reedsolomon-go/galois_noasm.go

59 lines
1.5 KiB
Go
Raw Normal View History

//go:build (!amd64 || noasm || appengine || gccgo) && (!arm64 || noasm || appengine || gccgo) && (!ppc64le || noasm || appengine || gccgo)
// +build !amd64 noasm appengine gccgo
// +build !arm64 noasm appengine gccgo
// +build !ppc64le noasm appengine gccgo
Add AMD64 SSE3 Galois multiplication. Approximately 5-10x faster. BenchmarkEncode10x2x10000 333.31 5827.17 17.48x BenchmarkEncode10x2x10000-2 431.20 2802.53 6.50x BenchmarkEncode10x2x10000-4 553.98 2432.95 4.39x BenchmarkEncode10x2x10000-8 585.79 3469.61 5.92x BenchmarkEncode100x20x10000 32.59 583.40 17.90x BenchmarkEncode100x20x10000-2 59.52 726.70 12.21x BenchmarkEncode100x20x10000-4 108.04 1363.25 12.62x BenchmarkEncode100x20x10000-8 113.76 1274.62 11.20x BenchmarkEncode17x3x1M 215.28 3141.85 14.59x BenchmarkEncode17x3x1M-2 398.76 3650.12 9.15x BenchmarkEncode17x3x1M-4 655.32 6071.11 9.26x BenchmarkEncode17x3x1M-8 832.16 6616.47 7.95x BenchmarkEncode10x4x16M 154.48 1357.30 8.79x BenchmarkEncode10x4x16M-2 295.62 2377.92 8.04x BenchmarkEncode10x4x16M-4 529.89 3519.49 6.64x BenchmarkEncode10x4x16M-8 632.11 4521.90 7.15x BenchmarkEncode5x2x1M 327.87 4879.09 14.88x BenchmarkEncode5x2x1M-2 576.11 2599.20 4.51x BenchmarkEncode5x2x1M-4 1043.65 3559.12 3.41x BenchmarkEncode5x2x1M-8 1227.77 4255.34 3.47x BenchmarkEncode10x2x1M 321.24 4574.68 14.24x BenchmarkEncode10x2x1M-2 587.73 3100.28 5.28x BenchmarkEncode10x2x1M-4 1101.96 4770.32 4.33x BenchmarkEncode10x2x1M-8 1217.08 5812.17 4.78x BenchmarkEncode10x4x1M 155.34 2037.27 13.11x BenchmarkEncode10x4x1M-2 298.38 2470.97 8.28x BenchmarkEncode10x4x1M-4 548.67 3603.15 6.57x BenchmarkEncode10x4x1M-8 625.23 4827.42 7.72x BenchmarkEncode50x20x1M 31.37 347.65 11.08x BenchmarkEncode50x20x1M-2 59.81 713.28 11.93x BenchmarkEncode50x20x1M-4 105.34 1175.47 11.16x BenchmarkEncode50x20x1M-8 123.84 1491.91 12.05x BenchmarkEncode17x3x16M 209.55 1861.59 8.88x BenchmarkEncode17x3x16M-2 394.19 3331.73 8.45x BenchmarkEncode17x3x16M-4 643.30 4942.74 7.68x BenchmarkEncode17x3x16M-8 839.64 6213.43 7.40x
2015-06-21 22:23:22 +03:00
// Copyright 2015, Klaus Post, see LICENSE for details.
package reedsolomon
import "encoding/binary"
func galMulSlice(c byte, in, out []byte, o *options) {
out = out[:len(in)]
if c == 1 {
copy(out, in)
return
}
mt := mulTable[c][:256]
Add AMD64 SSE3 Galois multiplication. Approximately 5-10x faster. BenchmarkEncode10x2x10000 333.31 5827.17 17.48x BenchmarkEncode10x2x10000-2 431.20 2802.53 6.50x BenchmarkEncode10x2x10000-4 553.98 2432.95 4.39x BenchmarkEncode10x2x10000-8 585.79 3469.61 5.92x BenchmarkEncode100x20x10000 32.59 583.40 17.90x BenchmarkEncode100x20x10000-2 59.52 726.70 12.21x BenchmarkEncode100x20x10000-4 108.04 1363.25 12.62x BenchmarkEncode100x20x10000-8 113.76 1274.62 11.20x BenchmarkEncode17x3x1M 215.28 3141.85 14.59x BenchmarkEncode17x3x1M-2 398.76 3650.12 9.15x BenchmarkEncode17x3x1M-4 655.32 6071.11 9.26x BenchmarkEncode17x3x1M-8 832.16 6616.47 7.95x BenchmarkEncode10x4x16M 154.48 1357.30 8.79x BenchmarkEncode10x4x16M-2 295.62 2377.92 8.04x BenchmarkEncode10x4x16M-4 529.89 3519.49 6.64x BenchmarkEncode10x4x16M-8 632.11 4521.90 7.15x BenchmarkEncode5x2x1M 327.87 4879.09 14.88x BenchmarkEncode5x2x1M-2 576.11 2599.20 4.51x BenchmarkEncode5x2x1M-4 1043.65 3559.12 3.41x BenchmarkEncode5x2x1M-8 1227.77 4255.34 3.47x BenchmarkEncode10x2x1M 321.24 4574.68 14.24x BenchmarkEncode10x2x1M-2 587.73 3100.28 5.28x BenchmarkEncode10x2x1M-4 1101.96 4770.32 4.33x BenchmarkEncode10x2x1M-8 1217.08 5812.17 4.78x BenchmarkEncode10x4x1M 155.34 2037.27 13.11x BenchmarkEncode10x4x1M-2 298.38 2470.97 8.28x BenchmarkEncode10x4x1M-4 548.67 3603.15 6.57x BenchmarkEncode10x4x1M-8 625.23 4827.42 7.72x BenchmarkEncode50x20x1M 31.37 347.65 11.08x BenchmarkEncode50x20x1M-2 59.81 713.28 11.93x BenchmarkEncode50x20x1M-4 105.34 1175.47 11.16x BenchmarkEncode50x20x1M-8 123.84 1491.91 12.05x BenchmarkEncode17x3x16M 209.55 1861.59 8.88x BenchmarkEncode17x3x16M-2 394.19 3331.73 8.45x BenchmarkEncode17x3x16M-4 643.30 4942.74 7.68x BenchmarkEncode17x3x16M-8 839.64 6213.43 7.40x
2015-06-21 22:23:22 +03:00
for n, input := range in {
out[n] = mt[input]
}
}
func galMulSliceXor(c byte, in, out []byte, o *options) {
out = out[:len(in)]
if c == 1 {
sliceXor(in, out, o)
return
}
mt := mulTable[c][:256]
Add AMD64 SSE3 Galois multiplication. Approximately 5-10x faster. BenchmarkEncode10x2x10000 333.31 5827.17 17.48x BenchmarkEncode10x2x10000-2 431.20 2802.53 6.50x BenchmarkEncode10x2x10000-4 553.98 2432.95 4.39x BenchmarkEncode10x2x10000-8 585.79 3469.61 5.92x BenchmarkEncode100x20x10000 32.59 583.40 17.90x BenchmarkEncode100x20x10000-2 59.52 726.70 12.21x BenchmarkEncode100x20x10000-4 108.04 1363.25 12.62x BenchmarkEncode100x20x10000-8 113.76 1274.62 11.20x BenchmarkEncode17x3x1M 215.28 3141.85 14.59x BenchmarkEncode17x3x1M-2 398.76 3650.12 9.15x BenchmarkEncode17x3x1M-4 655.32 6071.11 9.26x BenchmarkEncode17x3x1M-8 832.16 6616.47 7.95x BenchmarkEncode10x4x16M 154.48 1357.30 8.79x BenchmarkEncode10x4x16M-2 295.62 2377.92 8.04x BenchmarkEncode10x4x16M-4 529.89 3519.49 6.64x BenchmarkEncode10x4x16M-8 632.11 4521.90 7.15x BenchmarkEncode5x2x1M 327.87 4879.09 14.88x BenchmarkEncode5x2x1M-2 576.11 2599.20 4.51x BenchmarkEncode5x2x1M-4 1043.65 3559.12 3.41x BenchmarkEncode5x2x1M-8 1227.77 4255.34 3.47x BenchmarkEncode10x2x1M 321.24 4574.68 14.24x BenchmarkEncode10x2x1M-2 587.73 3100.28 5.28x BenchmarkEncode10x2x1M-4 1101.96 4770.32 4.33x BenchmarkEncode10x2x1M-8 1217.08 5812.17 4.78x BenchmarkEncode10x4x1M 155.34 2037.27 13.11x BenchmarkEncode10x4x1M-2 298.38 2470.97 8.28x BenchmarkEncode10x4x1M-4 548.67 3603.15 6.57x BenchmarkEncode10x4x1M-8 625.23 4827.42 7.72x BenchmarkEncode50x20x1M 31.37 347.65 11.08x BenchmarkEncode50x20x1M-2 59.81 713.28 11.93x BenchmarkEncode50x20x1M-4 105.34 1175.47 11.16x BenchmarkEncode50x20x1M-8 123.84 1491.91 12.05x BenchmarkEncode17x3x16M 209.55 1861.59 8.88x BenchmarkEncode17x3x16M-2 394.19 3331.73 8.45x BenchmarkEncode17x3x16M-4 643.30 4942.74 7.68x BenchmarkEncode17x3x16M-8 839.64 6213.43 7.40x
2015-06-21 22:23:22 +03:00
for n, input := range in {
out[n] ^= mt[input]
}
}
// simple slice xor
func sliceXor(in, out []byte, _ *options) {
for len(out) >= 32 {
inS := in[:32]
v0 := binary.LittleEndian.Uint64(out[:]) ^ binary.LittleEndian.Uint64(inS[:])
v1 := binary.LittleEndian.Uint64(out[8:]) ^ binary.LittleEndian.Uint64(inS[8:])
v2 := binary.LittleEndian.Uint64(out[16:]) ^ binary.LittleEndian.Uint64(inS[16:])
v3 := binary.LittleEndian.Uint64(out[24:]) ^ binary.LittleEndian.Uint64(inS[24:])
binary.LittleEndian.PutUint64(out[:], v0)
binary.LittleEndian.PutUint64(out[8:], v1)
binary.LittleEndian.PutUint64(out[16:], v2)
binary.LittleEndian.PutUint64(out[24:], v3)
out = out[32:]
in = in[32:]
}
for n, input := range in {
out[n] ^= input
}
}
func init() {
defaultOptions.useAVX512 = false
}