mirror of
https://github.com/golang/go
synced 2024-11-17 07:04:44 -07:00
math/big: speed-up addMulVVW on amd64
Use MULX/ADOX/ADCX instructions to speed-up addMulVVW, when they are available. addMulVVW is a hotspot in rsa. This is faster than ADD/ADC/IMUL version, because ADOX/ADCX only modify carry/overflow flag, so they can be interleaved with each other and with MULX, which doesn't modify flags at all. Increasing unroll factor to e. g. 16 makes rsa 1% faster, but 3PrimeRSA2048Decrypt performance falls back to baseline. Updates #20058 AddMulVVW/1-8 3.28ns ± 2% 3.26ns ± 3% ~ (p=0.107 n=10+10) AddMulVVW/2-8 4.26ns ± 2% 4.24ns ± 3% ~ (p=0.327 n=9+9) AddMulVVW/3-8 5.07ns ± 2% 5.26ns ± 2% +3.73% (p=0.000 n=10+10) AddMulVVW/4-8 6.40ns ± 2% 6.50ns ± 2% +1.61% (p=0.000 n=10+10) AddMulVVW/5-8 6.77ns ± 2% 6.86ns ± 1% +1.38% (p=0.001 n=9+9) AddMulVVW/10-8 12.2ns ± 2% 10.6ns ± 3% -13.65% (p=0.000 n=10+10) AddMulVVW/100-8 79.7ns ± 2% 52.4ns ± 1% -34.17% (p=0.000 n=10+10) AddMulVVW/1000-8 695ns ± 1% 491ns ± 2% -29.39% (p=0.000 n=9+10) AddMulVVW/10000-8 7.26µs ± 2% 5.92µs ± 6% -18.42% (p=0.000 n=10+10) AddMulVVW/100000-8 72.6µs ± 2% 62.2µs ± 2% -14.31% (p=0.000 n=10+10) crypto/rsa speed-up is smaller, but stil noticeable: RSA2048Decrypt-8 1.61ms ± 1% 1.38ms ± 1% -14.13% (p=0.000 n=10+10) RSA2048Sign-8 1.93ms ± 1% 1.70ms ± 1% -11.86% (p=0.000 n=10+10) 3PrimeRSA2048Decrypt-8 932µs ± 0% 828µs ± 0% -11.15% (p=0.000 n=10+10) Results on crypto/tls: HandshakeServer/RSA-8 901µs ± 1% 777µs ± 0% -13.70% (p=0.000 n=10+8) HandshakeServer/ECDHE-P256-RSA-8 1.01ms ± 1% 0.90ms ± 0% -11.53% (p=0.000 n=10+9) Full math/big benchmarks: name old time/op new time/op delta AddVV/1-8 3.74ns ± 6% 3.55ns ± 2% ~ (p=0.082 n=10+8) AddVV/2-8 3.96ns ± 2% 3.98ns ± 5% ~ (p=0.794 n=10+9) AddVV/3-8 4.97ns ± 2% 4.94ns ± 1% ~ (p=0.081 n=10+9) AddVV/4-8 5.59ns ± 2% 5.59ns ± 2% ~ (p=0.809 n=10+10) AddVV/5-8 6.63ns ± 1% 6.62ns ± 1% ~ (p=0.560 n=9+10) AddVV/10-8 8.11ns ± 1% 8.11ns ± 2% ~ (p=0.402 n=10+10) AddVV/100-8 46.9ns ± 2% 46.8ns ± 1% ~ (p=0.809 n=10+10) AddVV/1000-8 389ns ± 1% 391ns ± 4% ~ (p=0.809 n=10+10) AddVV/10000-8 5.05µs ± 5% 4.98µs ± 2% ~ (p=0.113 n=9+10) AddVV/100000-8 55.3µs ± 3% 55.2µs ± 3% ~ (p=0.796 n=10+10) AddVW/1-8 3.04ns ± 3% 3.02ns ± 3% ~ (p=0.538 n=10+10) AddVW/2-8 3.57ns ± 2% 3.61ns ± 2% +1.12% (p=0.032 n=9+9) AddVW/3-8 3.77ns ± 1% 3.79ns ± 2% ~ (p=0.719 n=10+10) AddVW/4-8 4.69ns ± 1% 4.69ns ± 2% ~ (p=0.920 n=10+9) AddVW/5-8 4.58ns ± 1% 4.58ns ± 1% ~ (p=0.812 n=10+10) AddVW/10-8 7.62ns ± 2% 7.63ns ± 1% ~ (p=0.926 n=10+10) AddVW/100-8 41.1ns ± 2% 42.4ns ± 3% +3.34% (p=0.000 n=10+10) AddVW/1000-8 386ns ± 2% 389ns ± 4% ~ (p=0.514 n=10+10) AddVW/10000-8 3.88µs ± 3% 3.87µs ± 3% ~ (p=0.448 n=10+10) AddVW/100000-8 41.2µs ± 3% 41.7µs ± 3% ~ (p=0.148 n=10+10) AddMulVVW/1-8 3.28ns ± 2% 3.26ns ± 3% ~ (p=0.107 n=10+10) AddMulVVW/2-8 4.26ns ± 2% 4.24ns ± 3% ~ (p=0.327 n=9+9) AddMulVVW/3-8 5.07ns ± 2% 5.26ns ± 2% +3.73% (p=0.000 n=10+10) AddMulVVW/4-8 6.40ns ± 2% 6.50ns ± 2% +1.61% (p=0.000 n=10+10) AddMulVVW/5-8 6.77ns ± 2% 6.86ns ± 1% +1.38% (p=0.001 n=9+9) AddMulVVW/10-8 12.2ns ± 2% 10.6ns ± 3% -13.65% (p=0.000 n=10+10) AddMulVVW/100-8 79.7ns ± 2% 52.4ns ± 1% -34.17% (p=0.000 n=10+10) AddMulVVW/1000-8 695ns ± 1% 491ns ± 2% -29.39% (p=0.000 n=9+10) AddMulVVW/10000-8 7.26µs ± 2% 5.92µs ± 6% -18.42% (p=0.000 n=10+10) AddMulVVW/100000-8 72.6µs ± 2% 62.2µs ± 2% -14.31% (p=0.000 n=10+10) DecimalConversion-8 108µs ±19% 104µs ± 4% ~ (p=0.460 n=10+8) FloatString/100-8 926ns ±14% 908ns ± 5% ~ (p=0.398 n=9+9) FloatString/1000-8 25.7µs ± 1% 25.7µs ± 1% ~ (p=0.739 n=10+10) FloatString/10000-8 2.13ms ± 1% 2.12ms ± 1% ~ (p=0.353 n=10+10) FloatString/100000-8 207ms ± 1% 206ms ± 2% ~ (p=0.912 n=10+10) FloatAdd/10-8 61.3ns ± 3% 61.9ns ± 3% ~ (p=0.183 n=10+10) FloatAdd/100-8 62.0ns ± 2% 62.9ns ± 4% ~ (p=0.118 n=10+10) FloatAdd/1000-8 84.7ns ± 2% 84.4ns ± 1% ~ (p=0.591 n=10+10) FloatAdd/10000-8 305ns ± 2% 306ns ± 1% ~ (p=0.443 n=10+10) FloatAdd/100000-8 2.45µs ± 1% 2.46µs ± 1% ~ (p=0.782 n=10+10) FloatSub/10-8 56.8ns ± 4% 56.5ns ± 5% ~ (p=0.423 n=10+10) FloatSub/100-8 57.3ns ± 4% 57.1ns ± 5% ~ (p=0.540 n=10+10) FloatSub/1000-8 66.8ns ± 4% 66.6ns ± 1% ~ (p=0.868 n=10+10) FloatSub/10000-8 199ns ± 1% 198ns ± 1% ~ (p=0.287 n=10+9) FloatSub/100000-8 1.47µs ± 2% 1.47µs ± 2% ~ (p=0.920 n=10+9) ParseFloatSmallExp-8 8.74µs ±10% 9.48µs ±10% +8.51% (p=0.010 n=9+10) ParseFloatLargeExp-8 39.2µs ±25% 39.6µs ±12% ~ (p=0.529 n=10+10) GCD10x10/WithoutXY-8 173ns ±23% 177ns ±20% ~ (p=0.698 n=10+10) GCD10x10/WithXY-8 736ns ±12% 728ns ±16% ~ (p=0.838 n=10+10) GCD10x100/WithoutXY-8 325ns ±16% 326ns ±14% ~ (p=0.912 n=10+10) GCD10x100/WithXY-8 1.14µs ±13% 1.16µs ± 6% ~ (p=0.287 n=10+9) GCD10x1000/WithoutXY-8 851ns ±25% 820ns ±12% ~ (p=0.592 n=10+10) GCD10x1000/WithXY-8 2.89µs ±17% 2.85µs ± 5% ~ (p=1.000 n=10+9) GCD10x10000/WithoutXY-8 6.66µs ±12% 6.82µs ±19% ~ (p=0.529 n=10+10) GCD10x10000/WithXY-8 18.0µs ± 5% 17.2µs ±19% ~ (p=0.315 n=7+10) GCD10x100000/WithoutXY-8 77.8µs ±18% 73.3µs ±11% ~ (p=0.315 n=10+9) GCD10x100000/WithXY-8 186µs ±14% 204µs ±29% ~ (p=0.218 n=10+10) GCD100x100/WithoutXY-8 1.09µs ± 1% 1.09µs ± 2% ~ (p=0.117 n=9+10) GCD100x100/WithXY-8 7.93µs ± 1% 7.97µs ± 1% +0.52% (p=0.006 n=10+10) GCD100x1000/WithoutXY-8 2.00µs ± 3% 2.04µs ± 6% ~ (p=0.053 n=9+10) GCD100x1000/WithXY-8 9.23µs ± 1% 9.29µs ± 1% +0.63% (p=0.009 n=10+10) GCD100x10000/WithoutXY-8 10.2µs ±11% 9.7µs ± 6% ~ (p=0.278 n=10+9) GCD100x10000/WithXY-8 33.3µs ± 4% 33.6µs ± 4% ~ (p=0.481 n=10+10) GCD100x100000/WithoutXY-8 106µs ±17% 105µs ±13% ~ (p=0.853 n=10+10) GCD100x100000/WithXY-8 289µs ±17% 276µs ± 8% ~ (p=0.353 n=10+10) GCD1000x1000/WithoutXY-8 12.2µs ± 1% 12.1µs ± 1% -0.45% (p=0.007 n=10+10) GCD1000x1000/WithXY-8 131µs ± 1% 132µs ± 0% +0.93% (p=0.000 n=9+7) GCD1000x10000/WithoutXY-8 20.6µs ± 2% 20.6µs ± 1% ~ (p=0.326 n=10+9) GCD1000x10000/WithXY-8 238µs ± 1% 237µs ± 1% ~ (p=0.356 n=9+10) GCD1000x100000/WithoutXY-8 117µs ± 8% 114µs ±11% ~ (p=0.190 n=10+10) GCD1000x100000/WithXY-8 1.51ms ± 1% 1.50ms ± 1% ~ (p=0.053 n=9+10) GCD10000x10000/WithoutXY-8 220µs ± 1% 218µs ± 1% -0.86% (p=0.000 n=10+10) GCD10000x10000/WithXY-8 3.04ms ± 0% 3.05ms ± 0% +0.33% (p=0.001 n=9+10) GCD10000x100000/WithoutXY-8 513µs ± 0% 511µs ± 0% -0.38% (p=0.000 n=10+10) GCD10000x100000/WithXY-8 15.1ms ± 0% 15.0ms ± 0% ~ (p=0.053 n=10+9) GCD100000x100000/WithoutXY-8 10.4ms ± 1% 10.4ms ± 2% ~ (p=0.258 n=9+9) GCD100000x100000/WithXY-8 205ms ± 1% 205ms ± 1% ~ (p=0.481 n=10+10) Hilbert-8 1.25ms ±15% 1.24ms ±17% ~ (p=0.853 n=10+10) Binomial-8 3.03µs ±24% 2.90µs ±16% ~ (p=0.481 n=10+10) QuoRem-8 1.95µs ± 1% 1.95µs ± 2% ~ (p=0.117 n=9+10) Exp-8 5.12ms ± 2% 3.99ms ± 1% -22.02% (p=0.000 n=10+9) Exp2-8 5.14ms ± 2% 3.98ms ± 0% -22.55% (p=0.000 n=10+9) Bitset-8 16.4ns ± 2% 16.5ns ± 2% ~ (p=0.311 n=9+10) BitsetNeg-8 46.3ns ± 4% 45.8ns ± 4% ~ (p=0.272 n=10+10) BitsetOrig-8 250ns ±19% 247ns ±14% ~ (p=0.671 n=10+10) BitsetNegOrig-8 416ns ±14% 429ns ±14% ~ (p=0.353 n=10+10) ModSqrt225_Tonelli-8 400µs ± 0% 320µs ± 0% -19.88% (p=0.000 n=9+7) ModSqrt224_3Mod4-8 123µs ± 1% 97µs ± 0% -21.21% (p=0.000 n=9+10) ModSqrt5430_Tonelli-8 1.87s ± 0% 1.39s ± 1% -25.70% (p=0.000 n=9+10) ModSqrt5430_3Mod4-8 630ms ± 2% 465ms ± 1% -26.12% (p=0.000 n=10+10) Sqrt-8 25.8µs ± 1% 25.9µs ± 0% +0.66% (p=0.002 n=10+8) IntSqr/1-8 11.3ns ± 1% 11.3ns ± 2% ~ (p=0.360 n=9+10) IntSqr/2-8 26.6ns ± 1% 27.4ns ± 2% +2.87% (p=0.000 n=8+9) IntSqr/3-8 36.5ns ± 6% 36.6ns ± 5% ~ (p=0.589 n=10+10) IntSqr/5-8 57.2ns ± 2% 57.8ns ± 1% +0.92% (p=0.045 n=10+9) IntSqr/8-8 112ns ± 1% 93ns ± 1% -16.60% (p=0.000 n=10+10) IntSqr/10-8 148ns ± 1% 129ns ± 5% -12.85% (p=0.000 n=10+10) IntSqr/20-8 642ns ±28% 692ns ±21% ~ (p=0.105 n=10+10) IntSqr/30-8 1.03µs ±18% 1.06µs ±15% ~ (p=0.422 n=10+8) IntSqr/50-8 2.33µs ±14% 2.14µs ±20% ~ (p=0.063 n=10+10) IntSqr/80-8 4.06µs ±13% 3.72µs ±14% -8.31% (p=0.029 n=10+10) IntSqr/100-8 5.79µs ±10% 5.20µs ±18% -10.15% (p=0.004 n=10+10) IntSqr/200-8 17.1µs ± 1% 12.9µs ± 3% -24.44% (p=0.000 n=10+10) IntSqr/300-8 35.9µs ± 0% 26.6µs ± 1% -25.75% (p=0.000 n=10+10) IntSqr/500-8 84.9µs ± 0% 71.7µs ± 1% -15.49% (p=0.000 n=10+10) IntSqr/800-8 170µs ± 1% 142µs ± 2% -16.73% (p=0.000 n=10+10) IntSqr/1000-8 258µs ± 1% 218µs ± 1% -15.65% (p=0.000 n=10+10) Mul-8 10.4ms ± 1% 8.3ms ± 0% -20.05% (p=0.000 n=10+9) Exp3Power/0x10-8 311ns ±15% 321ns ±24% ~ (p=0.447 n=10+10) Exp3Power/0x40-8 358ns ±21% 346ns ±37% ~ (p=0.591 n=10+10) Exp3Power/0x100-8 611ns ±19% 570ns ±27% ~ (p=0.393 n=10+10) Exp3Power/0x400-8 1.31µs ±26% 1.34µs ±19% ~ (p=0.853 n=10+10) Exp3Power/0x1000-8 6.76µs ±23% 6.22µs ±16% ~ (p=0.095 n=10+9) Exp3Power/0x4000-8 37.6µs ±14% 36.4µs ±21% ~ (p=0.247 n=10+10) Exp3Power/0x10000-8 345µs ±14% 310µs ±11% -9.99% (p=0.005 n=10+10) Exp3Power/0x40000-8 2.77ms ± 1% 2.34ms ± 1% -15.47% (p=0.000 n=10+10) Exp3Power/0x100000-8 25.1ms ± 1% 21.3ms ± 1% -15.26% (p=0.000 n=10+10) Exp3Power/0x400000-8 225ms ± 1% 190ms ± 1% -15.61% (p=0.000 n=10+10) Fibo-8 23.4ms ± 1% 23.3ms ± 0% ~ (p=0.052 n=10+10) NatSqr/1-8 58.4ns ±24% 59.8ns ±38% ~ (p=0.739 n=10+10) NatSqr/2-8 122ns ±21% 122ns ±16% ~ (p=0.896 n=10+10) NatSqr/3-8 140ns ±28% 148ns ±30% ~ (p=0.288 n=10+10) NatSqr/5-8 193ns ±29% 210ns ±34% ~ (p=0.469 n=10+10) NatSqr/8-8 317ns ±21% 296ns ±25% ~ (p=0.393 n=10+10) NatSqr/10-8 362ns ± 8% 373ns ±30% ~ (p=0.617 n=9+10) NatSqr/20-8 1.24µs ±16% 1.06µs ±29% -14.57% (p=0.019 n=10+10) NatSqr/30-8 1.90µs ±32% 1.71µs ±10% ~ (p=0.176 n=10+9) NatSqr/50-8 4.22µs ±19% 3.67µs ± 7% -13.03% (p=0.017 n=10+9) NatSqr/80-8 7.33µs ±20% 6.50µs ±15% -11.26% (p=0.009 n=10+10) NatSqr/100-8 9.84µs ±18% 9.33µs ± 8% ~ (p=0.280 n=10+10) NatSqr/200-8 21.4µs ± 7% 20.0µs ±14% ~ (p=0.075 n=10+10) NatSqr/300-8 38.0µs ± 2% 31.3µs ±10% -17.63% (p=0.000 n=10+10) NatSqr/500-8 102µs ± 5% 101µs ± 4% ~ (p=0.780 n=9+10) NatSqr/800-8 190µs ± 3% 166µs ± 6% -12.29% (p=0.000 n=10+10) NatSqr/1000-8 277µs ± 2% 245µs ± 6% -11.64% (p=0.000 n=10+10) ScanPi-8 144µs ±23% 149µs ±24% ~ (p=0.579 n=10+10) StringPiParallel-8 25.6µs ± 0% 25.8µs ± 0% +0.69% (p=0.000 n=9+10) Scan/10/Base2-8 305ns ± 1% 309ns ± 1% +1.32% (p=0.000 n=10+9) Scan/100/Base2-8 1.95µs ± 1% 1.98µs ± 1% +1.10% (p=0.000 n=10+10) Scan/1000/Base2-8 19.5µs ± 1% 19.7µs ± 1% +1.39% (p=0.000 n=10+10) Scan/10000/Base2-8 270µs ± 1% 272µs ± 1% +0.58% (p=0.024 n=9+9) Scan/100000/Base2-8 10.3ms ± 0% 10.3ms ± 0% +0.16% (p=0.022 n=9+10) Scan/10/Base8-8 146ns ± 4% 154ns ± 4% +5.57% (p=0.000 n=9+9) Scan/100/Base8-8 748ns ± 1% 759ns ± 1% +1.51% (p=0.000 n=9+10) Scan/1000/Base8-8 7.88µs ± 1% 8.00µs ± 1% +1.64% (p=0.000 n=10+10) Scan/10000/Base8-8 155µs ± 1% 155µs ± 1% ~ (p=0.968 n=10+9) Scan/100000/Base8-8 9.11ms ± 0% 9.11ms ± 0% ~ (p=0.604 n=9+10) Scan/10/Base10-8 140ns ± 5% 149ns ± 5% +6.39% (p=0.000 n=9+10) Scan/100/Base10-8 680ns ± 0% 688ns ± 1% +1.08% (p=0.000 n=9+10) Scan/1000/Base10-8 7.09µs ± 1% 7.16µs ± 1% +0.98% (p=0.019 n=10+10) Scan/10000/Base10-8 149µs ± 3% 150µs ± 3% ~ (p=0.143 n=10+10) Scan/100000/Base10-8 9.16ms ± 0% 9.16ms ± 0% ~ (p=0.661 n=10+9) Scan/10/Base16-8 134ns ± 5% 135ns ± 3% ~ (p=0.505 n=9+9) Scan/100/Base16-8 560ns ± 1% 563ns ± 0% +0.67% (p=0.000 n=10+8) Scan/1000/Base16-8 6.28µs ± 1% 6.26µs ± 1% ~ (p=0.448 n=10+10) Scan/10000/Base16-8 161µs ± 1% 162µs ± 1% +0.74% (p=0.008 n=9+9) Scan/100000/Base16-8 9.64ms ± 0% 9.64ms ± 0% ~ (p=0.436 n=10+10) String/10/Base2-8 116ns ±12% 118ns ±13% ~ (p=0.645 n=10+10) String/100/Base2-8 871ns ±23% 860ns ±22% ~ (p=0.699 n=10+10) String/1000/Base2-8 10.0µs ±20% 10.0µs ±23% ~ (p=0.853 n=10+10) String/10000/Base2-8 110µs ±21% 120µs ±25% ~ (p=0.436 n=10+10) String/100000/Base2-8 768µs ±11% 733µs ±16% ~ (p=0.393 n=10+10) String/10/Base8-8 51.3ns ± 1% 51.0ns ± 3% ~ (p=0.286 n=9+9) String/100/Base8-8 284ns ± 9% 272ns ±12% ~ (p=0.267 n=9+10) String/1000/Base8-8 3.06µs ± 9% 3.04µs ±10% ~ (p=0.739 n=10+10) String/10000/Base8-8 36.1µs ±14% 35.1µs ± 9% ~ (p=0.447 n=10+9) String/100000/Base8-8 371µs ±12% 373µs ±16% ~ (p=0.739 n=10+10) String/10/Base10-8 167ns ±11% 165ns ± 9% ~ (p=0.781 n=10+10) String/100/Base10-8 727ns ± 1% 740ns ± 2% +1.70% (p=0.001 n=10+10) String/1000/Base10-8 5.30µs ±18% 5.37µs ±14% ~ (p=0.631 n=10+10) String/10000/Base10-8 45.0µs ±14% 44.6µs ±10% ~ (p=0.720 n=9+10) String/100000/Base10-8 5.10ms ± 1% 5.05ms ± 3% ~ (p=0.211 n=9+10) String/10/Base16-8 47.7ns ± 6% 47.7ns ± 6% ~ (p=0.985 n=10+10) String/100/Base16-8 221ns ±10% 234ns ±27% ~ (p=0.541 n=10+10) String/1000/Base16-8 2.23µs ±11% 2.12µs ± 8% -4.81% (p=0.029 n=9+8) String/10000/Base16-8 28.3µs ±21% 28.5µs ±14% ~ (p=0.796 n=10+10) String/100000/Base16-8 291µs ±16% 293µs ±15% ~ (p=0.931 n=9+9) LeafSize/0-8 2.43ms ± 1% 2.49ms ± 1% +2.56% (p=0.000 n=10+10) LeafSize/1-8 49.7µs ± 9% 46.3µs ±16% -6.78% (p=0.017 n=10+9) LeafSize/2-8 48.4µs ±18% 46.3µs ±19% ~ (p=0.436 n=10+10) LeafSize/3-8 81.7µs ± 3% 80.9µs ± 3% ~ (p=0.278 n=10+9) LeafSize/4-8 47.0µs ± 7% 47.9µs ±13% ~ (p=0.905 n=9+10) LeafSize/5-8 96.8µs ± 1% 97.3µs ± 2% ~ (p=0.515 n=8+10) LeafSize/6-8 82.5µs ± 4% 80.9µs ± 2% -1.92% (p=0.019 n=10+10) LeafSize/7-8 67.2µs ±13% 66.6µs ± 9% ~ (p=0.842 n=10+9) LeafSize/8-8 46.0µs ±28% 45.1µs ±12% ~ (p=0.739 n=10+10) LeafSize/9-8 111µs ± 1% 111µs ± 1% ~ (p=0.739 n=10+10) LeafSize/10-8 98.8µs ± 4% 97.9µs ± 3% ~ (p=0.278 n=10+9) LeafSize/11-8 96.8µs ± 1% 96.4µs ± 1% ~ (p=0.211 n=9+10) LeafSize/12-8 81.0µs ± 4% 81.3µs ± 3% ~ (p=0.579 n=10+10) LeafSize/13-8 79.7µs ± 5% 79.2µs ± 3% ~ (p=0.661 n=10+9) LeafSize/14-8 67.6µs ±12% 65.8µs ± 7% ~ (p=0.447 n=10+9) LeafSize/15-8 63.9µs ±17% 66.3µs ±14% ~ (p=0.481 n=10+10) LeafSize/16-8 44.0µs ±28% 46.0µs ±27% ~ (p=0.481 n=10+10) LeafSize/32-8 46.2µs ±13% 43.5µs ±18% ~ (p=0.156 n=9+10) LeafSize/64-8 53.3µs ±10% 53.0µs ±19% ~ (p=0.730 n=9+9) ProbablyPrime/n=0-8 3.60ms ± 1% 3.39ms ± 1% -5.87% (p=0.000 n=10+9) ProbablyPrime/n=1-8 4.42ms ± 1% 4.08ms ± 1% -7.69% (p=0.000 n=10+10) ProbablyPrime/n=5-8 7.57ms ± 2% 6.79ms ± 1% -10.24% (p=0.000 n=10+10) ProbablyPrime/n=10-8 11.6ms ± 2% 10.2ms ± 1% -11.69% (p=0.000 n=10+10) ProbablyPrime/n=20-8 19.4ms ± 2% 16.9ms ± 2% -12.89% (p=0.000 n=10+10) ProbablyPrime/Lucas-8 2.81ms ± 2% 2.72ms ± 1% -3.22% (p=0.000 n=10+9) ProbablyPrime/MillerRabinBase2-8 797µs ± 1% 680µs ± 1% -14.64% (p=0.000 n=10+10) name old speed new speed delta AddVV/1-8 17.1GB/s ± 6% 18.0GB/s ± 2% ~ (p=0.122 n=10+8) AddVV/2-8 32.4GB/s ± 2% 32.2GB/s ± 4% ~ (p=0.661 n=10+9) AddVV/3-8 38.6GB/s ± 2% 38.9GB/s ± 1% ~ (p=0.113 n=10+9) AddVV/4-8 45.8GB/s ± 2% 45.8GB/s ± 2% ~ (p=0.796 n=10+10) AddVV/5-8 48.1GB/s ± 2% 48.3GB/s ± 1% ~ (p=0.315 n=10+10) AddVV/10-8 78.9GB/s ± 1% 78.9GB/s ± 2% ~ (p=0.353 n=10+10) AddVV/100-8 136GB/s ± 2% 137GB/s ± 1% ~ (p=0.971 n=10+10) AddVV/1000-8 164GB/s ± 1% 164GB/s ± 4% ~ (p=0.853 n=10+10) AddVV/10000-8 126GB/s ± 6% 129GB/s ± 2% ~ (p=0.063 n=10+10) AddVV/100000-8 116GB/s ± 3% 116GB/s ± 3% ~ (p=0.796 n=10+10) AddVW/1-8 2.64GB/s ± 3% 2.64GB/s ± 3% ~ (p=0.579 n=10+10) AddVW/2-8 4.49GB/s ± 2% 4.44GB/s ± 2% -1.09% (p=0.040 n=9+9) AddVW/3-8 6.36GB/s ± 1% 6.34GB/s ± 2% ~ (p=0.684 n=10+10) AddVW/4-8 6.83GB/s ± 1% 6.82GB/s ± 2% ~ (p=0.905 n=10+9) AddVW/5-8 8.75GB/s ± 1% 8.73GB/s ± 1% ~ (p=0.796 n=10+10) AddVW/10-8 10.5GB/s ± 2% 10.5GB/s ± 1% ~ (p=0.971 n=10+10) AddVW/100-8 19.5GB/s ± 2% 18.9GB/s ± 2% -3.22% (p=0.000 n=10+10) AddVW/1000-8 20.7GB/s ± 2% 20.6GB/s ± 4% ~ (p=0.631 n=10+10) AddVW/10000-8 20.6GB/s ± 3% 20.7GB/s ± 3% ~ (p=0.481 n=10+10) AddVW/100000-8 19.4GB/s ± 2% 19.2GB/s ± 3% ~ (p=0.165 n=10+10) AddMulVVW/1-8 19.5GB/s ± 2% 19.7GB/s ± 3% ~ (p=0.123 n=10+10) AddMulVVW/2-8 30.1GB/s ± 2% 30.2GB/s ± 3% ~ (p=0.297 n=9+9) AddMulVVW/3-8 37.9GB/s ± 2% 36.5GB/s ± 2% -3.63% (p=0.000 n=10+10) AddMulVVW/4-8 40.0GB/s ± 2% 39.4GB/s ± 2% -1.58% (p=0.001 n=10+10) AddMulVVW/5-8 47.3GB/s ± 2% 46.6GB/s ± 1% -1.35% (p=0.001 n=9+9) AddMulVVW/10-8 52.3GB/s ± 2% 60.6GB/s ± 3% +15.76% (p=0.000 n=10+10) AddMulVVW/100-8 80.3GB/s ± 2% 122.1GB/s ± 1% +51.92% (p=0.000 n=10+10) AddMulVVW/1000-8 92.0GB/s ± 1% 130.3GB/s ± 2% +41.61% (p=0.000 n=9+10) AddMulVVW/10000-8 88.2GB/s ± 2% 108.2GB/s ± 5% +22.66% (p=0.000 n=10+10) AddMulVVW/100000-8 88.2GB/s ± 2% 102.9GB/s ± 2% +16.69% (p=0.000 n=10+10) Change-Id: Ic98e30c91d437d845fed03e07e976c3fdbf02b36 Reviewed-on: https://go-review.googlesource.com/74851 Run-TryBot: Ilya Tocar <ilya.tocar@intel.com> TryBot-Result: Gobot Gobot <gobot@golang.org> Reviewed-by: Adam Langley <agl@golang.org>
This commit is contained in:
Ilya Tocar
Brad Fitzpatrick
parent
9697a119e6
commit
c3935c08d2
11
src/math/big/arith_amd64.go
Normal file
11
src/math/big/arith_amd64.go
Normal file
@ -0,0 +1,11 @@
|
||||
// Copyright 2017 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 !math_big_pure_go
|
||||
|
||||
package big
|
||||
|
||||
import "internal/cpu"
|
||||
|
||||
var support_adx = cpu.X86.HasADX && cpu.X86.HasBMI2
|
||||
@ -378,6 +378,8 @@ E5: CMPQ BX, R11 // i < n
|
||||
|
||||
// func addMulVVW(z, x []Word, y Word) (c Word)
|
||||
TEXT ·addMulVVW(SB),NOSPLIT,$0
|
||||
CMPB ·support_adx(SB), $1
|
||||
JEQ adx
|
||||
MOVQ z+0(FP), R10
|
||||
MOVQ x+24(FP), R8
|
||||
MOVQ y+48(FP), R9
|
||||
@ -429,6 +431,97 @@ E6: CMPQ BX, R11 // i < n
|
||||
MOVQ CX, c+56(FP)
|
||||
RET
|
||||
|
||||
adx:
|
||||
MOVQ z_len+8(FP), R11
|
||||
MOVQ z+0(FP), R10
|
||||
MOVQ x+24(FP), R8
|
||||
MOVQ y+48(FP), DX
|
||||
MOVQ $0, BX // i = 0
|
||||
MOVQ $0, CX // carry
|
||||
CMPQ R11, $8
|
||||
JAE adx_loop_header
|
||||
CMPQ BX, R11
|
||||
JL adx_short
|
||||
MOVQ CX, c+56(FP)
|
||||
RET
|
||||
|
||||
adx_loop_header:
|
||||
MOVQ R11, R13
|
||||
ANDQ $-8, R13
|
||||
adx_loop:
|
||||
XORQ R9, R9 // unset flags
|
||||
MULXQ (R8), SI, DI
|
||||
ADCXQ CX,SI
|
||||
ADOXQ (R10), SI
|
||||
MOVQ SI,(R10)
|
||||
|
||||
MULXQ 8(R8), AX, CX
|
||||
ADCXQ DI, AX
|
||||
ADOXQ 8(R10), AX
|
||||
MOVQ AX, 8(R10)
|
||||
|
||||
MULXQ 16(R8), SI, DI
|
||||
ADCXQ CX, SI
|
||||
ADOXQ 16(R10), SI
|
||||
MOVQ SI, 16(R10)
|
||||
|
||||
MULXQ 24(R8), AX, CX
|
||||
ADCXQ DI, AX
|
||||
ADOXQ 24(R10), AX
|
||||
MOVQ AX, 24(R10)
|
||||
|
||||
MULXQ 32(R8), SI, DI
|
||||
ADCXQ CX, SI
|
||||
ADOXQ 32(R10), SI
|
||||
MOVQ SI, 32(R10)
|
||||
|
||||
MULXQ 40(R8), AX, CX
|
||||
ADCXQ DI, AX
|
||||
ADOXQ 40(R10), AX
|
||||
MOVQ AX, 40(R10)
|
||||
|
||||
MULXQ 48(R8), SI, DI
|
||||
ADCXQ CX, SI
|
||||
ADOXQ 48(R10), SI
|
||||
MOVQ SI, 48(R10)
|
||||
|
||||
MULXQ 56(R8), AX, CX
|
||||
ADCXQ DI, AX
|
||||
ADOXQ 56(R10), AX
|
||||
MOVQ AX, 56(R10)
|
||||
|
||||
ADCXQ R9, CX
|
||||
ADOXQ R9, CX
|
||||
|
||||
ADDQ $64, R8
|
||||
ADDQ $64, R10
|
||||
ADDQ $8, BX
|
||||
|
||||
CMPQ BX, R13
|
||||
JL adx_loop
|
||||
MOVQ z+0(FP), R10
|
||||
MOVQ x+24(FP), R8
|
||||
CMPQ BX, R11
|
||||
JL adx_short
|
||||
MOVQ CX, c+56(FP)
|
||||
RET
|
||||
|
||||
adx_short:
|
||||
MULXQ (R8)(BX*8), SI, DI
|
||||
ADDQ CX, SI
|
||||
ADCQ $0, DI
|
||||
ADDQ SI, (R10)(BX*8)
|
||||
ADCQ $0, DI
|
||||
MOVQ DI, CX
|
||||
ADDQ $1, BX // i++
|
||||
|
||||
CMPQ BX, R11
|
||||
JL adx_short
|
||||
|
||||
MOVQ CX, c+56(FP)
|
||||
RET
|
||||
|
||||
|
||||
|
||||
// func divWVW(z []Word, xn Word, x []Word, y Word) (r Word)
|
||||
TEXT ·divWVW(SB),NOSPLIT,$0
|
||||
|
||||
Loading…
Reference in New Issue
Block a user