png: speed up opaque RGBA encoding

With Linux/8g on a 2006 Mac Mini (1.66 GHz Intel Core Duo,
2KB L1, 2MB L2, 2G main memory), GOMAXPROCS unset:

start:
png.BenchmarkEncodePaletted	      50	  44772820 ns/op
png.BenchmarkEncodeRGBOpaque	      10	 208395900 ns/op
png.BenchmarkEncodeRGBA		       5	 331088000 ns/op

remove interface method calls:
png.BenchmarkEncodePaletted	      50	  44722880 ns/op
png.BenchmarkEncodeRGBOpaque	      10	 139042600 ns/op
png.BenchmarkEncodeRGBA		       5	 334033600 ns/op

flate inline min/max():
png.BenchmarkEncodePaletted	      50	  40631180 ns/op
png.BenchmarkEncodeRGBOpaque	      10	 124894900 ns/op
png.BenchmarkEncodeRGBA		       5	 312099000 ns/op

after adler change:
png.BenchmarkEncodePaletted	      50	  40181760 ns/op
png.BenchmarkEncodeRGBOpaque	      20	 121781950 ns/op
png.BenchmarkEncodeRGBA		       5	 313890800 ns/op

In comparison to 121 ms on this 2006 machine, on my
Core2 Duo 2.66 GHz laptop, the final BenchmarkEncodeRGBOpaque
runs in 27 ms. (these are all for 640x480 images)

R=nigeltao, rsc, r
CC=golang-dev
https://golang.org/cl/4432077

src/pkg/compress/flate/deflate.go

@@ -143,10 +143,18 @@ func (d *compressor) fillWindow(index int) (int, os.Error) {
 			d.blockStart = math.MaxInt32
 		}
 		for i, h := range d.hashHead {
-			d.hashHead[i] = max(h-wSize, -1)
+			v := h - wSize
+			if v < -1 {
+				v = -1
+			}
+			d.hashHead[i] = v
 		}
 		for i, h := range d.hashPrev {
-			d.hashPrev[i] = max(h-wSize, -1)
+			v := -h - wSize
+			if v < -1 {
+				v = -1
+			}
+			d.hashPrev[i] = v
 		}
 	}
 	count, err := d.r.Read(d.window[d.windowEnd:])
@@ -177,10 +185,18 @@ func (d *compressor) writeBlock(tokens []token, index int, eof bool) os.Error {
 // Try to find a match starting at index whose length is greater than prevSize.
 // We only look at chainCount possibilities before giving up.
 func (d *compressor) findMatch(pos int, prevHead int, prevLength int, lookahead int) (length, offset int, ok bool) {
-	win := d.window[0 : pos+min(maxMatchLength, lookahead)]
+	minMatchLook := maxMatchLength
+	if lookahead < minMatchLook {
+		minMatchLook = lookahead
+	}
+
+	win := d.window[0 : pos+minMatchLook]
 
 	// We quit when we get a match that's at least nice long
-	nice := min(d.niceMatch, len(win)-pos)
+	nice := len(win) - pos
+	if d.niceMatch < nice {
+		nice = d.niceMatch
+	}
 
 	// If we've got a match that's good enough, only look in 1/4 the chain.
 	tries := d.maxChainLength
@@ -344,9 +360,12 @@ Loop:
 		}
 		prevLength := length
 		prevOffset := offset
-		minIndex := max(index-maxOffset, 0)
 		length = minMatchLength - 1
 		offset = 0
+		minIndex := index - maxOffset
+		if minIndex < 0 {
+			minIndex = 0
+		}
 
 		if chainHead >= minIndex &&
 			(isFastDeflate && lookahead > minMatchLength-1 ||

src/pkg/image/png/writer.go

@@ -263,7 +263,12 @@ func writeImage(w io.Writer, m image.Image, cb int) os.Error {
 	defer zw.Close()
 
 	bpp := 0 // Bytes per pixel.
+
+	// Used by fast paths for common image types
 	var paletted *image.Paletted
+	var rgba *image.RGBA
+	rgba, _ = m.(*image.RGBA)
+
 	switch cb {
 	case cbG8:
 		bpp = 1
@@ -303,12 +308,24 @@ func writeImage(w io.Writer, m image.Image, cb int) os.Error {
 				cr[0][x+1] = c.Y
 			}
 		case cbTC8:
-			for x := b.Min.X; x < b.Max.X; x++ {
 			// We have previously verified that the alpha value is fully opaque.
+			cr0 := cr[0]
+			if rgba != nil {
+				yoff := y * rgba.Stride
+				xoff := 3*b.Min.X + 1
+				for _, color := range rgba.Pix[yoff+b.Min.X : yoff+b.Max.X] {
+					cr0[xoff] = color.R
+					cr0[xoff+1] = color.G
+					cr0[xoff+2] = color.B
+					xoff += 3
+				}
+			} else {
+				for x := b.Min.X; x < b.Max.X; x++ {
 					r, g, b, _ := m.At(x, y).RGBA()
-				cr[0][3*x+1] = uint8(r >> 8)
-				cr[0][3*x+2] = uint8(g >> 8)
-				cr[0][3*x+3] = uint8(b >> 8)
+					cr0[3*x+1] = uint8(r >> 8)
+					cr0[3*x+2] = uint8(g >> 8)
+					cr0[3*x+3] = uint8(b >> 8)
+				}
 			}
 		case cbP8:
 			rowOffset := y * paletted.Stride