetLinkage(llvm.InternalLinkage)
-	c.mod.NamedFunction("runtime.free").SetLinkage(llvm.InternalLinkage)
-	c.mod.NamedFunction("runtime.sleepTask").SetLinkage(llvm.InternalLinkage)
-	c.mod.NamedFunction("runtime.setTaskPromisePtr").SetLinkage(llvm.InternalLinkage)
-	c.mod.NamedFunction("runtime.getTaskPromisePtr").SetLinkage(llvm.InternalLinkage)
-	c.mod.NamedFunction("runtime.scheduler").SetLinkage(llvm.InternalLinkage)
 
 	return nil
 }
@@ -173,9 +237,9 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 	if !sleep.IsNil() {
 		worklist = append(worklist, sleep)
 	}
-	deadlockStub := c.mod.NamedFunction("runtime.deadlockStub")
-	if !deadlockStub.IsNil() {
-		worklist = append(worklist, deadlockStub)
+	deadlock := c.mod.NamedFunction("runtime.deadlock")
+	if !deadlock.IsNil() {
+		worklist = append(worklist, deadlock)
 	}
 	chanSend := c.mod.NamedFunction("runtime.chanSend")
 	if !chanSend.IsNil() {
@@ -211,17 +275,25 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 
 		// Add all callees to the worklist.
 		for _, use := range getUses(f) {
-			if use.IsConstant() && use.Opcode() == llvm.BitCast {
-				bitcastUses := getUses(use)
-				for _, call := range bitcastUses {
+			if use.IsConstant() && use.Opcode() == llvm.PtrToInt {
+				for _, call := range getUses(use) {
 					if call.IsACallInst().IsNil() || call.CalledValue().Name() != "runtime.makeGoroutine" {
-						return false, errors.New("async function " + f.Name() + " incorrectly used in bitcast, expected runtime.makeGoroutine")
+						return false, errors.New("async function " + f.Name() + " incorrectly used in ptrtoint, expected runtime.makeGoroutine")
 					}
 				}
 				// This is a go statement. Do not mark the parent as async, as
 				// starting a goroutine is not a blocking operation.
 				continue
 			}
+			if use.IsConstant() && use.Opcode() == llvm.BitCast {
+				// Not sure why this const bitcast is here but as long as it
+				// has no uses it can be ignored, I guess?
+				// I think it was created for the runtime.isnil check but
+				// somehow wasn't removed when all these checks are removed.
+				if len(getUses(use)) == 0 {
+					continue
+				}
+			}
 			if use.IsACallInst().IsNil() {
 				// Not a call instruction. Maybe a store to a global? In any
 				// case, this requires support for async calls across function
@@ -250,12 +322,12 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 		// goroutine is not async (does not do any blocking operation), no
 		// scheduler is necessary as it can be called directly.
 		for _, use := range getUses(makeGoroutine) {
-			// Input param must be const bitcast of function.
-			bitcast := use.Operand(0)
-			if !bitcast.IsConstant() || bitcast.Opcode() != llvm.BitCast {
-				panic("expected const bitcast operand of runtime.makeGoroutine")
+			// Input param must be const ptrtoint of function.
+			ptrtoint := use.Operand(0)
+			if !ptrtoint.IsConstant() || ptrtoint.Opcode() != llvm.PtrToInt {
+				panic("expected const ptrtoint operand of runtime.makeGoroutine")
 			}
-			goroutine := bitcast.Operand(0)
+			goroutine := ptrtoint.Operand(0)
 			if _, ok := asyncFuncs[goroutine]; ok {
 				needsScheduler = true
 				break
@@ -292,7 +364,7 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 
 	// Transform all async functions into coroutines.
 	for _, f := range asyncList {
-		if f == sleep || f == deadlockStub || f == chanSend || f == chanRecv {
+		if f == sleep || f == deadlock || f == chanSend || f == chanRecv {
 			continue
 		}
 
@@ -309,7 +381,7 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 			for inst := bb.FirstInstruction(); !inst.IsNil(); inst = llvm.NextInstruction(inst) {
 				if !inst.IsACallInst().IsNil() {
 					callee := inst.CalledValue()
-					if _, ok := asyncFuncs[callee]; !ok || callee == sleep || callee == deadlockStub || callee == chanSend || callee == chanRecv {
+					if _, ok := asyncFuncs[callee]; !ok || callee == sleep || callee == deadlock || callee == chanSend || callee == chanRecv {
 						continue
 					}
 					asyncCalls = append(asyncCalls, inst)
@@ -321,7 +393,7 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 
 		// Coroutine setup.
 		c.builder.SetInsertPointBefore(f.EntryBasicBlock().FirstInstruction())
-		taskState := c.builder.CreateAlloca(c.mod.GetTypeByName("runtime.taskState"), "task.state")
+		taskState := c.builder.CreateAlloca(c.getLLVMRuntimeType("taskState"), "task.state")
 		stateI8 := c.builder.CreateBitCast(taskState, c.i8ptrType, "task.state.i8")
 		id := c.builder.CreateCall(coroIdFunc, []llvm.Value{
 			llvm.ConstInt(c.ctx.Int32Type(), 0, false),
@@ -336,6 +408,9 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 			size = c.builder.CreateZExt(size, c.uintptrType, "task.size.uintptr")
 		}
 		data := c.createRuntimeCall("alloc", []llvm.Value{size}, "task.data")
+		if c.needsStackObjects() {
+			c.trackPointer(data)
+		}
 		frame.taskHandle = c.builder.CreateCall(coroBeginFunc, []llvm.Value{id, data}, "task.handle")
 
 		// Modify async calls so this function suspends right after the child
@@ -354,7 +429,7 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 				retvalAlloca = c.builder.CreateAlloca(inst.Type(), "coro.retvalAlloca")
 				c.builder.SetInsertPointBefore(inst)
 				data := c.builder.CreateBitCast(retvalAlloca, c.i8ptrType, "")
-				c.createRuntimeCall("setTaskPromisePtr", []llvm.Value{frame.taskHandle, data}, "")
+				c.createRuntimeCall("setTaskStatePtr", []llvm.Value{frame.taskHandle, data}, "")
 			}
 
 			// Suspend.
@@ -392,7 +467,7 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 			var parentHandle llvm.Value
 			if f.Linkage() == llvm.ExternalLinkage {
 				// Exported function.
-				// Note that getTaskPromisePtr will panic if it is called with
+				// Note that getTaskStatePtr will panic if it is called with
 				// a nil pointer, so blocking exported functions that try to
 				// return anything will not work.
 				parentHandle = llvm.ConstPointerNull(c.i8ptrType)
@@ -400,7 +475,7 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 				parentHandle = f.LastParam()
 				if parentHandle.IsNil() || parentHandle.Name() != "parentHandle" {
 					// sanity check
-					panic("trying to make exported function async")
+					panic("trying to make exported function async: " + f.Name())
 				}
 			}
 
@@ -412,7 +487,7 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 				// Return this value by writing to the pointer stored in the
 				// parent handle. The parent coroutine has made an alloca that
 				// we can write to to store our return value.
-				returnValuePtr := c.createRuntimeCall("getTaskPromisePtr", []llvm.Value{parentHandle}, "coro.parentData")
+				returnValuePtr := c.createRuntimeCall("getTaskStatePtr", []llvm.Value{parentHandle}, "coro.parentData")
 				alloca := c.builder.CreateBitCast(returnValuePtr, llvm.PointerType(inst.Operand(0).Type(), 0), "coro.parentAlloca")
 				c.builder.CreateStore(inst.Operand(0), alloca)
 			default:
@@ -491,9 +566,9 @@ func (c *Compiler) markAsyncFunctions() (needsScheduler bool, err error) {
 		sleepCall.EraseFromParentAsInstruction()
 	}
 
-	// Transform calls to runtime.deadlockStub into coroutine suspends (without
+	// Transform calls to runtime.deadlock into coroutine suspends (without
 	// resume).
-	for _, deadlockCall := range getUses(deadlockStub) {
+	for _, deadlockCall := range getUses(deadlock) {
 		// deadlockCall must be a call instruction.
 		frame := asyncFuncs[deadlockCall.InstructionParent().Parent()]
 
@@ -568,14 +643,14 @@ func (c *Compiler) lowerMakeGoroutineCalls() error {
 
 	makeGoroutine := c.mod.NamedFunction("runtime.makeGoroutine")
 	for _, goroutine := range getUses(makeGoroutine) {
-		bitcastIn := goroutine.Operand(0)
-		origFunc := bitcastIn.Operand(0)
+		ptrtointIn := goroutine.Operand(0)
+		origFunc := ptrtointIn.Operand(0)
 		uses := getUses(goroutine)
-		if len(uses) != 1 || uses[0].IsABitCastInst().IsNil() {
-			return errors.New("expected exactly 1 bitcast use of runtime.makeGoroutine")
+		if len(uses) != 1 || uses[0].IsAIntToPtrInst().IsNil() {
+			return errors.New("expected exactly 1 inttoptr use of runtime.makeGoroutine")
 		}
-		bitcastOut := uses[0]
-		uses = getUses(bitcastOut)
+		inttoptrOut := uses[0]
+		uses = getUses(inttoptrOut)
 		if len(uses) != 1 || uses[0].IsACallInst().IsNil() {
 			return errors.New("expected exactly 1 call use of runtime.makeGoroutine bitcast")
 		}
@@ -590,7 +665,7 @@ func (c *Compiler) lowerMakeGoroutineCalls() error {
 		c.builder.SetInsertPointBefore(realCall)
 		c.builder.CreateCall(origFunc, params, "")
 		realCall.EraseFromParentAsInstruction()
-		bitcastOut.EraseFromParentAsInstruction()
+		inttoptrOut.EraseFromParentAsInstruction()
 		goroutine.EraseFromParentAsInstruction()
 	}
 

compiler/goroutine.go

@@ -0,0 +1,135 @@
+package compiler
+
+// This file implements the 'go' keyword to start a new goroutine. See
+// goroutine-lowering.go for more details.
+
+import "tinygo.org/x/go-llvm"
+
+// emitStartGoroutine starts a new goroutine with the provided function pointer
+// and parameters.
+//
+// Because a go statement doesn't return anything, return undef.
+func (c *Compiler) emitStartGoroutine(funcPtr llvm.Value, params []llvm.Value) llvm.Value {
+	switch c.selectScheduler() {
+	case "tasks":
+		paramBundle := c.emitPointerPack(params)
+		paramBundle = c.builder.CreatePtrToInt(paramBundle, c.uintptrType, "")
+
+		calleeValue := c.createGoroutineStartWrapper(funcPtr)
+		c.createRuntimeCall("startGoroutine", []llvm.Value{calleeValue, paramBundle}, "")
+	case "coroutines":
+		// We roundtrip through runtime.makeGoroutine as a signal (to find these
+		// calls) and to break any optimizations LLVM will try to do: they are
+		// invalid if we called this as a regular function to be updated later.
+		calleeValue := c.builder.CreatePtrToInt(funcPtr, c.uintptrType, "")
+		calleeValue = c.createRuntimeCall("makeGoroutine", []llvm.Value{calleeValue}, "")
+		calleeValue = c.builder.CreateIntToPtr(calleeValue, funcPtr.Type(), "")
+		c.createCall(calleeValue, params, "")
+	default:
+		panic("unreachable")
+	}
+	return llvm.Undef(funcPtr.Type().ElementType().ReturnType())
+}
+
+// createGoroutineStartWrapper creates a wrapper for the task-based
+// implementation of goroutines. For example, to call a function like this:
+//
+//     func add(x, y int) int { ... }
+//
+// It creates a wrapper like this:
+//
+//     func add$gowrapper(ptr *unsafe.Pointer) {
+//         args := (*struct{
+//             x, y int
+//         })(ptr)
+//         add(args.x, args.y)
+//     }
+//
+// This is useful because the task-based goroutine start implementation only
+// allows a single (pointer) argument to the newly started goroutine. Also, it
+// ignores the return value because newly started goroutines do not have a
+// return value.
+func (c *Compiler) createGoroutineStartWrapper(fn llvm.Value) llvm.Value {
+	var wrapper llvm.Value
+
+	if !fn.IsAFunction().IsNil() {
+		// See whether this wrapper has already been created. If so, return it.
+		name := fn.Name()
+		wrapper = c.mod.NamedFunction(name + "$gowrapper")
+		if !wrapper.IsNil() {
+			return c.builder.CreatePtrToInt(wrapper, c.uintptrType, "")
+		}
+
+		// Save the current position in the IR builder.
+		currentBlock := c.builder.GetInsertBlock()
+		defer c.builder.SetInsertPointAtEnd(currentBlock)
+
+		// Create the wrapper.
+		wrapperType := llvm.FunctionType(c.ctx.VoidType(), []llvm.Type{c.i8ptrType}, false)
+		wrapper = llvm.AddFunction(c.mod, name+"$gowrapper", wrapperType)
+		wrapper.SetLinkage(llvm.PrivateLinkage)
+		wrapper.SetUnnamedAddr(true)
+		entry := c.ctx.AddBasicBlock(wrapper, "entry")
+		c.builder.SetInsertPointAtEnd(entry)
+
+		// Create the list of params for the call.
+		paramTypes := fn.Type().ElementType().ParamTypes()
+		params := c.emitPointerUnpack(wrapper.Param(0), paramTypes[:len(paramTypes)-2])
+		params = append(params, llvm.Undef(c.i8ptrType), llvm.ConstPointerNull(c.i8ptrType))
+
+		// Create the call.
+		c.builder.CreateCall(fn, params, "")
+
+	} else {
+		// For a function pointer like this:
+		//
+		//     var funcPtr func(x, y int) int
+		//
+		// A wrapper like the following is created:
+		//
+		//     func .gowrapper(ptr *unsafe.Pointer) {
+		//         args := (*struct{
+		//             x, y int
+		//             fn   func(x, y int) int
+		//         })(ptr)
+		//         args.fn(x, y)
+		//     }
+		//
+		// With a bit of luck, identical wrapper functions like these can be
+		// merged into one.
+
+		// Save the current position in the IR builder.
+		currentBlock := c.builder.GetInsertBlock()
+		defer c.builder.SetInsertPointAtEnd(currentBlock)
+
+		// Create the wrapper.
+		wrapperType := llvm.FunctionType(c.ctx.VoidType(), []llvm.Type{c.i8ptrType}, false)
+		wrapper = llvm.AddFunction(c.mod, ".gowrapper", wrapperType)
+		wrapper.SetLinkage(llvm.InternalLinkage)
+		wrapper.SetUnnamedAddr(true)
+		entry := c.ctx.AddBasicBlock(wrapper, "entry")
+		c.builder.SetInsertPointAtEnd(entry)
+
+		// Get the list of parameters, with the extra parameters at the end.
+		paramTypes := fn.Type().ElementType().ParamTypes()
+		paramTypes[len(paramTypes)-1] = fn.Type() // the last element is the function pointer
+		params := c.emitPointerUnpack(wrapper.Param(0), paramTypes)
+
+		// Get the function pointer.
+		fnPtr := params[len(params)-1]
+
+		// Ignore the last param, which isn't used anymore.
+		// TODO: avoid this extra "parent handle" parameter in most functions.
+		params[len(params)-1] = llvm.Undef(c.i8ptrType)
+
+		// Create the call.
+		c.builder.CreateCall(fnPtr, params, "")
+	}
+
+	// Finish the function. Every basic block must end in a terminator, and
+	// because goroutines never return a value we can simply return void.
+	c.builder.CreateRetVoid()
+
+	// Return a ptrtoint of the wrapper, not the function itself.
+	return c.builder.CreatePtrToInt(wrapper, c.uintptrType, "")
+}

compiler/inlineasm.go

@@ -18,10 +18,19 @@ import (
 //     func ReadRegister(name string) uintptr
 //
 // The register name must be a constant, for example "sp".
-func (c *Compiler) emitReadRegister(args []ssa.Value) (llvm.Value, error) {
+func (c *Compiler) emitReadRegister(name string, args []ssa.Value) (llvm.Value, error) {
 	fnType := llvm.FunctionType(c.uintptrType, []llvm.Type{}, false)
 	regname := constant.StringVal(args[0].(*ssa.Const).Value)
-	target := llvm.InlineAsm(fnType, "mov $0, "+regname, "=r", false, false, 0)
+	var asm string
+	switch name {
+	case "device/arm.ReadRegister":
+		asm = "mov $0, " + regname
+	case "device/riscv.ReadRegister":
+		asm = "mv $0, " + regname
+	default:
+		panic("unknown architecture")
+	}
+	target := llvm.InlineAsm(fnType, asm, "=r", false, false, 0)
 	return c.builder.CreateCall(target, nil, ""), nil
 }
 

compiler/interface-lowering.go

@@ -163,8 +163,8 @@ func (c *Compiler) LowerInterfaces() {
 // run runs the pass itself.
 func (p *lowerInterfacesPass) run() {
 	// Collect all type codes.
-	typecodeIDPtr := llvm.PointerType(p.mod.GetTypeByName("runtime.typecodeID"), 0)
-	typeInInterfacePtr := llvm.PointerType(p.mod.GetTypeByName("runtime.typeInInterface"), 0)
+	typecodeIDPtr := llvm.PointerType(p.getLLVMRuntimeType("typecodeID"), 0)
+	typeInInterfacePtr := llvm.PointerType(p.getLLVMRuntimeType("typeInInterface"), 0)
 	var typesInInterfaces []llvm.Value
 	for global := p.mod.FirstGlobal(); !global.IsNil(); global = llvm.NextGlobal(global) {
 		switch global.Type() {
@@ -603,9 +603,9 @@ func (p *lowerInterfacesPass) createInterfaceImplementsFunc(itf *interfaceInfo)
 	// TODO: debug info
 
 	// Create all used basic blocks.
-	entry := llvm.AddBasicBlock(fn, "entry")
-	thenBlock := llvm.AddBasicBlock(fn, "then")
-	elseBlock := llvm.AddBasicBlock(fn, "else")
+	entry := p.ctx.AddBasicBlock(fn, "entry")
+	thenBlock := p.ctx.AddBasicBlock(fn, "then")
+	elseBlock := p.ctx.AddBasicBlock(fn, "else")
 
 	// Add all possible types as cases.
 	p.builder.SetInsertPointAtEnd(entry)
@@ -661,11 +661,11 @@ func (p *lowerInterfacesPass) createInterfaceMethodFunc(itf *interfaceInfo, sign
 	// TODO: debug info
 
 	// Create entry block.
-	entry := llvm.AddBasicBlock(fn, "entry")
+	entry := p.ctx.AddBasicBlock(fn, "entry")
 
 	// Create default block and make it unreachable (which it is, because all
 	// possible types are checked).
-	defaultBlock := llvm.AddBasicBlock(fn, "default")
+	defaultBlock := p.ctx.AddBasicBlock(fn, "default")
 	p.builder.SetInsertPointAtEnd(defaultBlock)
 	p.builder.CreateUnreachable()
 
@@ -684,7 +684,7 @@ func (p *lowerInterfacesPass) createInterfaceMethodFunc(itf *interfaceInfo, sign
 
 	// Define all possible functions that can be called.
 	for _, typ := range itf.types {
-		bb := llvm.AddBasicBlock(fn, typ.name)
+		bb := p.ctx.AddBasicBlock(fn, typ.name)
 		sw.AddCase(llvm.ConstInt(p.uintptrType, typ.num, false), bb)
 
 		// The function we will redirect to when the interface has this type.

compiler/interface.go

@@ -28,14 +28,14 @@ func (c *Compiler) parseMakeInterface(val llvm.Value, typ types.Type, pos token.
 	itfMethodSetGlobal := c.getTypeMethodSet(typ)
 	itfConcreteTypeGlobal := c.mod.NamedGlobal("typeInInterface:" + itfTypeCodeGlobal.Name())
 	if itfConcreteTypeGlobal.IsNil() {
-		typeInInterface := c.mod.GetTypeByName("runtime.typeInInterface")
+		typeInInterface := c.getLLVMRuntimeType("typeInInterface")
 		itfConcreteTypeGlobal = llvm.AddGlobal(c.mod, typeInInterface, "typeInInterface:"+itfTypeCodeGlobal.Name())
 		itfConcreteTypeGlobal.SetInitializer(llvm.ConstNamedStruct(typeInInterface, []llvm.Value{itfTypeCodeGlobal, itfMethodSetGlobal}))
 		itfConcreteTypeGlobal.SetGlobalConstant(true)
 		itfConcreteTypeGlobal.SetLinkage(llvm.PrivateLinkage)
 	}
 	itfTypeCode := c.builder.CreatePtrToInt(itfConcreteTypeGlobal, c.uintptrType, "")
-	itf := llvm.Undef(c.mod.GetTypeByName("runtime._interface"))
+	itf := llvm.Undef(c.getLLVMRuntimeType("_interface"))
 	itf = c.builder.CreateInsertValue(itf, itfTypeCode, 0, "")
 	itf = c.builder.CreateInsertValue(itf, itfValue, 1, "")
 	return itf
@@ -45,27 +45,100 @@ func (c *Compiler) parseMakeInterface(val llvm.Value, typ types.Type, pos token.
 // It returns a pointer to an external global which should be replaced with the
 // real type in the interface lowering pass.
 func (c *Compiler) getTypeCode(typ types.Type) llvm.Value {
-	globalName := "type:" + getTypeCodeName(typ)
+	globalName := "reflect/types.type:" + getTypeCodeName(typ)
 	global := c.mod.NamedGlobal(globalName)
 	if global.IsNil() {
-		global = llvm.AddGlobal(c.mod, c.mod.GetTypeByName("runtime.typecodeID"), globalName)
+		// Create a new typecode global.
+		global = llvm.AddGlobal(c.mod, c.getLLVMRuntimeType("typecodeID"), globalName)
+		// Some type classes contain more information for underlying types or
+		// element types. Store it directly in the typecode global to make
+		// reflect lowering simpler.
+		var references llvm.Value
+		var length int64
+		switch typ := typ.(type) {
+		case *types.Named:
+			references = c.getTypeCode(typ.Underlying())
+		case *types.Chan:
+			references = c.getTypeCode(typ.Elem())
+		case *types.Pointer:
+			references = c.getTypeCode(typ.Elem())
+		case *types.Slice:
+			references = c.getTypeCode(typ.Elem())
+		case *types.Array:
+			references = c.getTypeCode(typ.Elem())
+			length = typ.Len()
+		case *types.Struct:
+			// Take a pointer to the typecodeID of the first field (if it exists).
+			structGlobal := c.makeStructTypeFields(typ)
+			references = llvm.ConstBitCast(structGlobal, global.Type())
+		}
+		if !references.IsNil() {
+			// Set the 'references' field of the runtime.typecodeID struct.
+			globalValue := llvm.ConstNull(global.Type().ElementType())
+			globalValue = llvm.ConstInsertValue(globalValue, references, []uint32{0})
+			if length != 0 {
+				lengthValue := llvm.ConstInt(c.uintptrType, uint64(length), false)
+				globalValue = llvm.ConstInsertValue(globalValue, lengthValue, []uint32{1})
+			}
+			global.SetInitializer(globalValue)
+			global.SetLinkage(llvm.PrivateLinkage)
+		}
 		global.SetGlobalConstant(true)
 	}
 	return global
 }
 
+// makeStructTypeFields creates a new global that stores all type information
+// related to this struct type, and returns the resulting global. This global is
+// actually an array of all the fields in the structs.
+func (c *Compiler) makeStructTypeFields(typ *types.Struct) llvm.Value {
+	// The global is an array of runtime.structField structs.
+	runtimeStructField := c.getLLVMRuntimeType("structField")
+	structGlobalType := llvm.ArrayType(runtimeStructField, typ.NumFields())
+	structGlobal := llvm.AddGlobal(c.mod, structGlobalType, "reflect/types.structFields")
+	structGlobalValue := llvm.ConstNull(structGlobalType)
+	for i := 0; i < typ.NumFields(); i++ {
+		fieldGlobalValue := llvm.ConstNull(runtimeStructField)
+		fieldGlobalValue = llvm.ConstInsertValue(fieldGlobalValue, c.getTypeCode(typ.Field(i).Type()), []uint32{0})
+		fieldName := c.makeGlobalArray([]byte(typ.Field(i).Name()), "reflect/types.structFieldName", c.ctx.Int8Type())
+		fieldName.SetLinkage(llvm.PrivateLinkage)
+		fieldName.SetUnnamedAddr(true)
+		fieldName = llvm.ConstGEP(fieldName, []llvm.Value{
+			llvm.ConstInt(llvm.Int32Type(), 0, false),
+			llvm.ConstInt(llvm.Int32Type(), 0, false),
+		})
+		fieldGlobalValue = llvm.ConstInsertValue(fieldGlobalValue, fieldName, []uint32{1})
+		if typ.Tag(i) != "" {
+			fieldTag := c.makeGlobalArray([]byte(typ.Tag(i)), "reflect/types.structFieldTag", c.ctx.Int8Type())
+			fieldTag.SetLinkage(llvm.PrivateLinkage)
+			fieldTag.SetUnnamedAddr(true)
+			fieldTag = llvm.ConstGEP(fieldTag, []llvm.Value{
+				llvm.ConstInt(llvm.Int32Type(), 0, false),
+				llvm.ConstInt(llvm.Int32Type(), 0, false),
+			})
+			fieldGlobalValue = llvm.ConstInsertValue(fieldGlobalValue, fieldTag, []uint32{2})
+		}
+		if typ.Field(i).Embedded() {
+			fieldEmbedded := llvm.ConstInt(c.ctx.Int1Type(), 1, false)
+			fieldGlobalValue = llvm.ConstInsertValue(fieldGlobalValue, fieldEmbedded, []uint32{3})
+		}
+		structGlobalValue = llvm.ConstInsertValue(structGlobalValue, fieldGlobalValue, []uint32{uint32(i)})
+	}
+	structGlobal.SetInitializer(structGlobalValue)
+	structGlobal.SetUnnamedAddr(true)
+	structGlobal.SetLinkage(llvm.PrivateLinkage)
+	return structGlobal
+}
+
 // getTypeCodeName returns a name for this type that can be used in the
 // interface lowering pass to assign type codes as expected by the reflect
 // package. See getTypeCodeNum.
 func getTypeCodeName(t types.Type) string {
-	name := ""
-	if named, ok := t.(*types.Named); ok {
-		name = "~" + named.String() + ":"
-		t = t.Underlying()
-	}
 	switch t := t.(type) {
+	case *types.Named:
+		return "named:" + t.String()
 	case *types.Array:
-		return "array:" + name + strconv.FormatInt(t.Len(), 10) + ":" + getTypeCodeName(t.Elem())
+		return "array:" + strconv.FormatInt(t.Len(), 10) + ":" + getTypeCodeName(t.Elem())
 	case *types.Basic:
 		var kind string
 		switch t.Kind() {
@@ -108,21 +181,21 @@ func getTypeCodeName(t types.Type) string {
 		default:
 			panic("unknown basic type: " + t.Name())
 		}
-		return "basic:" + name + kind
+		return "basic:" + kind
 	case *types.Chan:
-		return "chan:" + name + getTypeCodeName(t.Elem())
+		return "chan:" + getTypeCodeName(t.Elem())
 	case *types.Interface:
 		methods := make([]string, t.NumMethods())
 		for i := 0; i < t.NumMethods(); i++ {
 			methods[i] = getTypeCodeName(t.Method(i).Type())
 		}
-		return "interface:" + name + "{" + strings.Join(methods, ",") + "}"
+		return "interface:" + "{" + strings.Join(methods, ",") + "}"
 	case *types.Map:
 		keyType := getTypeCodeName(t.Key())
 		elemType := getTypeCodeName(t.Elem())
-		return "map:" + name + "{" + keyType + "," + elemType + "}"
+		return "map:" + "{" + keyType + "," + elemType + "}"
 	case *types.Pointer:
-		return "pointer:" + name + getTypeCodeName(t.Elem())
+		return "pointer:" + getTypeCodeName(t.Elem())
 	case *types.Signature:
 		params := make([]string, t.Params().Len())
 		for i := 0; i < t.Params().Len(); i++ {
@@ -132,9 +205,9 @@ func getTypeCodeName(t types.Type) string {
 		for i := 0; i < t.Results().Len(); i++ {
 			results[i] = getTypeCodeName(t.Results().At(i).Type())
 		}
-		return "func:" + name + "{" + strings.Join(params, ",") + "}{" + strings.Join(results, ",") + "}"
+		return "func:" + "{" + strings.Join(params, ",") + "}{" + strings.Join(results, ",") + "}"
 	case *types.Slice:
-		return "slice:" + name + getTypeCodeName(t.Elem())
+		return "slice:" + getTypeCodeName(t.Elem())
 	case *types.Struct:
 		elems := make([]string, t.NumFields())
 		if t.NumFields() > 2 && t.Field(0).Name() == "C union" {
@@ -142,9 +215,16 @@ func getTypeCodeName(t types.Type) string {
 			panic("cgo unions are not allowed in interfaces")
 		}
 		for i := 0; i < t.NumFields(); i++ {
-			elems[i] = getTypeCodeName(t.Field(i).Type())
+			embedded := ""
+			if t.Field(i).Embedded() {
+				embedded = "#"
+			}
+			elems[i] = embedded + t.Field(i).Name() + ":" + getTypeCodeName(t.Field(i).Type())
+			if t.Tag(i) != "" {
+				elems[i] += "`" + t.Tag(i) + "`"
+			}
 		}
-		return "struct:" + name + "{" + strings.Join(elems, ",") + "}"
+		return "struct:" + "{" + strings.Join(elems, ",") + "}"
 	default:
 		panic("unknown type: " + t.String())
 	}
@@ -163,11 +243,11 @@ func (c *Compiler) getTypeMethodSet(typ types.Type) llvm.Value {
 	ms := c.ir.Program.MethodSets.MethodSet(typ)
 	if ms.Len() == 0 {
 		// no methods, so can leave that one out
-		return llvm.ConstPointerNull(llvm.PointerType(c.mod.GetTypeByName("runtime.interfaceMethodInfo"), 0))
+		return llvm.ConstPointerNull(llvm.PointerType(c.getLLVMRuntimeType("interfaceMethodInfo"), 0))
 	}
 
 	methods := make([]llvm.Value, ms.Len())
-	interfaceMethodInfoType := c.mod.GetTypeByName("runtime.interfaceMethodInfo")
+	interfaceMethodInfoType := c.getLLVMRuntimeType("interfaceMethodInfo")
 	for i := 0; i < ms.Len(); i++ {
 		method := ms.At(i)
 		signatureGlobal := c.getMethodSignature(method.Obj().(*types.Func))
@@ -300,7 +380,7 @@ func (c *Compiler) parseTypeAssert(frame *Frame, expr *ssa.TypeAssert) llvm.Valu
 	// Continue after the if statement.
 	c.builder.SetInsertPointAtEnd(nextBlock)
 	phi := c.builder.CreatePHI(assertedType, "typeassert.value")
-	phi.AddIncoming([]llvm.Value{c.getZeroValue(assertedType), valueOk}, []llvm.BasicBlock{prevBlock, okBlock})
+	phi.AddIncoming([]llvm.Value{llvm.ConstNull(assertedType), valueOk}, []llvm.BasicBlock{prevBlock, okBlock})
 
 	if expr.CommaOk {
 		tuple := c.ctx.ConstStruct([]llvm.Value{llvm.Undef(assertedType), llvm.Undef(c.ctx.Int1Type())}, false) // create empty tuple

compiler/llvm.go

@@ -1,6 +1,8 @@
 package compiler
 
 import (
+	"reflect"
+
 	"tinygo.org/x/go-llvm"
 )
 
@@ -152,3 +154,48 @@ func (c *Compiler) splitBasicBlock(afterInst llvm.Value, insertAfter llvm.BasicB
 
 	return newBlock
 }
+
+// makeGlobalArray creates a new LLVM global with the given name and integers as
+// contents, and returns the global.
+// Note that it is left with the default linkage etc., you should set
+// linkage/constant/etc properties yourself.
+func (c *Compiler) makeGlobalArray(bufItf interface{}, name string, elementType llvm.Type) llvm.Value {
+	buf := reflect.ValueOf(bufItf)
+	globalType := llvm.ArrayType(elementType, buf.Len())
+	global := llvm.AddGlobal(c.mod, globalType, name)
+	value := llvm.Undef(globalType)
+	for i := 0; i < buf.Len(); i++ {
+		ch := buf.Index(i).Uint()
+		value = llvm.ConstInsertValue(value, llvm.ConstInt(elementType, ch, false), []uint32{uint32(i)})
+	}
+	global.SetInitializer(value)
+	return global
+}
+
+// getGlobalBytes returns the slice contained in the array of the provided
+// global. It can recover the bytes originally created using makeGlobalArray, if
+// makeGlobalArray was given a byte slice.
+func getGlobalBytes(global llvm.Value) []byte {
+	value := global.Initializer()
+	buf := make([]byte, value.Type().ArrayLength())
+	for i := range buf {
+		buf[i] = byte(llvm.ConstExtractValue(value, []uint32{uint32(i)}).ZExtValue())
+	}
+	return buf
+}
+
+// replaceGlobalByteWithArray replaces a global integer type in the module with
+// an integer array, using a GEP to make the types match. It is a convenience
+// function used for creating reflection sidetables, for example.
+func (c *Compiler) replaceGlobalIntWithArray(name string, buf interface{}) llvm.Value {
+	oldGlobal := c.mod.NamedGlobal(name)
+	global := c.makeGlobalArray(buf, name+".tmp", oldGlobal.Type().ElementType())
+	gep := llvm.ConstGEP(global, []llvm.Value{
+		llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+		llvm.ConstInt(c.ctx.Int32Type(), 0, false),
+	})
+	oldGlobal.ReplaceAllUsesWith(gep)
+	oldGlobal.EraseFromParentAsGlobal()
+	global.SetName(name)
+	return global
+}

compiler/map.go

@@ -35,7 +35,7 @@ func (c *Compiler) emitMapLookup(keyType, valueType types.Type, m, key llvm.Valu
 		c.emitLifetimeEnd(mapKeyPtr, mapKeySize)
 	} else {
 		// Not trivially comparable using memcmp.
-		return llvm.Value{}, c.makeError(pos, "only strings, bools, ints or structs of bools/ints are supported as map keys, but got: "+keyType.String())
+		return llvm.Value{}, c.makeError(pos, "only strings, bools, ints, pointers or structs of bools/ints are supported as map keys, but got: "+keyType.String())
 	}
 
 	// Load the resulting value from the hashmap. The value is set to the zero
@@ -69,7 +69,7 @@ func (c *Compiler) emitMapUpdate(keyType types.Type, m, key, value llvm.Value, p
 		c.createRuntimeCall("hashmapBinarySet", params, "")
 		c.emitLifetimeEnd(keyPtr, keySize)
 	} else {
-		c.addError(pos, "only strings, bools, ints or structs of bools/ints are supported as map keys, but got: "+keyType.String())
+		c.addError(pos, "only strings, bools, ints, pointers or structs of bools/ints are supported as map keys, but got: "+keyType.String())
 	}
 	c.emitLifetimeEnd(valuePtr, valueSize)
 }
@@ -89,7 +89,7 @@ func (c *Compiler) emitMapDelete(keyType types.Type, m, key llvm.Value, pos toke
 		c.emitLifetimeEnd(keyPtr, keySize)
 		return nil
 	} else {
-		return c.makeError(pos, "only strings, bools, ints or structs of bools/ints are supported as map keys, but got: "+keyType.String())
+		return c.makeError(pos, "only strings, bools, ints, pointers or structs of bools/ints are supported as map keys, but got: "+keyType.String())
 	}
 }
 
@@ -121,6 +121,8 @@ func hashmapIsBinaryKey(keyType types.Type) bool {
 	switch keyType := keyType.(type) {
 	case *types.Basic:
 		return keyType.Info()&(types.IsBoolean|types.IsInteger) != 0
+	case *types.Pointer:
+		return true
 	case *types.Struct:
 		for i := 0; i < keyType.NumFields(); i++ {
 			fieldType := keyType.Field(i).Type().Underlying()

compiler/optimizer.go

@@ -3,6 +3,7 @@ package compiler
 import (
 	"errors"
 
+	"github.com/tinygo-org/tinygo/transform"
 	"tinygo.org/x/go-llvm"
 )
 
@@ -22,6 +23,11 @@ func (c *Compiler) Optimize(optLevel, sizeLevel int, inlinerThreshold uint) erro
 		c.replacePanicsWithTrap() // -panic=trap
 	}
 
+	// run a check of all of our code
+	if c.VerifyIR {
+		c.checkModule()
+	}
+
 	// Run function passes for each function.
 	funcPasses := llvm.NewFunctionPassManagerForModule(c.mod)
 	defer funcPasses.Dispose()
@@ -43,9 +49,9 @@ func (c *Compiler) Optimize(optLevel, sizeLevel int, inlinerThreshold uint) erro
 		goPasses.Run(c.mod)
 
 		// Run Go-specific optimization passes.
-		c.OptimizeMaps()
+		transform.OptimizeMaps(c.mod)
 		c.OptimizeStringToBytes()
-		c.OptimizeAllocs()
+		transform.OptimizeAllocs(c.mod)
 		c.LowerInterfaces()
 		c.LowerFuncValues()
 
@@ -55,7 +61,7 @@ func (c *Compiler) Optimize(optLevel, sizeLevel int, inlinerThreshold uint) erro
 		goPasses.Run(c.mod)
 
 		// Run TinyGo-specific interprocedural optimizations.
-		c.OptimizeAllocs()
+		transform.OptimizeAllocs(c.mod)
 		c.OptimizeStringToBytes()
 
 		// Lower runtime.isnil calls to regular nil comparisons.
@@ -101,6 +107,15 @@ func (c *Compiler) Optimize(optLevel, sizeLevel int, inlinerThreshold uint) erro
 		}
 	}
 
+	// After TinyGo-specific transforms have finished, undo exporting these functions.
+	for _, name := range functionsUsedInTransforms {
+		fn := c.mod.NamedFunction(name)
+		if fn.IsNil() {
+			continue
+		}
+		fn.SetLinkage(llvm.InternalLinkage)
+	}
+
 	// Run function passes again, because without it, llvm.coro.size.i32()
 	// doesn't get lowered.
 	for fn := c.mod.FirstFunction(); !fn.IsNil(); fn = llvm.NextFunction(fn) {
@@ -114,6 +129,14 @@ func (c *Compiler) Optimize(optLevel, sizeLevel int, inlinerThreshold uint) erro
 	builder.Populate(modPasses)
 	modPasses.Run(c.mod)
 
+	hasGCPass := c.addGlobalsBitmap()
+	hasGCPass = c.makeGCStackSlots() || hasGCPass
+	if hasGCPass {
+		if err := c.Verify(); err != nil {
+			return errors.New("GC pass caused a verification failure")
+		}
+	}
+
 	return nil
 }
 
@@ -136,48 +159,6 @@ func (c *Compiler) replacePanicsWithTrap() {
 	}
 }
 
-// Eliminate created but not used maps.
-//
-// In the future, this should statically allocate created but never modified
-// maps. This has not yet been implemented, however.
-func (c *Compiler) OptimizeMaps() {
-	hashmapMake := c.mod.NamedFunction("runtime.hashmapMake")
-	if hashmapMake.IsNil() {
-		// nothing to optimize
-		return
-	}
-
-	hashmapBinarySet := c.mod.NamedFunction("runtime.hashmapBinarySet")
-	hashmapStringSet := c.mod.NamedFunction("runtime.hashmapStringSet")
-
-	for _, makeInst := range getUses(hashmapMake) {
-		updateInsts := []llvm.Value{}
-		unknownUses := false // are there any uses other than setting a value?
-
-		for _, use := range getUses(makeInst) {
-			if use := use.IsACallInst(); !use.IsNil() {
-				switch use.CalledValue() {
-				case hashmapBinarySet, hashmapStringSet:
-					updateInsts = append(updateInsts, use)
-				default:
-					unknownUses = true
-				}
-			} else {
-				unknownUses = true
-			}
-		}
-
-		if !unknownUses {
-			// This map can be entirely removed, as it is only created but never
-			// used.
-			for _, inst := range updateInsts {
-				inst.EraseFromParentAsInstruction()
-			}
-			makeInst.EraseFromParentAsInstruction()
-		}
-	}
-}
-
 // Transform runtime.stringToBytes(...) calls into const []byte slices whenever
 // possible. This optimizes the following pattern:
 //     w.Write([]byte("foo"))
@@ -228,101 +209,6 @@ func (c *Compiler) OptimizeStringToBytes() {
 	}
 }
 
-// Basic escape analysis: translate runtime.alloc calls into alloca
-// instructions.
-func (c *Compiler) OptimizeAllocs() {
-	allocator := c.mod.NamedFunction("runtime.alloc")
-	if allocator.IsNil() {
-		// nothing to optimize
-		return
-	}
-
-	heapallocs := getUses(allocator)
-	for _, heapalloc := range heapallocs {
-		nilValue := llvm.Value{}
-		if heapalloc.Operand(0).IsAConstant() == nilValue {
-			// Do not allocate variable length arrays on the stack.
-			continue
-		}
-		size := heapalloc.Operand(0).ZExtValue()
-		if size > 256 {
-			// The maximum value for a stack allocation.
-			// TODO: tune this, this is just a random value.
-			continue
-		}
-
-		// In general the pattern is:
-		//     %0 = call i8* @runtime.alloc(i32 %size)
-		//     %1 = bitcast i8* %0 to type*
-		//     (use %1 only)
-		// But the bitcast might sometimes be dropped when allocating an *i8.
-		// The 'bitcast' variable below is thus usually a bitcast of the
-		// heapalloc but not always.
-		bitcast := heapalloc // instruction that creates the value
-		if uses := getUses(heapalloc); len(uses) == 1 && uses[0].IsABitCastInst() != nilValue {
-			// getting only bitcast use
-			bitcast = uses[0]
-		}
-		if !c.doesEscape(bitcast) {
-			// Insert alloca in the entry block. Do it here so that mem2reg can
-			// promote it to a SSA value.
-			fn := bitcast.InstructionParent().Parent()
-			c.builder.SetInsertPointBefore(fn.EntryBasicBlock().FirstInstruction())
-			alignment := c.targetData.ABITypeAlignment(c.i8ptrType)
-			sizeInWords := (size + uint64(alignment) - 1) / uint64(alignment)
-			allocaType := llvm.ArrayType(c.ctx.IntType(alignment*8), int(sizeInWords))
-			alloca := c.builder.CreateAlloca(allocaType, "stackalloc.alloca")
-			zero := c.getZeroValue(alloca.Type().ElementType())
-			c.builder.CreateStore(zero, alloca)
-			stackalloc := c.builder.CreateBitCast(alloca, bitcast.Type(), "stackalloc")
-			bitcast.ReplaceAllUsesWith(stackalloc)
-			if heapalloc != bitcast {
-				bitcast.EraseFromParentAsInstruction()
-			}
-			heapalloc.EraseFromParentAsInstruction()
-		}
-	}
-}
-
-// Very basic escape analysis.
-func (c *Compiler) doesEscape(value llvm.Value) bool {
-	uses := getUses(value)
-	for _, use := range uses {
-		nilValue := llvm.Value{}
-		if use.IsAGetElementPtrInst() != nilValue {
-			if c.doesEscape(use) {
-				return true
-			}
-		} else if use.IsABitCastInst() != nilValue {
-			// A bitcast escapes if the casted-to value escapes.
-			if c.doesEscape(use) {
-				return true
-			}
-		} else if use.IsALoadInst() != nilValue {
-			// Load does not escape.
-		} else if use.IsAStoreInst() != nilValue {
-			// Store only escapes when the value is stored to, not when the
-			// value is stored into another value.
-			if use.Operand(0) == value {
-				return true
-			}
-		} else if use.IsACallInst() != nilValue {
-			if !c.hasFlag(use, value, "nocapture") {
-				return true
-			}
-		} else if use.IsAICmpInst() != nilValue {
-			// Comparing pointers don't let the pointer escape.
-			// This is often a compiler-inserted nil check.
-		} else {
-			// Unknown instruction, might escape.
-			return true
-		}
-	}
-
-	// does not escape
-	return false
-}
-
 // Check whether the given value (which is of pointer type) is never stored to.
 func (c *Compiler) isReadOnly(value llvm.Value) bool {
 	uses := getUses(value)

compiler/reflect.go

@@ -1,10 +1,43 @@
 package compiler
 
+// This file has some compiler support for run-time reflection using the reflect
+// package. In particular, it encodes type information in type codes in such a
+// way that the reflect package can decode the type from this information.
+// Where needed, it also adds some side tables for looking up more information
+// about a type, when that information cannot be stored directly in the type
+// code.
+//
+// Go has 26 different type kinds.
+//
+// Type kinds are subdivided in basic types (see the list of basicTypes below)
+// that are mostly numeric literals and non-basic (or "complex") types that are
+// more difficult to encode. These non-basic types come in two forms:
+//   * Prefix types (pointer, slice, interface, channel): these just add
+//     something to an existing type. For example, a pointer like *int just adds
+//     the fact that it's a pointer to an existing type (int).
+//     These are encoded efficiently by adding a prefix to a type code.
+//   * Types with multiple fields (struct, array, func, map). All of these have
+//     multiple fields contained within. Most obviously structs can contain many
+//     types as fields. Also arrays contain not just the element type but also
+//     the length parameter which can be any arbitrary number and thus may not
+//     fit in a type code.
+//     These types are encoded using side tables.
+//
+// This distinction is also important for how named types are encoded. At the
+// moment, named basic type just get a unique number assigned while named
+// non-basic types have their underlying type stored in a sidetable.
+
 import (
+	"encoding/binary"
+	"go/ast"
 	"math/big"
 	"strings"
+
+	"tinygo.org/x/go-llvm"
 )
 
+// A list of basic types and their numbers. This list should be kept in sync
+// with the list of Kind constants of type.go in the reflect package.
 var basicTypes = map[string]int64{
 	"bool":       1,
 	"int":        2,
@@ -26,6 +59,72 @@ var basicTypes = map[string]int64{
 	"unsafeptr":  18,
 }
 
+// A list of non-basic types. Adding 19 to this number will give the Kind as
+// used in src/reflect/types.go, and it must be kept in sync with that list.
+var nonBasicTypes = map[string]int64{
+	"chan":      0,
+	"interface": 1,
+	"pointer":   2,
+	"slice":     3,
+	"array":     4,
+	"func":      5,
+	"map":       6,
+	"struct":    7,
+}
+
+// typeCodeAssignmentState keeps some global state around for type code
+// assignments, used to assign one unique type code to each Go type.
+type typeCodeAssignmentState struct {
+	// An integer that's incremented each time it's used to give unique IDs to
+	// type codes that are not yet fully supported otherwise by the reflect
+	// package (or are simply unused in the compiled program).
+	fallbackIndex int
+
+	// This is the length of an uintptr. Only used occasionally to know whether
+	// a given number can be encoded as a varint.
+	uintptrLen int
+
+	// Map of named types to their type code. It is important that named types
+	// get unique IDs for each type.
+	namedBasicTypes    map[string]int
+	namedNonBasicTypes map[string]int
+
+	// Map of array types to their type code.
+	arrayTypes               map[string]int
+	arrayTypesSidetable      []byte
+	needsArrayTypesSidetable bool
+
+	// Map of struct types to their type code.
+	structTypes               map[string]int
+	structTypesSidetable      []byte
+	needsStructNamesSidetable bool
+
+	// Map of struct names and tags to their name string.
+	structNames               map[string]int
+	structNamesSidetable      []byte
+	needsStructTypesSidetable bool
+
+	// This byte array is stored in reflect.namedNonBasicTypesSidetable and is
+	// used at runtime to get details about a named non-basic type.
+	// Entries are varints (see makeVarint below and readVarint in
+	// reflect/sidetables.go for the encoding): one varint per entry. The
+	// integers in namedNonBasicTypes are indices into this array. Because these
+	// are varints, most type codes are really small (just one byte).
+	//
+	// Note that this byte buffer is not created when it is not needed
+	// (reflect.namedNonBasicTypesSidetable has no uses), see
+	// needsNamedTypesSidetable.
+	namedNonBasicTypesSidetable []uint64
+
+	// This indicates whether namedNonBasicTypesSidetable needs to be created at
+	// all. If it is false, namedNonBasicTypesSidetable will contain simple
+	// monotonically increasing numbers.
+	needsNamedNonBasicTypesSidetable bool
+}
+
+// assignTypeCodes is used to assign a type code to each type in the program
+// that is ever stored in an interface. It tries to use the smallest possible
+// numbers to make the code that works with interfaces as small as possible.
 func (c *Compiler) assignTypeCodes(typeSlice typeInfoSlice) {
 	fn := c.mod.NamedFunction("reflect.ValueOf")
 	if fn.IsNil() {
@@ -38,13 +137,21 @@ func (c *Compiler) assignTypeCodes(typeSlice typeInfoSlice) {
 	}
 
 	// Assign typecodes the way the reflect package expects.
-	fallbackIndex := 1
-	namedTypes := make(map[string]int)
+	state := typeCodeAssignmentState{
+		fallbackIndex:                    1,
+		uintptrLen:                       c.uintptrType.IntTypeWidth(),
+		namedBasicTypes:                  make(map[string]int),
+		namedNonBasicTypes:               make(map[string]int),
+		arrayTypes:                       make(map[string]int),
+		structTypes:                      make(map[string]int),
+		structNames:                      make(map[string]int),
+		needsNamedNonBasicTypesSidetable: len(getUses(c.mod.NamedGlobal("reflect.namedNonBasicTypesSidetable"))) != 0,
+		needsStructTypesSidetable:        len(getUses(c.mod.NamedGlobal("reflect.structTypesSidetable"))) != 0,
+		needsStructNamesSidetable:        len(getUses(c.mod.NamedGlobal("reflect.structNamesSidetable"))) != 0,
+		needsArrayTypesSidetable:         len(getUses(c.mod.NamedGlobal("reflect.arrayTypesSidetable"))) != 0,
+	}
 	for _, t := range typeSlice {
-		if t.name[:5] != "type:" {
-			panic("expected type name to start with 'type:'")
-		}
-		num := c.getTypeCodeNum(t.name[5:], &fallbackIndex, namedTypes)
+		num := state.getTypeCodeNum(t.typecode)
 		if num.BitLen() > c.uintptrType.IntTypeWidth() || !num.IsUint64() {
 			// TODO: support this in some way, using a side table for example.
 			// That's less efficient but better than not working at all.
@@ -54,25 +161,41 @@ func (c *Compiler) assignTypeCodes(typeSlice typeInfoSlice) {
 		}
 		t.num = num.Uint64()
 	}
+
+	// Only create this sidetable when it is necessary.
+	if state.needsNamedNonBasicTypesSidetable {
+		global := c.replaceGlobalIntWithArray("reflect.namedNonBasicTypesSidetable", state.namedNonBasicTypesSidetable)
+		global.SetLinkage(llvm.InternalLinkage)
+		global.SetUnnamedAddr(true)
+	}
+	if state.needsArrayTypesSidetable {
+		global := c.replaceGlobalIntWithArray("reflect.arrayTypesSidetable", state.arrayTypesSidetable)
+		global.SetLinkage(llvm.InternalLinkage)
+		global.SetUnnamedAddr(true)
+	}
+	if state.needsStructTypesSidetable {
+		global := c.replaceGlobalIntWithArray("reflect.structTypesSidetable", state.structTypesSidetable)
+		global.SetLinkage(llvm.InternalLinkage)
+		global.SetUnnamedAddr(true)
+	}
+	if state.needsStructNamesSidetable {
+		global := c.replaceGlobalIntWithArray("reflect.structNamesSidetable", state.structNamesSidetable)
+		global.SetLinkage(llvm.InternalLinkage)
+		global.SetUnnamedAddr(true)
+	}
 }
 
 // getTypeCodeNum returns the typecode for a given type as expected by the
 // reflect package. Also see getTypeCodeName, which serializes types to a string
 // based on a types.Type value for this function.
-func (c *Compiler) getTypeCodeNum(id string, fallbackIndex *int, namedTypes map[string]int) *big.Int {
+func (state *typeCodeAssignmentState) getTypeCodeNum(typecode llvm.Value) *big.Int {
 	// Note: see src/reflect/type.go for bit allocations.
-	// A type can be named or unnamed. Example of both:
-	//     basic:~foo:uint64
-	//     basic:uint64
-	// Extract the class (basic, slice, pointer, etc.), the name, and the
-	// contents of this type ID string. Allocate bits based on that, as
-	// src/runtime/types.go expects.
-	class := id[:strings.IndexByte(id, ':')]
-	value := id[len(class)+1:]
+	class, value := getClassAndValueFromTypeCode(typecode)
 	name := ""
-	if value[0] == '~' {
-		name = value[1:strings.IndexByte(value, ':')]
-		value = value[len(name)+2:]
+	if class == "named" {
+		name = value
+		typecode = llvm.ConstExtractValue(typecode.Initializer(), []uint32{0})
+		class, value = getClassAndValueFromTypeCode(typecode)
 	}
 	if class == "basic" {
 		// Basic types follow the following bit pattern:
@@ -81,76 +204,286 @@ func (c *Compiler) getTypeCodeNum(id string, fallbackIndex *int, namedTypes map[
 		// upper bits are used to indicate the named type.
 		num, ok := basicTypes[value]
 		if !ok {
-			panic("invalid basic type: " + id)
+			panic("invalid basic type: " + value)
 		}
 		if name != "" {
 			// This type is named, set the upper bits to the name ID.
-			num |= int64(getNamedTypeNum(namedTypes, name)) << 5
+			num |= int64(state.getBasicNamedTypeNum(name)) << 5
 		}
 		return big.NewInt(num << 1)
 	} else {
-		// Complex types use the following bit pattern:
+		// Non-baisc types use the following bit pattern:
 		//    ...nxxx1
-		// where xxx indicates the complex type (any non-basic type). The upper
-		// bits contain whatever the type contains. Types that wrap a single
-		// other type (channel, interface, pointer, slice) just contain the bits
-		// of the wrapped type. Other types (like struct) have a different
-		// method of encoding the contents of the type.
-		var num *big.Int
+		// where xxx indicates the non-basic type. The upper bits contain
+		// whatever the type contains. Types that wrap a single other type
+		// (channel, interface, pointer, slice) just contain the bits of the
+		// wrapped type. Other types (like struct) need more fields and thus
+		// cannot be encoded as a simple prefix.
 		var classNumber int64
-		switch class {
-		case "chan":
-			num = c.getTypeCodeNum(value, fallbackIndex, namedTypes)
-			classNumber = 0
-		case "interface":
-			num = big.NewInt(int64(*fallbackIndex))
-			*fallbackIndex++
-			classNumber = 1
-		case "pointer":
-			num = c.getTypeCodeNum(value, fallbackIndex, namedTypes)
-			classNumber = 2
-		case "slice":
-			num = c.getTypeCodeNum(value, fallbackIndex, namedTypes)
-			classNumber = 3
-		case "array":
-			num = big.NewInt(int64(*fallbackIndex))
-			*fallbackIndex++
-			classNumber = 4
-		case "func":
-			num = big.NewInt(int64(*fallbackIndex))
-			*fallbackIndex++
-			classNumber = 5
-		case "map":
-			num = big.NewInt(int64(*fallbackIndex))
-			*fallbackIndex++
-			classNumber = 6
-		case "struct":
-			num = big.NewInt(int64(*fallbackIndex))
-			*fallbackIndex++
-			classNumber = 7
-		default:
-			panic("unknown type kind: " + id)
-		}
-		if name == "" {
-			num.Lsh(num, 5).Or(num, big.NewInt((classNumber<<1)+1))
+		if n, ok := nonBasicTypes[class]; ok {
+			classNumber = n
 		} else {
-			// TODO: store num in a sidetable
-			num = big.NewInt(int64(getNamedTypeNum(namedTypes, name))<<1 | 1)
-			num.Lsh(num, 4).Or(num, big.NewInt((classNumber<<1)+1))
+			panic("unknown type kind: " + class)
 		}
+		var num *big.Int
+		lowBits := (classNumber << 1) + 1 // the 5 low bits of the typecode
+		if name == "" {
+			num = state.getNonBasicTypeCode(class, typecode)
+		} else {
+			// We must return a named type here. But first check whether it
+			// has already been defined.
+			if index, ok := state.namedNonBasicTypes[name]; ok {
+				num := big.NewInt(int64(index))
+				num.Lsh(num, 5).Or(num, big.NewInt((classNumber<<1)+1+(1<<4)))
+				return num
+			}
+			lowBits |= 1 << 4 // set the 'n' bit (see above)
+			if !state.needsNamedNonBasicTypesSidetable {
+				// Use simple small integers in this case, to make these numbers
+				// smaller.
+				index := len(state.namedNonBasicTypes) + 1
+				state.namedNonBasicTypes[name] = index
+				num = big.NewInt(int64(index))
+			} else {
+				// We need to store full type information.
+				// First allocate a number in the named non-basic type
+				// sidetable.
+				index := len(state.namedNonBasicTypesSidetable)
+				state.namedNonBasicTypesSidetable = append(state.namedNonBasicTypesSidetable, 0)
+				state.namedNonBasicTypes[name] = index
+				// Get the typecode of the underlying type (which could be the
+				// element type in the case of pointers, for example).
+				num = state.getNonBasicTypeCode(class, typecode)
+				if num.BitLen() > state.uintptrLen || !num.IsUint64() {
+					panic("cannot store value in sidetable")
+				}
+				// Now update the side table with the number we just
+				// determined. We need this multi-step approach to avoid stack
+				// overflow due to adding types recursively in the case of
+				// linked lists (a pointer which points to a struct that
+				// contains that same pointer).
+				state.namedNonBasicTypesSidetable[index] = num.Uint64()
+				num = big.NewInt(int64(index))
+			}
+		}
+		// Concatenate the 'num' and 'lowBits' bitstrings.
+		num.Lsh(num, 5).Or(num, big.NewInt(lowBits))
 		return num
 	}
 }
 
-// getNamedTypeNum returns an appropriate (unique) number for the given named
-// type. If the name already has a number that number is returned, else a new
-// number is returned. The number is always non-zero.
-func getNamedTypeNum(namedTypes map[string]int, name string) int {
-	if num, ok := namedTypes[name]; ok {
-		return num
-	} else {
-		num = len(namedTypes) + 1
-		namedTypes[name] = num
+// getNonBasicTypeCode is used by getTypeCodeNum. It returns the upper bits of
+// the type code used there in the type code.
+func (state *typeCodeAssignmentState) getNonBasicTypeCode(class string, typecode llvm.Value) *big.Int {
+	switch class {
+	case "chan", "pointer", "slice":
+		// Prefix-style type kinds. The upper bits contain the element type.
+		sub := llvm.ConstExtractValue(typecode.Initializer(), []uint32{0})
+		return state.getTypeCodeNum(sub)
+	case "array":
+		// An array is basically a pair of (typecode, length) stored in a
+		// sidetable.
+		return big.NewInt(int64(state.getArrayTypeNum(typecode)))
+	case "struct":
+		// More complicated type kind. The upper bits contain the index to the
+		// struct type in the struct types sidetable.
+		return big.NewInt(int64(state.getStructTypeNum(typecode)))
+	default:
+		// Type has not yet been implemented, so fall back by using a unique
+		// number.
+		num := big.NewInt(int64(state.fallbackIndex))
+		state.fallbackIndex++
 		return num
 	}
 }
+
+// getClassAndValueFromTypeCode takes a typecode (a llvm.Value of type
+// runtime.typecodeID), looks at the name, and extracts the typecode class and
+// value from it. For example, for a typecode with the following name:
+//     reflect/types.type:pointer:named:reflect.ValueError
+// It extracts:
+//     class = "pointer"
+//     value = "named:reflect.ValueError"
+func getClassAndValueFromTypeCode(typecode llvm.Value) (class, value string) {
+	typecodeName := typecode.Name()
+	const prefix = "reflect/types.type:"
+	if !strings.HasPrefix(typecodeName, prefix) {
+		panic("unexpected typecode name: " + typecodeName)
+	}
+	id := typecodeName[len(prefix):]
+	class = id[:strings.IndexByte(id, ':')]
+	value = id[len(class)+1:]
+	return
+}
+
+// getBasicNamedTypeNum returns an appropriate (unique) number for the given
+// named type. If the name already has a number that number is returned, else a
+// new number is returned. The number is always non-zero.
+func (state *typeCodeAssignmentState) getBasicNamedTypeNum(name string) int {
+	if num, ok := state.namedBasicTypes[name]; ok {
+		return num
+	}
+	num := len(state.namedBasicTypes) + 1
+	state.namedBasicTypes[name] = num
+	return num
+}
+
+// getArrayTypeNum returns the array type number, which is an index into the
+// reflect.arrayTypesSidetable or a unique number for this type if this table is
+// not used.
+func (state *typeCodeAssignmentState) getArrayTypeNum(typecode llvm.Value) int {
+	name := typecode.Name()
+	if num, ok := state.arrayTypes[name]; ok {
+		// This array type already has an entry in the sidetable. Don't store
+		// it twice.
+		return num
+	}
+
+	if !state.needsArrayTypesSidetable {
+		// We don't need array sidetables, so we can just assign monotonically
+		// increasing numbers to each array type.
+		num := len(state.arrayTypes)
+		state.arrayTypes[name] = num
+		return num
+	}
+
+	elemTypeCode := llvm.ConstExtractValue(typecode.Initializer(), []uint32{0})
+	elemTypeNum := state.getTypeCodeNum(elemTypeCode)
+	if elemTypeNum.BitLen() > state.uintptrLen || !elemTypeNum.IsUint64() {
+		// TODO: make this a regular error
+		panic("array element type has a type code that is too big")
+	}
+
+	// The array side table is a sequence of {element type, array length}.
+	arrayLength := llvm.ConstExtractValue(typecode.Initializer(), []uint32{1}).ZExtValue()
+	buf := makeVarint(elemTypeNum.Uint64())
+	buf = append(buf, makeVarint(arrayLength)...)
+
+	index := len(state.arrayTypesSidetable)
+	state.arrayTypes[name] = index
+	state.arrayTypesSidetable = append(state.arrayTypesSidetable, buf...)
+	return index
+}
+
+// getStructTypeNum returns the struct type number, which is an index into
+// reflect.structTypesSidetable or an unique number for every struct if this
+// sidetable is not needed in the to-be-compiled program.
+func (state *typeCodeAssignmentState) getStructTypeNum(typecode llvm.Value) int {
+	name := typecode.Name()
+	if num, ok := state.structTypes[name]; ok {
+		// This struct already has an assigned type code.
+		return num
+	}
+
+	if !state.needsStructTypesSidetable {
+		// We don't need struct sidetables, so we can just assign monotonically
+		// increasing numbers to each struct type.
+		num := len(state.structTypes)
+		state.structTypes[name] = num
+		return num
+	}
+
+	// Get the fields this struct type contains.
+	// The struct number will be the start index of
+	structTypeGlobal := llvm.ConstExtractValue(typecode.Initializer(), []uint32{0}).Operand(0).Initializer()
+	numFields := structTypeGlobal.Type().ArrayLength()
+
+	// The first data that is stored in the struct sidetable is the number of
+	// fields this struct contains. This is usually just a single byte because
+	// most structs don't contain that many fields, but make it a varint just
+	// to be sure.
+	buf := makeVarint(uint64(numFields))
+
+	// Iterate over every field in the struct.
+	// Every field is stored sequentially in the struct sidetable. Fields can
+	// be retrieved from this list of fields at runtime by iterating over all
+	// of them until the right field has been found.
+	// Perhaps adding some index would speed things up, but it would also make
+	// the sidetable bigger.
+	for i := 0; i < numFields; i++ {
+		// Collect some information about this field.
+		field := llvm.ConstExtractValue(structTypeGlobal, []uint32{uint32(i)})
+
+		nameGlobal := llvm.ConstExtractValue(field, []uint32{1})
+		if nameGlobal == llvm.ConstPointerNull(nameGlobal.Type()) {
+			panic("compiler: no name for this struct field")
+		}
+		fieldNameBytes := getGlobalBytes(nameGlobal.Operand(0))
+		fieldNameNumber := state.getStructNameNumber(fieldNameBytes)
+
+		// See whether this struct field has an associated tag, and if so,
+		// store that tag in the tags sidetable.
+		tagGlobal := llvm.ConstExtractValue(field, []uint32{2})
+		hasTag := false
+		tagNumber := 0
+		if tagGlobal != llvm.ConstPointerNull(tagGlobal.Type()) {
+			hasTag = true
+			tagBytes := getGlobalBytes(tagGlobal.Operand(0))
+			tagNumber = state.getStructNameNumber(tagBytes)
+		}
+
+		// The 'embedded' or 'anonymous' flag for this field.
+		embedded := llvm.ConstExtractValue(field, []uint32{3}).ZExtValue() != 0
+
+		// The first byte in the struct types sidetable is a flags byte with
+		// two bits in it.
+		flagsByte := byte(0)
+		if embedded {
+			flagsByte |= 1
+		}
+		if hasTag {
+			flagsByte |= 2
+		}
+		if ast.IsExported(string(fieldNameBytes)) {
+			flagsByte |= 4
+		}
+		buf = append(buf, flagsByte)
+
+		// Get the type number and add it to the buffer.
+		// All fields have a type, so include it directly here.
+		typeNum := state.getTypeCodeNum(llvm.ConstExtractValue(field, []uint32{0}))
+		if typeNum.BitLen() > state.uintptrLen || !typeNum.IsUint64() {
+			// TODO: make this a regular error
+			panic("struct field has a type code that is too big")
+		}
+		buf = append(buf, makeVarint(typeNum.Uint64())...)
+
+		// Add the name.
+		buf = append(buf, makeVarint(uint64(fieldNameNumber))...)
+
+		// Add the tag, if there is one.
+		if hasTag {
+			buf = append(buf, makeVarint(uint64(tagNumber))...)
+		}
+	}
+
+	num := len(state.structTypesSidetable)
+	state.structTypes[name] = num
+	state.structTypesSidetable = append(state.structTypesSidetable, buf...)
+	return num
+}
+
+// getStructNameNumber stores this string (name or tag) onto the struct names
+// sidetable. The format is a varint of the length of the struct, followed by
+// the raw bytes of the name. Multiple identical strings are stored under the
+// same name for space efficiency.
+func (state *typeCodeAssignmentState) getStructNameNumber(nameBytes []byte) int {
+	name := string(nameBytes)
+	if n, ok := state.structNames[name]; ok {
+		// This name was used before, re-use it now (for space efficiency).
+		return n
+	}
+	// This name is not yet in the names sidetable. Add it now.
+	n := len(state.structNamesSidetable)
+	state.structNames[name] = n
+	state.structNamesSidetable = append(state.structNamesSidetable, makeVarint(uint64(len(nameBytes)))...)
+	state.structNamesSidetable = append(state.structNamesSidetable, nameBytes...)
+	return n
+}
+
+// makeVarint is a small helper function that returns the bytes of the number in
+// varint encoding.
+func makeVarint(n uint64) []byte {
+	buf := make([]byte, binary.MaxVarintLen64)
+	return buf[:binary.PutUvarint(buf, n)]
+}

compiler/symbol.go

@@ -0,0 +1,107 @@
+package compiler
+
+// This file manages symbols, that is, functions and globals. It reads their
+// pragmas, determines the link name, etc.
+
+import (
+	"go/ast"
+	"go/token"
+	"go/types"
+	"strings"
+
+	"github.com/tinygo-org/tinygo/loader"
+	"golang.org/x/tools/go/ssa"
+	"tinygo.org/x/go-llvm"
+)
+
+// globalInfo contains some information about a specific global. By default,
+// linkName is equal to .RelString(nil) on a global and extern is false, but for
+// some symbols this is different (due to //go:extern for example).
+type globalInfo struct {
+	linkName string // go:extern
+	extern   bool   // go:extern
+}
+
+// loadASTComments loads comments on globals from the AST, for use later in the
+// program. In particular, they are required for //go:extern pragmas on globals.
+func (c *Compiler) loadASTComments(lprogram *loader.Program) {
+	c.astComments = map[string]*ast.CommentGroup{}
+	for _, pkgInfo := range lprogram.Sorted() {
+		for _, file := range pkgInfo.Files {
+			for _, decl := range file.Decls {
+				switch decl := decl.(type) {
+				case *ast.GenDecl:
+					switch decl.Tok {
+					case token.VAR:
+						if len(decl.Specs) != 1 {
+							continue
+						}
+						for _, spec := range decl.Specs {
+							switch spec := spec.(type) {
+							case *ast.ValueSpec: // decl.Tok == token.VAR
+								for _, name := range spec.Names {
+									id := pkgInfo.Pkg.Path() + "." + name.Name
+									c.astComments[id] = decl.Doc
+								}
+							}
+						}
+					}
+				}
+			}
+		}
+	}
+}
+
+// getGlobal returns a LLVM IR global value for a Go SSA global. It is added to
+// the LLVM IR if it has not been added already.
+func (c *Compiler) getGlobal(g *ssa.Global) llvm.Value {
+	info := c.getGlobalInfo(g)
+	llvmGlobal := c.mod.NamedGlobal(info.linkName)
+	if llvmGlobal.IsNil() {
+		llvmType := c.getLLVMType(g.Type().(*types.Pointer).Elem())
+		llvmGlobal = llvm.AddGlobal(c.mod, llvmType, info.linkName)
+		if !info.extern {
+			llvmGlobal.SetInitializer(llvm.ConstNull(llvmType))
+			llvmGlobal.SetLinkage(llvm.InternalLinkage)
+		}
+	}
+	return llvmGlobal
+}
+
+// getGlobalInfo returns some information about a specific global.
+func (c *Compiler) getGlobalInfo(g *ssa.Global) globalInfo {
+	info := globalInfo{}
+	if strings.HasPrefix(g.Name(), "C.") {
+		// Created by CGo: such a name cannot be created by regular C code.
+		info.linkName = g.Name()[2:]
+		info.extern = true
+	} else {
+		// Pick the default linkName.
+		info.linkName = g.RelString(nil)
+		// Check for //go: pragmas, which may change the link name (among
+		// others).
+		doc := c.astComments[info.linkName]
+		if doc != nil {
+			info.parsePragmas(doc)
+		}
+	}
+	return info
+}
+
+// Parse //go: pragma comments from the source. In particular, it parses the
+// //go:extern pragma on globals.
+func (info *globalInfo) parsePragmas(doc *ast.CommentGroup) {
+	for _, comment := range doc.List {
+		if !strings.HasPrefix(comment.Text, "//go:") {
+			continue
+		}
+		parts := strings.Fields(comment.Text)
+		switch parts[0] {
+		case "//go:extern":
+			info.extern = true
+			if len(parts) == 2 {
+				info.linkName = parts[1]
+			}
+		}
+	}
+}

compiler/syscall.go

@@ -4,7 +4,6 @@ package compiler
 // compiler builtins.
 
 import (
-	"go/constant"
 	"strconv"
 
 	"golang.org/x/tools/go/ssa"
@@ -14,7 +13,7 @@ import (
 // emitSyscall emits an inline system call instruction, depending on the target
 // OS/arch.
 func (c *Compiler) emitSyscall(frame *Frame, call *ssa.CallCommon) (llvm.Value, error) {
-	num, _ := constant.Uint64Val(call.Args[0].(*ssa.Const).Value)
+	num := c.getValue(frame, call.Args[0])
 	var syscallResult llvm.Value
 	switch {
 	case c.GOARCH == "amd64":
@@ -29,12 +28,12 @@ func (c *Compiler) emitSyscall(frame *Frame, call *ssa.CallCommon) (llvm.Value,
 			// > All system classes enter the kernel via the syscall instruction.
 			//
 			// Source: https://opensource.apple.com/source/xnu/xnu-792.13.8/osfmk/mach/i386/syscall_sw.h
-			num += 0x2000000
+			num = c.builder.CreateOr(num, llvm.ConstInt(c.uintptrType, 0x2000000, false), "")
 		}
 		// Sources:
 		//   https://stackoverflow.com/a/2538212
 		//   https://en.wikibooks.org/wiki/X86_Assembly/Interfacing_with_Linux#syscall
-		args := []llvm.Value{llvm.ConstInt(c.uintptrType, num, false)}
+		args := []llvm.Value{num}
 		argTypes := []llvm.Type{c.uintptrType}
 		// Constraints will look something like:
 		//   "={rax},0,{rdi},{rsi},{rdx},{r10},{r8},{r9},~{rcx},~{r11}"
@@ -59,6 +58,32 @@ func (c *Compiler) emitSyscall(frame *Frame, call *ssa.CallCommon) (llvm.Value,
 		fnType := llvm.FunctionType(c.uintptrType, argTypes, false)
 		target := llvm.InlineAsm(fnType, "syscall", constraints, true, false, llvm.InlineAsmDialectIntel)
 		syscallResult = c.builder.CreateCall(target, args, "")
+	case c.GOARCH == "386" && c.GOOS == "linux":
+		// Sources:
+		//   syscall(2) man page
+		//   https://stackoverflow.com/a/2538212
+		//   https://en.wikibooks.org/wiki/X86_Assembly/Interfacing_with_Linux#int_0x80
+		args := []llvm.Value{num}
+		argTypes := []llvm.Type{c.uintptrType}
+		// Constraints will look something like:
+		//   "={eax},0,{ebx},{ecx},{edx},{esi},{edi},{ebp}"
+		constraints := "={eax},0"
+		for i, arg := range call.Args[1:] {
+			constraints += "," + [...]string{
+				"{ebx}",
+				"{ecx}",
+				"{edx}",
+				"{esi}",
+				"{edi}",
+				"{ebp}",
+			}[i]
+			llvmValue := c.getValue(frame, arg)
+			args = append(args, llvmValue)
+			argTypes = append(argTypes, llvmValue.Type())
+		}
+		fnType := llvm.FunctionType(c.uintptrType, argTypes, false)
+		target := llvm.InlineAsm(fnType, "int 0x80", constraints, true, false, llvm.InlineAsmDialectIntel)
+		syscallResult = c.builder.CreateCall(target, args, "")
 	case c.GOARCH == "arm" && c.GOOS == "linux":
 		// Implement the EABI system call convention for Linux.
 		// Source: syscall(2) man page.
@@ -81,7 +106,7 @@ func (c *Compiler) emitSyscall(frame *Frame, call *ssa.CallCommon) (llvm.Value,
 			args = append(args, llvmValue)
 			argTypes = append(argTypes, llvmValue.Type())
 		}
-		args = append(args, llvm.ConstInt(c.uintptrType, num, false))
+		args = append(args, num)
 		argTypes = append(argTypes, c.uintptrType)
 		constraints += ",{r7}" // syscall number
 		for i := len(call.Args) - 1; i < 4; i++ {
@@ -111,7 +136,7 @@ func (c *Compiler) emitSyscall(frame *Frame, call *ssa.CallCommon) (llvm.Value,
 			args = append(args, llvmValue)
 			argTypes = append(argTypes, llvmValue.Type())
 		}
-		args = append(args, llvm.ConstInt(c.uintptrType, num, false))
+		args = append(args, num)
 		argTypes = append(argTypes, c.uintptrType)
 		constraints += ",{x8}" // syscall number
 		for i := len(call.Args) - 1; i < 8; i++ {
@@ -140,7 +165,7 @@ func (c *Compiler) emitSyscall(frame *Frame, call *ssa.CallCommon) (llvm.Value,
 		inrange2 := c.builder.CreateICmp(llvm.IntSGT, syscallResult, llvm.ConstInt(c.uintptrType, 0xfffffffffffff000, true), "") // -4096
 		hasError := c.builder.CreateAnd(inrange1, inrange2, "")
 		errResult := c.builder.CreateSelect(hasError, c.builder.CreateSub(zero, syscallResult, ""), zero, "syscallError")
-		retval := llvm.Undef(llvm.StructType([]llvm.Type{c.uintptrType, c.uintptrType, c.uintptrType}, false))
+		retval := llvm.Undef(c.ctx.StructType([]llvm.Type{c.uintptrType, c.uintptrType, c.uintptrType}, false))
 		retval = c.builder.CreateInsertValue(retval, syscallResult, 0, "")
 		retval = c.builder.CreateInsertValue(retval, zero, 1, "")
 		retval = c.builder.CreateInsertValue(retval, errResult, 2, "")
@@ -156,7 +181,7 @@ func (c *Compiler) emitSyscall(frame *Frame, call *ssa.CallCommon) (llvm.Value,
 		zero := llvm.ConstInt(c.uintptrType, 0, false)
 		hasError := c.builder.CreateICmp(llvm.IntNE, syscallResult, llvm.ConstInt(c.uintptrType, 0, false), "")
 		errResult := c.builder.CreateSelect(hasError, syscallResult, zero, "syscallError")
-		retval := llvm.Undef(llvm.StructType([]llvm.Type{c.uintptrType, c.uintptrType, c.uintptrType}, false))
+		retval := llvm.Undef(c.ctx.StructType([]llvm.Type{c.uintptrType, c.uintptrType, c.uintptrType}, false))
 		retval = c.builder.CreateInsertValue(retval, syscallResult, 0, "")
 		retval = c.builder.CreateInsertValue(retval, zero, 1, "")
 		retval = c.builder.CreateInsertValue(retval, errResult, 2, "")

compiler/wordpack.go

@@ -39,6 +39,9 @@ func (c *Compiler) emitPointerPack(values []llvm.Value) llvm.Value {
 		// Packed data is bigger than a pointer, so allocate it on the heap.
 		sizeValue := llvm.ConstInt(c.uintptrType, size, false)
 		packedHeapAlloc = c.createRuntimeCall("alloc", []llvm.Value{sizeValue}, "")
+		if c.needsStackObjects() {
+			c.trackPointer(packedHeapAlloc)
+		}
 		packedAlloc = c.builder.CreateBitCast(packedHeapAlloc, llvm.PointerType(packedType, 0), "")
 	}
 	// Store all values in the alloca or heap pointer.
@@ -98,7 +101,7 @@ func (c *Compiler) emitPointerUnpack(ptr llvm.Value, valueTypes []llvm.Type) []l
 	for i, valueType := range valueTypes {
 		if c.targetData.TypeAllocSize(valueType) == 0 {
 			// This value has length zero, so there's nothing to load.
-			values[i] = c.getZeroValue(valueType)
+			values[i] = llvm.ConstNull(valueType)
 			continue
 		}
 		indices := []llvm.Value{

go.mod

@@ -6,5 +6,5 @@ require (
 	github.com/blakesmith/ar v0.0.0-20150311145944-8bd4349a67f2
 	github.com/marcinbor85/gohex v0.0.0-20180128172054-7a43cd876e46
 	golang.org/x/tools v0.0.0-20190227180812-8dcc6e70cdef
-	tinygo.org/x/go-llvm v0.0.0-20190224120431-7707ae5d1261
+	tinygo.org/x/go-llvm v0.0.0-20190818154551-95bc4ffe1add
 )

go.sum

@@ -12,3 +12,5 @@ golang.org/x/tools v0.0.0-20190227180812-8dcc6e70cdef/go.mod h1:9Yl7xja0Znq3iFh3
 google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
 tinygo.org/x/go-llvm v0.0.0-20190224120431-7707ae5d1261 h1:rJS2Hga39YAnm7DE4qrPm6Dr/67EOojL0XPzvbEeBiw=
 tinygo.org/x/go-llvm v0.0.0-20190224120431-7707ae5d1261/go.mod h1:fv1F0BSNpxMfCL0zF3M4OPFbgYHnhtB6ST0HvUtu/LE=
+tinygo.org/x/go-llvm v0.0.0-20190818154551-95bc4ffe1add h1:dFjMH1sLhYADg8UQm7DB56B7e+TfvAmWmEZLhyv3r/w=
+tinygo.org/x/go-llvm v0.0.0-20190818154551-95bc4ffe1add/go.mod h1:fv1F0BSNpxMfCL0zF3M4OPFbgYHnhtB6ST0HvUtu/LE=

interp/frame.go

@@ -86,7 +86,7 @@ func (fr *frame) evalBasicBlock(bb, incoming llvm.BasicBlock, indent string) (re
 		case !inst.IsAAllocaInst().IsNil():
 			allocType := inst.Type().ElementType()
 			alloca := llvm.AddGlobal(fr.Mod, allocType, fr.pkgName+"$alloca")
-			alloca.SetInitializer(getZeroValue(allocType))
+			alloca.SetInitializer(llvm.ConstNull(allocType))
 			alloca.SetLinkage(llvm.InternalLinkage)
 			fr.locals[inst] = &LocalValue{
 				Underlying: alloca,
@@ -176,6 +176,20 @@ func (fr *frame) evalBasicBlock(bb, incoming llvm.BasicBlock, indent string) (re
 					continue // special case: bitcast of alloc
 				}
 			}
+			if _, ok := fr.getLocal(operand).(*MapValue); ok {
+				// Special case for runtime.trackPointer calls.
+				// Note: this might not be entirely sound in some rare cases
+				// where the map is stored in a dirty global.
+				uses := getUses(inst)
+				if len(uses) == 1 {
+					use := uses[0]
+					if !use.IsACallInst().IsNil() && !use.CalledValue().IsAFunction().IsNil() && use.CalledValue().Name() == "runtime.trackPointer" {
+						continue
+					}
+				}
+				// It is not possible in Go to bitcast a map value to a pointer.
+				panic("unimplemented: bitcast of map")
+			}
 			value := fr.getLocal(operand).(*LocalValue)
 			fr.locals[inst] = &LocalValue{fr.Eval, fr.builder.CreateBitCast(value.Value(), inst.Type(), "")}
 
@@ -239,7 +253,7 @@ func (fr *frame) evalBasicBlock(bb, incoming llvm.BasicBlock, indent string) (re
 					allocType = llvm.ArrayType(allocType, elementCount)
 				}
 				alloc := llvm.AddGlobal(fr.Mod, allocType, fr.pkgName+"$alloc")
-				alloc.SetInitializer(getZeroValue(allocType))
+				alloc.SetInitializer(llvm.ConstNull(allocType))
 				alloc.SetLinkage(llvm.InternalLinkage)
 				result := &LocalValue{
 					Underlying: alloc,
@@ -298,7 +312,7 @@ func (fr *frame) evalBasicBlock(bb, incoming llvm.BasicBlock, indent string) (re
 				stringType := fr.Mod.GetTypeByName("runtime._string")
 				retPtr := llvm.ConstGEP(global, getLLVMIndices(fr.Mod.Context().Int32Type(), []uint32{0, 0}))
 				retLen := llvm.ConstInt(stringType.StructElementTypes()[1], uint64(len(result)), false)
-				ret := getZeroValue(stringType)
+				ret := llvm.ConstNull(stringType)
 				ret = llvm.ConstInsertValue(ret, retPtr, []uint32{0})
 				ret = llvm.ConstInsertValue(ret, retLen, []uint32{1})
 				fr.locals[inst] = &LocalValue{fr.Eval, ret}
@@ -321,7 +335,7 @@ func (fr *frame) evalBasicBlock(bb, incoming llvm.BasicBlock, indent string) (re
 				sliceType := inst.Type()
 				retPtr := llvm.ConstGEP(global, getLLVMIndices(fr.Mod.Context().Int32Type(), []uint32{0, 0}))
 				retLen := llvm.ConstInt(sliceType.StructElementTypes()[1], uint64(len(result)), false)
-				ret := getZeroValue(sliceType)
+				ret := llvm.ConstNull(sliceType)
 				ret = llvm.ConstInsertValue(ret, retPtr, []uint32{0}) // ptr
 				ret = llvm.ConstInsertValue(ret, retLen, []uint32{1}) // len
 				ret = llvm.ConstInsertValue(ret, retLen, []uint32{2}) // cap
@@ -368,6 +382,8 @@ func (fr *frame) evalBasicBlock(bb, incoming llvm.BasicBlock, indent string) (re
 				fr.locals[inst] = &LocalValue{fr.Eval, llvm.ConstInt(fr.Mod.Context().Int64Type(), 0, false)}
 			case callee.Name() == "llvm.dbg.value":
 				// do nothing
+			case callee.Name() == "runtime.trackPointer":
+				// do nothing
 			case strings.HasPrefix(callee.Name(), "runtime.print") || callee.Name() == "runtime._panic":
 				// This are all print instructions, which necessarily have side
 				// effects but no results.

interp/scan.go

@@ -35,6 +35,8 @@ func (e *Eval) hasSideEffects(fn llvm.Value) *sideEffectResult {
 		return &sideEffectResult{severity: sideEffectLimited}
 	case "runtime.interfaceImplements":
 		return &sideEffectResult{severity: sideEffectNone}
+	case "runtime.trackPointer":
+		return &sideEffectResult{severity: sideEffectNone}
 	case "llvm.dbg.value":
 		return &sideEffectResult{severity: sideEffectNone}
 	}

interp/utils.go

@@ -16,50 +16,6 @@ func getUses(value llvm.Value) []llvm.Value {
 	return uses
 }
 
-// Return a zero LLVM value for any LLVM type. Setting this value as an
-// initializer has the same effect as setting 'zeroinitializer' on a value.
-// Sadly, I haven't found a way to do it directly with the Go API but this works
-// just fine.
-func getZeroValue(typ llvm.Type) llvm.Value {
-	switch typ.TypeKind() {
-	case llvm.ArrayTypeKind:
-		subTyp := typ.ElementType()
-		subVal := getZeroValue(subTyp)
-		vals := make([]llvm.Value, typ.ArrayLength())
-		for i := range vals {
-			vals[i] = subVal
-		}
-		return llvm.ConstArray(subTyp, vals)
-	case llvm.FloatTypeKind, llvm.DoubleTypeKind:
-		return llvm.ConstFloat(typ, 0.0)
-	case llvm.IntegerTypeKind:
-		return llvm.ConstInt(typ, 0, false)
-	case llvm.PointerTypeKind:
-		return llvm.ConstPointerNull(typ)
-	case llvm.StructTypeKind:
-		types := typ.StructElementTypes()
-		vals := make([]llvm.Value, len(types))
-		for i, subTyp := range types {
-			val := getZeroValue(subTyp)
-			vals[i] = val
-		}
-		if typ.StructName() != "" {
-			return llvm.ConstNamedStruct(typ, vals)
-		} else {
-			return typ.Context().ConstStruct(vals, false)
-		}
-	case llvm.VectorTypeKind:
-		zero := getZeroValue(typ.ElementType())
-		vals := make([]llvm.Value, typ.VectorSize())
-		for i := range vals {
-			vals[i] = zero
-		}
-		return llvm.ConstVector(vals, false)
-	default:
-		panic("interp: unknown LLVM type: " + typ.String())
-	}
-}
-
 // getStringBytes loads the byte slice of a Go string represented as a
 // {ptr, len} pair.
 func getStringBytes(strPtr Value, strLen llvm.Value) []byte {

interp/values.go

@@ -162,7 +162,7 @@ func (v *MapValue) newBucket() llvm.Value {
 		llvm.ArrayType(v.KeyType, 8),      // key type
 		llvm.ArrayType(v.ValueType, 8),    // value type
 	}, false)
-	bucketValue := getZeroValue(bucketType)
+	bucketValue := llvm.ConstNull(bucketType)
 	bucket := llvm.AddGlobal(v.Eval.Mod, bucketType, v.PkgName+"$mapbucket")
 	bucket.SetInitializer(bucketValue)
 	bucket.SetLinkage(llvm.InternalLinkage)
@@ -311,7 +311,7 @@ func (v *MapValue) PutString(keyBuf, keyLen, valPtr *LocalValue) {
 
 	keyType := v.Eval.Mod.GetTypeByName("runtime._string")
 	v.KeyType = keyType
-	key := getZeroValue(keyType)
+	key := llvm.ConstNull(keyType)
 	key = llvm.ConstInsertValue(key, keyBuf.Value(), []uint32{0})
 	key = llvm.ConstInsertValue(key, keyLen.Value(), []uint32{1})
 

ir/ir.go

@@ -2,7 +2,6 @@ package ir
 
 import (
 	"go/ast"
-	"go/token"
 	"go/types"
 	"sort"
 	"strings"
@@ -23,16 +22,13 @@ type Program struct {
 	mainPkg       *ssa.Package
 	Functions     []*Function
 	functionMap   map[*ssa.Function]*Function
-	Globals       []*Global
-	globalMap     map[*ssa.Global]*Global
-	comments      map[string]*ast.CommentGroup
-	NamedTypes    []*NamedType
 }
 
 // Function or method.
 type Function struct {
 	*ssa.Function
 	LLVMFn    llvm.Value
+	module    string     // go:wasm-module
 	linkName  string     // go:linkname, go:export, go:interrupt
 	exported  bool       // go:export
 	nobounds  bool       // go:nobounds
@@ -41,28 +37,6 @@ type Function struct {
 	inline    InlineType // go:inline
 }
 
-// Global variable, possibly constant.
-type Global struct {
-	*ssa.Global
-	program    *Program
-	LLVMGlobal llvm.Value
-	linkName   string // go:extern
-	extern     bool   // go:extern
-}
-
-// Type with a name and possibly methods.
-type NamedType struct {
-	*ssa.Type
-	LLVMType llvm.Type
-}
-
-// Type that is at some point put in an interface.
-type TypeWithMethods struct {
-	t       types.Type
-	Num     int
-	Methods map[string]*types.Selection
-}
-
 // Interface type that is at some point used in a type assert (to check whether
 // it implements another interface).
 type Interface struct {
@@ -83,39 +57,14 @@ const (
 	// //go:inline). The compiler will be more likely to inline this function,
 	// but it is not a guarantee.
 	InlineHint
+
+	// Don't inline, just like the GCC noinline attribute. Signalled using
+	// //go:noinline.
+	InlineNone
 )
 
 // Create and initialize a new *Program from a *ssa.Program.
 func NewProgram(lprogram *loader.Program, mainPath string) *Program {
-	comments := map[string]*ast.CommentGroup{}
-	for _, pkgInfo := range lprogram.Sorted() {
-		for _, file := range pkgInfo.Files {
-			for _, decl := range file.Decls {
-				switch decl := decl.(type) {
-				case *ast.GenDecl:
-					switch decl.Tok {
-					case token.TYPE, token.VAR:
-						if len(decl.Specs) != 1 {
-							continue
-						}
-						for _, spec := range decl.Specs {
-							switch spec := spec.(type) {
-							case *ast.TypeSpec: // decl.Tok == token.TYPE
-								id := pkgInfo.Pkg.Path() + "." + spec.Name.Name
-								comments[id] = decl.Doc
-							case *ast.ValueSpec: // decl.Tok == token.VAR
-								for _, name := range spec.Names {
-									id := pkgInfo.Pkg.Path() + "." + name.Name
-									comments[id] = decl.Doc
-								}
-							}
-						}
-					}
-				}
-			}
-		}
-	}
-
 	program := lprogram.LoadSSA()
 	program.Build()
 
@@ -187,8 +136,6 @@ func NewProgram(lprogram *loader.Program, mainPath string) *Program {
 		LoaderProgram: lprogram,
 		mainPkg:       mainPkg,
 		functionMap:   make(map[*ssa.Function]*Function),
-		globalMap:     make(map[*ssa.Global]*Global),
-		comments:      comments,
 	}
 
 	for _, pkg := range packageList {
@@ -213,8 +160,6 @@ func (p *Program) AddPackage(pkg *ssa.Package) {
 		case *ssa.Function:
 			p.addFunction(member)
 		case *ssa.Type:
-			t := &NamedType{Type: member}
-			p.NamedTypes = append(p.NamedTypes, t)
 			methods := getAllMethods(pkg.Prog, member.Type())
 			if !types.IsInterface(member.Type()) {
 				// named type
@@ -223,13 +168,7 @@ func (p *Program) AddPackage(pkg *ssa.Package) {
 				}
 			}
 		case *ssa.Global:
-			g := &Global{program: p, Global: member}
-			doc := p.comments[g.RelString(nil)]
-			if doc != nil {
-				g.parsePragmas(doc)
-			}
-			p.Globals = append(p.Globals, g)
-			p.globalMap[member] = g
+			// Ignore. Globals are not handled here.
 		case *ssa.NamedConst:
 			// Ignore: these are already resolved.
 		default:
@@ -263,10 +202,6 @@ func (p *Program) GetFunction(ssaFn *ssa.Function) *Function {
 	return p.functionMap[ssaFn]
 }
 
-func (p *Program) GetGlobal(ssaGlobal *ssa.Global) *Global {
-	return p.globalMap[ssaGlobal]
-}
-
 func (p *Program) MainPkg() *ssa.Package {
 	return p.mainPkg
 }
@@ -295,8 +230,16 @@ func (f *Function) parsePragmas() {
 				}
 				f.linkName = parts[1]
 				f.exported = true
+			case "//go:wasm-module":
+				// Alternative comment for setting the import module.
+				if len(parts) != 2 {
+					continue
+				}
+				f.module = parts[1]
 			case "//go:inline":
 				f.inline = InlineHint
+			case "//go:noinline":
+				f.inline = InlineNone
 			case "//go:interrupt":
 				if len(parts) != 2 {
 					continue
@@ -355,6 +298,11 @@ func (f *Function) Inline() InlineType {
 	return f.inline
 }
 
+// Return the module name if not the default.
+func (f *Function) Module() string {
+	return f.module
+}
+
 // Return the link name for this function.
 func (f *Function) LinkName() string {
 	if f.linkName != "" {
@@ -389,72 +337,6 @@ func (f *Function) CName() string {
 	return ""
 }
 
-// Parse //go: pragma comments from the source.
-func (g *Global) parsePragmas(doc *ast.CommentGroup) {
-	for _, comment := range doc.List {
-		if !strings.HasPrefix(comment.Text, "//go:") {
-			continue
-		}
-		parts := strings.Fields(comment.Text)
-		switch parts[0] {
-		case "//go:extern":
-			g.extern = true
-			if len(parts) == 2 {
-				g.linkName = parts[1]
-			}
-		}
-	}
-}
-
-// Return the link name for this global.
-func (g *Global) LinkName() string {
-	if g.linkName != "" {
-		return g.linkName
-	}
-	if name := g.CName(); name != "" {
-		return name
-	}
-	return g.RelString(nil)
-}
-
-func (g *Global) IsExtern() bool {
-	return g.extern || g.CName() != ""
-}
-
-// Return the name of the C global if this is a CGo wrapper. Otherwise, return a
-// zero-length string.
-func (g *Global) CName() string {
-	name := g.Name()
-	if strings.HasPrefix(name, "C.") {
-		// created by ../loader/cgo.go
-		return name[2:]
-	}
-	return ""
-}
-
-// Return true if this named type is annotated with the //go:volatile pragma,
-// for volatile loads and stores.
-func (p *Program) IsVolatile(t types.Type) bool {
-	if t, ok := t.(*types.Named); !ok {
-		return false
-	} else {
-		if t.Obj().Pkg() == nil {
-			return false
-		}
-		id := t.Obj().Pkg().Path() + "." + t.Obj().Name()
-		doc := p.comments[id]
-		if doc == nil {
-			return false
-		}
-		for _, line := range doc.List {
-			if strings.TrimSpace(line.Text) == "//go:volatile" {
-				return true
-			}
-		}
-		return false
-	}
-}
-
 // Get all methods of a type.
 func getAllMethods(prog *ssa.Program, typ types.Type) []*types.Selection {
 	ms := prog.MethodSets.MethodSet(typ)

linker-builtin.go

@@ -63,6 +63,7 @@ func Link(linker string, flags ...string) error {
 		cmd := exec.Command(linker, flags...)
 		cmd.Stdout = os.Stdout
 		cmd.Stderr = os.Stderr
+		cmd.Dir = sourceDir()
 		return cmd.Run()
 	}
 }

linker-external.go

@@ -20,5 +20,6 @@ func Link(linker string, flags ...string) error {
 	cmd := exec.Command(linker, flags...)
 	cmd.Stdout = os.Stdout
 	cmd.Stderr = os.Stderr
+	cmd.Dir = sourceDir()
 	return cmd.Run()
 }

loader/loader.go

@@ -1,6 +1,7 @@
 package loader
 
 import (
+	"bytes"
 	"errors"
 	"go/ast"
 	"go/build"
@@ -10,22 +11,26 @@ import (
 	"os"
 	"path/filepath"
 	"sort"
+	"strings"
+	"text/template"
 
 	"github.com/tinygo-org/tinygo/cgo"
 )
 
 // Program holds all packages and some metadata about the program as a whole.
 type Program struct {
-	Build         *build.Context
-	OverlayBuild  *build.Context
-	ShouldOverlay func(path string) bool
-	Packages      map[string]*Package
-	sorted        []*Package
-	fset          *token.FileSet
-	TypeChecker   types.Config
-	Dir           string // current working directory (for error reporting)
-	TINYGOROOT    string // root of the TinyGo installation or root of the source code
-	CFlags        []string
+	mainPkg      string
+	Build        *build.Context
+	OverlayBuild *build.Context
+	OverlayPath  func(path string) string
+	Packages     map[string]*Package
+	sorted       []*Package
+	fset         *token.FileSet
+	TypeChecker  types.Config
+	Dir          string // current working directory (for error reporting)
+	TINYGOROOT   string // root of the TinyGo installation or root of the source code
+	CFlags       []string
+	ClangHeaders string
 }
 
 // Package holds a loaded package, its imports, and its parsed files.
@@ -48,8 +53,9 @@ func (p *Program) Import(path, srcDir string) (*Package, error) {
 
 	// Load this package.
 	ctx := p.Build
-	if p.ShouldOverlay(path) {
+	if newPath := p.OverlayPath(path); newPath != "" {
 		ctx = p.OverlayBuild
+		path = newPath
 	}
 	buildPkg, err := ctx.Import(path, srcDir, build.ImportComment)
 	if err != nil {
@@ -62,6 +68,11 @@ func (p *Program) Import(path, srcDir string) (*Package, error) {
 	p.sorted = nil // invalidate the sorted order of packages
 	pkg := p.newPackage(buildPkg)
 	p.Packages[buildPkg.ImportPath] = pkg
+
+	if p.mainPkg == "" {
+		p.mainPkg = buildPkg.ImportPath
+	}
+
 	return pkg, nil
 }
 
@@ -91,6 +102,11 @@ func (p *Program) ImportFile(path string) (*Package, error) {
 	p.sorted = nil // invalidate the sorted order of packages
 	pkg := p.newPackage(buildPkg)
 	p.Packages[buildPkg.ImportPath] = pkg
+
+	if p.mainPkg == "" {
+		p.mainPkg = buildPkg.ImportPath
+	}
+
 	return pkg, nil
 }
 
@@ -169,10 +185,12 @@ func (p *Program) sort() {
 // The returned error may be an Errors error, which contains a list of errors.
 //
 // Idempotent.
-func (p *Program) Parse() error {
+func (p *Program) Parse(compileTestBinary bool) error {
+	includeTests := compileTestBinary
+
 	// Load all imports
 	for _, pkg := range p.Sorted() {
-		err := pkg.importRecursively()
+		err := pkg.importRecursively(includeTests)
 		if err != nil {
 			if err, ok := err.(*ImportCycleError); ok {
 				if pkg.ImportPath != err.Packages[0] {
@@ -185,7 +203,14 @@ func (p *Program) Parse() error {
 
 	// Parse all packages.
 	for _, pkg := range p.Sorted() {
-		err := pkg.Parse()
+		err := pkg.Parse(includeTests)
+		if err != nil {
+			return err
+		}
+	}
+
+	if compileTestBinary {
+		err := p.SwapTestMain()
 		if err != nil {
 			return err
 		}
@@ -202,6 +227,83 @@ func (p *Program) Parse() error {
 	return nil
 }
 
+func (p *Program) SwapTestMain() error {
+	var tests []string
+
+	isTestFunc := func(f *ast.FuncDecl) bool {
+		// TODO: improve signature check
+		if strings.HasPrefix(f.Name.Name, "Test") && f.Name.Name != "TestMain" {
+			return true
+		}
+		return false
+	}
+	mainPkg := p.Packages[p.mainPkg]
+	for _, f := range mainPkg.Files {
+		for i, d := range f.Decls {
+			switch v := d.(type) {
+			case *ast.FuncDecl:
+				if isTestFunc(v) {
+					tests = append(tests, v.Name.Name)
+				}
+				if v.Name.Name == "main" {
+					// Remove main
+					if len(f.Decls) == 1 {
+						f.Decls = make([]ast.Decl, 0)
+					} else {
+						f.Decls[i] = f.Decls[len(f.Decls)-1]
+						f.Decls = f.Decls[:len(f.Decls)-1]
+					}
+				}
+			}
+		}
+	}
+
+	// TODO: Check if they defined a TestMain and call it instead of testing.TestMain
+	const mainBody = `package main
+
+import (
+	"testing"
+)
+
+func main () {
+	m := &testing.M{
+		Tests: []testing.TestToCall{
+{{range .TestFunctions}}
+			{Name: "{{.}}", Func: {{.}}},
+{{end}}
+		},
+	}
+
+	testing.TestMain(m)
+}
+`
+	tmpl := template.Must(template.New("testmain").Parse(mainBody))
+	b := bytes.Buffer{}
+	tmplData := struct {
+		TestFunctions []string
+	}{
+		TestFunctions: tests,
+	}
+
+	err := tmpl.Execute(&b, tmplData)
+	if err != nil {
+		return err
+	}
+	path := filepath.Join(p.mainPkg, "$testmain.go")
+
+	if p.fset == nil {
+		p.fset = token.NewFileSet()
+	}
+
+	newMain, err := parser.ParseFile(p.fset, path, b.Bytes(), parser.AllErrors)
+	if err != nil {
+		return err
+	}
+	mainPkg.Files = append(mainPkg.Files, newMain)
+
+	return nil
+}
+
 // parseFile is a wrapper around parser.ParseFile.
 func (p *Program) parseFile(path string, mode parser.Mode) (*ast.File, error) {
 	if p.fset == nil {
@@ -226,7 +328,7 @@ func (p *Program) parseFile(path string, mode parser.Mode) (*ast.File, error) {
 // Parse parses and typechecks this package.
 //
 // Idempotent.
-func (p *Package) Parse() error {
+func (p *Package) Parse(includeTests bool) error {
 	if len(p.Files) != 0 {
 		return nil
 	}
@@ -240,7 +342,7 @@ func (p *Package) Parse() error {
 		return nil
 	}
 
-	files, err := p.parseFiles()
+	files, err := p.parseFiles(includeTests)
 	if err != nil {
 		return err
 	}
@@ -279,11 +381,21 @@ func (p *Package) Check() error {
 }
 
 // parseFiles parses the loaded list of files and returns this list.
-func (p *Package) parseFiles() ([]*ast.File, error) {
+func (p *Package) parseFiles(includeTests bool) ([]*ast.File, error) {
 	// TODO: do this concurrently.
 	var files []*ast.File
 	var fileErrs []error
-	for _, file := range p.GoFiles {
+
+	var gofiles []string
+	if includeTests {
+		gofiles = make([]string, 0, len(p.GoFiles)+len(p.TestGoFiles))
+		gofiles = append(gofiles, p.GoFiles...)
+		gofiles = append(gofiles, p.TestGoFiles...)
+	} else {
+		gofiles = p.GoFiles
+	}
+
+	for _, file := range gofiles {
 		f, err := p.parseFile(filepath.Join(p.Package.Dir, file), parser.ParseComments)
 		if err != nil {
 			fileErrs = append(fileErrs, err)
@@ -305,15 +417,11 @@ func (p *Package) parseFiles() ([]*ast.File, error) {
 		files = append(files, f)
 	}
 	if len(p.CgoFiles) != 0 {
-		clangIncludes := ""
-		if _, err := os.Stat(filepath.Join(p.TINYGOROOT, "llvm", "tools", "clang", "lib", "Headers")); !os.IsNotExist(err) {
-			// Running from the source directory.
-			clangIncludes = filepath.Join(p.TINYGOROOT, "llvm", "tools", "clang", "lib", "Headers")
-		} else {
-			// Running from the installation directory.
-			clangIncludes = filepath.Join(p.TINYGOROOT, "lib", "clang", "include")
+		cflags := append(p.CFlags, "-I"+p.Package.Dir)
+		if p.ClangHeaders != "" {
+			cflags = append(cflags, "-I"+p.ClangHeaders)
 		}
-		generated, errs := cgo.Process(files, p.Program.Dir, p.fset, append(p.CFlags, "-I"+p.Package.Dir, "-I"+clangIncludes))
+		generated, errs := cgo.Process(files, p.Program.Dir, p.fset, cflags)
 		if errs != nil {
 			fileErrs = append(fileErrs, errs...)
 		}
@@ -322,6 +430,7 @@ func (p *Package) parseFiles() ([]*ast.File, error) {
 	if len(fileErrs) != 0 {
 		return nil, Errors{p, fileErrs}
 	}
+
 	return files, nil
 }
 
@@ -342,9 +451,15 @@ func (p *Package) Import(to string) (*types.Package, error) {
 // importRecursively() on the imported packages as well.
 //
 // Idempotent.
-func (p *Package) importRecursively() error {
+func (p *Package) importRecursively(includeTests bool) error {
 	p.Importing = true
-	for _, to := range p.Package.Imports {
+
+	imports := p.Package.Imports
+	if includeTests {
+		imports = append(imports, p.Package.TestImports...)
+	}
+
+	for _, to := range imports {
 		if to == "C" {
 			// Do CGo processing in a later stage.
 			continue
@@ -362,7 +477,7 @@ func (p *Package) importRecursively() error {
 		if importedPkg.Importing {
 			return &ImportCycleError{[]string{p.ImportPath, importedPkg.ImportPath}, p.ImportPos[to]}
 		}
-		err = importedPkg.importRecursively()
+		err = importedPkg.importRecursively(false)
 		if err != nil {
 			if err, ok := err.(*ImportCycleError); ok {
 				err.Packages = append([]string{p.ImportPath}, err.Packages...)

main.go

@@ -47,13 +47,18 @@ type BuildConfig struct {
 	opt           string
 	gc            string
 	panicStrategy string
+	scheduler     string
 	printIR       bool
 	dumpSSA       bool
+	verifyIR      bool
 	debug         bool
 	printSizes    string
 	cFlags        []string
 	ldFlags       []string
+	tags          string
 	wasmAbi       string
+	heapSize      int64
+	testConfig    compiler.TestConfig
 }
 
 // Helper function for Compiler object.
@@ -81,16 +86,23 @@ func Compile(pkgName, outpath string, spec *TargetSpec, config *BuildConfig, act
 		return errors.New("cannot locate $GOROOT, please set it manually")
 	}
 	tags := spec.BuildTags
-	major, minor := getGorootVersion(goroot)
-	if major != 1 {
-		if major == 0 {
-			return errors.New("could not read version from GOROOT: " + goroot)
-		}
-		return fmt.Errorf("expected major version 1, got go%d.%d", major, minor)
+	major, minor, err := getGorootVersion(goroot)
+	if err != nil {
+		return fmt.Errorf("could not read version from GOROOT (%v): %v", goroot, err)
+	}
+	if major != 1 || (minor != 11 && minor != 12) {
+		return fmt.Errorf("requires go version 1.11 or 1.12, got go%d.%d", major, minor)
 	}
 	for i := 1; i <= minor; i++ {
 		tags = append(tags, fmt.Sprintf("go1.%d", i))
 	}
+	if extraTags := strings.Fields(config.tags); len(extraTags) != 0 {
+		tags = append(tags, extraTags...)
+	}
+	scheduler := spec.Scheduler
+	if config.scheduler != "" {
+		scheduler = config.scheduler
+	}
 	compilerConfig := compiler.Config{
 		Triple:        spec.Triple,
 		CPU:           spec.CPU,
@@ -99,14 +111,18 @@ func Compile(pkgName, outpath string, spec *TargetSpec, config *BuildConfig, act
 		GOARCH:        spec.GOARCH,
 		GC:            config.gc,
 		PanicStrategy: config.panicStrategy,
+		Scheduler:     scheduler,
 		CFlags:        cflags,
 		LDFlags:       ldflags,
+		ClangHeaders:  getClangHeaderPath(root),
 		Debug:         config.debug,
 		DumpSSA:       config.dumpSSA,
+		VerifyIR:      config.verifyIR,
 		TINYGOROOT:    root,
 		GOROOT:        goroot,
 		GOPATH:        getGopath(),
 		BuildTags:     tags,
+		TestConfig:    config.testConfig,
 	}
 	c, err := compiler.NewCompiler(pkgName, compilerConfig)
 	if err != nil {
@@ -140,9 +156,6 @@ func Compile(pkgName, outpath string, spec *TargetSpec, config *BuildConfig, act
 	if spec.GOOS != "darwin" {
 		c.ApplyFunctionSections() // -ffunction-sections
 	}
-	if err := c.Verify(); err != nil {
-		return errors.New("verification error after applying function sections")
-	}
 
 	// Browsers cannot handle external functions that have type i64 because it
 	// cannot be represented exactly in JavaScript (JS only has doubles). To
@@ -154,9 +167,6 @@ func Compile(pkgName, outpath string, spec *TargetSpec, config *BuildConfig, act
 		if err != nil {
 			return err
 		}
-		if err := c.Verify(); err != nil {
-			return errors.New("verification error after running the wasm i64 hack")
-		}
 	}
 
 	// Optimization levels here are roughly the same as Clang, but probably not
@@ -233,10 +243,16 @@ func Compile(pkgName, outpath string, spec *TargetSpec, config *BuildConfig, act
 		// Prepare link command.
 		executable := filepath.Join(dir, "main")
 		tmppath := executable // final file
-		ldflags := append(ldflags, "-o", executable, objfile, "-L", root)
+		ldflags = append(ldflags, "-o", executable, objfile, "-L", root)
 		if spec.RTLib == "compiler-rt" {
 			ldflags = append(ldflags, librt)
 		}
+		if spec.GOARCH == "wasm" {
+			// Round heap size to next multiple of 65536 (the WebAssembly page
+			// size).
+			heapSize := (config.heapSize + (65536 - 1)) &^ (65536 - 1)
+			ldflags = append(ldflags, "--initial-memory="+strconv.FormatInt(heapSize, 10))
+		}
 
 		// Compile extra files.
 		for i, path := range spec.ExtraFiles {
@@ -348,6 +364,33 @@ func Build(pkgName, outpath, target string, config *BuildConfig) error {
 	})
 }
 
+func Test(pkgName, target string, config *BuildConfig) error {
+	spec, err := LoadTarget(target)
+	if err != nil {
+		return err
+	}
+
+	spec.BuildTags = append(spec.BuildTags, "test")
+	config.testConfig.CompileTestBinary = true
+	return Compile(pkgName, ".elf", spec, config, func(tmppath string) error {
+		cmd := exec.Command(tmppath)
+		cmd.Stdout = os.Stdout
+		cmd.Stderr = os.Stderr
+		err := cmd.Run()
+		if err != nil {
+			// Propagate the exit code
+			if err, ok := err.(*exec.ExitError); ok {
+				if status, ok := err.Sys().(syscall.WaitStatus); ok {
+					os.Exit(status.ExitStatus())
+				}
+				os.Exit(1)
+			}
+			return &commandError{"failed to run compiled binary", tmppath, err}
+		}
+		return nil
+	})
+}
+
 func Flash(pkgName, target, port string, config *BuildConfig) error {
 	spec, err := LoadTarget(target)
 	if err != nil {
@@ -506,6 +549,30 @@ func Run(pkgName, target string, config *BuildConfig) error {
 	})
 }
 
+// parseSize converts a human-readable size (with k/m/g suffix) into a plain
+// number.
+func parseSize(s string) (int64, error) {
+	s = strings.ToLower(strings.TrimSpace(s))
+	if len(s) == 0 {
+		return 0, errors.New("no size provided")
+	}
+	multiply := int64(1)
+	switch s[len(s)-1] {
+	case 'k':
+		multiply = 1 << 10
+	case 'm':
+		multiply = 1 << 20
+	case 'g':
+		multiply = 1 << 30
+	}
+	if multiply != 1 {
+		s = s[:len(s)-1]
+	}
+	n, err := strconv.ParseInt(s, 0, 64)
+	n *= multiply
+	return n, err
+}
+
 func usage() {
 	fmt.Fprintln(os.Stderr, "TinyGo is a Go compiler for small places.")
 	fmt.Fprintln(os.Stderr, "version:", version)
@@ -513,6 +580,7 @@ func usage() {
 	fmt.Fprintln(os.Stderr, "\ncommands:")
 	fmt.Fprintln(os.Stderr, "  build: compile packages and dependencies")
 	fmt.Fprintln(os.Stderr, "  run:   compile and run immediately")
+	fmt.Fprintln(os.Stderr, "  test:  test packages")
 	fmt.Fprintln(os.Stderr, "  flash: compile and flash to the device")
 	fmt.Fprintln(os.Stderr, "  gdb:   run/flash and immediately enter GDB")
 	fmt.Fprintln(os.Stderr, "  clean: empty cache directory ("+cacheDir()+")")
@@ -523,23 +591,24 @@ func usage() {
 
 func handleCompilerError(err error) {
 	if err != nil {
-		if errUnsupported, ok := err.(*interp.Unsupported); ok {
+		switch err := err.(type) {
+		case *interp.Unsupported:
 			// hit an unknown/unsupported instruction
 			fmt.Fprintln(os.Stderr, "unsupported instruction during init evaluation:")
-			errUnsupported.Inst.Dump()
+			err.Inst.Dump()
 			fmt.Fprintln(os.Stderr)
-		} else if errCompiler, ok := err.(types.Error); ok {
-			fmt.Fprintln(os.Stderr, errCompiler)
-		} else if errLoader, ok := err.(loader.Errors); ok {
-			fmt.Fprintln(os.Stderr, "#", errLoader.Pkg.ImportPath)
-			for _, err := range errLoader.Errs {
+		case types.Error:
+			fmt.Fprintln(os.Stderr, err)
+		case loader.Errors:
+			fmt.Fprintln(os.Stderr, "#", err.Pkg.ImportPath)
+			for _, err := range err.Errs {
 				fmt.Fprintln(os.Stderr, err)
 			}
-		} else if errMulti, ok := err.(*multiError); ok {
-			for _, err := range errMulti.Errs {
+		case *multiError:
+			for _, err := range err.Errs {
 				fmt.Fprintln(os.Stderr, err)
 			}
-		} else {
+		default:
 			fmt.Fprintln(os.Stderr, "error:", err)
 		}
 		os.Exit(1)
@@ -549,11 +618,14 @@ func handleCompilerError(err error) {
 func main() {
 	outpath := flag.String("o", "", "output filename")
 	opt := flag.String("opt", "z", "optimization level: 0, 1, 2, s, z")
-	gc := flag.String("gc", "", "garbage collector to use (none, dumb, marksweep)")
-	panicStrategy := flag.String("panic", "print", "panic strategy (abort, trap)")
+	gc := flag.String("gc", "", "garbage collector to use (none, leaking, conservative)")
+	panicStrategy := flag.String("panic", "print", "panic strategy (print, trap)")
+	scheduler := flag.String("scheduler", "", "which scheduler to use (coroutines, tasks)")
 	printIR := flag.Bool("printir", false, "print LLVM IR")
 	dumpSSA := flag.Bool("dumpssa", false, "dump internal Go SSA")
-	target := flag.String("target", "", "LLVM target")
+	verifyIR := flag.Bool("verifyir", false, "run extra verification steps on LLVM IR")
+	tags := flag.String("tags", "", "a space-separated list of extra build tags")
+	target := flag.String("target", "", "LLVM target | .json file with TargetSpec")
 	printSize := flag.String("size", "", "print sizes (none, short, full)")
 	nodebug := flag.Bool("no-debug", false, "disable DWARF debug symbol generation")
 	ocdOutput := flag.Bool("ocd-output", false, "print OCD daemon output during debug")
@@ -561,6 +633,7 @@ func main() {
 	cFlags := flag.String("cflags", "", "additional cflags for compiler")
 	ldFlags := flag.String("ldflags", "", "additional ldflags for linker")
 	wasmAbi := flag.String("wasm-abi", "js", "WebAssembly ABI conventions: js (no i64 params) or generic")
+	heapSize := flag.String("heap-size", "1M", "default heap size in bytes (only supported by WebAssembly)")
 
 	if len(os.Args) < 2 {
 		fmt.Fprintln(os.Stderr, "No command-line arguments supplied.")
@@ -574,10 +647,13 @@ func main() {
 		opt:           *opt,
 		gc:            *gc,
 		panicStrategy: *panicStrategy,
+		scheduler:     *scheduler,
 		printIR:       *printIR,
 		dumpSSA:       *dumpSSA,
+		verifyIR:      *verifyIR,
 		debug:         !*nodebug,
 		printSizes:    *printSize,
+		tags:          *tags,
 		wasmAbi:       *wasmAbi,
 	}
 
@@ -595,6 +671,13 @@ func main() {
 		os.Exit(1)
 	}
 
+	var err error
+	if config.heapSize, err = parseSize(*heapSize); err != nil {
+		fmt.Fprintln(os.Stderr, "Could not read heap size:", *heapSize)
+		usage()
+		os.Exit(1)
+	}
+
 	os.Setenv("CC", "clang -target="+*target)
 
 	switch command {
@@ -604,8 +687,11 @@ func main() {
 			usage()
 			os.Exit(1)
 		}
-		if flag.NArg() != 1 {
-			fmt.Fprintln(os.Stderr, "No package specified.")
+		pkgName := "."
+		if flag.NArg() == 1 {
+			pkgName = flag.Arg(0)
+		} else if flag.NArg() > 1 {
+			fmt.Fprintln(os.Stderr, "build only accepts a single positional argument: package name, but multiple were specified")
 			usage()
 			os.Exit(1)
 		}
@@ -613,7 +699,7 @@ func main() {
 		if target == "" && filepath.Ext(*outpath) == ".wasm" {
 			target = "wasm"
 		}
-		err := Build(flag.Arg(0), *outpath, target, config)
+		err := Build(pkgName, *outpath, target, config)
 		handleCompilerError(err)
 	case "build-builtins":
 		// Note: this command is only meant to be used while making a release!
@@ -655,6 +741,17 @@ func main() {
 		}
 		err := Run(flag.Arg(0), *target, config)
 		handleCompilerError(err)
+	case "test":
+		pkgName := "."
+		if flag.NArg() == 1 {
+			pkgName = flag.Arg(0)
+		} else if flag.NArg() > 1 {
+			fmt.Fprintln(os.Stderr, "test only accepts a single positional argument: package name, but multiple were specified")
+			usage()
+			os.Exit(1)
+		}
+		err := Test(pkgName, *target, config)
+		handleCompilerError(err)
 	case "clean":
 		// remove cache directory
 		dir := cacheDir()

main_test.go

@@ -116,6 +116,7 @@ func runTest(path, tmpdir string, target string, t *testing.T) {
 		opt:        "z",
 		printIR:    false,
 		dumpSSA:    false,
+		verifyIR:   true,
 		debug:      false,
 		printSizes: "",
 		wasmAbi:    "js",

src/device/arm/arm.go

@@ -30,6 +30,7 @@
 package arm
 
 import (
+	"runtime/volatile"
 	"unsafe"
 )
 
@@ -69,37 +70,58 @@ func SVCall3(num uintptr, a1, a2, a3 interface{}) uintptr
 // Run the following system call (SVCall) with 4 arguments.
 func SVCall4(num uintptr, a1, a2, a3, a4 interface{}) uintptr
 
-//go:volatile
-type RegValue uint32
-
 const (
 	SCS_BASE  = 0xE000E000
 	NVIC_BASE = SCS_BASE + 0x0100
+	SCB_BASE  = SCS_BASE + 0x0D00
 )
 
+const (
+	SCB_AIRCR_VECTKEY_Pos     = 16
+	SCB_AIRCR_SYSRESETREQ_Pos = 2
+	SCB_AIRCR_SYSRESETREQ_Msk = 1 << SCB_AIRCR_SYSRESETREQ_Pos
+)
+
+// System Control Block (SCB)
+//
+// SCB_Type provides the definitions for the System Control Block Registers.
+type SCB_Type struct {
+	CPUID volatile.Register32    // CPUID Base Register
+	ICSR  volatile.Register32    // Interrupt Control and State Register
+	VTOR  volatile.Register32    // Vector Table Offset Register
+	AIRCR volatile.Register32    // Application Interrupt and Reset Control Register
+	SCR   volatile.Register32    // System Control Register
+	CCR   volatile.Register32    // Configuration Control Register
+	_     volatile.Register32    // RESERVED1;
+	SHP   [2]volatile.Register32 // System Handlers Priority Registers. [0] is RESERVED
+	SHCSR volatile.Register32    // System Handler Control and State Register
+}
+
+var SCB = (*SCB_Type)(unsafe.Pointer(uintptr(SCB_BASE)))
+
 // Nested Vectored Interrupt Controller (NVIC).
 //
 // Source:
 // http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.dui0553a/CIHIGCIF.html
 type NVIC_Type struct {
-	ISER [8]RegValue // Interrupt Set-enable Registers
+	ISER [8]volatile.Register32 // Interrupt Set-enable Registers
 	_    [24]uint32
-	ICER [8]RegValue // Interrupt Clear-enable Registers
+	ICER [8]volatile.Register32 // Interrupt Clear-enable Registers
 	_    [24]uint32
-	ISPR [8]RegValue // Interrupt Set-pending Registers
+	ISPR [8]volatile.Register32 // Interrupt Set-pending Registers
 	_    [24]uint32
-	ICPR [8]RegValue // Interrupt Clear-pending Registers
+	ICPR [8]volatile.Register32 // Interrupt Clear-pending Registers
 	_    [24]uint32
-	IABR [8]RegValue // Interrupt Active Bit Registers
+	IABR [8]volatile.Register32 // Interrupt Active Bit Registers
 	_    [56]uint32
-	IPR  [60]RegValue // Interrupt Priority Registers
+	IPR  [60]volatile.Register32 // Interrupt Priority Registers
 }
 
 var NVIC = (*NVIC_Type)(unsafe.Pointer(uintptr(NVIC_BASE)))
 
 // Enable the given interrupt number.
 func EnableIRQ(irq uint32) {
-	NVIC.ISER[irq>>5] = 1 << (irq & 0x1F)
+	NVIC.ISER[irq>>5].Set(1 << (irq & 0x1F))
 }
 
 // Set the priority of the given interrupt number.
@@ -116,7 +138,7 @@ func SetPriority(irq uint32, priority uint32) {
 	regpos := irq % 4
 	mask := uint32(0xff) << (regpos * 8) // bits to clear
 	priority = priority << (regpos * 8)  // bits to set
-	NVIC.IPR[regnum] = RegValue((uint32(NVIC.IPR[regnum]) &^ mask) | priority)
+	NVIC.IPR[regnum].Set((uint32(NVIC.IPR[regnum].Get()) &^ mask) | priority)
 }
 
 // DisableInterrupts disables all interrupts, and returns the old state.
@@ -136,3 +158,14 @@ func DisableInterrupts() uintptr {
 func EnableInterrupts(mask uintptr) {
 	Asm("cpsie if")
 }
+
+// SystemReset performs a hard system reset.
+func SystemReset() {
+	// SCB->AIRCR  = ((0x5FA << SCB_AIRCR_VECTKEY_Pos)      |
+	//              SCB_AIRCR_SYSRESETREQ_Msk);
+	SCB.AIRCR.Set((0x5FA << SCB_AIRCR_VECTKEY_Pos) | SCB_AIRCR_SYSRESETREQ_Msk)
+
+	for {
+		Asm("wfi")
+	}
+}

src/device/riscv/riscv.go

@@ -0,0 +1,10 @@
+package riscv
+
+// Run the given assembly code. The code will be marked as having side effects,
+// as it doesn't produce output and thus would normally be eliminated by the
+// optimizer.
+func Asm(asm string)
+
+// ReadRegister returns the contents of the specified register. The register
+// must be a processor register, reachable with the "mov" instruction.
+func ReadRegister(name string) uintptr

src/device/riscv/start.S

@@ -0,0 +1,13 @@
+.section .init
+.global _start
+.type _start,@function
+
+_start:
+    // Workaround for missing support of the la pseudo-instruction in Clang 8:
+    // https://reviews.llvm.org/D55325
+    lui sp,      %hi(_stack_top)
+    addi sp, sp, %lo(_stack_top)
+    // see https://gnu-mcu-eclipse.github.io/arch/riscv/programmer/#the-gp-global-pointer-register
+    lui gp,      %hi(__global_pointer$)
+    addi gp, gp, %lo(__global_pointer$)
+    call main

src/examples/gba-display/gba-display.go

@@ -0,0 +1,21 @@
+package main
+
+// Draw a red square on the GameBoy Advance screen.
+
+import (
+	"image/color"
+	"machine"
+)
+
+var display = machine.Display
+
+func main() {
+	display.Configure()
+
+	for x := int16(30); x < 50; x++ {
+		for y := int16(80); y < 100; y++ {
+			display.SetPixel(x, y, color.RGBA{255, 0, 0, 255})
+		}
+	}
+	display.Display()
+}

src/examples/wasm/Makefile

@@ -1,3 +1,8 @@
+invoke: clean wasm_exec
+	tinygo build -o ./html/wasm.wasm -target wasm -no-debug ./invoke/wasm.go
+	cp ./invoke/wasm.js ./html/
+	cp ./invoke/index.html ./html/
+
 export: clean wasm_exec
 	tinygo build -o ./html/wasm.wasm -target wasm -no-debug ./export/wasm.go
 	cp ./export/wasm.js ./html/
@@ -8,6 +13,12 @@ callback: clean wasm_exec
 	cp ./callback/wasm.js ./html/
 	cp ./callback/index.html ./html/
 
+slices: clean wasm_exec
+	tinygo build -o ./html/wasm.wasm -target wasm -no-debug ./slices/wasm.go
+	cp ./slices/wasm.js ./html/
+	cp ./slices/index.html ./html/
+
+
 main: clean wasm_exec
 	tinygo build -o ./html/wasm.wasm -target wasm -no-debug ./main/main.go
 	cp ./main/index.html ./html/

src/examples/wasm/README.md

@@ -3,7 +3,9 @@
 The examples here show two different ways of using WebAssembly with TinyGo:
 
 1. Defining and exporting functions via the `//go:export <name>` directive. See
-[the export folder](./export) for an example of this.
+[the export folder](./export) for an example of this.  Additionally, the Wasm
+module (which has a default value of `env`) can be specified using
+`//go:wasm-module <module>`.
 1. Defining and executing a `func main()`. This is similar to how the Go
 standard library implementation works. See [the main folder](./main) for an
 example of this.
@@ -34,7 +36,7 @@ $ make main
 Start the local web server:
 
 ```bash
-$ go run main.go
+$ go run server.go
 Serving ./html on http://localhost:8080
 ```
 

src/examples/wasm/invoke/index.html

@@ -0,0 +1,19 @@
+<!DOCTYPE html>
+
+<html>
+
+<head>
+    <meta charset="utf-8"/>
+    <title>Go WebAssembly</title>
+    <meta name="viewport" content="width=device-width, initial-scale=1"/>
+    <script src="wasm_exec.js" defer></script>
+    <script src="wasm.js" defer></script>
+</head>
+
+<body>
+    <h1>WebAssembly</h1>
+    <p>Edit on either side to mimic values, using WebAssembly:</p>
+    <input type="text" id="a" value=""/>==<input type="text" id="b" value=""/>
+</body>
+
+</html>

src/examples/wasm/invoke/wasm.go

@@ -0,0 +1,15 @@
+package main
+
+import (
+	"syscall/js"
+)
+
+func runner(this js.Value, args []js.Value) interface{} {
+	return args[0].Invoke(args[1]).String()
+}
+
+func main() {
+	wait := make(chan struct{}, 0)
+	js.Global().Set("runner", js.FuncOf(runner))
+	<-wait
+}

src/examples/wasm/invoke/wasm.js

@@ -0,0 +1,43 @@
+'use strict';
+
+const WASM_URL = 'wasm.wasm';
+
+var wasm;
+
+function updateRight() {
+    const value = document.getElementById("a").value;
+    window.runner(function (value) {
+        document.getElementById("b").value = value;
+    }, value);
+}
+
+function updateLeft() {
+    const value = document.getElementById("b").value;
+    window.runner(function (value) {
+        document.getElementById("a").value = value;
+    }, value);
+}
+
+function init() {
+    document.querySelector('#a').oninput = updateRight;
+    document.querySelector('#b').oninput = updateLeft;
+
+    const go = new Go();
+    if ('instantiateStreaming' in WebAssembly) {
+        WebAssembly.instantiateStreaming(fetch(WASM_URL), go.importObject).then(function (obj) {
+            wasm = obj.instance;
+            go.run(wasm);
+        })
+    } else {
+        fetch(WASM_URL).then(resp =>
+            resp.arrayBuffer()
+        ).then(bytes =>
+            WebAssembly.instantiate(bytes, go.importObject).then(function (obj) {
+                wasm = obj.instance;
+                go.run(wasm);
+            })
+        )
+    }
+}
+
+init();

src/examples/wasm/slices/index.html

@@ -0,0 +1,19 @@
+<!DOCTYPE html>
+
+<html>
+
+<head>
+    <meta charset="utf-8"/>
+    <title>Go WebAssembly</title>
+    <meta name="viewport" content="width=device-width, initial-scale=1"/>
+    <script src="wasm_exec.js" defer></script>
+    <script src="wasm.js" defer></script>
+</head>
+
+<body>
+    <h1>WebAssembly</h1>
+    <p>type values separated by comma, using WebAssembly:</p>
+    <input type="text" id="a" value=""/>==<div id="b"></div>
+</body>
+
+</html>

src/examples/wasm/slices/wasm.go

@@ -0,0 +1,23 @@
+package main
+
+import (
+	"strings"
+	"syscall/js"
+)
+
+func splitter(this js.Value, args []js.Value) interface{} {
+	values := strings.Split(args[0].String(), ",")
+
+	result := make([]interface{}, 0)
+	for _, each := range values {
+		result = append(result, each)
+	}
+
+	return js.ValueOf(result)
+}
+
+func main() {
+	wait := make(chan struct{}, 0)
+	js.Global().Set("splitter", js.FuncOf(splitter))
+	<-wait
+}

src/examples/wasm/slices/wasm.js

@@ -0,0 +1,33 @@
+'use strict';
+
+const WASM_URL = 'wasm.wasm';
+
+var wasm;
+
+function update() {
+    const value = document.getElementById("a").value;
+    document.getElementById("b").innerHTML = JSON.stringify(window.splitter(value));
+}
+
+function init() {
+    document.querySelector('#a').oninput = update;
+
+    const go = new Go();
+    if ('instantiateStreaming' in WebAssembly) {
+        WebAssembly.instantiateStreaming(fetch(WASM_URL), go.importObject).then(function (obj) {
+            wasm = obj.instance;
+            go.run(wasm);
+        })
+    } else {
+        fetch(WASM_URL).then(resp =>
+            resp.arrayBuffer()
+        ).then(bytes =>
+            WebAssembly.instantiate(bytes, go.importObject).then(function (obj) {
+                wasm = obj.instance;
+                go.run(wasm);
+            })
+        )
+    }
+}
+
+init();

src/machine/board_arduino.go

@@ -1,4 +1,4 @@
-// +build avr,arduino
+// +build arduino
 
 package machine
 

src/machine/board_arduino_nano33.go

@@ -0,0 +1,147 @@
+// +build sam,atsamd21,arduino_nano33
+
+// This contains the pin mappings for the Arduino Nano33 IoT board.
+//
+// For more information, see: https://store.arduino.cc/nano-33-iot
+//
+package machine
+
+import "device/sam"
+
+// used to reset into bootloader
+const RESET_MAGIC_VALUE = 0x07738135
+
+// GPIO Pins
+const (
+	RX0 Pin = PB23 // UART2 RX
+	TX1 Pin = PB22 // UART2 TX
+
+	D2 Pin = PB10 // PWM available
+	D3 Pin = PB11 // PWM available
+	D4 Pin = PA07
+	D5 Pin = PA05 // PWM available
+	D6 Pin = PA04 // PWM available
+	D7 Pin = PA06
+
+	D8  Pin = PA18
+	D9  Pin = PA20 // PWM available
+	D10 Pin = PA21 // PWM available
+	D11 Pin = PA16 // PWM available
+	D12 Pin = PA19 // PWM available
+
+	D13 Pin = PA17
+)
+
+// Analog pins
+const (
+	A0 Pin = PA02 // ADC/AIN[0]
+	A1 Pin = PB02 // ADC/AIN[10]
+	A2 Pin = PA11 // ADC/AIN[19]
+	A3 Pin = PA10 // ADC/AIN[18],
+	A4 Pin = PB08 // ADC/AIN[2], SCL:  SERCOM2/PAD[1]
+	A5 Pin = PB09 // ADC/AIN[3], SDA:  SERCOM2/PAD[1]
+	A6 Pin = PA09 // ADC/AIN[17]
+	A7 Pin = PB03 // ADC/AIN[11]
+)
+
+const (
+	LED = D13
+)
+
+// NINA-W102 Pins
+
+const (
+	NINA_MOSI   Pin = PA12
+	NINA_MISO   Pin = PA13
+	NINA_CS     Pin = PA14
+	NINA_SCK    Pin = PA15
+	NINA_GPIO0  Pin = PA27
+	NINA_RESETN Pin = PA08
+	NINA_ACK    Pin = PA28
+)
+
+// UART0 aka USBCDC pins
+const (
+	USBCDC_DM_PIN Pin = PA24
+	USBCDC_DP_PIN Pin = PA25
+)
+
+// UART1 on the Arduino Nano 33 connects to the onboard NINA-W102 WiFi chip.
+var (
+	UART1 = UART{Bus: sam.SERCOM5_USART,
+		Buffer: NewRingBuffer(),
+		Mode:   PinSERCOMAlt,
+		IRQVal: sam.IRQ_SERCOM5,
+	}
+)
+
+// UART1 pins
+const (
+	UART_TX_PIN Pin = PA22
+	UART_RX_PIN Pin = PA23
+)
+
+//go:export SERCOM5_IRQHandler
+func handleUART1() {
+	defaultUART1Handler()
+}
+
+// UART2 on the Arduino Nano 33 connects to the normal TX/RX pins.
+var (
+	UART2 = UART{Bus: sam.SERCOM3_USART,
+		Buffer: NewRingBuffer(),
+		Mode:   PinSERCOMAlt,
+		IRQVal: sam.IRQ_SERCOM3,
+	}
+)
+
+//go:export SERCOM3_IRQHandler
+func handleUART2() {
+	// should reset IRQ
+	UART2.Receive(byte((UART2.Bus.DATA.Get() & 0xFF)))
+	UART2.Bus.INTFLAG.SetBits(sam.SERCOM_USART_INTFLAG_RXC)
+}
+
+// I2C pins
+const (
+	SDA_PIN Pin = A4 // SDA: SERCOM4/PAD[1]
+	SCL_PIN Pin = A5 // SCL: SERCOM4/PAD[1]
+)
+
+// I2C on the Arduino Nano 33.
+var (
+	I2C0 = I2C{Bus: sam.SERCOM4_I2CM,
+		SDA:     SDA_PIN,
+		SCL:     SCL_PIN,
+		PinMode: PinSERCOMAlt}
+)
+
+// SPI pins
+const (
+	SPI0_SCK_PIN  Pin = A2 // SCK: SERCOM0/PAD[3]
+	SPI0_MOSI_PIN Pin = A3 // MOSI: SERCOM0/PAD[2]
+	SPI0_MISO_PIN Pin = A6 // MISO: SERCOM0/PAD[1]
+)
+
+// SPI on the Arduino Nano 33.
+var (
+	SPI0 = SPI{Bus: sam.SERCOM0_SPI,
+		SCK:     SPI0_SCK_PIN,
+		MOSI:    SPI0_MOSI_PIN,
+		MISO:    SPI0_MISO_PIN,
+		DOpad:   spiTXPad2SCK3,
+		DIpad:   sercomRXPad0,
+		PinMode: PinSERCOM}
+)
+
+// I2S pins
+const (
+	I2S_SCK_PIN Pin = PA10
+	I2S_SD_PIN  Pin = PA08
+	I2S_WS_PIN      = NoPin // TODO: figure out what this is on Arduino Nano 33.
+)
+
+// I2S on the Arduino Nano 33.
+var (
+	I2S0 = I2S{Bus: sam.I2S}
+)

src/machine/board_bluepill.go

@@ -1,7 +1,9 @@
-// +build stm32,bluepill
+// +build bluepill
 
 package machine
 
+import "device/stm32"
+
 // https://wiki.stm32duino.com/index.php?title=File:Bluepillpinout.gif
 const (
 	PA0  = portA + 0
@@ -47,10 +49,28 @@ const (
 
 // UART pins
 const (
-	UART_TX_PIN = PA9
-	UART_RX_PIN = PA10
+	UART_TX_PIN     = PA9
+	UART_RX_PIN     = PA10
+	UART_ALT_TX_PIN = PB6
+	UART_ALT_RX_PIN = PB7
 )
 
+var (
+	// USART1 is the first hardware serial port on the STM32.
+	// Both UART0 and UART1 refer to USART1.
+	UART0 = UART{
+		Buffer: NewRingBuffer(),
+		Bus:    stm32.USART1,
+		IRQVal: stm32.IRQ_USART1,
+	}
+	UART1 = &UART0
+)
+
+//go:export USART1_IRQHandler
+func handleUART1() {
+	UART1.Receive(byte((UART1.Bus.DR.Get() & 0xFF)))
+}
+
 // SPI pins
 const (
 	SPI0_SCK_PIN  = PA5

src/machine/board_circuitplay_express.go

@@ -4,6 +4,9 @@ package machine
 
 import "device/sam"
 
+// used to reset into bootloader
+const RESET_MAGIC_VALUE = 0xf01669ef
+
 // GPIO Pins
 const (
 	D0  = PB09
@@ -65,6 +68,20 @@ const (
 	UART_RX_PIN = PB09 // PORTB
 )
 
+// UART1 on the Circuit Playground Express.
+var (
+	UART1 = UART{Bus: sam.SERCOM1_USART,
+		Buffer: NewRingBuffer(),
+		Mode:   PinSERCOM,
+		IRQVal: sam.IRQ_SERCOM1,
+	}
+)
+
+//go:export SERCOM1_IRQHandler
+func handleUART1() {
+	defaultUART1Handler()
+}
+
 // I2C pins
 const (
 	SDA_PIN = PB02 // I2C0 external
@@ -97,7 +114,13 @@ const (
 
 // SPI on the Circuit Playground Express.
 var (
-	SPI0 = SPI{Bus: sam.SERCOM3_SPI}
+	SPI0 = SPI{Bus: sam.SERCOM3_SPI,
+		SCK:     SPI0_SCK_PIN,
+		MOSI:    SPI0_MOSI_PIN,
+		MISO:    SPI0_MISO_PIN,
+		DOpad:   spiTXPad2SCK3,
+		DIpad:   sercomRXPad0,
+		PinMode: PinSERCOMAlt}
 )
 
 // I2S pins

src/machine/board_digispark.go

@@ -1,4 +1,4 @@
-// +build attiny85,digispark
+// +build digispark
 
 package machine
 

src/machine/board_fe310.go

@@ -0,0 +1,38 @@
+// +build hifive1b
+
+package machine
+
+const (
+	P00 Pin = 0
+	P01 Pin = 1
+	P02 Pin = 2
+	P03 Pin = 3
+	P04 Pin = 4
+	P05 Pin = 5
+	P06 Pin = 6
+	P07 Pin = 7
+	P08 Pin = 8
+	P09 Pin = 9
+	P10 Pin = 10
+	P11 Pin = 11
+	P12 Pin = 12
+	P13 Pin = 13
+	P14 Pin = 14
+	P15 Pin = 15
+	P16 Pin = 16
+	P17 Pin = 17
+	P18 Pin = 18
+	P19 Pin = 19
+	P20 Pin = 20
+	P21 Pin = 21
+	P22 Pin = 22
+	P23 Pin = 23
+	P24 Pin = 24
+	P25 Pin = 25
+	P26 Pin = 26
+	P27 Pin = 27
+	P28 Pin = 28
+	P29 Pin = 29
+	P30 Pin = 30
+	P31 Pin = 31
+)

src/machine/board_feather-m0.go

@@ -4,6 +4,9 @@ package machine
 
 import "device/sam"
 
+// used to reset into bootloader
+const RESET_MAGIC_VALUE = 0xf01669ef
+
 // GPIO Pins
 const (
 	D0  = PA11  // UART0 RX
@@ -48,6 +51,20 @@ const (
 	UART_RX_PIN = D11
 )
 
+// UART1 on the Feather M0.
+var (
+	UART1 = UART{Bus: sam.SERCOM1_USART,
+		Buffer: NewRingBuffer(),
+		Mode:   PinSERCOM,
+		IRQVal: sam.IRQ_SERCOM1,
+	}
+)
+
+//go:export SERCOM1_IRQHandler
+func handleUART1() {
+	defaultUART1Handler()
+}
+
 // I2C pins
 const (
 	SDA_PIN = PA22 // SDA: SERCOM3/PAD[0]
@@ -71,7 +88,13 @@ const (
 
 // SPI on the Feather M0.
 var (
-	SPI0 = SPI{Bus: sam.SERCOM4_SPI}
+	SPI0 = SPI{Bus: sam.SERCOM4_SPI,
+		SCK:     SPI0_SCK_PIN,
+		MOSI:    SPI0_MOSI_PIN,
+		MISO:    SPI0_MISO_PIN,
+		DOpad:   spiTXPad2SCK3,
+		DIpad:   sercomRXPad0,
+		PinMode: PinSERCOMAlt}
 )
 
 // I2S pins

src/machine/board_hifive1b.go

@@ -0,0 +1,19 @@
+// +build hifive1b
+
+package machine
+
+const (
+	LED       = LED1
+	LED1      = LED_RED
+	LED2      = LED_GREEN
+	LED3      = LED_BLUE
+	LED_RED   = P22
+	LED_GREEN = P19
+	LED_BLUE  = P21
+)
+
+const (
+	// TODO: figure out the pin numbers for these.
+	UART_TX_PIN = NoPin
+	UART_RX_PIN = NoPin
+)

src/machine/board_itsybitsy-m0.go

@@ -2,7 +2,12 @@
 
 package machine
 
-import "device/sam"
+import (
+	"device/sam"
+)
+
+// used to reset into bootloader
+const RESET_MAGIC_VALUE = 0xf01669ef
 
 // GPIO Pins
 const (
@@ -48,6 +53,20 @@ const (
 	UART_RX_PIN = D11
 )
 
+// UART1 on the ItsyBitsy M0.
+var (
+	UART1 = UART{Bus: sam.SERCOM1_USART,
+		Buffer: NewRingBuffer(),
+		Mode:   PinSERCOM,
+		IRQVal: sam.IRQ_SERCOM1,
+	}
+)
+
+//go:export SERCOM1_IRQHandler
+func handleUART1() {
+	defaultUART1Handler()
+}
+
 // I2C pins
 const (
 	SDA_PIN = PA22 // SDA: SERCOM3/PAD[0]
@@ -71,7 +90,32 @@ const (
 
 // SPI on the ItsyBitsy M0.
 var (
-	SPI0 = SPI{Bus: sam.SERCOM4_SPI}
+	SPI0 = SPI{Bus: sam.SERCOM4_SPI,
+		SCK:     SPI0_SCK_PIN,
+		MOSI:    SPI0_MOSI_PIN,
+		MISO:    SPI0_MISO_PIN,
+		DOpad:   spiTXPad2SCK3,
+		DIpad:   sercomRXPad0,
+		PinMode: PinSERCOMAlt}
+)
+
+// "Internal" SPI pins; SPI flash is attached to these on ItsyBitsy M0
+const (
+	SPI1_CS_PIN   = PA27
+	SPI1_SCK_PIN  = PB23
+	SPI1_MOSI_PIN = PB22
+	SPI1_MISO_PIN = PB03
+)
+
+// "Internal" SPI on Sercom 5
+var (
+	SPI1 = SPI{Bus: sam.SERCOM5_SPI,
+		SCK:     SPI1_SCK_PIN,
+		MOSI:    SPI1_MOSI_PIN,
+		MISO:    SPI1_MISO_PIN,
+		DOpad:   spiTXPad2SCK3,
+		DIpad:   sercomRXPad1,
+		PinMode: PinSERCOMAlt}
 )
 
 // I2S pins

src/machine/board_itsybitsy-m4.go

@@ -0,0 +1,83 @@
+// +build sam,atsamd51,itsybitsy_m4
+
+package machine
+
+import "device/sam"
+
+// used to reset into bootloader
+const RESET_MAGIC_VALUE = 0xf01669ef
+
+// GPIO Pins
+const (
+	D0  = PA16 // UART0 RX/PWM available
+	D1  = PA17 // UART0 TX/PWM available
+	D2  = PA07
+	D3  = PB22
+	D4  = PA14 // PWM available
+	D5  = PA15 // PWM available
+	D6  = PB02 // dotStar clock
+	D7  = PA18 // PWM available
+	D8  = PB03 // dotStar data
+	D9  = PA19 // PWM available
+	D10 = PA20 // can be used for PWM or UART1 TX
+	D11 = PA21 // can be used for PWM or UART1 RX
+	D12 = PA23 // PWM available
+	D13 = PA22 // PWM available
+)
+
+// Analog pins
+const (
+	A0 = PA02 // ADC/AIN[0]
+	A1 = PB05 // ADC/AIN[2]
+	A2 = PB08 // ADC/AIN[3]
+	A3 = PB09 // ADC/AIN[4]
+	A4 = PA04 // ADC/AIN[5]
+	A5 = PA06 // ADC/AIN[10]
+)
+
+const (
+	LED = D13
+)
+
+// UART0 aka USBCDC pins
+const (
+	USBCDC_DM_PIN = PA24
+	USBCDC_DP_PIN = PA25
+)
+
+// UART1 pins
+const (
+	UART_TX_PIN = D1
+	UART_RX_PIN = D0
+)
+
+// I2C pins
+const (
+	SDA_PIN = PA12 // SDA: SERCOM3/PAD[0]
+	SCL_PIN = PA13 // SCL: SERCOM3/PAD[1]
+)
+
+// I2C on the ItsyBitsy M4.
+var (
+	I2C0 = I2C{Bus: sam.SERCOM2_I2CM,
+		SDA:     SDA_PIN,
+		SCL:     SCL_PIN,
+		PinMode: PinSERCOM}
+)
+
+// SPI pins
+const (
+	SPI0_SCK_PIN  = PA01 // SCK: SERCOM1/PAD[1]
+	SPI0_MOSI_PIN = PA00 // MOSI: SERCOM1/PAD[0]
+	SPI0_MISO_PIN = PB23 // MISO: SERCOM1/PAD[3]
+)
+
+// SPI on the ItsyBitsy M4.
+var (
+	SPI0 = SPI{Bus: sam.SERCOM1_SPI,
+		SCK:   SPI0_SCK_PIN,
+		MOSI:  SPI0_MOSI_PIN,
+		MISO:  SPI0_MISO_PIN,
+		DOpad: spiTXPad2SCK3,
+		DIpad: sercomRXPad0}
+)

src/machine/board_microbit.go

@@ -1,4 +1,4 @@
-// +build nrf51,microbit
+// +build microbit
 
 package machine
 

src/machine/board_nucleof103rb.go

@@ -0,0 +1,124 @@
+// +build nucleof103rb
+
+package machine
+
+import "device/stm32"
+
+const (
+	PA0  = portA + 0
+	PA1  = portA + 1
+	PA2  = portA + 2
+	PA3  = portA + 3
+	PA4  = portA + 4
+	PA5  = portA + 5
+	PA6  = portA + 6
+	PA7  = portA + 7
+	PA8  = portA + 8
+	PA9  = portA + 9
+	PA10 = portA + 10
+	PA11 = portA + 11
+	PA12 = portA + 12
+	PA13 = portA + 13
+	PA14 = portA + 14
+	PA15 = portA + 15
+
+	PB0  = portB + 0
+	PB1  = portB + 1
+	PB2  = portB + 2
+	PB3  = portB + 3
+	PB4  = portB + 4
+	PB5  = portB + 5
+	PB6  = portB + 6
+	PB7  = portB + 7
+	PB8  = portB + 8
+	PB9  = portB + 9
+	PB10 = portB + 10
+	PB11 = portB + 11
+	PB12 = portB + 12
+	PB13 = portB + 13
+	PB14 = portB + 14
+	PB15 = portB + 15
+
+	PC0  = portC + 0
+	PC1  = portC + 1
+	PC2  = portC + 2
+	PC3  = portC + 3
+	PC4  = portC + 4
+	PC5  = portC + 5
+	PC6  = portC + 6
+	PC7  = portC + 7
+	PC8  = portC + 8
+	PC9  = portC + 9
+	PC10 = portC + 10
+	PC11 = portC + 11
+	PC12 = portC + 12
+	PC13 = portC + 13
+	PC14 = portC + 14
+	PC15 = portC + 15
+
+	PD0  = portD + 0
+	PD1  = portD + 1
+	PD2  = portD + 2
+	PD3  = portD + 3
+	PD4  = portD + 4
+	PD5  = portD + 5
+	PD6  = portD + 6
+	PD7  = portD + 7
+	PD8  = portD + 8
+	PD9  = portD + 9
+	PD10 = portD + 10
+	PD11 = portD + 11
+	PD12 = portD + 12
+	PD13 = portD + 13
+	PD14 = portD + 14
+	PD15 = portD + 15
+)
+
+const (
+	LED         = LED_BUILTIN
+	LED_BUILTIN = LED_GREEN
+	LED_GREEN   = PA5
+)
+
+const (
+	BUTTON      = BUTTON_USER
+	BUTTON_USER = PC13
+)
+
+// UART pins
+const (
+	UART_TX_PIN     = PA2
+	UART_RX_PIN     = PA3
+	UART_ALT_TX_PIN = PD5
+	UART_ALT_RX_PIN = PD6
+)
+
+var (
+	// USART2 is the hardware serial port connected to the onboard ST-LINK
+	// debugger to be exposed as virtual COM port over USB on Nucleo boards.
+	// Both UART0 and UART1 refer to USART2.
+	UART0 = UART{
+		Buffer: NewRingBuffer(),
+		Bus:    stm32.USART2,
+		IRQVal: stm32.IRQ_USART2,
+	}
+	UART2 = &UART0
+)
+
+//go:export USART2_IRQHandler
+func handleUART2() {
+	UART2.Receive(byte((UART2.Bus.DR.Get() & 0xFF)))
+}
+
+// SPI pins
+const (
+	SPI0_SCK_PIN  = PA5
+	SPI0_MISO_PIN = PA6
+	SPI0_MOSI_PIN = PA7
+)
+
+// I2C pins
+const (
+	SCL_PIN = PB6
+	SDA_PIN = PB7
+)

src/machine/board_pca10031.go

@@ -1,4 +1,4 @@
-// +build nrf51,pca10031
+// +build pca10031
 
 // pca10031 is a nrf51 based dongle, intended for use in wireless applications.
 //

src/machine/board_pca10040.go

@@ -1,4 +1,4 @@
-// +build nrf,pca10040
+// +build pca10040
 
 package machine
 

src/machine/board_reelboard.go

@@ -4,17 +4,24 @@ package machine
 
 const HasLowFrequencyCrystal = true
 
-// LEDs on the reel board
+// Pins on the reel board
 const (
-	LED        Pin = LED1
-	LED1       Pin = LED_YELLOW
-	LED2       Pin = LED_RED
-	LED3       Pin = LED_GREEN
-	LED4       Pin = LED_BLUE
-	LED_RED    Pin = 11
-	LED_GREEN  Pin = 12
-	LED_BLUE   Pin = 41
-	LED_YELLOW Pin = 13
+	LED              Pin = LED1
+	LED1             Pin = LED_YELLOW
+	LED2             Pin = LED_RED
+	LED3             Pin = LED_GREEN
+	LED4             Pin = LED_BLUE
+	LED_RED          Pin = 11
+	LED_GREEN        Pin = 12
+	LED_BLUE         Pin = 41
+	LED_YELLOW       Pin = 13
+	EPD_BUSY_PIN     Pin = 14
+	EPD_RESET_PIN    Pin = 15
+	EPD_DC_PIN       Pin = 16
+	EPD_CS_PIN       Pin = 17
+	EPD_SCK_PIN      Pin = 19
+	EPD_MOSI_PIN     Pin = 20
+	POWER_SUPPLY_PIN Pin = 32
 )
 
 // User "a" button on the reel board
@@ -40,3 +47,15 @@ const (
 	SPI0_MOSI_PIN Pin = 45
 	SPI0_MISO_PIN Pin = 46
 )
+
+// PowerSupplyActive enables the supply voltages for nRF52840 and peripherals (true) or only for nRF52840 (false)
+// This controls the TPS610981 boost converter. You must turn the power supply active in order to use the EPD and
+// other onboard peripherals.
+func PowerSupplyActive(active bool) {
+	POWER_SUPPLY_PIN.Configure(PinConfig{Mode: PinOutput})
+	if active {
+		POWER_SUPPLY_PIN.High()
+	} else {
+		POWER_SUPPLY_PIN.Low()
+	}
+}

src/machine/board_stm32.go

@@ -0,0 +1,16 @@
+// +build bluepill nucleof103rb stm32f4disco
+
+package machine
+
+// Peripheral abstraction layer for the stm32.
+
+const (
+	portA Pin = iota * 16
+	portB
+	portC
+	portD
+	portE
+	portF
+	portG
+	portH
+)

src/machine/board_stm32f4disco.go

@@ -1,4 +1,4 @@
-// +build stm32,stm32f4disco
+// +build stm32f4disco
 
 package machine
 

src/machine/board_trinket.go

@@ -4,6 +4,9 @@ package machine
 
 import "device/sam"
 
+// used to reset into bootloader
+const RESET_MAGIC_VALUE = 0xf01669ef
+
 // GPIO Pins
 const (
 	D0  = PA08 // PWM available
@@ -39,6 +42,20 @@ const (
 	UART_RX_PIN = D3
 )
 
+// UART1 on the Trinket M0.
+var (
+	UART1 = UART{Bus: sam.SERCOM1_USART,
+		Buffer: NewRingBuffer(),
+		Mode:   PinSERCOM,
+		IRQVal: sam.IRQ_SERCOM1,
+	}
+)
+
+//go:export SERCOM1_IRQHandler
+func handleUART1() {
+	defaultUART1Handler()
+}
+
 // SPI pins
 const (
 	SPI0_SCK_PIN  = D3
@@ -48,7 +65,13 @@ const (
 
 // SPI on the Trinket M0.
 var (
-	SPI0 = SPI{Bus: sam.SERCOM0_SPI}
+	SPI0 = SPI{Bus: sam.SERCOM0_SPI,
+		SCK:     SPI0_SCK_PIN,
+		MOSI:    SPI0_MOSI_PIN,
+		MISO:    SPI0_MISO_PIN,
+		DOpad:   spiTXPad2SCK3,
+		DIpad:   sercomRXPad0,
+		PinMode: PinSERCOMAlt}
 )
 
 // I2C pins

src/machine/buffer.go

@@ -1,9 +1,10 @@
 package machine
 
-const bufferSize = 128
+import (
+	"runtime/volatile"
+)
 
-//go:volatile
-type volatileByte byte
+const bufferSize = 128
 
 // RingBuffer is ring buffer implementation inspired by post at
 // https://www.embeddedrelated.com/showthread/comp.arch.embedded/77084-1.php
@@ -12,9 +13,9 @@ type volatileByte byte
 // members of a struct are not compiled correctly by TinyGo.
 // See https://github.com/tinygo-org/tinygo/issues/151 for details.
 type RingBuffer struct {
-	rxbuffer [bufferSize]volatileByte
-	head     volatileByte
-	tail     volatileByte
+	rxbuffer [bufferSize]volatile.Register8
+	head     volatile.Register8
+	tail     volatile.Register8
 }
 
 // NewRingBuffer returns a new ring buffer.
@@ -24,15 +25,15 @@ func NewRingBuffer() *RingBuffer {
 
 // Used returns how many bytes in buffer have been used.
 func (rb *RingBuffer) Used() uint8 {
-	return uint8(rb.head - rb.tail)
+	return uint8(rb.head.Get() - rb.tail.Get())
 }
 
 // Put stores a byte in the buffer. If the buffer is already
 // full, the method will return false.
 func (rb *RingBuffer) Put(val byte) bool {
 	if rb.Used() != bufferSize {
-		rb.head++
-		rb.rxbuffer[rb.head%bufferSize] = volatileByte(val)
+		rb.head.Set(rb.head.Get() + 1)
+		rb.rxbuffer[rb.head.Get()%bufferSize].Set(val)
 		return true
 	}
 	return false
@@ -42,8 +43,8 @@ func (rb *RingBuffer) Put(val byte) bool {
 // the method will return a false as the second value.
 func (rb *RingBuffer) Get() (byte, bool) {
 	if rb.Used() != 0 {
-		rb.tail++
-		return byte(rb.rxbuffer[rb.tail%bufferSize]), true
+		rb.tail.Set(rb.tail.Get() + 1)
+		return rb.rxbuffer[rb.tail.Get()%bufferSize].Get(), true
 	}
 	return 0, false
 }

src/machine/i2c.go

@@ -1,4 +1,4 @@
-// +build avr nrf sam stm32f103xx
+// +build avr nrf sam stm32,!stm32f4disco
 
 package machine
 

src/machine/machine_atmega.go

@@ -4,6 +4,7 @@ package machine
 
 import (
 	"device/avr"
+	"runtime/volatile"
 )
 
 // Configure sets the pin to input or output.
@@ -34,7 +35,7 @@ func (p Pin) Get() bool {
 	}
 }
 
-func (p Pin) getPortMask() (*avr.Register8, uint8) {
+func (p Pin) getPortMask() (*volatile.Register8, uint8) {
 	if p < 8 {
 		return avr.PORTD, 1 << uint8(p)
 	} else {

src/machine/machine_atsamd21.go

@@ -192,6 +192,11 @@ func (a ADC) Get() uint16 {
 	sam.ADC.SWTRIG.SetBits(sam.ADC_SWTRIG_START)
 	waitADCSync()
 
+	// wait for first conversion to finish to fix same issue as
+	// https://github.com/arduino/ArduinoCore-samd/issues/446
+	for !sam.ADC.INTFLAG.HasBits(sam.ADC_INTFLAG_RESRDY) {
+	}
+
 	// Clear the Data Ready flag
 	sam.ADC.INTFLAG.SetBits(sam.ADC_INTFLAG_RESRDY)
 	waitADCSync()
@@ -250,14 +255,13 @@ func waitADCSync() {
 type UART struct {
 	Buffer *RingBuffer
 	Bus    *sam.SERCOM_USART_Type
+	Mode   PinMode
+	IRQVal uint32
 }
 
 var (
 	// UART0 is actually a USB CDC interface.
 	UART0 = USBCDC{Buffer: NewRingBuffer()}
-
-	// The first hardware serial port on the SAMD21. Uses the SERCOM0 interface.
-	UART1 = UART{Bus: sam.SERCOM1_USART, Buffer: NewRingBuffer()}
 )
 
 const (
@@ -300,6 +304,8 @@ func (uart UART) Configure(config UARTConfig) {
 		txpad = sercomTXPad2
 	case PA16:
 		txpad = sercomTXPad0
+	case PA22:
+		txpad = sercomTXPad0
 	default:
 		panic("Invalid TX pin for UART")
 	}
@@ -315,13 +321,15 @@ func (uart UART) Configure(config UARTConfig) {
 		rxpad = sercomRXPad3
 	case PA17:
 		rxpad = sercomRXPad1
+	case PA23:
+		rxpad = sercomRXPad1
 	default:
 		panic("Invalid RX pin for UART")
 	}
 
 	// configure pins
-	config.TX.Configure(PinConfig{Mode: PinSERCOM})
-	config.RX.Configure(PinConfig{Mode: PinSERCOM})
+	config.TX.Configure(PinConfig{Mode: uart.Mode})
+	config.RX.Configure(PinConfig{Mode: uart.Mode})
 
 	// reset SERCOM0
 	uart.Bus.CTRLA.SetBits(sam.SERCOM_USART_CTRLA_SWRST)
@@ -372,13 +380,7 @@ func (uart UART) Configure(config UARTConfig) {
 	uart.Bus.INTENSET.Set(sam.SERCOM_USART_INTENSET_RXC)
 
 	// Enable RX IRQ.
-	if config.TX == PA10 {
-		// UART0
-		arm.EnableIRQ(sam.IRQ_SERCOM0)
-	} else {
-		// UART1 which is the normal default, since UART0 is used for USBCDC.
-		arm.EnableIRQ(sam.IRQ_SERCOM1)
-	}
+	arm.EnableIRQ(uart.IRQVal)
 }
 
 // SetBaudRate sets the communication speed for the UART.
@@ -404,8 +406,8 @@ func (uart UART) WriteByte(c byte) error {
 	return nil
 }
 
-//go:export SERCOM1_IRQHandler
-func handleUART1() {
+// defaultUART1Handler handles the UART1 IRQ.
+func defaultUART1Handler() {
 	// should reset IRQ
 	UART1.Receive(byte((UART1.Bus.DATA.Get() & 0xFF)))
 	UART1.Bus.INTFLAG.SetBits(sam.SERCOM_USART_INTFLAG_RXC)
@@ -874,7 +876,13 @@ func waitForSync() {
 
 // SPI
 type SPI struct {
-	Bus *sam.SERCOM_SPI_Type
+	Bus     *sam.SERCOM_SPI_Type
+	SCK     Pin
+	MOSI    Pin
+	MISO    Pin
+	DOpad   int
+	DIpad   int
+	PinMode PinMode
 }
 
 // SPIConfig is used to store config info for SPI.
@@ -889,12 +897,14 @@ type SPIConfig struct {
 
 // Configure is intended to setup the SPI interface.
 func (spi SPI) Configure(config SPIConfig) {
-	config.SCK = SPI0_SCK_PIN
-	config.MOSI = SPI0_MOSI_PIN
-	config.MISO = SPI0_MISO_PIN
+	config.SCK = spi.SCK
+	config.MOSI = spi.MOSI
+	config.MISO = spi.MISO
 
-	doPad := spiTXPad2SCK3
-	diPad := sercomRXPad0
+	doPad := spi.DOpad
+	diPad := spi.DIpad
+
+	pinMode := spi.PinMode
 
 	// set default frequency
 	if config.Frequency == 0 {
@@ -907,9 +917,9 @@ func (spi SPI) Configure(config SPIConfig) {
 	}
 
 	// enable pins
-	config.SCK.Configure(PinConfig{Mode: PinSERCOMAlt})
-	config.MOSI.Configure(PinConfig{Mode: PinSERCOMAlt})
-	config.MISO.Configure(PinConfig{Mode: PinSERCOMAlt})
+	config.SCK.Configure(PinConfig{Mode: pinMode})
+	config.MOSI.Configure(PinConfig{Mode: pinMode})
+	config.MISO.Configure(PinConfig{Mode: pinMode})
 
 	// reset SERCOM
 	spi.Bus.CTRLA.SetBits(sam.SERCOM_SPI_CTRLA_SWRST)
@@ -1182,23 +1192,35 @@ func (usbcdc USBCDC) WriteByte(c byte) error {
 		usbEndpointDescriptors[usb_CDC_ENDPOINT_IN].DeviceDescBank[1].PCKSIZE.ClearBits(usb_DEVICE_PCKSIZE_MULTI_PACKET_SIZE_Mask << usb_DEVICE_PCKSIZE_MULTI_PACKET_SIZE_Pos)
 
 		// set count of bytes to be sent
-		usbEndpointDescriptors[usb_CDC_ENDPOINT_IN].DeviceDescBank[1].PCKSIZE.SetBits((1&usb_DEVICE_PCKSIZE_BYTE_COUNT_Mask)<<usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos |
-			(epPacketSize(64) << usb_DEVICE_PCKSIZE_SIZE_Pos))
+		usbEndpointDescriptors[usb_CDC_ENDPOINT_IN].DeviceDescBank[1].PCKSIZE.SetBits((1 & usb_DEVICE_PCKSIZE_BYTE_COUNT_Mask) << usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos)
 
-		// ack transfer complete flag
+		// clear transfer complete flag
 		setEPINTFLAG(usb_CDC_ENDPOINT_IN, sam.USB_DEVICE_EPINTFLAG_TRCPT1)
 
 		// send data by setting bank ready
 		setEPSTATUSSET(usb_CDC_ENDPOINT_IN, sam.USB_DEVICE_EPSTATUSSET_BK1RDY)
 
 		// wait for transfer to complete
+		timeout := 3000
 		for (getEPINTFLAG(usb_CDC_ENDPOINT_IN) & sam.USB_DEVICE_EPINTFLAG_TRCPT1) == 0 {
+			timeout--
+			if timeout == 0 {
+				return errors.New("USBCDC write byte timeout")
+			}
 		}
 	}
 
 	return nil
 }
 
+func (usbcdc USBCDC) DTR() bool {
+	return (usbLineInfo.lineState & usb_CDC_LINESTATE_DTR) > 0
+}
+
+func (usbcdc USBCDC) RTS() bool {
+	return (usbLineInfo.lineState & usb_CDC_LINESTATE_RTS) > 0
+}
+
 const (
 	// these are SAMD21 specific.
 	usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos  = 0
@@ -1346,6 +1368,7 @@ func handleUSB() {
 
 		// Clear the Bank 0 ready flag on Control OUT
 		setEPSTATUSCLR(0, sam.USB_DEVICE_EPSTATUSCLR_BK0RDY)
+		usbEndpointDescriptors[0].DeviceDescBank[0].PCKSIZE.ClearBits(usb_DEVICE_PCKSIZE_BYTE_COUNT_Mask << usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos)
 
 		ok := false
 		if (setup.bmRequestType & usb_REQUEST_TYPE) == usb_REQUEST_STANDARD {
@@ -1375,19 +1398,20 @@ func handleUSB() {
 		}
 	}
 
-	// Now the actual transfer handlers
-	eptInts := sam.USB_DEVICE.EPINTSMRY.Get() & 0xFE // Remove endpoint number 0 (setup)
+	// Now the actual transfer handlers, ignore endpoint number 0 (setup)
 	var i uint32
 	for i = 1; i < uint32(len(endPoints)); i++ {
 		// Check if endpoint has a pending interrupt
-		if eptInts&(1<<i) > 0 {
-			// yes, so handle flags
-			epFlags := getEPINTFLAG(i)
-			setEPINTFLAG(i, epFlags)
-
-			// Endpoint Transfer Complete Interrupt
-			if (epFlags & sam.USB_DEVICE_EPINTFLAG_TRCPT0) > 0 {
+		epFlags := getEPINTFLAG(i)
+		if (epFlags&sam.USB_DEVICE_EPINTFLAG_TRCPT0) > 0 ||
+			(epFlags&sam.USB_DEVICE_EPINTFLAG_TRCPT1) > 0 {
+			switch i {
+			case usb_CDC_ENDPOINT_OUT:
 				handleEndpoint(i)
+				setEPINTFLAG(i, epFlags)
+			case usb_CDC_ENDPOINT_IN, usb_CDC_ENDPOINT_ACM:
+				setEPSTATUSCLR(i, sam.USB_DEVICE_EPSTATUSCLR_BK1RDY)
+				setEPINTFLAG(i, sam.USB_DEVICE_EPINTFLAG_TRCPT1)
 			}
 		}
 	}
@@ -1403,7 +1427,7 @@ func initEndpoint(ep, config uint32) {
 		usbEndpointDescriptors[ep].DeviceDescBank[1].ADDR.Set(uint32(uintptr(unsafe.Pointer(&udd_ep_in_cache_buffer[ep]))))
 
 		// set endpoint type
-		setEPCFG(ep, getEPCFG(ep)|((usb_ENDPOINT_TYPE_INTERRUPT+1)<<sam.USB_DEVICE_EPCFG_EPTYPE1_Pos))
+		setEPCFG(ep, ((usb_ENDPOINT_TYPE_INTERRUPT + 1) << sam.USB_DEVICE_EPCFG_EPTYPE1_Pos))
 
 	case usb_ENDPOINT_TYPE_BULK | usbEndpointOut:
 		// set packet size
@@ -1413,11 +1437,14 @@ func initEndpoint(ep, config uint32) {
 		usbEndpointDescriptors[ep].DeviceDescBank[0].ADDR.Set(uint32(uintptr(unsafe.Pointer(&udd_ep_out_cache_buffer[ep]))))
 
 		// set endpoint type
-		setEPCFG(ep, getEPCFG(ep)|((usb_ENDPOINT_TYPE_BULK+1)<<sam.USB_DEVICE_EPCFG_EPTYPE0_Pos))
+		setEPCFG(ep, ((usb_ENDPOINT_TYPE_BULK + 1) << sam.USB_DEVICE_EPCFG_EPTYPE0_Pos))
 
-		// ack the current transfer
+		// receive interrupts when current transfer complete
 		setEPINTENSET(ep, sam.USB_DEVICE_EPINTENSET_TRCPT0)
 
+		// set byte count to zero, we have not received anything yet
+		usbEndpointDescriptors[ep].DeviceDescBank[0].PCKSIZE.ClearBits(usb_DEVICE_PCKSIZE_BYTE_COUNT_Mask << usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos)
+
 		// ready for next transfer
 		setEPSTATUSCLR(ep, sam.USB_DEVICE_EPSTATUSCLR_BK0RDY)
 
@@ -1432,7 +1459,7 @@ func initEndpoint(ep, config uint32) {
 		usbEndpointDescriptors[ep].DeviceDescBank[1].ADDR.Set(uint32(uintptr(unsafe.Pointer(&udd_ep_in_cache_buffer[ep]))))
 
 		// set endpoint type
-		setEPCFG(ep, getEPCFG(ep)|((usb_ENDPOINT_TYPE_BULK+1)<<sam.USB_DEVICE_EPCFG_EPTYPE1_Pos))
+		setEPCFG(ep, ((usb_ENDPOINT_TYPE_BULK + 1) << sam.USB_DEVICE_EPCFG_EPTYPE1_Pos))
 
 		// NAK on endpoint IN, the bank is not yet filled in.
 		setEPSTATUSCLR(ep, sam.USB_DEVICE_EPSTATUSCLR_BK1RDY)
@@ -1515,7 +1542,12 @@ func handleStandardSetup(setup usbSetup) bool {
 		setEPSTATUSSET(0, sam.USB_DEVICE_EPSTATUSSET_BK1RDY)
 
 		// wait for transfer to complete
+		timeout := 3000
 		for (getEPINTFLAG(0) & sam.USB_DEVICE_EPINTFLAG_TRCPT1) == 0 {
+			timeout--
+			if timeout == 0 {
+				return true
+			}
 		}
 
 		// last, set the device address to that requested by host
@@ -1601,17 +1633,19 @@ func cdcSetup(setup usbSetup) bool {
 
 		if setup.bRequest == usb_CDC_SET_LINE_CODING || setup.bRequest == usb_CDC_SET_CONTROL_LINE_STATE {
 			// auto-reset into the bootloader
-			if usbLineInfo.dwDTERate == 1200 && (usbLineInfo.lineState&0x01) == 0 {
-				// TODO: system reset
+			if usbLineInfo.dwDTERate == 1200 && usbLineInfo.lineState&usb_CDC_LINESTATE_DTR == 0 {
+				ResetProcessor()
 			} else {
 				// TODO: cancel any reset
 			}
+			sendZlp(0)
 		}
 
 		if setup.bRequest == usb_CDC_SEND_BREAK {
 			// TODO: something with this value?
 			// breakValue = ((uint16_t)setup.wValueH << 8) | setup.wValueL;
 			// return false;
+			sendZlp(0)
 		}
 		return true
 	}
@@ -1632,43 +1666,41 @@ func sendUSBPacket(ep uint32, data []byte) {
 }
 
 func receiveUSBControlPacket() []byte {
-	// set ready to receive data
+	// address
+	usbEndpointDescriptors[0].DeviceDescBank[0].ADDR.Set(uint32(uintptr(unsafe.Pointer(&udd_ep_out_cache_buffer[0]))))
+
+	// set byte count to zero
+	usbEndpointDescriptors[0].DeviceDescBank[0].PCKSIZE.ClearBits(usb_DEVICE_PCKSIZE_BYTE_COUNT_Mask << usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos)
+
+	// set ready for next data
 	setEPSTATUSCLR(0, sam.USB_DEVICE_EPSTATUSCLR_BK0RDY)
 
-	// read the data
-	bytesread := armRecvCtrlOUT(0)
-
-	// return the data
-	data := make([]byte, 0, bytesread)
-	copy(data, udd_ep_out_cache_buffer[0][:bytesread])
-	return data
-}
-
-func armRecvCtrlOUT(ep uint32) uint32 {
-	// Set output address to receive data
-	usbEndpointDescriptors[ep].DeviceDescBank[0].ADDR.Set(uint32(uintptr(unsafe.Pointer(&udd_ep_out_cache_buffer[ep]))))
-
-	// set multi-packet size which is total expected number of bytes to receive.
-	usbEndpointDescriptors[ep].DeviceDescBank[0].PCKSIZE.SetBits((8 << usb_DEVICE_PCKSIZE_MULTI_PACKET_SIZE_Pos) |
-		uint32(epPacketSize(64)<<usb_DEVICE_PCKSIZE_SIZE_Pos))
-
-	// clear byte count of bytes received so far.
-	usbEndpointDescriptors[ep].DeviceDescBank[0].PCKSIZE.ClearBits(usb_DEVICE_PCKSIZE_BYTE_COUNT_Mask << usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos)
-
-	// clear ready state to start transfer
-	setEPSTATUSCLR(ep, sam.USB_DEVICE_EPSTATUSCLR_BK0RDY)
-
 	// Wait until OUT transfer is ready.
-	for (getEPSTATUS(ep) & sam.USB_DEVICE_EPSTATUS_BK0RDY) == 0 {
+	timeout := 3000
+	for (getEPSTATUS(0) & sam.USB_DEVICE_EPSTATUS_BK0RDY) == 0 {
+		timeout--
+		if timeout == 0 {
+			return []byte{}
+		}
 	}
 
 	// Wait until OUT transfer is completed.
-	for (getEPINTFLAG(ep) & sam.USB_DEVICE_EPINTFLAG_TRCPT0) == 0 {
+	timeout = 300000
+	for (getEPINTFLAG(0) & sam.USB_DEVICE_EPINTFLAG_TRCPT0) == 0 {
+		timeout--
+		if timeout == 0 {
+			return []byte{}
+		}
 	}
 
-	// return number of bytes received
-	return (usbEndpointDescriptors[ep].DeviceDescBank[0].PCKSIZE.Get() >>
-		usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos) & usb_DEVICE_PCKSIZE_BYTE_COUNT_Mask
+	// get data
+	bytesread := uint32((usbEndpointDescriptors[0].DeviceDescBank[0].PCKSIZE.Get() >>
+		usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos) & usb_DEVICE_PCKSIZE_BYTE_COUNT_Mask)
+
+	data := make([]byte, bytesread)
+	copy(data, udd_ep_out_cache_buffer[0][:])
+
+	return data
 }
 
 // sendDescriptor creates and sends the various USB descriptor types that
@@ -1764,9 +1796,9 @@ func sendConfiguration(setup usbSetup) {
 
 		dif := NewInterfaceDescriptor(usb_CDC_DATA_INTERFACE, 2, usb_CDC_DATA_INTERFACE_CLASS, 0, 0)
 
-		in := NewEndpointDescriptor((usb_CDC_ENDPOINT_OUT | usbEndpointOut), usb_ENDPOINT_TYPE_BULK, usbEndpointPacketSize, 0)
+		out := NewEndpointDescriptor((usb_CDC_ENDPOINT_OUT | usbEndpointOut), usb_ENDPOINT_TYPE_BULK, usbEndpointPacketSize, 0)
 
-		out := NewEndpointDescriptor((usb_CDC_ENDPOINT_IN | usbEndpointIn), usb_ENDPOINT_TYPE_BULK, usbEndpointPacketSize, 0)
+		in := NewEndpointDescriptor((usb_CDC_ENDPOINT_IN | usbEndpointIn), usb_ENDPOINT_TYPE_BULK, usbEndpointPacketSize, 0)
 
 		cdc := NewCDCDescriptor(iad,
 			cif,
@@ -1776,8 +1808,8 @@ func sendConfiguration(setup usbSetup) {
 			callManagement,
 			cifin,
 			dif,
-			in,
-			out)
+			out,
+			in)
 
 		sz := uint16(configDescriptorSize + cdcSize)
 		config := NewConfigDescriptor(sz, 2)
@@ -1800,9 +1832,14 @@ func handleEndpoint(ep uint32) {
 		UART0.Receive(byte((udd_ep_out_cache_buffer[ep][i] & 0xFF)))
 	}
 
+	// set byte count to zero
+	usbEndpointDescriptors[ep].DeviceDescBank[0].PCKSIZE.ClearBits(usb_DEVICE_PCKSIZE_BYTE_COUNT_Mask << usb_DEVICE_PCKSIZE_BYTE_COUNT_Pos)
+
+	// set multi packet size to 64
+	usbEndpointDescriptors[ep].DeviceDescBank[0].PCKSIZE.SetBits(64 << usb_DEVICE_PCKSIZE_MULTI_PACKET_SIZE_Pos)
+
 	// set ready for next data
 	setEPSTATUSCLR(ep, sam.USB_DEVICE_EPSTATUSCLR_BK0RDY)
-
 }
 
 func sendZlp(ep uint32) {
@@ -2038,3 +2075,15 @@ func setEPINTENSET(ep uint32, val uint8) {
 		return
 	}
 }
+
+// ResetProcessor should perform a system reset in preperation
+// to switch to the bootloader to flash new firmware.
+func ResetProcessor() {
+	arm.DisableInterrupts()
+
+	// Perform magic reset into bootloader, as mentioned in
+	// https://github.com/arduino/ArduinoCore-samd/issues/197
+	*(*uint32)(unsafe.Pointer(uintptr(0x20007FFC))) = RESET_MAGIC_VALUE
+
+	arm.SystemReset()
+}

src/machine/machine_atsamd51g19.go

@@ -0,0 +1,569 @@
+// +build sam,atsamd51,atsamd51g19
+
+// Peripheral abstraction layer for the atsamd51.
+//
+// Datasheet:
+// http://ww1.microchip.com/downloads/en/DeviceDoc/60001507C.pdf
+//
+package machine
+
+import (
+	"device/sam"
+)
+
+// Return the register and mask to enable a given GPIO pin. This can be used to
+// implement bit-banged drivers.
+func (p Pin) PortMaskSet() (*uint32, uint32) {
+	if p < 32 {
+		return &sam.PORT.OUTSET0.Reg, 1 << uint8(p)
+	} else {
+		return &sam.PORT.OUTSET1.Reg, 1 << uint8(p-32)
+	}
+}
+
+// Return the register and mask to disable a given port. This can be used to
+// implement bit-banged drivers.
+func (p Pin) PortMaskClear() (*uint32, uint32) {
+	if p < 32 {
+		return &sam.PORT.OUTCLR0.Reg, 1 << uint8(p)
+	} else {
+		return &sam.PORT.OUTCLR1.Reg, 1 << uint8(p-32)
+	}
+}
+
+// Set the pin to high or low.
+// Warning: only use this on an output pin!
+func (p Pin) Set(high bool) {
+	if p < 32 {
+		if high {
+			sam.PORT.OUTSET0.Set(1 << uint8(p))
+		} else {
+			sam.PORT.OUTCLR0.Set(1 << uint8(p))
+		}
+	} else {
+		if high {
+			sam.PORT.OUTSET1.Set(1 << uint8(p-32))
+		} else {
+			sam.PORT.OUTCLR1.Set(1 << uint8(p-32))
+		}
+	}
+}
+
+// Get returns the current value of a GPIO pin.
+func (p Pin) Get() bool {
+	if p < 32 {
+		return (sam.PORT.IN0.Get()>>uint8(p))&1 > 0
+	} else {
+		return (sam.PORT.IN1.Get()>>(uint8(p)-32))&1 > 0
+	}
+}
+
+// Configure this pin with the given configuration.
+func (p Pin) Configure(config PinConfig) {
+	switch config.Mode {
+	case PinOutput:
+		if p < 32 {
+			sam.PORT.DIRSET0.Set(1 << uint8(p))
+			// output is also set to input enable so pin can read back its own value
+			p.setPinCfg(sam.PORT_PINCFG0_INEN)
+		} else {
+			sam.PORT.DIRSET1.Set(1 << uint8(p-32))
+			// output is also set to input enable so pin can read back its own value
+			p.setPinCfg(sam.PORT_PINCFG0_INEN)
+		}
+
+	case PinInput:
+		if p < 32 {
+			sam.PORT.DIRCLR0.Set(1 << uint8(p))
+			p.setPinCfg(sam.PORT_PINCFG0_INEN)
+		} else {
+			sam.PORT.DIRCLR1.Set(1<<uint8(p) - 32)
+			p.setPinCfg(sam.PORT_PINCFG0_INEN)
+		}
+
+	case PinInputPulldown:
+		if p < 32 {
+			sam.PORT.DIRCLR0.Set(1 << uint8(p))
+			sam.PORT.OUTCLR0.Set(1 << uint8(p))
+			p.setPinCfg(sam.PORT_PINCFG0_INEN | sam.PORT_PINCFG0_PULLEN)
+		} else {
+			sam.PORT.DIRCLR1.Set(1<<uint8(p) - 32)
+			sam.PORT.OUTCLR1.Set(1<<uint8(p) - 32)
+			p.setPinCfg(sam.PORT_PINCFG0_INEN | sam.PORT_PINCFG0_PULLEN)
+		}
+
+	case PinInputPullup:
+		if p < 32 {
+			sam.PORT.DIRCLR0.Set(1 << uint8(p))
+			sam.PORT.OUTSET0.Set(1 << uint8(p))
+			p.setPinCfg(sam.PORT_PINCFG0_INEN | sam.PORT_PINCFG0_PULLEN)
+		} else {
+			sam.PORT.DIRCLR1.Set(1<<uint8(p) - 32)
+			sam.PORT.OUTSET1.Set(1<<uint8(p) - 32)
+			p.setPinCfg(sam.PORT_PINCFG0_INEN | sam.PORT_PINCFG0_PULLEN)
+		}
+
+	case PinSERCOM:
+		if p&1 > 0 {
+			// odd pin, so save the even pins
+			val := p.getPMux() & sam.PORT_PMUX0_PMUXE_Msk
+			p.setPMux(val | (uint8(PinSERCOM) << sam.PORT_PMUX0_PMUXO_Pos))
+		} else {
+			// even pin, so save the odd pins
+			val := p.getPMux() & sam.PORT_PMUX0_PMUXO_Msk
+			p.setPMux(val | (uint8(PinSERCOM) << sam.PORT_PMUX0_PMUXE_Pos))
+		}
+		// enable port config
+		p.setPinCfg(sam.PORT_PINCFG0_PMUXEN | sam.PORT_PINCFG0_DRVSTR | sam.PORT_PINCFG0_INEN)
+
+	case PinSERCOMAlt:
+		if p&1 > 0 {
+			// odd pin, so save the even pins
+			val := p.getPMux() & sam.PORT_PMUX0_PMUXE_Msk
+			p.setPMux(val | (uint8(PinSERCOMAlt) << sam.PORT_PMUX0_PMUXO_Pos))
+		} else {
+			// even pin, so save the odd pins
+			val := p.getPMux() & sam.PORT_PMUX0_PMUXO_Msk
+			p.setPMux(val | (uint8(PinSERCOMAlt) << sam.PORT_PMUX0_PMUXE_Pos))
+		}
+		// enable port config
+		p.setPinCfg(sam.PORT_PINCFG0_PMUXEN | sam.PORT_PINCFG0_DRVSTR)
+
+	case PinCom:
+		if p&1 > 0 {
+			// odd pin, so save the even pins
+			val := p.getPMux() & sam.PORT_PMUX0_PMUXE_Msk
+			p.setPMux(val | (uint8(PinCom) << sam.PORT_PMUX0_PMUXO_Pos))
+		} else {
+			// even pin, so save the odd pins
+			val := p.getPMux() & sam.PORT_PMUX0_PMUXO_Msk
+			p.setPMux(val | (uint8(PinCom) << sam.PORT_PMUX0_PMUXE_Pos))
+		}
+		// enable port config
+		p.setPinCfg(sam.PORT_PINCFG0_PMUXEN)
+	case PinAnalog:
+		if p&1 > 0 {
+			// odd pin, so save the even pins
+			val := p.getPMux() & sam.PORT_PMUX0_PMUXE_Msk
+			p.setPMux(val | (uint8(PinAnalog) << sam.PORT_PMUX0_PMUXO_Pos))
+		} else {
+			// even pin, so save the odd pins
+			val := p.getPMux() & sam.PORT_PMUX0_PMUXO_Msk
+			p.setPMux(val | (uint8(PinAnalog) << sam.PORT_PMUX0_PMUXE_Pos))
+		}
+		// enable port config
+		p.setPinCfg(sam.PORT_PINCFG0_PMUXEN | sam.PORT_PINCFG0_DRVSTR)
+	}
+}
+
+// getPMux returns the value for the correct PMUX register for this pin.
+func (p Pin) getPMux() uint8 {
+	switch uint8(p) >> 1 {
+	case 0:
+		return sam.PORT.PMUX0_0.Get()
+	case 1:
+		return sam.PORT.PMUX0_1.Get()
+	case 2:
+		return sam.PORT.PMUX0_2.Get()
+	case 3:
+		return sam.PORT.PMUX0_3.Get()
+	case 4:
+		return sam.PORT.PMUX0_4.Get()
+	case 5:
+		return sam.PORT.PMUX0_5.Get()
+	case 6:
+		return sam.PORT.PMUX0_6.Get()
+	case 7:
+		return sam.PORT.PMUX0_7.Get()
+	case 8:
+		return sam.PORT.PMUX0_8.Get()
+	case 9:
+		return sam.PORT.PMUX0_9.Get()
+	case 10:
+		return sam.PORT.PMUX0_10.Get()
+	case 11:
+		return sam.PORT.PMUX0_11.Get()
+	case 12:
+		return sam.PORT.PMUX0_12.Get()
+	case 13:
+		return sam.PORT.PMUX0_13.Get()
+	case 14:
+		return sam.PORT.PMUX0_14.Get()
+	case 15:
+		return sam.PORT.PMUX0_15.Get()
+	case 16:
+		return uint8(sam.PORT.PMUX1_0.Get()>>0) & 0xff
+	case 17:
+		return uint8(sam.PORT.PMUX1_0.Get()>>8) & 0xff
+	case 18:
+		return uint8(sam.PORT.PMUX1_0.Get()>>16) & 0xff
+	case 19:
+		return uint8(sam.PORT.PMUX1_0.Get()>>24) & 0xff
+	case 20:
+		return uint8(sam.PORT.PMUX1_4.Get()>>0) & 0xff
+	case 21:
+		return uint8(sam.PORT.PMUX1_4.Get()>>8) & 0xff
+	case 22:
+		return uint8(sam.PORT.PMUX1_4.Get()>>16) & 0xff
+	case 23:
+		return uint8(sam.PORT.PMUX1_4.Get()>>24) & 0xff
+	case 24:
+		return uint8(sam.PORT.PMUX1_8.Get()>>0) & 0xff
+	case 25:
+		return uint8(sam.PORT.PMUX1_8.Get()>>8) & 0xff
+	case 26:
+		return uint8(sam.PORT.PMUX1_8.Get()>>16) & 0xff
+	case 27:
+		return uint8(sam.PORT.PMUX1_8.Get()>>24) & 0xff
+	case 28:
+		return uint8(sam.PORT.PMUX1_12.Get()>>0) & 0xff
+	case 29:
+		return uint8(sam.PORT.PMUX1_12.Get()>>8) & 0xff
+	case 30:
+		return uint8(sam.PORT.PMUX1_12.Get()>>16) & 0xff
+	case 31:
+		return uint8(sam.PORT.PMUX1_12.Get()>>24) & 0xff
+	default:
+		return 0
+	}
+}
+
+// setPMux sets the value for the correct PMUX register for this pin.
+func (p Pin) setPMux(val uint8) {
+	switch uint8(p) >> 1 {
+	case 0:
+		sam.PORT.PMUX0_0.Set(val)
+	case 1:
+		sam.PORT.PMUX0_1.Set(val)
+	case 2:
+		sam.PORT.PMUX0_2.Set(val)
+	case 3:
+		sam.PORT.PMUX0_3.Set(val)
+	case 4:
+		sam.PORT.PMUX0_4.Set(val)
+	case 5:
+		sam.PORT.PMUX0_5.Set(val)
+	case 6:
+		sam.PORT.PMUX0_6.Set(val)
+	case 7:
+		sam.PORT.PMUX0_7.Set(val)
+	case 8:
+		sam.PORT.PMUX0_8.Set(val)
+	case 9:
+		sam.PORT.PMUX0_9.Set(val)
+	case 10:
+		sam.PORT.PMUX0_10.Set(val)
+	case 11:
+		sam.PORT.PMUX0_11.Set(val)
+	case 12:
+		sam.PORT.PMUX0_12.Set(val)
+	case 13:
+		sam.PORT.PMUX0_13.Set(val)
+	case 14:
+		sam.PORT.PMUX0_14.Set(val)
+	case 15:
+		sam.PORT.PMUX0_15.Set(val)
+	case 16:
+		sam.PORT.PMUX1_0.Set(sam.PORT.PMUX1_0.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 17:
+		sam.PORT.PMUX1_0.Set(sam.PORT.PMUX1_0.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 18:
+		sam.PORT.PMUX1_0.Set(sam.PORT.PMUX1_0.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 19:
+		sam.PORT.PMUX1_0.Set(sam.PORT.PMUX1_0.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 20:
+		sam.PORT.PMUX1_4.Set(sam.PORT.PMUX1_4.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 21:
+		sam.PORT.PMUX1_4.Set(sam.PORT.PMUX1_4.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 22:
+		sam.PORT.PMUX1_4.Set(sam.PORT.PMUX1_4.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 23:
+		sam.PORT.PMUX1_4.Set(sam.PORT.PMUX1_4.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 24:
+		sam.PORT.PMUX1_8.Set(sam.PORT.PMUX1_8.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 25:
+		sam.PORT.PMUX1_8.Set(sam.PORT.PMUX1_8.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 26:
+		sam.PORT.PMUX1_8.Set(sam.PORT.PMUX1_8.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 27:
+		sam.PORT.PMUX1_8.Set(sam.PORT.PMUX1_8.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 28:
+		sam.PORT.PMUX1_12.Set(sam.PORT.PMUX1_12.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 29:
+		sam.PORT.PMUX1_12.Set(sam.PORT.PMUX1_12.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 30:
+		sam.PORT.PMUX1_12.Set(sam.PORT.PMUX1_12.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 31:
+		sam.PORT.PMUX1_12.Set(sam.PORT.PMUX1_12.Get()&^(0xff<<24) | (uint32(val) << 24))
+	}
+}
+
+// getPinCfg returns the value for the correct PINCFG register for this pin.
+func (p Pin) getPinCfg() uint8 {
+	switch p {
+	case 0:
+		return sam.PORT.PINCFG0_0.Get()
+	case 1:
+		return sam.PORT.PINCFG0_1.Get()
+	case 2:
+		return sam.PORT.PINCFG0_2.Get()
+	case 3:
+		return sam.PORT.PINCFG0_3.Get()
+	case 4:
+		return sam.PORT.PINCFG0_4.Get()
+	case 5:
+		return sam.PORT.PINCFG0_5.Get()
+	case 6:
+		return sam.PORT.PINCFG0_6.Get()
+	case 7:
+		return sam.PORT.PINCFG0_7.Get()
+	case 8:
+		return sam.PORT.PINCFG0_8.Get()
+	case 9:
+		return sam.PORT.PINCFG0_9.Get()
+	case 10:
+		return sam.PORT.PINCFG0_10.Get()
+	case 11:
+		return sam.PORT.PINCFG0_11.Get()
+	case 12:
+		return sam.PORT.PINCFG0_12.Get()
+	case 13:
+		return sam.PORT.PINCFG0_13.Get()
+	case 14:
+		return sam.PORT.PINCFG0_14.Get()
+	case 15:
+		return sam.PORT.PINCFG0_15.Get()
+	case 16:
+		return sam.PORT.PINCFG0_16.Get()
+	case 17:
+		return sam.PORT.PINCFG0_17.Get()
+	case 18:
+		return sam.PORT.PINCFG0_18.Get()
+	case 19:
+		return sam.PORT.PINCFG0_19.Get()
+	case 20:
+		return sam.PORT.PINCFG0_20.Get()
+	case 21:
+		return sam.PORT.PINCFG0_21.Get()
+	case 22:
+		return sam.PORT.PINCFG0_22.Get()
+	case 23:
+		return sam.PORT.PINCFG0_23.Get()
+	case 24:
+		return sam.PORT.PINCFG0_24.Get()
+	case 25:
+		return sam.PORT.PINCFG0_25.Get()
+	case 26:
+		return sam.PORT.PINCFG0_26.Get()
+	case 27:
+		return sam.PORT.PINCFG0_27.Get()
+	case 28:
+		return sam.PORT.PINCFG0_28.Get()
+	case 29:
+		return sam.PORT.PINCFG0_29.Get()
+	case 30:
+		return sam.PORT.PINCFG0_30.Get()
+	case 31:
+		return sam.PORT.PINCFG0_31.Get()
+	case 32: // PB00
+		return uint8(sam.PORT.PINCFG1_0.Get()>>0) & 0xff
+	case 33: // PB01
+		return uint8(sam.PORT.PINCFG1_0.Get()>>8) & 0xff
+	case 34: // PB02
+		return uint8(sam.PORT.PINCFG1_0.Get()>>16) & 0xff
+	case 35: // PB03
+		return uint8(sam.PORT.PINCFG1_0.Get()>>24) & 0xff
+	case 37: // PB04
+		return uint8(sam.PORT.PINCFG1_4.Get()>>0) & 0xff
+	case 38: // PB05
+		return uint8(sam.PORT.PINCFG1_4.Get()>>8) & 0xff
+	case 39: // PB06
+		return uint8(sam.PORT.PINCFG1_4.Get()>>16) & 0xff
+	case 40: // PB07
+		return uint8(sam.PORT.PINCFG1_4.Get()>>24) & 0xff
+	case 41: // PB08
+		return uint8(sam.PORT.PINCFG1_8.Get()>>0) & 0xff
+	case 42: // PB09
+		return uint8(sam.PORT.PINCFG1_8.Get()>>8) & 0xff
+	case 43: // PB10
+		return uint8(sam.PORT.PINCFG1_8.Get()>>16) & 0xff
+	case 44: // PB11
+		return uint8(sam.PORT.PINCFG1_8.Get()>>24) & 0xff
+	case 45: // PB12
+		return uint8(sam.PORT.PINCFG1_12.Get()>>0) & 0xff
+	case 46: // PB13
+		return uint8(sam.PORT.PINCFG1_12.Get()>>8) & 0xff
+	case 47: // PB14
+		return uint8(sam.PORT.PINCFG1_12.Get()>>16) & 0xff
+	case 48: // PB15
+		return uint8(sam.PORT.PINCFG1_12.Get()>>24) & 0xff
+	case 49: // PB16
+		return uint8(sam.PORT.PINCFG1_16.Get()>>0) & 0xff
+	case 50: // PB17
+		return uint8(sam.PORT.PINCFG1_16.Get()>>8) & 0xff
+	case 51: // PB18
+		return uint8(sam.PORT.PINCFG1_16.Get()>>16) & 0xff
+	case 52: // PB19
+		return uint8(sam.PORT.PINCFG1_16.Get()>>24) & 0xff
+	case 53: // PB20
+		return uint8(sam.PORT.PINCFG1_20.Get()>>0) & 0xff
+	case 54: // PB21
+		return uint8(sam.PORT.PINCFG1_20.Get()>>8) & 0xff
+	case 55: // PB22
+		return uint8(sam.PORT.PINCFG1_20.Get()>>16) & 0xff
+	case 56: // PB23
+		return uint8(sam.PORT.PINCFG1_20.Get()>>24) & 0xff
+	case 57: // PB24
+		return uint8(sam.PORT.PINCFG1_24.Get()>>0) & 0xff
+	case 58: // PB25
+		return uint8(sam.PORT.PINCFG1_24.Get()>>8) & 0xff
+	case 59: // PB26
+		return uint8(sam.PORT.PINCFG1_24.Get()>>16) & 0xff
+	case 60: // PB27
+		return uint8(sam.PORT.PINCFG1_24.Get()>>24) & 0xff
+	case 61: // PB28
+		return uint8(sam.PORT.PINCFG1_28.Get()>>0) & 0xff
+	case 62: // PB29
+		return uint8(sam.PORT.PINCFG1_28.Get()>>8) & 0xff
+	case 63: // PB30
+		return uint8(sam.PORT.PINCFG1_28.Get()>>16) & 0xff
+	case 64: // PB31
+		return uint8(sam.PORT.PINCFG1_28.Get()>>24) & 0xff
+	default:
+		return 0
+	}
+}
+
+// setPinCfg sets the value for the correct PINCFG register for this pin.
+func (p Pin) setPinCfg(val uint8) {
+	switch p {
+	case 0:
+		sam.PORT.PINCFG0_0.Set(val)
+	case 1:
+		sam.PORT.PINCFG0_1.Set(val)
+	case 2:
+		sam.PORT.PINCFG0_2.Set(val)
+	case 3:
+		sam.PORT.PINCFG0_3.Set(val)
+	case 4:
+		sam.PORT.PINCFG0_4.Set(val)
+	case 5:
+		sam.PORT.PINCFG0_5.Set(val)
+	case 6:
+		sam.PORT.PINCFG0_6.Set(val)
+	case 7:
+		sam.PORT.PINCFG0_7.Set(val)
+	case 8:
+		sam.PORT.PINCFG0_8.Set(val)
+	case 9:
+		sam.PORT.PINCFG0_9.Set(val)
+	case 10:
+		sam.PORT.PINCFG0_10.Set(val)
+	case 11:
+		sam.PORT.PINCFG0_11.Set(val)
+	case 12:
+		sam.PORT.PINCFG0_12.Set(val)
+	case 13:
+		sam.PORT.PINCFG0_13.Set(val)
+	case 14:
+		sam.PORT.PINCFG0_14.Set(val)
+	case 15:
+		sam.PORT.PINCFG0_15.Set(val)
+	case 16:
+		sam.PORT.PINCFG0_16.Set(val)
+	case 17:
+		sam.PORT.PINCFG0_17.Set(val)
+	case 18:
+		sam.PORT.PINCFG0_18.Set(val)
+	case 19:
+		sam.PORT.PINCFG0_19.Set(val)
+	case 20:
+		sam.PORT.PINCFG0_20.Set(val)
+	case 21:
+		sam.PORT.PINCFG0_21.Set(val)
+	case 22:
+		sam.PORT.PINCFG0_22.Set(val)
+	case 23:
+		sam.PORT.PINCFG0_23.Set(val)
+	case 24:
+		sam.PORT.PINCFG0_24.Set(val)
+	case 25:
+		sam.PORT.PINCFG0_25.Set(val)
+	case 26:
+		sam.PORT.PINCFG0_26.Set(val)
+	case 27:
+		sam.PORT.PINCFG0_27.Set(val)
+	case 28:
+		sam.PORT.PINCFG0_28.Set(val)
+	case 29:
+		sam.PORT.PINCFG0_29.Set(val)
+	case 30:
+		sam.PORT.PINCFG0_30.Set(val)
+	case 31:
+		sam.PORT.PINCFG0_31.Set(val)
+	case 32: // PB00
+		sam.PORT.PINCFG1_0.Set(sam.PORT.PINCFG1_0.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 33: // PB01
+		sam.PORT.PINCFG1_0.Set(sam.PORT.PINCFG1_0.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 34: // PB02
+		sam.PORT.PINCFG1_0.Set(sam.PORT.PINCFG1_0.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 35: // PB03
+		sam.PORT.PINCFG1_0.Set(sam.PORT.PINCFG1_0.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 36: // PB04
+		sam.PORT.PINCFG1_4.Set(sam.PORT.PINCFG1_4.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 37: // PB05
+		sam.PORT.PINCFG1_4.Set(sam.PORT.PINCFG1_4.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 38: // PB06
+		sam.PORT.PINCFG1_4.Set(sam.PORT.PINCFG1_4.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 39: // PB07
+		sam.PORT.PINCFG1_4.Set(sam.PORT.PINCFG1_4.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 40: // PB08
+		sam.PORT.PINCFG1_8.Set(sam.PORT.PINCFG1_8.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 41: // PB09
+		sam.PORT.PINCFG1_8.Set(sam.PORT.PINCFG1_8.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 42: // PB10
+		sam.PORT.PINCFG1_8.Set(sam.PORT.PINCFG1_8.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 43: // PB11
+		sam.PORT.PINCFG1_8.Set(sam.PORT.PINCFG1_8.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 44: // PB12
+		sam.PORT.PINCFG1_12.Set(sam.PORT.PINCFG1_12.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 45: // PB13
+		sam.PORT.PINCFG1_12.Set(sam.PORT.PINCFG1_12.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 46: // PB14
+		sam.PORT.PINCFG1_12.Set(sam.PORT.PINCFG1_12.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 47: // PB15
+		sam.PORT.PINCFG1_12.Set(sam.PORT.PINCFG1_12.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 48: // PB16
+		sam.PORT.PINCFG1_16.Set(sam.PORT.PINCFG1_16.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 49: // PB17
+		sam.PORT.PINCFG1_16.Set(sam.PORT.PINCFG1_16.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 50: // PB18
+		sam.PORT.PINCFG1_16.Set(sam.PORT.PINCFG1_16.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 51: // PB19
+		sam.PORT.PINCFG1_16.Set(sam.PORT.PINCFG1_16.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 52: // PB20
+		sam.PORT.PINCFG1_20.Set(sam.PORT.PINCFG1_20.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 53: // PB21
+		sam.PORT.PINCFG1_20.Set(sam.PORT.PINCFG1_20.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 54: // PB22
+		sam.PORT.PINCFG1_20.Set(sam.PORT.PINCFG1_20.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 55: // PB23
+		sam.PORT.PINCFG1_20.Set(sam.PORT.PINCFG1_20.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 56: // PB24
+		sam.PORT.PINCFG1_24.Set(sam.PORT.PINCFG1_24.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 57: // PB25
+		sam.PORT.PINCFG1_24.Set(sam.PORT.PINCFG1_24.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 58: // PB26
+		sam.PORT.PINCFG1_24.Set(sam.PORT.PINCFG1_24.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 59: // PB27
+		sam.PORT.PINCFG1_24.Set(sam.PORT.PINCFG1_24.Get()&^(0xff<<24) | (uint32(val) << 24))
+	case 60: // PB28
+		sam.PORT.PINCFG1_28.Set(sam.PORT.PINCFG1_28.Get()&^(0xff<<0) | (uint32(val) << 0))
+	case 61: // PB29
+		sam.PORT.PINCFG1_28.Set(sam.PORT.PINCFG1_28.Get()&^(0xff<<8) | (uint32(val) << 8))
+	case 62: // PB30
+		sam.PORT.PINCFG1_28.Set(sam.PORT.PINCFG1_28.Get()&^(0xff<<16) | (uint32(val) << 16))
+	case 63: // PB31
+		sam.PORT.PINCFG1_28.Set(sam.PORT.PINCFG1_28.Get()&^(0xff<<24) | (uint32(val) << 24))
+	}
+}

src/machine/machine_attiny.go

@@ -4,6 +4,7 @@ package machine
 
 import (
 	"device/avr"
+	"runtime/volatile"
 )
 
 // Configure sets the pin to input or output.
@@ -15,7 +16,7 @@ func (p Pin) Configure(config PinConfig) {
 	}
 }
 
-func (p Pin) getPortMask() (*avr.Register8, uint8) {
+func (p Pin) getPortMask() (*volatile.Register8, uint8) {
 	return avr.PORTB, 1 << uint8(p)
 }
 

src/machine/machine_avr.go

@@ -4,6 +4,7 @@ package machine
 
 import (
 	"device/avr"
+	"runtime/volatile"
 )
 
 type PinMode uint8
@@ -30,7 +31,7 @@ func (p Pin) Set(value bool) {
 // Warning: there are no separate pin set/clear registers on the AVR. The
 // returned mask is only valid as long as no other pin in the same port has been
 // changed.
-func (p Pin) PortMaskSet() (*avr.Register8, uint8) {
+func (p Pin) PortMaskSet() (*volatile.Register8, uint8) {
 	port, mask := p.getPortMask()
 	return port, port.Get() | mask
 }
@@ -41,7 +42,7 @@ func (p Pin) PortMaskSet() (*avr.Register8, uint8) {
 // Warning: there are no separate pin set/clear registers on the AVR. The
 // returned mask is only valid as long as no other pin in the same port has been
 // changed.
-func (p Pin) PortMaskClear() (*avr.Register8, uint8) {
+func (p Pin) PortMaskClear() (*volatile.Register8, uint8) {
 	port, mask := p.getPortMask()
 	return port, port.Get() &^ mask
 }

src/machine/machine_dummy.go

@@ -1,40 +0,0 @@
-// +build !avr,!nrf,!sam,!stm32
-
-package machine
-
-// Dummy machine package, filled with no-ops.
-
-type PinMode uint8
-
-const (
-	PinInput PinMode = iota
-	PinOutput
-)
-
-// Fake LED numbers, for testing.
-const (
-	LED  Pin = LED1
-	LED1 Pin = 0
-	LED2 Pin = 0
-	LED3 Pin = 0
-	LED4 Pin = 0
-)
-
-// Fake button numbers, for testing.
-const (
-	BUTTON  Pin = BUTTON1
-	BUTTON1 Pin = 0
-	BUTTON2 Pin = 0
-	BUTTON3 Pin = 0
-	BUTTON4 Pin = 0
-)
-
-func (p Pin) Configure(config PinConfig) {
-}
-
-func (p Pin) Set(value bool) {
-}
-
-func (p Pin) Get() bool {
-	return false
-}

src/machine/machine_fe310.go

@@ -0,0 +1,54 @@
+// +build fe310
+
+package machine
+
+import (
+	"device/sifive"
+)
+
+type PinMode uint8
+
+const (
+	PinInput PinMode = iota
+	PinOutput
+)
+
+// Configure this pin with the given configuration.
+func (p Pin) Configure(config PinConfig) {
+	sifive.GPIO0.INPUT_EN.SetBits(1 << uint8(p))
+	if config.Mode == PinOutput {
+		sifive.GPIO0.OUTPUT_EN.SetBits(1 << uint8(p))
+	}
+}
+
+// Set the pin to high or low.
+func (p Pin) Set(high bool) {
+	if high {
+		sifive.GPIO0.PORT.SetBits(1 << uint8(p))
+	} else {
+		sifive.GPIO0.PORT.ClearBits(1 << uint8(p))
+	}
+}
+
+type UART struct {
+	Bus    *sifive.UART_Type
+	Buffer *RingBuffer
+}
+
+var (
+	UART0 = UART{Bus: sifive.UART0, Buffer: NewRingBuffer()}
+)
+
+func (uart UART) Configure(config UARTConfig) {
+	// Assuming a 16Mhz Crystal (which is Y1 on the HiFive1), the divisor for a
+	// 115200 baud rate is 138.
+	sifive.UART0.DIV.Set(138)
+	sifive.UART0.TXCTRL.Set(sifive.UART_TXCTRL_ENABLE)
+}
+
+func (uart UART) WriteByte(c byte) {
+	for sifive.UART0.TXDATA.Get()&sifive.UART_TXDATA_FULL != 0 {
+	}
+
+	sifive.UART0.TXDATA.Set(uint32(c))
+}

src/machine/machine_gameboyadvance.go

@@ -0,0 +1,44 @@
+// +build gameboyadvance
+
+package machine
+
+import (
+	"image/color"
+	"runtime/volatile"
+	"unsafe"
+)
+
+// Make it easier to directly write to I/O RAM.
+var ioram = (*[0x400]volatile.Register8)(unsafe.Pointer(uintptr(0x04000000)))
+
+type PinMode uint8
+
+// Set has not been implemented.
+func (p Pin) Set(value bool) {
+	// do nothing
+}
+
+var Display = FramebufDisplay{(*[160][240]volatile.Register16)(unsafe.Pointer(uintptr(0x06000000)))}
+
+type FramebufDisplay struct {
+	port *[160][240]volatile.Register16
+}
+
+func (d FramebufDisplay) Configure() {
+	// Write into the I/O registers, setting video display parameters.
+	ioram[0].Set(0x03) // Use video mode 3 (in BG2, a 16bpp bitmap in VRAM)
+	ioram[1].Set(0x04) // Enable BG2 (BG0 = 1, BG1 = 2, BG2 = 4, ...)
+}
+
+func (d FramebufDisplay) Size() (x, y int16) {
+	return 240, 160
+}
+
+func (d FramebufDisplay) SetPixel(x, y int16, c color.RGBA) {
+	d.port[y][x].Set(uint16(c.R)&0x1f | uint16(c.G)&0x1f<<5 | uint16(c.B)&0x1f<<10)
+}
+
+func (d FramebufDisplay) Display() error {
+	// Nothing to do here.
+	return nil
+}

src/machine/machine_generic.go

@@ -0,0 +1,184 @@
+// +build !baremetal
+
+package machine
+
+// Dummy machine package that calls out to external functions.
+
+var (
+	SPI0  = SPI{0}
+	I2C0  = I2C{0}
+	UART0 = UART{0}
+)
+
+type PinMode uint8
+
+const (
+	PinInput PinMode = iota
+	PinOutput
+	PinInputPullup
+	PinInputPulldown
+)
+
+func (p Pin) Configure(config PinConfig) {
+	gpioConfigure(p, config)
+}
+
+func (p Pin) Set(value bool) {
+	gpioSet(p, value)
+}
+
+func (p Pin) Get() bool {
+	return gpioGet(p)
+}
+
+//go:export __tinygo_gpio_configure
+func gpioConfigure(pin Pin, config PinConfig)
+
+//go:export __tinygo_gpio_set
+func gpioSet(pin Pin, value bool)
+
+//go:export __tinygo_gpio_get
+func gpioGet(pin Pin) bool
+
+type SPI struct {
+	Bus uint8
+}
+
+type SPIConfig struct {
+	Frequency uint32
+	SCK       Pin
+	MOSI      Pin
+	MISO      Pin
+	Mode      uint8
+}
+
+func (spi SPI) Configure(config SPIConfig) {
+	spiConfigure(spi.Bus, config.SCK, config.MOSI, config.MISO)
+}
+
+// Transfer writes/reads a single byte using the SPI interface.
+func (spi SPI) Transfer(w byte) (byte, error) {
+	return spiTransfer(spi.Bus, w), nil
+}
+
+//go:export __tinygo_spi_configure
+func spiConfigure(bus uint8, sck Pin, mosi Pin, miso Pin)
+
+//go:export __tinygo_spi_transfer
+func spiTransfer(bus uint8, w uint8) uint8
+
+// InitADC enables support for ADC peripherals.
+func InitADC() {
+	// Nothing to do here.
+}
+
+// Configure configures an ADC pin to be able to be used to read data.
+func (adc ADC) Configure() {
+}
+
+// Get reads the current analog value from this ADC peripheral.
+func (adc ADC) Get() uint16 {
+	return adcRead(adc.Pin)
+}
+
+//go:export __tinygo_adc_read
+func adcRead(pin Pin) uint16
+
+// InitPWM enables support for PWM peripherals.
+func InitPWM() {
+	// Nothing to do here.
+}
+
+// Configure configures a PWM pin for output.
+func (pwm PWM) Configure() {
+}
+
+// Set turns on the duty cycle for a PWM pin using the provided value.
+func (pwm PWM) Set(value uint16) {
+	pwmSet(pwm.Pin, value)
+}
+
+//go:export __tinygo_pwm_set
+func pwmSet(pin Pin, value uint16)
+
+// I2C is a generic implementation of the Inter-IC communication protocol.
+type I2C struct {
+	Bus uint8
+}
+
+// I2CConfig is used to store config info for I2C.
+type I2CConfig struct {
+	Frequency uint32
+	SCL       Pin
+	SDA       Pin
+}
+
+// Configure is intended to setup the I2C interface.
+func (i2c I2C) Configure(config I2CConfig) {
+	i2cConfigure(i2c.Bus, config.SCL, config.SDA)
+}
+
+// Tx does a single I2C transaction at the specified address.
+func (i2c I2C) Tx(addr uint16, w, r []byte) error {
+	i2cTransfer(i2c.Bus, &w[0], len(w), &r[0], len(r))
+	// TODO: do something with the returned error code.
+	return nil
+}
+
+//go:export __tinygo_i2c_configure
+func i2cConfigure(bus uint8, scl Pin, sda Pin)
+
+//go:export __tinygo_i2c_transfer
+func i2cTransfer(bus uint8, w *byte, wlen int, r *byte, rlen int) int
+
+type UART struct {
+	Bus uint8
+}
+
+type UARTConfig struct {
+	BaudRate uint32
+	TX       Pin
+	RX       Pin
+}
+
+// Configure the UART.
+func (uart UART) Configure(config UARTConfig) {
+	uartConfigure(uart.Bus, config.TX, config.RX)
+}
+
+// Read from the UART.
+func (uart UART) Read(data []byte) (n int, err error) {
+	return uartRead(uart.Bus, &data[0], len(data)), nil
+}
+
+// Write to the UART.
+func (uart UART) Write(data []byte) (n int, err error) {
+	return uartWrite(uart.Bus, &data[0], len(data)), nil
+}
+
+// Buffered returns the number of bytes currently stored in the RX buffer.
+func (uart UART) Buffered() int {
+	return 0
+}
+
+// ReadByte reads a single byte from the UART.
+func (uart UART) ReadByte() (byte, error) {
+	var b byte
+	uartRead(uart.Bus, &b, 1)
+	return b, nil
+}
+
+// WriteByte writes a single byte to the UART.
+func (uart UART) WriteByte(b byte) error {
+	uartWrite(uart.Bus, &b, 1)
+	return nil
+}
+
+//go:export __tinygo_uart_configure
+func uartConfigure(bus uint8, tx Pin, rx Pin)
+
+//go:export __tinygo_uart_read
+func uartRead(bus uint8, buf *byte, bufLen int) int
+
+//go:export __tinygo_uart_write
+func uartWrite(bus uint8, buf *byte, bufLen int) int

src/machine/machine_nrf.go

@@ -5,6 +5,12 @@ package machine
 import (
 	"device/arm"
 	"device/nrf"
+	"errors"
+)
+
+var (
+	ErrTxSlicesRequired   = errors.New("SPI Tx requires a write or read slice, or both")
+	ErrTxInvalidSliceSize = errors.New("SPI write and read slices must be same size")
 )
 
 type PinMode uint8
@@ -322,3 +328,70 @@ func (spi SPI) Transfer(w byte) (byte, error) {
 	// TODO: handle SPI errors
 	return byte(r), nil
 }
+
+// Tx handles read/write operation for SPI interface. Since SPI is a syncronous write/read
+// interface, there must always be the same number of bytes written as bytes read.
+// The Tx method knows about this, and offers a few different ways of calling it.
+//
+// This form sends the bytes in tx buffer, putting the resulting bytes read into the rx buffer.
+// Note that the tx and rx buffers must be the same size:
+//
+// 		spi.Tx(tx, rx)
+//
+// This form sends the tx buffer, ignoring the result. Useful for sending "commands" that return zeros
+// until all the bytes in the command packet have been received:
+//
+// 		spi.Tx(tx, nil)
+//
+// This form sends zeros, putting the result into the rx buffer. Good for reading a "result packet":
+//
+// 		spi.Tx(nil, rx)
+//
+func (spi SPI) Tx(w, r []byte) error {
+	if w == nil && r == nil {
+		return ErrTxSlicesRequired
+	}
+
+	var err error
+
+	switch {
+	case len(w) == 0:
+		// read only, so write zero and read a result.
+		for i := range r {
+			r[i], err = spi.Transfer(0)
+			if err != nil {
+				return err
+			}
+		}
+	case len(r) == 0:
+		// write only
+		spi.Bus.TXD.Set(uint32(w[0]))
+		w = w[1:]
+		for _, b := range w {
+			spi.Bus.TXD.Set(uint32(b))
+			for spi.Bus.EVENTS_READY.Get() == 0 {
+			}
+			_ = spi.Bus.RXD.Get()
+			spi.Bus.EVENTS_READY.Set(0)
+		}
+		for spi.Bus.EVENTS_READY.Get() == 0 {
+		}
+		_ = spi.Bus.RXD.Get()
+		spi.Bus.EVENTS_READY.Set(0)
+
+	default:
+		// write/read
+		if len(w) != len(r) {
+			return ErrTxInvalidSliceSize
+		}
+
+		for i, b := range w {
+			r[i], err = spi.Transfer(b)
+			if err != nil {
+				return err
+			}
+		}
+	}
+
+	return nil
+}

src/machine/machine_stm32.go

@@ -5,14 +5,3 @@ package machine
 // Peripheral abstraction layer for the stm32.
 
 type PinMode uint8
-
-const (
-	portA Pin = iota * 16
-	portB
-	portC
-	portD
-	portE
-	portF
-	portG
-	portH
-)

src/machine/machine_stm32f103xx.go

@@ -99,18 +99,21 @@ func (p Pin) Set(high bool) {
 	}
 }
 
+// Get returns the current value of a GPIO pin.
+func (p Pin) Get() bool {
+	port := p.getPort()
+	pin := uint8(p) % 16
+	val := port.IDR.Get() & (1 << pin)
+	return (val > 0)
+}
+
 // UART
 type UART struct {
 	Buffer *RingBuffer
+	Bus    *stm32.USART_Type
+	IRQVal uint32
 }
 
-var (
-	// USART1 is the first hardware serial port on the STM32.
-	// Both UART0 and UART1 refer to USART1.
-	UART0 = UART{Buffer: NewRingBuffer()}
-	UART1 = &UART0
-)
-
 // Configure the UART.
 func (uart UART) Configure(config UARTConfig) {
 	// Default baud rate to 115200.
@@ -120,53 +123,63 @@ func (uart UART) Configure(config UARTConfig) {
 
 	// pins
 	switch config.TX {
-	case PB6:
-		// use alternate TX/RX pins PB6/PB7 via AFIO mapping
+	case UART_ALT_TX_PIN:
+		// use alternate TX/RX pins via AFIO mapping
 		stm32.RCC.APB2ENR.SetBits(stm32.RCC_APB2ENR_AFIOEN)
-		stm32.AFIO.MAPR.SetBits(stm32.AFIO_MAPR_USART1_REMAP)
-		PB6.Configure(PinConfig{Mode: PinOutput50MHz + PinOutputModeAltPushPull})
-		PB7.Configure(PinConfig{Mode: PinInputModeFloating})
+		if uart.Bus == stm32.USART1 {
+			stm32.AFIO.MAPR.SetBits(stm32.AFIO_MAPR_USART1_REMAP)
+		} else if uart.Bus == stm32.USART2 {
+			stm32.AFIO.MAPR.SetBits(stm32.AFIO_MAPR_USART2_REMAP)
+		}
+		UART_ALT_TX_PIN.Configure(PinConfig{Mode: PinOutput50MHz + PinOutputModeAltPushPull})
+		UART_ALT_RX_PIN.Configure(PinConfig{Mode: PinInputModeFloating})
 	default:
 		// use standard TX/RX pins PA9 and PA10
 		UART_TX_PIN.Configure(PinConfig{Mode: PinOutput50MHz + PinOutputModeAltPushPull})
 		UART_RX_PIN.Configure(PinConfig{Mode: PinInputModeFloating})
 	}
 
-	// Enable USART1 clock
-	stm32.RCC.APB2ENR.SetBits(stm32.RCC_APB2ENR_USART1EN)
+	// Enable USART clock
+	if uart.Bus == stm32.USART1 {
+		stm32.RCC.APB2ENR.SetBits(stm32.RCC_APB2ENR_USART1EN)
+	} else if uart.Bus == stm32.USART2 {
+		stm32.RCC.APB1ENR.SetBits(stm32.RCC_APB1ENR_USART2EN)
+	}
 
 	// Set baud rate
 	uart.SetBaudRate(config.BaudRate)
 
-	// Enable USART1 port.
-	stm32.USART1.CR1.Set(stm32.USART_CR1_TE | stm32.USART_CR1_RE | stm32.USART_CR1_RXNEIE | stm32.USART_CR1_UE)
+	// Enable USART port
+	uart.Bus.CR1.Set(stm32.USART_CR1_TE | stm32.USART_CR1_RE | stm32.USART_CR1_RXNEIE | stm32.USART_CR1_UE)
 
-	// Enable RX IRQ.
-	arm.SetPriority(stm32.IRQ_USART1, 0xc0)
-	arm.EnableIRQ(stm32.IRQ_USART1)
+	// Enable RX IRQ
+	arm.SetPriority(uart.IRQVal, 0xc0)
+	arm.EnableIRQ(uart.IRQVal)
 }
 
 // SetBaudRate sets the communication speed for the UART.
 func (uart UART) SetBaudRate(br uint32) {
-	// first divide by PCLK2 prescaler (div 1) and then desired baudrate
-	divider := CPU_FREQUENCY / br
-	stm32.USART1.BRR.Set(divider)
+	// Note: PCLK2 (from APB2) used for USART1 and PCLK1 for USART2, 3, 4, 5
+	var divider uint32
+	if uart.Bus == stm32.USART1 {
+		// first divide by PCLK2 prescaler (div 1) and then desired baudrate
+		divider = CPU_FREQUENCY / br
+	} else {
+		// first divide by PCLK1 prescaler (div 2) and then desired baudrate
+		divider = CPU_FREQUENCY / 2 / br
+	}
+	uart.Bus.BRR.Set(divider)
 }
 
 // WriteByte writes a byte of data to the UART.
 func (uart UART) WriteByte(c byte) error {
-	stm32.USART1.DR.Set(uint32(c))
+	uart.Bus.DR.Set(uint32(c))
 
-	for !stm32.USART1.SR.HasBits(stm32.USART_SR_TXE) {
+	for !uart.Bus.SR.HasBits(stm32.USART_SR_TXE) {
 	}
 	return nil
 }
 
-//go:export USART1_IRQHandler
-func handleUART1() {
-	UART1.Receive(byte((stm32.USART1.DR.Get() & 0xFF)))
-}
-
 // SPI on the STM32.
 type SPI struct {
 	Bus *stm32.SPI_Type
@@ -202,24 +215,25 @@ func (spi SPI) Configure(config SPIConfig) {
 
 	var conf uint32
 
-	// set frequency
+	// set frequency dependent on PCLK2 prescaler (div 1)
 	switch config.Frequency {
 	case 125000:
-		conf |= stm32.SPI_BaudRatePrescaler_128
+		// Note: impossible to achieve lower frequency with current PCLK2!
+		conf |= stm32.SPI_BaudRatePrescaler_256
 	case 250000:
-		conf |= stm32.SPI_BaudRatePrescaler_64
+		conf |= stm32.SPI_BaudRatePrescaler_256
 	case 500000:
-		conf |= stm32.SPI_BaudRatePrescaler_32
-	case 1000000:
-		conf |= stm32.SPI_BaudRatePrescaler_16
-	case 2000000:
-		conf |= stm32.SPI_BaudRatePrescaler_8
-	case 4000000:
-		conf |= stm32.SPI_BaudRatePrescaler_4
-	case 8000000:
-		conf |= stm32.SPI_BaudRatePrescaler_2
-	default:
 		conf |= stm32.SPI_BaudRatePrescaler_128
+	case 1000000:
+		conf |= stm32.SPI_BaudRatePrescaler_64
+	case 2000000:
+		conf |= stm32.SPI_BaudRatePrescaler_32
+	case 4000000:
+		conf |= stm32.SPI_BaudRatePrescaler_16
+	case 8000000:
+		conf |= stm32.SPI_BaudRatePrescaler_8
+	default:
+		conf |= stm32.SPI_BaudRatePrescaler_256
 	}
 
 	// set bit transfer order
@@ -345,11 +359,11 @@ func (i2c I2C) Configure(config I2CConfig) {
 	// Disable the selected I2C peripheral to configure
 	i2c.Bus.CR1.ClearBits(stm32.I2C_CR1_PE)
 
-	// pclk1 clock speed is main frequency divided by PCK1 prescaler (div 2)
+	// pclk1 clock speed is main frequency divided by PCLK1 prescaler (div 2)
 	pclk1 := uint32(CPU_FREQUENCY / 2)
 
-	// set freqency range to pclk1 clock speed in Mhz.
-	// aka setting the value 36 means to use 36MhZ clock.
+	// set freqency range to PCLK1 clock speed in MHz
+	// aka setting the value 36 means to use 36 MHz clock
 	pclk1Mhz := pclk1 / 1000000
 	i2c.Bus.CR2.SetBits(pclk1Mhz)
 

src/machine/spi.go

@@ -1,4 +1,4 @@
-// +build nrf stm32f103xx atsamd21g18a
+// +build sam stm32,!stm32f407
 
 package machine
 

src/machine/uart.go

@@ -1,4 +1,4 @@
-// +build avr nrf sam stm32
+// +build avr nrf sam sifive stm32
 
 package machine
 

src/machine/usb.go

@@ -4,9 +4,9 @@ package machine
 
 import (
 	"bytes"
-	"device/sam"
 	"encoding/binary"
 	"errors"
+	"runtime/volatile"
 )
 
 const deviceDescriptorSize = 18
@@ -316,8 +316,8 @@ func NewCDCDescriptor(i IADDescriptor, c InterfaceDescriptor,
 	callm CMFunctionalDescriptor,
 	ci EndpointDescriptor,
 	di InterfaceDescriptor,
-	inp EndpointDescriptor,
-	outp EndpointDescriptor) CDCDescriptor {
+	outp EndpointDescriptor,
+	inp EndpointDescriptor) CDCDescriptor {
 	return CDCDescriptor{iad: i,
 		cif:                  c,
 		header:               h,
@@ -352,8 +352,8 @@ func (d CDCDescriptor) Bytes() []byte {
 	buf.Write(d.callManagement.Bytes())
 	buf.Write(d.cifin.Bytes())
 	buf.Write(d.dif.Bytes())
-	buf.Write(d.in.Bytes())
 	buf.Write(d.out.Bytes())
+	buf.Write(d.in.Bytes())
 	return buf.Bytes()
 }
 
@@ -473,6 +473,9 @@ const (
 	usb_CDC_CS_INTERFACE                = 0x24
 	usb_CDC_CS_ENDPOINT                 = 0x25
 	usb_CDC_DATA_INTERFACE_CLASS        = 0x0A
+
+	usb_CDC_LINESTATE_DTR = 0x01
+	usb_CDC_LINESTATE_RTS = 0x02
 )
 
 // usbDeviceDescBank is the USB device endpoint descriptor.
@@ -484,11 +487,11 @@ const (
 // 		 RoReg8                    Reserved1[0x5];
 //   } UsbDeviceDescBank;
 type usbDeviceDescBank struct {
-	ADDR      sam.Register32
-	PCKSIZE   sam.Register32
-	EXTREG    sam.Register16
-	STATUS_BK sam.Register8
-	_reserved [5]sam.Register8
+	ADDR      volatile.Register32
+	PCKSIZE   volatile.Register32
+	EXTREG    volatile.Register16
+	STATUS_BK volatile.Register8
+	_reserved [5]volatile.Register8
 }
 
 type usbDeviceDescriptor struct {

src/os/file.go

@@ -11,7 +11,8 @@ import (
 
 // Portable analogs of some common system call errors.
 var (
-	ErrUnsupported = errors.New("operation not supported")
+	errUnsupported = errors.New("operation not supported")
+	notImplemented = errors.New("os: not implemented")
 )
 
 // Stdin, Stdout, and Stderr are open Files pointing to the standard input,
@@ -28,6 +29,21 @@ type File struct {
 	name string
 }
 
+// Readdir is a stub, not yet implemented
+func (f *File) Readdir(n int) ([]FileInfo, error) {
+	return nil, notImplemented
+}
+
+// Readdirnames is a stub, not yet implemented
+func (f *File) Readdirnames(n int) (names []string, err error) {
+	return nil, notImplemented
+}
+
+// Stat is a stub, not yet implemented
+func (f *File) Stat() (FileInfo, error) {
+	return nil, notImplemented
+}
+
 // NewFile returns a new File with the given file descriptor and name.
 func NewFile(fd uintptr, name string) *File {
 	return &File{fd, name}
@@ -38,3 +54,146 @@ func NewFile(fd uintptr, name string) *File {
 func (f *File) Fd() uintptr {
 	return f.fd
 }
+
+const (
+	PathSeparator     = '/' // OS-specific path separator
+	PathListSeparator = ':' // OS-specific path list separator
+)
+
+// IsPathSeparator reports whether c is a directory separator character.
+func IsPathSeparator(c uint8) bool {
+	return PathSeparator == c
+}
+
+// PathError records an error and the operation and file path that caused it.
+type PathError struct {
+	Op   string
+	Path string
+	Err  error
+}
+
+func (e *PathError) Error() string { return e.Op + " " + e.Path + ": " + e.Err.Error() }
+
+// Open is a super simple stub function (for now), only capable of opening stdin, stdout, and stderr
+func Open(name string) (*File, error) {
+	fd := uintptr(999)
+	switch name {
+	case "/dev/stdin":
+		fd = 0
+	case "/dev/stdout":
+		fd = 1
+	case "/dev/stderr":
+		fd = 2
+	default:
+		return nil, &PathError{"open", name, notImplemented}
+	}
+	return &File{fd, name}, nil
+}
+
+// OpenFile is a stub, passing through to the stub Open() call
+func OpenFile(name string, flag int, perm FileMode) (*File, error) {
+	return Open(name)
+}
+
+// Create is a stub, passing through to the stub Open() call
+func Create(name string) (*File, error) {
+	return Open(name)
+}
+
+type FileMode uint32
+
+// Mode constants, copied from the mainline Go source
+// https://github.com/golang/go/blob/4ce6a8e89668b87dce67e2f55802903d6eb9110a/src/os/types.go#L35-L63
+const (
+	// The single letters are the abbreviations used by the String method's formatting.
+	ModeDir        FileMode = 1 << (32 - 1 - iota) // d: is a directory
+	ModeAppend                                     // a: append-only
+	ModeExclusive                                  // l: exclusive use
+	ModeTemporary                                  // T: temporary file; Plan 9 only
+	ModeSymlink                                    // L: symbolic link
+	ModeDevice                                     // D: device file
+	ModeNamedPipe                                  // p: named pipe (FIFO)
+	ModeSocket                                     // S: Unix domain socket
+	ModeSetuid                                     // u: setuid
+	ModeSetgid                                     // g: setgid
+	ModeCharDevice                                 // c: Unix character device, when ModeDevice is set
+	ModeSticky                                     // t: sticky
+	ModeIrregular                                  // ?: non-regular file; nothing else is known about this file
+
+	// Mask for the type bits. For regular files, none will be set.
+	ModeType = ModeDir | ModeSymlink | ModeNamedPipe | ModeSocket | ModeDevice | ModeCharDevice | ModeIrregular
+
+	ModePerm FileMode = 0777 // Unix permission bits
+)
+
+// IsDir is a stub, always returning false
+func (m FileMode) IsDir() bool {
+	return false
+}
+
+// Stub constants
+const (
+	O_RDONLY int = 1
+	O_WRONLY int = 2
+	O_RDWR   int = 4
+	O_APPEND int = 8
+	O_CREATE int = 16
+	O_EXCL   int = 32
+	O_SYNC   int = 64
+	O_TRUNC  int = 128
+)
+
+// A FileInfo describes a file and is returned by Stat and Lstat.
+type FileInfo interface {
+	Name() string   // base name of the file
+	Size() int64    // length in bytes for regular files; system-dependent for others
+	Mode() FileMode // file mode bits
+	// ModTime() time.Time // modification time
+	IsDir() bool      // abbreviation for Mode().IsDir()
+	Sys() interface{} // underlying data source (can return nil)
+}
+
+// Stat is a stub, not yet implemented
+func Stat(name string) (FileInfo, error) {
+	return nil, notImplemented
+}
+
+// Lstat is a stub, not yet implemented
+func Lstat(name string) (FileInfo, error) {
+	return nil, notImplemented
+}
+
+// Getwd is a stub (for now), always returning an empty string
+func Getwd() (string, error) {
+	return "", nil
+}
+
+// Readlink is a stub (for now), always returning the string it was given
+func Readlink(name string) (string, error) {
+	return name, nil
+}
+
+// TempDir is a stub (for now), always returning the string "/tmp"
+func TempDir() string {
+	return "/tmp"
+}
+
+// Mkdir is a stub, not yet implemented
+func Mkdir(name string, perm FileMode) error {
+	return notImplemented
+}
+
+// IsExist is a stub (for now), always returning false
+func IsExist(err error) bool {
+	return false
+}
+
+// IsNotExist is a stub (for now), always returning false
+func IsNotExist(err error) bool {
+	return false
+}
+
+// Getpid is a stub (for now), always returning 1
+func Getpid() int {
+	return 1
+}

src/os/file_other.go

@@ -1,4 +1,4 @@
-// +build avr cortexm wasm
+// +build baremetal wasm
 
 package os
 
@@ -8,7 +8,7 @@ import (
 
 // Read is unsupported on this system.
 func (f *File) Read(b []byte) (n int, err error) {
-	return 0, ErrUnsupported
+	return 0, errUnsupported
 }
 
 // Write writes len(b) bytes to the output. It returns the number of bytes
@@ -21,13 +21,13 @@ func (f *File) Write(b []byte) (n int, err error) {
 		}
 		return len(b), nil
 	default:
-		return 0, ErrUnsupported
+		return 0, errUnsupported
 	}
 }
 
 // Close is unsupported on this system.
 func (f *File) Close() error {
-	return ErrUnsupported
+	return errUnsupported
 }
 
 //go:linkname putchar runtime.putchar