diff --git a/ws2812/ws2812_m4_64m.go b/ws2812/ws2812_m4_64m.go
index 4090b80..2cb330c 100644
--- a/ws2812/ws2812_m4_64m.go
+++ b/ws2812/ws2812_m4_64m.go
@@ -17,12 +17,12 @@ func (d Device) WriteByte(c byte) error {
 
 	// See:
 	// https://wp.josh.com/2014/05/13/ws2812-neopixels-are-not-so-finicky-once-you-get-to-know-them/
-	// T0H: 14-16 cycles or  218.75ns -  250.00ns
+	// T0H: 17-19 cycles or  265.63ns -  296.88ns
 	// T0L: 54-56 cycles or  843.75ns -  875.00ns
-	//   +: 68-72 cycles or 1062.50ns - 1125.00ns
-	// T1H: 36-38 cycles or  562.50ns -  593.75ns
+	//   +: 71-75 cycles or 1109.38ns - 1171.88ns
+	// T1H: 39-41 cycles or  609.38ns -  640.63ns
 	// T1L: 30-32 cycles or  468.75ns -  500.0ns
-	//   +: 66-70 cycles or 1031.25ns - 1093.75ns
+	//   +: 69-73 cycles or 1078.13ns - 1140.63ns
 	// A branch is treated here as 1-3 cycles, because apparently it might get
 	// speculated. This is more of a guess than hard fact, because the only docs
 	// by ARM that state this are now considered superseded (by what?).
@@ -41,6 +41,9 @@ func (d Device) WriteByte(c byte) error {
 		nop
 		nop
 		nop
+		nop
+		nop
+		nop
 		bcs.n skip_store               @ [1-3]
 		str   {maskClear}, {portClear} @ [2]   T0H -> T0L transition
 	skip_store: