apa102: use 4-byte buffer to improve speed

Instead of sending the APA102 data byte by byte, it's more efficient to
send multiple bytes at once (especially when the SPI peripheral uses
DMA). This requires the apa102.Device object to be a pointer receiver to
avoid excessive heap allocations.

This commit also just happens to work around a hardware bug on the
nrf52832:
https://infocenter.nordicsemi.com/index.jsp?topic=%2Ferrata_nRF52832_Rev2%2FERR%2FnRF52832%2FRev2%2Flatest%2Fanomaly_832_58.html&anchor=anomaly_832_58

apa102/apa102.go

@@ -27,44 +27,46 @@ var startFrame = []byte{0x00, 0x00, 0x00, 0x00}
 type Device struct {
 	bus   drivers.SPI
 	Order int
+	buf   [4]byte
 }
 
 // New returns a new APA102 driver. Pass in a fully configured SPI bus.
-func New(b drivers.SPI) Device {
-	return Device{bus: b, Order: BGR}
+func New(b drivers.SPI) *Device {
+	return &Device{bus: b, Order: BGR}
 }
 
 // NewSoftwareSPI returns a new APA102 driver that will use a software based
 // implementation of the SPI protocol.
-func NewSoftwareSPI(sckPin, sdoPin machine.Pin, delay uint32) Device {
+func NewSoftwareSPI(sckPin, sdoPin machine.Pin, delay uint32) *Device {
 	return New(&bbSPI{SCK: sckPin, SDO: sdoPin, Delay: delay})
 }
 
 // WriteColors writes the given RGBA color slice out using the APA102 protocol.
 // The A value (Alpha channel) is used for brightness, set to 0xff (255) for maximum.
-func (d Device) WriteColors(cs []color.RGBA) (n int, err error) {
+func (d *Device) WriteColors(cs []color.RGBA) (n int, err error) {
 	d.startFrame()
 
 	// write data
 	for _, c := range cs {
 		// brightness is scaled to 5 bit value
-		d.bus.Transfer(0xe0 | (c.A >> 3))
+		d.buf[0] = 0xe0 | (c.A >> 3)
 
 		// set the colors
 		switch d.Order {
 		case BRG:
-			d.bus.Transfer(c.B)
-			d.bus.Transfer(c.R)
-			d.bus.Transfer(c.G)
+			d.buf[1] = c.B
+			d.buf[2] = c.R
+			d.buf[3] = c.G
 		case GRB:
-			d.bus.Transfer(c.G)
-			d.bus.Transfer(c.R)
-			d.bus.Transfer(c.B)
+			d.buf[1] = c.G
+			d.buf[2] = c.R
+			d.buf[3] = c.B
 		case BGR:
-			d.bus.Transfer(c.B)
-			d.bus.Transfer(c.G)
-			d.bus.Transfer(c.R)
+			d.buf[1] = c.B
+			d.buf[2] = c.G
+			d.buf[3] = c.R
 		}
+		d.bus.Tx(d.buf[:], nil)
 	}
 
 	d.endFrame(len(cs))
@@ -73,7 +75,7 @@ func (d Device) WriteColors(cs []color.RGBA) (n int, err error) {
 }
 
 // Write the raw bytes using the APA102 protocol.
-func (d Device) Write(buf []byte) (n int, err error) {
+func (d *Device) Write(buf []byte) (n int, err error) {
 	d.startFrame()
 	d.bus.Tx(buf, nil)
 	d.endFrame(len(buf) / 4)
@@ -82,14 +84,14 @@ func (d Device) Write(buf []byte) (n int, err error) {
 }
 
 // startFrame sends the start bytes for a strand of LEDs.
-func (d Device) startFrame() {
+func (d *Device) startFrame() {
 	d.bus.Tx(startFrame, nil)
 }
 
 // endFrame sends the end frame marker with one extra bit per LED so
 // long strands of LEDs receive the necessary termination for updates.
 // See https://cpldcpu.wordpress.com/2014/11/30/understanding-the-apa102-superled/
-func (d Device) endFrame(count int) {
+func (d *Device) endFrame(count int) {
 	for i := 0; i < count/16; i++ {
 		d.bus.Transfer(0xff)
 	}

examples/apa102/itsybitsy-m0/main.go

@@ -13,7 +13,7 @@ import (
 )
 
 var (
-	apa apa102.Device
+	apa *apa102.Device
 
 	pwm   = machine.TCC0
 	leds  = make([]color.RGBA, 1)