golang-image/vector/acc_amd64.go

35 lines
784 B
Go
Raw Normal View History

// Copyright 2016 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build !appengine
// +build gc
// +build go1.6
// +build !noasm
package vector
func haveSSE4_1() bool
var haveFixedAccumulateSIMD = haveSSE4_1()
const haveFloatingAccumulateSIMD = true
//go:noescape
func fixedAccumulateOpOverSIMD(dst []uint8, src []uint32)
//go:noescape
func fixedAccumulateOpSrcSIMD(dst []uint8, src []uint32)
vector: add SIMD versions of xxxAccumulateMask. name old time/op new time/op delta GlyphAlphaLoose16Over-8 3.96µs ± 0% 3.64µs ± 1% -8.08% (p=0.000 n=8+10) GlyphAlphaLoose16Src-8 3.64µs ± 0% 3.35µs ± 0% -7.88% (p=0.000 n=8+9) GlyphAlphaLoose32Over-8 8.45µs ± 0% 6.74µs ± 0% -20.22% (p=0.000 n=8+9) GlyphAlphaLoose32Src-8 7.24µs ± 0% 5.54µs ± 1% -23.48% (p=0.000 n=8+10) GlyphAlphaLoose64Over-8 22.2µs ± 0% 17.4µs ± 0% -21.67% (p=0.000 n=9+9) GlyphAlphaLoose64Src-8 17.6µs ± 1% 12.2µs ± 1% -30.32% (p=0.000 n=10+10) GlyphAlphaLoose128Over-8 67.9µs ± 0% 53.3µs ± 1% -21.53% (p=0.000 n=10+10) GlyphAlphaLoose128Src-8 48.2µs ± 0% 32.6µs ± 2% -32.41% (p=0.000 n=9+10) GlyphAlphaLoose256Over-8 242µs ± 1% 187µs ± 1% -22.96% (p=0.000 n=9+9) GlyphAlphaLoose256Src-8 163µs ± 0% 105µs ± 1% -35.83% (p=0.000 n=9+9) GlyphRGBA16Over-8 5.25µs ± 1% 4.95µs ± 0% -5.78% (p=0.000 n=9+9) GlyphRGBA16Src-8 4.72µs ± 0% 4.43µs ± 1% -6.22% (p=0.000 n=9+10) GlyphRGBA32Over-8 13.5µs ± 0% 11.9µs ± 1% -12.19% (p=0.000 n=9+10) GlyphRGBA32Src-8 11.5µs ± 1% 9.8µs ± 0% -14.72% (p=0.000 n=9+9) GlyphRGBA64Over-8 42.0µs ± 2% 36.9µs ± 1% -12.19% (p=0.000 n=10+10) GlyphRGBA64Src-8 34.1µs ± 1% 28.5µs ± 0% -16.25% (p=0.000 n=9+7) GlyphRGBA128Over-8 149µs ± 2% 133µs ± 1% -10.24% (p=0.000 n=10+9) GlyphRGBA128Src-8 115µs ± 1% 99µs ± 1% -13.57% (p=0.000 n=9+10) GlyphRGBA256Over-8 566µs ± 0% 511µs ± 1% -9.85% (p=0.000 n=9+10) GlyphRGBA256Src-8 435µs ± 0% 372µs ± 0% -14.64% (p=0.000 n=9+8) GlyphNRGBA16Over-8 26.9µs ± 3% 26.0µs ± 3% -3.55% (p=0.000 n=10+9) GlyphNRGBA16Src-8 18.8µs ± 2% 18.4µs ± 2% -2.21% (p=0.000 n=9+10) GlyphNRGBA32Over-8 99.1µs ± 2% 95.9µs ± 3% -3.23% (p=0.000 n=10+10) GlyphNRGBA32Src-8 65.6µs ± 3% 62.8µs ± 2% -4.36% (p=0.000 n=10+10) GlyphNRGBA64Over-8 376µs ± 4% 370µs ± 2% ~ (p=0.063 n=10+10) GlyphNRGBA64Src-8 238µs ± 3% 233µs ± 1% -2.21% (p=0.000 n=9+10) GlyphNRGBA128Over-8 1.52ms ± 2% 1.48ms ± 0% -2.11% (p=0.000 n=10+8) GlyphNRGBA128Src-8 951µs ± 3% 935µs ± 1% -1.69% (p=0.013 n=10+9) GlyphNRGBA256Over-8 6.00ms ± 1% 5.87ms ± 3% -2.12% (p=0.002 n=10+10) GlyphNRGBA256Src-8 3.94ms ± 2% 3.80ms ± 2% -3.64% (p=0.000 n=10+10) A comparison of the non-SIMD and SIMD versions: name time/op FixedAccumulateMask16-8 237ns ± 0% FixedAccumulateMaskSIMD16-8 80.0ns ± 1% FloatingAccumulateMask16-8 413ns ± 2% FloatingAccumulateMaskSIMD16-8 166ns ± 0% FixedAccumulateMask64-8 3.42µs ± 0% FixedAccumulateMaskSIMD64-8 1.09µs ± 0% FloatingAccumulateMask64-8 6.92µs ± 0% FloatingAccumulateMaskSIMD64-8 2.47µs ± 1% Change-Id: Ib6980e5975ed2842ff2a372f76dd5f2e95c5526c Reviewed-on: https://go-review.googlesource.com/30898 Reviewed-by: David Crawshaw <crawshaw@golang.org>
2016-10-13 05:50:52 +02:00
//go:noescape
func fixedAccumulateMaskSIMD(buf []uint32)
//go:noescape
func floatingAccumulateOpOverSIMD(dst []uint8, src []float32)
//go:noescape
func floatingAccumulateOpSrcSIMD(dst []uint8, src []float32)
vector: add SIMD versions of xxxAccumulateMask. name old time/op new time/op delta GlyphAlphaLoose16Over-8 3.96µs ± 0% 3.64µs ± 1% -8.08% (p=0.000 n=8+10) GlyphAlphaLoose16Src-8 3.64µs ± 0% 3.35µs ± 0% -7.88% (p=0.000 n=8+9) GlyphAlphaLoose32Over-8 8.45µs ± 0% 6.74µs ± 0% -20.22% (p=0.000 n=8+9) GlyphAlphaLoose32Src-8 7.24µs ± 0% 5.54µs ± 1% -23.48% (p=0.000 n=8+10) GlyphAlphaLoose64Over-8 22.2µs ± 0% 17.4µs ± 0% -21.67% (p=0.000 n=9+9) GlyphAlphaLoose64Src-8 17.6µs ± 1% 12.2µs ± 1% -30.32% (p=0.000 n=10+10) GlyphAlphaLoose128Over-8 67.9µs ± 0% 53.3µs ± 1% -21.53% (p=0.000 n=10+10) GlyphAlphaLoose128Src-8 48.2µs ± 0% 32.6µs ± 2% -32.41% (p=0.000 n=9+10) GlyphAlphaLoose256Over-8 242µs ± 1% 187µs ± 1% -22.96% (p=0.000 n=9+9) GlyphAlphaLoose256Src-8 163µs ± 0% 105µs ± 1% -35.83% (p=0.000 n=9+9) GlyphRGBA16Over-8 5.25µs ± 1% 4.95µs ± 0% -5.78% (p=0.000 n=9+9) GlyphRGBA16Src-8 4.72µs ± 0% 4.43µs ± 1% -6.22% (p=0.000 n=9+10) GlyphRGBA32Over-8 13.5µs ± 0% 11.9µs ± 1% -12.19% (p=0.000 n=9+10) GlyphRGBA32Src-8 11.5µs ± 1% 9.8µs ± 0% -14.72% (p=0.000 n=9+9) GlyphRGBA64Over-8 42.0µs ± 2% 36.9µs ± 1% -12.19% (p=0.000 n=10+10) GlyphRGBA64Src-8 34.1µs ± 1% 28.5µs ± 0% -16.25% (p=0.000 n=9+7) GlyphRGBA128Over-8 149µs ± 2% 133µs ± 1% -10.24% (p=0.000 n=10+9) GlyphRGBA128Src-8 115µs ± 1% 99µs ± 1% -13.57% (p=0.000 n=9+10) GlyphRGBA256Over-8 566µs ± 0% 511µs ± 1% -9.85% (p=0.000 n=9+10) GlyphRGBA256Src-8 435µs ± 0% 372µs ± 0% -14.64% (p=0.000 n=9+8) GlyphNRGBA16Over-8 26.9µs ± 3% 26.0µs ± 3% -3.55% (p=0.000 n=10+9) GlyphNRGBA16Src-8 18.8µs ± 2% 18.4µs ± 2% -2.21% (p=0.000 n=9+10) GlyphNRGBA32Over-8 99.1µs ± 2% 95.9µs ± 3% -3.23% (p=0.000 n=10+10) GlyphNRGBA32Src-8 65.6µs ± 3% 62.8µs ± 2% -4.36% (p=0.000 n=10+10) GlyphNRGBA64Over-8 376µs ± 4% 370µs ± 2% ~ (p=0.063 n=10+10) GlyphNRGBA64Src-8 238µs ± 3% 233µs ± 1% -2.21% (p=0.000 n=9+10) GlyphNRGBA128Over-8 1.52ms ± 2% 1.48ms ± 0% -2.11% (p=0.000 n=10+8) GlyphNRGBA128Src-8 951µs ± 3% 935µs ± 1% -1.69% (p=0.013 n=10+9) GlyphNRGBA256Over-8 6.00ms ± 1% 5.87ms ± 3% -2.12% (p=0.002 n=10+10) GlyphNRGBA256Src-8 3.94ms ± 2% 3.80ms ± 2% -3.64% (p=0.000 n=10+10) A comparison of the non-SIMD and SIMD versions: name time/op FixedAccumulateMask16-8 237ns ± 0% FixedAccumulateMaskSIMD16-8 80.0ns ± 1% FloatingAccumulateMask16-8 413ns ± 2% FloatingAccumulateMaskSIMD16-8 166ns ± 0% FixedAccumulateMask64-8 3.42µs ± 0% FixedAccumulateMaskSIMD64-8 1.09µs ± 0% FloatingAccumulateMask64-8 6.92µs ± 0% FloatingAccumulateMaskSIMD64-8 2.47µs ± 1% Change-Id: Ib6980e5975ed2842ff2a372f76dd5f2e95c5526c Reviewed-on: https://go-review.googlesource.com/30898 Reviewed-by: David Crawshaw <crawshaw@golang.org>
2016-10-13 05:50:52 +02:00
//go:noescape
func floatingAccumulateMaskSIMD(dst []uint32, src []float32)