image/png: use branch-free abs function

benchmark                        old ns/op     new ns/op     delta
BenchmarkPaeth                   5.06          6.02          +18.97%
BenchmarkDecodeGray              1010551       956911        -5.31%
BenchmarkDecodeNRGBAGradient     3877813       3754160       -3.19%
BenchmarkDecodeNRGBAOpaque       3194058       3079094       -3.60%
BenchmarkDecodePaletted          699243        700211        +0.14%
BenchmarkDecodeRGB               2835733       2692120       -5.06%
BenchmarkDecodeInterlacing       3651805       3563124       -2.43%
BenchmarkEncodeGray              4399183       4404113       +0.11%
BenchmarkEncodeNRGBOpaque        13323627      13306485      -0.13%
BenchmarkEncodeNRGBA             15840092      15751188      -0.56%
BenchmarkEncodePaletted          4396622       4404373       +0.18%
BenchmarkEncodeRGBOpaque         13320475      13279189      -0.31%
BenchmarkEncodeRGBA              36898392      36781002      -0.32%

LGTM=nigeltao
R=nigeltao
CC=golang-codereviews
https://golang.org/cl/117290043

2 files changed, 25 insertions, 24 deletions

diff --git a/src/pkg/image/png/paeth.go b/src/pkg/image/png/paeth.go
index 37978aa662..9ed6300c86 100644
--- a/src/pkg/image/png/paeth.go
+++ b/src/pkg/image/png/paeth.go
@@ -4,6 +4,21 @@
 
 package png
 
+// intSize is either 32 or 64.
+const intSize = 32 << (^uint(0) >> 63)
+
+func abs(x int) int {
+	// m := -1 if x < 0. m := 0 otherwise.
+	m := x >> (intSize - 1)
+
+	// In two's complement representation, the negative number
+	// of any number (except the smallest one) can be computed
+	// by flipping all the bits and add 1. This is faster than
+	// code with a branch.
+	// See Hacker's Delight, section 2-4.
+	return (x ^ m) - m
+}
+
 // paeth implements the Paeth filter function, as per the PNG specification.
 func paeth(a, b, c uint8) uint8 {
 	// This is an optimized version of the sample code in the PNG spec.
@@ -16,16 +31,9 @@ func paeth(a, b, c uint8) uint8 {
 	pc := int(c)
 	pa := int(b) - pc
 	pb := int(a) - pc
-	pc = pa + pb
-	if pa < 0 {
-		pa = -pa
-	}
-	if pb < 0 {
-		pb = -pb
-	}
-	if pc < 0 {
-		pc = -pc
-	}
+	pc = abs(pa + pb)
+	pa = abs(pa)
+	pb = abs(pb)
 	if pa <= pb && pa <= pc {
 		return a
 	} else if pb <= pc {
@@ -44,16 +52,9 @@ func filterPaeth(cdat, pdat []byte, bytesPerPixel int) {
 			b = int(pdat[j])
 			pa = b - c
 			pb = a - c
-			pc = pa + pb
-			if pa < 0 {
-				pa = -pa
-			}
-			if pb < 0 {
-				pb = -pb
-			}
-			if pc < 0 {
-				pc = -pc
-			}
+			pc = abs(pa + pb)
+			pa = abs(pa)
+			pb = abs(pb)
 			if pa <= pb && pa <= pc {
 				// No-op.
 			} else if pb <= pc {
diff --git a/src/pkg/image/png/paeth_test.go b/src/pkg/image/png/paeth_test.go
index bb084861ae..cfc1896cd7 100644
--- a/src/pkg/image/png/paeth_test.go
+++ b/src/pkg/image/png/paeth_test.go
@@ -10,7 +10,7 @@ import (
 	"testing"
 )
 
-func abs(x int) int {
+func slowAbs(x int) int {
 	if x < 0 {
 		return -x
 	}
@@ -21,9 +21,9 @@ func abs(x int) int {
 // It is a straight port of the sample code in the PNG spec, section 9.4.
 func slowPaeth(a, b, c uint8) uint8 {
 	p := int(a) + int(b) - int(c)
-	pa := abs(p - int(a))
-	pb := abs(p - int(b))
-	pc := abs(p - int(c))
+	pa := slowAbs(p - int(a))
+	pb := slowAbs(p - int(b))
+	pc := slowAbs(p - int(c))
 	if pa <= pb && pa <= pc {
 		return a
 	} else if pb <= pc {