internal/bytealg: simplify memchr for wasm

Get rid of an extra register R5 which just recalculated the value of R4. Reuse R4 instead. We also remove the casting of c to an unsigned char because the initial load of R0 is done with I32Load8U anyways. Also indent the code to make it more readable. name old time/op new time/op delta IndexRune 597ns ± 3% 580ns ± 3% -2.93% (p=0.002 n=10+10) IndexRuneLongString 634ns ± 4% 654ns ± 3% +3.07% (p=0.004 n=10+10) IndexRuneFastPath 57.6ns ± 3% 56.9ns ± 4% ~ (p=0.210 n=10+10) Index 104ns ± 3% 104ns ± 4% ~ (p=0.639 n=10+10) LastIndex 87.1ns ± 5% 85.7ns ± 3% ~ (p=0.171 n=10+10) IndexByte 34.4ns ± 4% 32.9ns ± 5% -4.28% (p=0.002 n=10+10) IndexHard1 21.6ms ± 1% 21.8ms ± 3% ~ (p=0.460 n=8+10) IndexHard2 21.6ms ± 2% 21.9ms ± 5% ~ (p=0.133 n=9+10) IndexHard3 21.8ms ± 3% 21.7ms ± 1% ~ (p=0.579 n=10+10) IndexHard4 21.6ms ± 1% 21.9ms ± 4% ~ (p=0.360 n=8+10) LastIndexHard1 25.1ms ± 2% 25.4ms ± 5% ~ (p=0.853 n=10+10) LastIndexHard2 25.3ms ± 6% 25.2ms ± 5% ~ (p=0.796 n=10+10) LastIndexHard3 25.3ms ± 4% 25.2ms ± 3% ~ (p=0.739 n=10+10) IndexTorture 130µs ± 3% 133µs ± 5% ~ (p=0.218 n=10+10) IndexAnyASCII/1:1 98.4ns ± 5% 96.6ns ± 5% ~ (p=0.054 n=10+10) IndexAnyASCII/1:2 109ns ± 4% 110ns ± 3% ~ (p=0.232 n=10+10) IndexAnyASCII/1:4 135ns ± 4% 134ns ± 3% ~ (p=0.671 n=10+10) IndexAnyASCII/1:8 184ns ± 4% 184ns ± 3% ~ (p=0.749 n=10+10) IndexAnyASCII/1:16 289ns ± 3% 281ns ± 3% -2.73% (p=0.001 n=9+10) IndexAnyASCII/16:1 322ns ± 3% 307ns ± 3% -4.71% (p=0.000 n=10+10) IndexAnyASCII/16:2 329ns ± 3% 320ns ± 3% -2.89% (p=0.008 n=10+10) IndexAnyASCII/16:4 353ns ± 3% 339ns ± 3% -3.91% (p=0.001 n=10+10) IndexAnyASCII/16:8 390ns ± 3% 374ns ± 3% -4.06% (p=0.000 n=10+10) IndexAnyASCII/16:16 471ns ± 4% 452ns ± 2% -4.22% (p=0.000 n=10+10) IndexAnyASCII/256:1 2.94µs ± 4% 2.91µs ± 2% ~ (p=0.424 n=10+10) IndexAnyASCII/256:2 2.92µs ± 3% 2.90µs ± 2% ~ (p=0.388 n=9+10) IndexAnyASCII/256:4 2.93µs ± 1% 2.90µs ± 1% -0.98% (p=0.036 n=8+9) IndexAnyASCII/256:8 3.03µs ± 5% 2.97µs ± 3% ~ (p=0.085 n=10+10) IndexAnyASCII/256:16 3.07µs ± 4% 3.01µs ± 1% -2.03% (p=0.003 n=10+9) IndexAnyASCII/4096:1 45.8µs ± 3% 45.9µs ± 2% ~ (p=0.905 n=10+9) IndexAnyASCII/4096:2 46.7µs ± 3% 46.2µs ± 3% ~ (p=0.190 n=10+10) IndexAnyASCII/4096:4 45.7µs ± 2% 46.4µs ± 3% +1.37% (p=0.022 n=9+10) IndexAnyASCII/4096:8 46.4µs ± 3% 46.0µs ± 2% ~ (p=0.436 n=10+10) IndexAnyASCII/4096:16 46.6µs ± 3% 46.7µs ± 2% ~ (p=0.971 n=10+10) IndexPeriodic/IndexPeriodic2 1.40ms ± 3% 1.40ms ± 2% ~ (p=0.853 n=10+10) IndexPeriodic/IndexPeriodic4 1.40ms ± 3% 1.40ms ± 3% ~ (p=0.579 n=10+10) IndexPeriodic/IndexPeriodic8 1.42ms ± 3% 1.39ms ± 2% -1.60% (p=0.029 n=10+10) IndexPeriodic/IndexPeriodic16 616µs ± 5% 583µs ± 5% -5.32% (p=0.001 n=10+10) IndexPeriodic/IndexPeriodic32 313µs ± 5% 301µs ± 2% -3.67% (p=0.002 n=10+10) IndexPeriodic/IndexPeriodic64 169µs ± 5% 164µs ± 5% -3.17% (p=0.023 n=10+10) NodeJS version - 10.2.1 Change-Id: I9a8268314b5652c4aeffc4c5c72d2fd1a384aa9e Reviewed-on: https://go-review.googlesource.com/c/go/+/169777 Run-TryBot: Agniva De Sarker <agniva.quicksilver@gmail.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Cherry Zhang <cherryyz@google.com>
remyoudompheng · Mar 29, 2019 · 4a7cd9d · 4a7cd9d
1 parent 5b68cb6
commit 4a7cd9d
Showing 1 changed file with 133 additions and 138 deletions.
diff --git a/src/internal/bytealg/indexbyte_wasm.s b/src/internal/bytealg/indexbyte_wasm.s
@@ -49,149 +49,144 @@ TEXT ·IndexByteString(SB), NOSPLIT, $0-32
 
 	RET
 
-// compiled with emscripten
-// params: s, c, len
+// initially compiled with emscripten and then modified over time.
+// params:
+//   R0: s
+//   R1: c
+//   R2: len
 // ret: index
 TEXT memchr<>(SB), NOSPLIT, $0
 	Get R1
-	I32Const $255
-	I32And
 	Set R4
 	Block
-	Block
-	Get R2
-	I32Const $0
-	I32Ne
-	Tee R3
-	Get R0
-	I32Const $3
-	I32And
-	I32Const $0
-	I32Ne
-	I32And
-	If
-	Get R1
-	I32Const $255
-	I32And
-	Set R5
-	Loop
-	Get R0
-	I32Load8U $0
-	Get R5
-	I32Eq
-	BrIf $2
-	Get R2
-	I32Const $-1
-	I32Add
-	Tee R2
-	I32Const $0
-	I32Ne
-	Tee R3
-	Get R0
-	I32Const $1
-	I32Add
-	Tee R0
-	I32Const $3
-	I32And
-	I32Const $0
-	I32Ne
-	I32And
-	BrIf $0
-	End
-	End
-	Get R3
-	BrIf $0
-	I32Const $0
-	Set R1
-	Br $1
-	End
-	Get R0
-	I32Load8U $0
-	Get R1
-	I32Const $255
-	I32And
-	Tee R3
-	I32Eq
-	If
-	Get R2
-	Set R1
-	Else
-	Get R4
-	I32Const $16843009
-	I32Mul
-	Set R4
-	Block
-	Block
-	Get R2
-	I32Const $3
-	I32GtU
-	If
-	Get R2
-	Set R1
-	Loop
-	Get R0
-	I32Load $0
-	Get R4
-	I32Xor
-	Tee R2
-	I32Const $-2139062144
-	I32And
-	I32Const $-2139062144
-	I32Xor
-	Get R2
-	I32Const $-16843009
-	I32Add
-	I32And
-	I32Eqz
-	If
-	Get R0
-	I32Const $4
-	I32Add
-	Set R0
-	Get R1
-	I32Const $-4
-	I32Add
-	Tee R1
-	I32Const $3
-	I32GtU
-	BrIf $1
-	Br $3
-	End
-	End
-	Else
-	Get R2
-	Set R1
-	Br $1
-	End
-	Br $1
-	End
-	Get R1
-	I32Eqz
-	If
-	I32Const $0
-	Set R1
-	Br $3
-	End
-	End
-	Loop
-	Get R0
-	I32Load8U $0
-	Get R3
-	I32Eq
-	BrIf $2
-	Get R0
-	I32Const $1
-	I32Add
-	Set R0
-	Get R1
-	I32Const $-1
-	I32Add
-	Tee R1
-	BrIf $0
-	I32Const $0
-	Set R1
-	End
-	End
+		Block
+			Get R2
+			I32Const $0
+			I32Ne
+			Tee R3
+			Get R0
+			I32Const $3
+			I32And
+			I32Const $0
+			I32Ne
+			I32And
+			If
+				Loop
+					Get R0
+					I32Load8U $0
+					Get R1
+					I32Eq
+					BrIf $2
+					Get R2
+					I32Const $-1
+					I32Add
+					Tee R2
+					I32Const $0
+					I32Ne
+					Tee R3
+					Get R0
+					I32Const $1
+					I32Add
+					Tee R0
+					I32Const $3
+					I32And
+					I32Const $0
+					I32Ne
+					I32And
+					BrIf $0
+				End
+			End
+			Get R3
+			BrIf $0
+			I32Const $0
+			Set R1
+			Br $1
+		End
+		Get R0
+		I32Load8U $0
+		Get R4
+		Tee R3
+		I32Eq
+		If
+			Get R2
+			Set R1
+		Else
+			Get R4
+			I32Const $16843009
+			I32Mul
+			Set R4
+			Block
+				Block
+					Get R2
+					I32Const $3
+					I32GtU
+					If
+						Get R2
+						Set R1
+						Loop
+							Get R0
+							I32Load $0
+							Get R4
+							I32Xor
+							Tee R2
+							I32Const $-2139062144
+							I32And
+							I32Const $-2139062144
+							I32Xor
+							Get R2
+							I32Const $-16843009
+							I32Add
+							I32And
+							I32Eqz
+							If
+								Get R0
+								I32Const $4
+								I32Add
+								Set R0
+								Get R1
+								I32Const $-4
+								I32Add
+								Tee R1
+								I32Const $3
+								I32GtU
+								BrIf $1
+								Br $3
+							End
+						End
+					Else
+						Get R2
+						Set R1
+						Br $1
+					End
+					Br $1
+				End
+				Get R1
+				I32Eqz
+				If
+					I32Const $0
+					Set R1
+					Br $3
+				End
+			End
+			Loop
+				Get R0
+				I32Load8U $0
+				Get R3
+				I32Eq
+				BrIf $2
+				Get R0
+				I32Const $1
+				I32Add
+				Set R0
+				Get R1
+				I32Const $-1
+				I32Add
+				Tee R1
+				BrIf $0
+				I32Const $0
+				Set R1
+			End
+		End
 	End
 	Get R0
 	I32Const $0