ws2812: support high-MHz ARMv6M chips like the RP2040

The possible branch distance is a lot shorter on ARMv6M (Cortex-M and
Cortex-M0+) for conditional branches. Therefore, convert this long
conditional branch into an unconditional branch.

This probably makes the code a little bit slower but because it is in
the low period of the WS2812 signal it shouldn't matter for the
protocol. And it avoids difficult workarounds specifically for the
RP2040.

ws2812/gen-ws2812.go

@@ -59,7 +59,7 @@ var architectures = map[string]architectureImpl{
 		maxBaseCyclesT0H: 1 + 3 + 2, // shift + branch (not taken) + store
 		minBaseCyclesT1H: 1 + 1 + 2, // shift + branch (taken) + store
 		maxBaseCyclesT1H: 1 + 3 + 2, // shift + branch (taken) + store
-		minBaseCyclesTLD: 1 + 1 + 2, // subtraction + branch + store (in next cycle)
+		minBaseCyclesTLD: 1 + 2 + 2, // subtraction + branch x2 + store (in next cycle)
 		valueTemplate:    "uint32(c) << 24",
 		template: `
 1: @ send_bit
@@ -73,7 +73,9 @@ var architectures = map[string]architectureImpl{
   str   {maskClear}, {portClear} @ [2]   T1H -> T1L transition
   @DELAY3
   subs  {i}, #1                  @ [1]
-  bne.n 1b                       @ [1/3] send_bit
+  beq.n 3f                       @ [1/3] end
+  b     1b                       @ [1/3] send_bit
+3: @ end
 `,
 	},
 	"tinygoriscv": {

ws2812/ws2812-asm_cortexm.go

@@ -56,9 +56,10 @@ func (d Device) writeByte16(c byte) {
 	  nop
 	  nop
 	  nop
-	  nop
 	  subs  {i}, #1                  @ [1]
-	  bne.n 1b                       @ [1/3] send_bit
+	  beq.n 3f                       @ [1/3] end
+	  b     1b                       @ [1/3] send_bit
+	3: @ end
 	`, map[string]interface{}{
 		"value":     value,
 		"i":         8,
@@ -186,9 +187,10 @@ func (d Device) writeByte48(c byte) {
 	  nop
 	  nop
 	  nop
-	  nop
 	  subs  {i}, #1                  @ [1]
-	  bne.n 1b                       @ [1/3] send_bit
+	  beq.n 3f                       @ [1/3] end
+	  b     1b                       @ [1/3] send_bit
+	3: @ end
 	`, map[string]interface{}{
 		"value":     value,
 		"i":         8,
@@ -351,9 +353,10 @@ func (d Device) writeByte64(c byte) {
 	  nop
 	  nop
 	  nop
-	  nop
 	  subs  {i}, #1                  @ [1]
-	  bne.n 1b                       @ [1/3] send_bit
+	  beq.n 3f                       @ [1/3] end
+	  b     1b                       @ [1/3] send_bit
+	3: @ end
 	`, map[string]interface{}{
 		"value":     value,
 		"i":         8,
@@ -638,9 +641,10 @@ func (d Device) writeByte120(c byte) {
 	  nop
 	  nop
 	  nop
-	  nop
 	  subs  {i}, #1                  @ [1]
-	  bne.n 1b                       @ [1/3] send_bit
+	  beq.n 3f                       @ [1/3] end
+	  b     1b                       @ [1/3] send_bit
+	3: @ end
 	`, map[string]interface{}{
 		"value":     value,
 		"i":         8,
@@ -1032,9 +1036,10 @@ func (d Device) writeByte168(c byte) {
 	  nop
 	  nop
 	  nop
-	  nop
 	  subs  {i}, #1                  @ [1]
-	  bne.n 1b                       @ [1/3] send_bit
+	  beq.n 3f                       @ [1/3] end
+	  b     1b                       @ [1/3] send_bit
+	3: @ end
 	`, map[string]interface{}{
 		"value":     value,
 		"i":         8,