cb7a0b5aef
Do fast by one multiplication ( #130 )
...
When multiplying by one we can use faster math.
2020-05-06 11:14:25 +02:00
0e9e10435f
avx2: Add 64 bytes per loop processing ( #128 )
...
* avx2: Add 64 bytes per loop processing
Not super clean benchmark run, but `BenchmarkGalois` is consistently faster.
```
benchmark old ns/op new ns/op delta
BenchmarkGalois128K-32 2551 2261 -11.37%
BenchmarkGalois1M-32 22492 21107 -6.16%
BenchmarkGaloisXor128K-32 2972 2808 -5.52%
BenchmarkGaloisXor1M-32 25181 23951 -4.88%
BenchmarkEncode10x2x10000-32 5081 4722 -7.07%
BenchmarkEncode100x20x10000-32 383800 346655 -9.68%
BenchmarkEncode17x3x1M-32 264806 263191 -0.61%
BenchmarkEncode10x4x16M-32 8337857 8376910 +0.47%
BenchmarkEncode5x2x1M-32 77119 73598 -4.57%
BenchmarkEncode10x2x1M-32 108424 102423 -5.53%
BenchmarkEncode10x4x1M-32 194427 184301 -5.21%
BenchmarkEncode50x20x1M-32 3870301 3747639 -3.17%
BenchmarkEncode17x3x16M-32 10617586 10602449 -0.14%
BenchmarkEncode_8x4x8M-32 3227254 3229451 +0.07%
BenchmarkEncode_12x4x12M-32 6841898 6847261 +0.08%
BenchmarkEncode_16x4x16M-32 11153469 11048738 -0.94%
BenchmarkEncode_16x4x32M-32 21947506 21826647 -0.55%
BenchmarkEncode_16x4x64M-32 43163608 42971338 -0.45%
BenchmarkEncode_8x5x8M-32 3856675 3780730 -1.97%
BenchmarkEncode_8x6x8M-32 4322023 4437109 +2.66%
BenchmarkEncode_8x7x8M-32 5011434 4959623 -1.03%
BenchmarkEncode_8x9x8M-32 6243694 6098824 -2.32%
BenchmarkEncode_8x10x8M-32 6724456 6657099 -1.00%
BenchmarkEncode_8x11x8M-32 7207693 7340332 +1.84%
BenchmarkEncode_8x8x05M-32 176877 172183 -2.65%
BenchmarkEncode_8x8x1M-32 309716 301743 -2.57%
BenchmarkEncode_8x8x8M-32 5498952 5489078 -0.18%
BenchmarkEncode_8x8x32M-32 22630195 22557074 -0.32%
BenchmarkEncode_24x8x24M-32 28488886 28220702 -0.94%
BenchmarkEncode_24x8x48M-32 56124735 54862495 -2.25%
BenchmarkVerify10x2x10000-32 9874 9356 -5.25%
BenchmarkVerify50x5x50000-32 175610 159735 -9.04%
BenchmarkVerify10x2x1M-32 331276 311726 -5.90%
BenchmarkVerify5x2x1M-32 265466 248075 -6.55%
BenchmarkVerify10x4x1M-32 701627 606420 -13.57%
BenchmarkVerify50x20x1M-32 4338171 4245635 -2.13%
BenchmarkVerify10x4x16M-32 12312830 11932698 -3.09%
BenchmarkReconstruct10x2x10000-32 1594 1504 -5.65%
BenchmarkReconstruct50x5x50000-32 95101 79558 -16.34%
BenchmarkReconstruct10x2x1M-32 38479 37225 -3.26%
BenchmarkReconstruct5x2x1M-32 30968 30013 -3.08%
BenchmarkReconstruct10x4x1M-32 81630 75350 -7.69%
BenchmarkReconstruct50x20x1M-32 1136952 1040156 -8.51%
BenchmarkReconstruct10x4x16M-32 685408 656484 -4.22%
BenchmarkReconstructData10x2x10000-32 1609 1486 -7.64%
BenchmarkReconstructData50x5x50000-32 87090 71512 -17.89%
BenchmarkReconstructData10x2x1M-32 31497 30347 -3.65%
BenchmarkReconstructData5x2x1M-32 23379 22611 -3.28%
BenchmarkReconstructData10x4x1M-32 63853 61035 -4.41%
BenchmarkReconstructData50x20x1M-32 1048807 966201 -7.88%
BenchmarkReconstructData10x4x16M-32 866658 892252 +2.95%
BenchmarkReconstructP10x2x10000-32 544 540 -0.74%
BenchmarkReconstructP10x5x20000-32 1242 1206 -2.90%
BenchmarkSplit10x4x160M-32 2735508 2743214 +0.28%
BenchmarkSplit5x2x5M-32 276232 288523 +4.45%
BenchmarkSplit10x2x1M-32 44389 45517 +2.54%
BenchmarkSplit10x4x10M-32 477282 460888 -3.43%
BenchmarkSplit50x20x50M-32 1608821 1602105 -0.42%
BenchmarkSplit17x3x272M-32 2035932 2034705 -0.06%
BenchmarkParallel_8x8x05M-32 346733 351837 +1.47%
BenchmarkParallel_20x10x05M-32 577127 586232 +1.58%
BenchmarkParallel_8x8x1M-32 722453 729294 +0.95%
BenchmarkParallel_8x8x8M-32 5717650 5817130 +1.74%
BenchmarkParallel_8x8x32M-32 22914260 24132696 +5.32%
BenchmarkStreamEncode10x2x10000-32 6703131 7141021 +6.53%
BenchmarkStreamEncode100x20x10000-32 38175873 39767386 +4.17%
BenchmarkStreamEncode17x3x1M-32 8920549 9218973 +3.35%
BenchmarkStreamEncode10x4x16M-32 21841702 21784898 -0.26%
BenchmarkStreamEncode5x2x1M-32 4088001 3247404 -20.56%
BenchmarkStreamEncode10x2x1M-32 5860652 5932381 +1.22%
BenchmarkStreamEncode10x4x1M-32 7555172 7589960 +0.46%
BenchmarkStreamEncode50x20x1M-32 30006814 30250054 +0.81%
BenchmarkStreamEncode17x3x16M-32 32757489 32818254 +0.19%
BenchmarkStreamVerify10x2x10000-32 6714996 6831093 +1.73%
BenchmarkStreamVerify50x5x50000-32 18525904 18761767 +1.27%
BenchmarkStreamVerify10x2x1M-32 5232278 5444148 +4.05%
BenchmarkStreamVerify5x2x1M-32 3673843 3755283 +2.22%
BenchmarkStreamVerify10x4x1M-32 7184419 7185293 +0.01%
BenchmarkStreamVerify50x20x1M-32 28441187 28574766 +0.47%
BenchmarkStreamVerify10x4x16M-32 8538440 8668614 +1.52%
benchmark old MB/s new MB/s speedup
BenchmarkGalois128K-32 51374.59 57976.36 1.13x
BenchmarkGalois1M-32 46620.03 49679.10 1.07x
BenchmarkGaloisXor128K-32 44106.22 46671.56 1.06x
BenchmarkGaloisXor1M-32 41641.82 43779.89 1.05x
BenchmarkEncode10x2x10000-32 19682.61 21176.81 1.08x
BenchmarkEncode100x20x10000-32 2605.52 2884.71 1.11x
BenchmarkEncode17x3x1M-32 67316.54 67729.50 1.01x
BenchmarkEncode10x4x16M-32 20121.74 20027.93 1.00x
BenchmarkEncode5x2x1M-32 67984.17 71236.47 1.05x
BenchmarkEncode10x2x1M-32 96710.29 102377.00 1.06x
BenchmarkEncode10x4x1M-32 53931.74 56894.82 1.05x
BenchmarkEncode50x20x1M-32 13546.44 13989.82 1.03x
BenchmarkEncode17x3x16M-32 26862.29 26900.64 1.00x
BenchmarkEncode_8x4x8M-32 20794.42 20780.27 1.00x
BenchmarkEncode_12x4x12M-32 22069.16 22051.88 1.00x
BenchmarkEncode_16x4x16M-32 24067.44 24295.58 1.01x
BenchmarkEncode_16x4x32M-32 24461.59 24597.04 1.01x
BenchmarkEncode_16x4x64M-32 24876.09 24987.40 1.00x
BenchmarkEncode_8x5x8M-32 17400.71 17750.24 1.02x
BenchmarkEncode_8x6x8M-32 15527.19 15124.46 0.97x
BenchmarkEncode_8x7x8M-32 13391.15 13531.04 1.01x
BenchmarkEncode_8x9x8M-32 10748.26 11003.58 1.02x
BenchmarkEncode_8x10x8M-32 9979.82 10080.80 1.01x
BenchmarkEncode_8x11x8M-32 9310.73 9142.48 0.98x
BenchmarkEncode_8x8x05M-32 23713.12 24359.50 1.03x
BenchmarkEncode_8x8x1M-32 27084.87 27800.50 1.03x
BenchmarkEncode_8x8x8M-32 12203.94 12225.89 1.00x
BenchmarkEncode_8x8x32M-32 11861.83 11900.28 1.00x
BenchmarkEncode_24x8x24M-32 21200.54 21402.01 1.01x
BenchmarkEncode_24x8x48M-32 21522.77 22017.95 1.02x
BenchmarkVerify10x2x10000-32 10127.24 10688.01 1.06x
BenchmarkVerify50x5x50000-32 28472.25 31301.75 1.10x
BenchmarkVerify10x2x1M-32 31652.63 33637.74 1.06x
BenchmarkVerify5x2x1M-32 19749.74 21134.27 1.07x
BenchmarkVerify10x4x1M-32 14944.92 17291.25 1.16x
BenchmarkVerify50x20x1M-32 12085.46 12348.87 1.02x
BenchmarkVerify10x4x16M-32 13625.80 14059.87 1.03x
BenchmarkReconstruct10x2x10000-32 62723.68 66470.81 1.06x
BenchmarkReconstruct50x5x50000-32 52575.87 62847.32 1.20x
BenchmarkReconstruct10x2x1M-32 272507.04 281685.84 1.03x
BenchmarkReconstruct5x2x1M-32 169299.03 174685.39 1.03x
BenchmarkReconstruct10x4x1M-32 128455.17 139161.42 1.08x
BenchmarkReconstruct50x20x1M-32 46113.48 50404.73 1.09x
BenchmarkReconstruct10x4x16M-32 244777.11 255561.72 1.04x
BenchmarkReconstructData10x2x10000-32 62160.46 67305.98 1.08x
BenchmarkReconstructData50x5x50000-32 57411.81 69917.97 1.22x
BenchmarkReconstructData10x2x1M-32 332909.82 345526.29 1.04x
BenchmarkReconstructData5x2x1M-32 224254.60 231868.74 1.03x
BenchmarkReconstructData10x4x1M-32 164216.61 171799.68 1.05x
BenchmarkReconstructData50x20x1M-32 49988.98 54262.82 1.09x
BenchmarkReconstructData10x4x16M-32 193585.15 188032.29 0.97x
BenchmarkReconstructP10x2x10000-32 183806.57 185284.57 1.01x
BenchmarkReconstructP10x5x20000-32 160985.46 165852.51 1.03x
BenchmarkParallel_8x8x05M-32 12096.63 11921.17 0.99x
BenchmarkParallel_20x10x05M-32 18168.91 17886.72 0.98x
BenchmarkParallel_8x8x1M-32 11611.28 11502.36 0.99x
BenchmarkParallel_8x8x8M-32 11737.14 11536.42 0.98x
BenchmarkParallel_8x8x32M-32 11714.78 11123.31 0.95x
BenchmarkStreamEncode10x2x10000-32 14.92 14.00 0.94x
BenchmarkStreamEncode100x20x10000-32 26.19 25.15 0.96x
BenchmarkStreamEncode17x3x1M-32 1998.28 1933.60 0.97x
BenchmarkStreamEncode10x4x16M-32 7681.28 7701.31 1.00x
BenchmarkStreamEncode5x2x1M-32 1282.50 1614.48 1.26x
BenchmarkStreamEncode10x2x1M-32 1789.18 1767.55 0.99x
BenchmarkStreamEncode10x4x1M-32 1387.89 1381.53 1.00x
BenchmarkStreamEncode50x20x1M-32 1747.23 1733.18 0.99x
BenchmarkStreamEncode17x3x16M-32 8706.79 8690.67 1.00x
BenchmarkStreamVerify10x2x10000-32 14.89 14.64 0.98x
BenchmarkStreamVerify50x5x50000-32 269.89 266.50 0.99x
BenchmarkStreamVerify10x2x1M-32 2004.05 1926.06 0.96x
BenchmarkStreamVerify5x2x1M-32 1427.08 1396.13 0.98x
BenchmarkStreamVerify10x4x1M-32 1459.51 1459.34 1.00x
BenchmarkStreamVerify50x20x1M-32 1843.41 1834.79 1.00x
BenchmarkStreamVerify10x4x16M-32 19649.04 19353.98 0.98x
```
2020-05-05 16:36:01 +02:00
abb309aca7
Fix stream allocations ( #129 )
...
Numbers speak for themselves:
```
benchmark old ns/op new ns/op delta
BenchmarkStreamEncode10x2x10000-32 4792420 7937 -99.83%
BenchmarkStreamEncode100x20x10000-32 38424066 473285 -98.77%
BenchmarkStreamEncode17x3x1M-32 8195036 1482191 -81.91%
BenchmarkStreamEncode10x4x16M-32 21356715 18051773 -15.47%
BenchmarkStreamEncode5x2x1M-32 3295827 412301 -87.49%
BenchmarkStreamEncode10x2x1M-32 5249011 798828 -84.78%
BenchmarkStreamEncode10x4x1M-32 6392974 904818 -85.85%
BenchmarkStreamEncode50x20x1M-32 29083474 7199282 -75.25%
BenchmarkStreamEncode17x3x16M-32 32451850 28036421 -13.61%
BenchmarkStreamVerify10x2x10000-32 4858416 12988 -99.73%
BenchmarkStreamVerify50x5x50000-32 17047361 377003 -97.79%
BenchmarkStreamVerify10x2x1M-32 4869964 887214 -81.78%
BenchmarkStreamVerify5x2x1M-32 3282999 591669 -81.98%
BenchmarkStreamVerify10x4x1M-32 5824392 1230888 -78.87%
BenchmarkStreamVerify50x20x1M-32 27301648 6204613 -77.27%
BenchmarkStreamVerify10x4x16M-32 8508963 18845695 +121.48%
benchmark old MB/s new MB/s speedup
BenchmarkStreamEncode10x2x10000-32 20.87 12599.82 603.73x
BenchmarkStreamEncode100x20x10000-32 26.03 2112.89 81.17x
BenchmarkStreamEncode17x3x1M-32 2175.19 12026.65 5.53x
BenchmarkStreamEncode10x4x16M-32 7855.71 9293.94 1.18x
BenchmarkStreamEncode5x2x1M-32 1590.76 12716.14 7.99x
BenchmarkStreamEncode10x2x1M-32 1997.66 13126.43 6.57x
BenchmarkStreamEncode10x4x1M-32 1640.20 11588.81 7.07x
BenchmarkStreamEncode50x20x1M-32 1802.70 7282.50 4.04x
BenchmarkStreamEncode17x3x16M-32 8788.80 10172.93 1.16x
BenchmarkStreamVerify10x2x10000-32 20.58 7699.20 374.11x
BenchmarkStreamVerify50x5x50000-32 293.30 13262.49 45.22x
BenchmarkStreamVerify10x2x1M-32 2153.15 11818.75 5.49x
BenchmarkStreamVerify5x2x1M-32 1596.98 8861.17 5.55x
BenchmarkStreamVerify10x4x1M-32 1800.32 8518.86 4.73x
BenchmarkStreamVerify50x20x1M-32 1920.35 8449.97 4.40x
BenchmarkStreamVerify10x4x16M-32 19717.11 8902.41 0.45x
```
2020-05-05 16:35:35 +02:00
dccac354fe
Add cross compilation ( #127 )
...
* Add cross compilation
Add 386 as 32 bit test, arm64 and ppc64le since they have assembly.
2020-05-04 21:19:49 +02:00
f525ef0450
Clean up build tags ( #126 )
...
Move non-amd64 code to a separate file and remove references in other files.
Fixes #125
2020-05-04 20:06:47 +02:00
a0556fddfa
Add go.sum as well.
2020-05-04 10:19:03 +02:00
de70cc155f
AVX512 parallel processing ( #120 )
...
Do concurrent processing in AVX512 mode and split jobs by cache size.
2020-05-04 09:17:40 +02:00
e920b5fec3
Add direct modules support ( #124 )
...
* Add direct modules support
* Add tests with various assembly disabled.
* Add Go 1.14 - remove 1.11
2020-05-03 21:53:25 +02:00
d069fb1019
Remove a bounds check in pure Go ( #123 )
...
40% faster on the pure operation.
```
benchmark old ns/op new ns/op delta
BenchmarkParallel_8x8x05M-8 2990849 2763554 -7.60%
BenchmarkParallel_8x8x1M-8 4941575 5061619 +2.43%
BenchmarkParallel_8x8x8M-8 34257722 33192541 -3.11%
BenchmarkParallel_8x8x32M-8 143157262 131654688 -8.03%
BenchmarkGalois128K-8 64201 38374 -40.23%
BenchmarkGalois1M-8 507053 307236 -39.41%
BenchmarkGaloisXor128K-8 63815 63157 -1.03%
BenchmarkGaloisXor1M-8 506369 505641 -0.14%
BenchmarkEncode10x2x10000-8 96414 92781 -3.77%
BenchmarkEncode100x20x10000-8 3188549 3238299 +1.56%
BenchmarkEncode17x3x1M-8 3741349 3633535 -2.88%
BenchmarkEncode10x4x16M-8 41628596 40306100 -3.18%
BenchmarkEncode5x2x1M-8 724162 699137 -3.46%
BenchmarkEncode10x2x1M-8 1451401 1423224 -1.94%
BenchmarkEncode10x4x1M-8 2839382 2740249 -3.49%
BenchmarkEncode50x20x1M-8 68415407 67015156 -2.05%
BenchmarkEncode17x3x16M-8 53734221 51784418 -3.63%
BenchmarkEncode_8x4x8M-8 16826004 16013691 -4.83%
BenchmarkEncode_12x4x12M-8 37544203 36392439 -3.07%
BenchmarkEncode_16x4x16M-8 66070450 69062838 +4.53%
BenchmarkEncode_16x4x32M-8 133905200 130529500 -2.52%
BenchmarkEncode_16x4x64M-8 281313400 265809900 -5.51%
BenchmarkEncode_8x5x8M-8 20789000 19866553 -4.44%
BenchmarkEncode_8x6x8M-8 25027385 25087290 +0.24%
BenchmarkEncode_8x7x8M-8 29156578 28231372 -3.17%
BenchmarkEncode_8x9x8M-8 37286413 37383431 +0.26%
BenchmarkEncode_8x10x8M-8 41722722 39786752 -4.64%
BenchmarkEncode_8x11x8M-8 45692118 43409812 -4.99%
BenchmarkEncode_8x8x05M-8 2358946 2298631 -2.56%
BenchmarkEncode_8x8x1M-8 4551026 4357599 -4.25%
BenchmarkEncode_8x8x8M-8 33596074 31951653 -4.89%
BenchmarkEncode_8x8x32M-8 135030488 127382850 -5.66%
BenchmarkEncode_24x8x24M-8 297317050 301777575 +1.50%
BenchmarkEncode_24x8x48M-8 611638100 596134400 -2.53%
BenchmarkVerify10x2x10000-8 103723 103523 -0.19%
BenchmarkVerify50x5x50000-8 2170780 2148170 -1.04%
BenchmarkVerify10x2x1M-8 1693351 1676973 -0.97%
BenchmarkVerify5x2x1M-8 997721 995888 -0.18%
BenchmarkVerify10x4x1M-8 3354687 3296939 -1.72%
BenchmarkVerify50x20x1M-8 67491300 66890056 -0.89%
BenchmarkVerify10x4x16M-8 44195152 44356146 +0.36%
BenchmarkReconstruct10x2x10000-8 24720 23373 -5.45%
BenchmarkReconstruct50x5x50000-8 880988 858684 -2.53%
BenchmarkReconstruct10x2x1M-8 387655 368900 -4.84%
BenchmarkReconstruct5x2x1M-8 191067 175841 -7.97%
BenchmarkReconstruct10x4x1M-8 1040639 1004731 -3.45%
BenchmarkReconstruct50x20x1M-8 28507103 28467956 -0.14%
BenchmarkReconstruct10x4x16M-8 15829872 15225654 -3.82%
BenchmarkReconstructData10x2x10000-8 24369 23374 -4.08%
BenchmarkReconstructData50x5x50000-8 865039 852456 -1.45%
BenchmarkReconstructData10x2x1M-8 383240 366751 -4.30%
BenchmarkReconstructData5x2x1M-8 183644 170444 -7.19%
BenchmarkReconstructData10x4x1M-8 1010537 969151 -4.10%
BenchmarkReconstructData50x20x1M-8 28288428 28051051 -0.84%
BenchmarkReconstructData10x4x16M-8 15048840 14443250 -4.02%
BenchmarkReconstructP10x2x10000-8 3219 3122 -3.01%
BenchmarkReconstructP10x5x20000-8 23574 22704 -3.69%
BenchmarkSplit10x4x160M-8 2822150 2735071 -3.09%
BenchmarkSplit5x2x5M-8 409699 311346 -24.01%
BenchmarkSplit10x2x1M-8 43767 40247 -8.04%
BenchmarkSplit10x4x10M-8 741097 566888 -23.51%
BenchmarkSplit50x20x50M-8 1913475 1682060 -12.09%
BenchmarkSplit17x3x272M-8 2059505 2095628 +1.75%
BenchmarkStreamEncode10x2x10000-8 8517255 5226284 -38.64%
BenchmarkStreamEncode100x20x10000-8 41903836 40969212 -2.23%
BenchmarkStreamEncode17x3x1M-8 12038007 14129765 +17.38%
BenchmarkStreamEncode10x4x16M-8 56512840 54821895 -2.99%
BenchmarkStreamEncode5x2x1M-8 5326508 3966411 -25.53%
BenchmarkStreamEncode10x2x1M-8 6924358 6589396 -4.84%
BenchmarkStreamEncode10x4x1M-8 9016080 8459049 -6.18%
BenchmarkStreamEncode50x20x1M-8 93583042 94021200 +0.47%
BenchmarkStreamEncode17x3x16M-8 76643714 74750193 -2.47%
BenchmarkStreamVerify10x2x10000-8 8311646 5162179 -37.89%
BenchmarkStreamVerify50x5x50000-8 19015944 18352626 -3.49%
BenchmarkStreamVerify10x2x1M-8 5738380 5441592 -5.17%
BenchmarkStreamVerify5x2x1M-8 3462751 3328057 -3.89%
BenchmarkStreamVerify10x4x1M-8 6735717 6381116 -5.26%
BenchmarkStreamVerify50x20x1M-8 29844543 29416921 -1.43%
BenchmarkStreamVerify10x4x16M-8 8512699 8375778 -1.61%
benchmark old MB/s new MB/s speedup
BenchmarkParallel_8x8x05M-8 1402.38 1517.72 1.08x
BenchmarkParallel_8x8x1M-8 1697.56 1657.30 0.98x
BenchmarkParallel_8x8x8M-8 1958.94 2021.81 1.03x
BenchmarkParallel_8x8x32M-8 1875.11 2038.94 1.09x
BenchmarkGalois128K-8 2041.59 3415.64 1.67x
BenchmarkGalois1M-8 2067.98 3412.93 1.65x
BenchmarkGaloisXor128K-8 2053.92 2075.33 1.01x
BenchmarkGaloisXor1M-8 2070.77 2073.76 1.00x
BenchmarkEncode10x2x10000-8 1037.19 1077.81 1.04x
BenchmarkEncode100x20x10000-8 313.62 308.80 0.98x
BenchmarkEncode17x3x1M-8 4764.54 4905.91 1.03x
BenchmarkEncode10x4x16M-8 4030.21 4162.45 1.03x
BenchmarkEncode5x2x1M-8 7239.93 7499.07 1.04x
BenchmarkEncode10x2x1M-8 7224.58 7367.61 1.02x
BenchmarkEncode10x4x1M-8 3692.97 3826.57 1.04x
BenchmarkEncode50x20x1M-8 766.33 782.34 1.02x
BenchmarkEncode17x3x16M-8 5307.84 5507.69 1.04x
BenchmarkEncode_8x4x8M-8 3988.40 4190.72 1.05x
BenchmarkEncode_12x4x12M-8 4021.79 4149.07 1.03x
BenchmarkEncode_16x4x16M-8 4062.87 3886.83 0.96x
BenchmarkEncode_16x4x32M-8 4009.34 4113.02 1.03x
BenchmarkEncode_16x4x64M-8 3816.89 4039.51 1.06x
BenchmarkEncode_8x5x8M-8 3228.09 3377.98 1.05x
BenchmarkEncode_8x6x8M-8 2681.42 2675.01 1.00x
BenchmarkEncode_8x7x8M-8 2301.67 2377.10 1.03x
BenchmarkEncode_8x9x8M-8 1799.82 1795.15 1.00x
BenchmarkEncode_8x10x8M-8 1608.45 1686.71 1.05x
BenchmarkEncode_8x11x8M-8 1468.72 1545.94 1.05x
BenchmarkEncode_8x8x05M-8 1778.04 1824.70 1.03x
BenchmarkEncode_8x8x1M-8 1843.23 1925.05 1.04x
BenchmarkEncode_8x8x8M-8 1997.52 2100.33 1.05x
BenchmarkEncode_8x8x32M-8 1987.96 2107.31 1.06x
BenchmarkEncode_24x8x24M-8 2031.43 2001.41 0.99x
BenchmarkEncode_24x8x48M-8 1974.96 2026.32 1.03x
BenchmarkVerify10x2x10000-8 964.10 965.97 1.00x
BenchmarkVerify50x5x50000-8 2303.32 2327.56 1.01x
BenchmarkVerify10x2x1M-8 6192.31 6252.79 1.01x
BenchmarkVerify5x2x1M-8 5254.86 5264.53 1.00x
BenchmarkVerify10x4x1M-8 3125.70 3180.45 1.02x
BenchmarkVerify50x20x1M-8 776.82 783.81 1.01x
BenchmarkVerify10x4x16M-8 3796.17 3782.39 1.00x
BenchmarkReconstruct10x2x10000-8 4045.30 4278.40 1.06x
BenchmarkReconstruct50x5x50000-8 5675.45 5822.87 1.03x
BenchmarkReconstruct10x2x1M-8 27049.21 28424.40 1.05x
BenchmarkReconstruct5x2x1M-8 27440.02 29815.96 1.09x
BenchmarkReconstruct10x4x1M-8 10076.27 10436.39 1.04x
BenchmarkReconstruct50x20x1M-8 1839.15 1841.68 1.00x
BenchmarkReconstruct10x4x16M-8 10598.45 11019.04 1.04x
BenchmarkReconstructData10x2x10000-8 4103.60 4278.25 1.04x
BenchmarkReconstructData50x5x50000-8 5780.09 5865.40 1.01x
BenchmarkReconstructData10x2x1M-8 27360.79 28590.95 1.04x
BenchmarkReconstructData5x2x1M-8 28549.19 30760.16 1.08x
BenchmarkReconstructData10x4x1M-8 10376.42 10819.53 1.04x
BenchmarkReconstructData50x20x1M-8 1853.37 1869.05 1.01x
BenchmarkReconstructData10x4x16M-8 11148.51 11615.96 1.04x
BenchmarkReconstructP10x2x10000-8 31068.70 32026.22 1.03x
BenchmarkReconstructP10x5x20000-8 8484.08 8808.93 1.04x
BenchmarkStreamEncode10x2x10000-8 11.74 19.13 1.63x
BenchmarkStreamEncode100x20x10000-8 23.86 24.41 1.02x
BenchmarkStreamEncode17x3x1M-8 1480.79 1261.58 0.85x
BenchmarkStreamEncode10x4x16M-8 2968.74 3060.31 1.03x
BenchmarkStreamEncode5x2x1M-8 984.30 1321.82 1.34x
BenchmarkStreamEncode10x2x1M-8 1514.33 1591.31 1.05x
BenchmarkStreamEncode10x4x1M-8 1163.01 1239.59 1.07x
BenchmarkStreamEncode50x20x1M-8 560.24 557.63 1.00x
BenchmarkStreamEncode17x3x16M-8 3721.28 3815.54 1.03x
BenchmarkStreamVerify10x2x10000-8 12.03 19.37 1.61x
BenchmarkStreamVerify50x5x50000-8 262.94 272.44 1.04x
BenchmarkStreamVerify10x2x1M-8 1827.30 1926.97 1.05x
BenchmarkStreamVerify5x2x1M-8 1514.08 1575.36 1.04x
BenchmarkStreamVerify10x4x1M-8 1556.74 1643.25 1.06x
BenchmarkStreamVerify50x20x1M-8 1756.73 1782.27 1.01x
BenchmarkStreamVerify10x4x16M-8 19708.46 20030.64 1.02x
```
2020-05-03 19:38:55 +02:00
65df535980
Make single goroutine encodes more efficient ( #122 )
...
Calculate the optimal per round size to keep data in cache when not using WithAutoGoroutines.
```
λ benchcmp before.txt after.txt
benchmark old ns/op new ns/op delta
BenchmarkParallel_8x8x05M-16 675225 321053 -52.45%
BenchmarkParallel_20x10x05M-16 3471988 600740 -82.70%
BenchmarkParallel_8x8x1M-16 3948606 728093 -81.56%
BenchmarkParallel_8x8x8M-16 47361588 5976467 -87.38%
BenchmarkParallel_8x8x32M-16 195044200 24365474 -87.51%
benchmark old MB/s new MB/s speedup
BenchmarkParallel_8x8x05M-16 6211.71 13064.22 2.10x
BenchmarkParallel_20x10x05M-16 3020.10 17454.73 5.78x
BenchmarkParallel_8x8x1M-16 2124.45 11521.34 5.42x
BenchmarkParallel_8x8x8M-16 1416.95 11228.85 7.92x
BenchmarkParallel_8x8x32M-16 1376.28 11017.04 8.00x
```
2020-05-03 19:37:22 +02:00
0b98f5350a
Refactor AVX512 code to use Go assembly instructions. ( #121 )
...
Additionally there is a small performance improvement using VPTERNLOGD (instead of two VPXORD instructions).
2020-05-03 13:43:52 +02:00
17098a4f19
Use stream test options ( #118 )
2020-04-22 17:22:16 +02:00
c3634dce94
Use CPU cache to set minSplitSize ( #117 )
...
Use L1 cache size to set default split size.
2020-04-22 16:12:18 +02:00
d2cfcb8065
Add commandline arg to disable asm for tests. ( #116 )
...
* Add commandline test args
2020-04-22 15:38:21 +02:00
0abe9de20c
Update tests ( #115 )
...
Don't create new slices.
2020-02-21 11:30:44 -08:00
101092fa3b
Make AVX512 short tests ( #114 )
...
Tests are timing out. Use shorter tests for -short.
2020-01-18 14:50:31 +01:00
70d6279761
Update travis script
2019-09-27 16:33:57 -07:00
4681100338
Removed unused struct members ( #106 )
...
creads & cwrites both seem to be unused.
2019-09-27 16:31:11 -07:00
993c27a5ba
Avoid unnecessary conversion ( #107 )
...
No need to convert to byte here.
2019-09-27 16:30:54 -07:00
1f1369aa84
limit capacity of shards to shard size ( #109 )
...
This commit limits the capacity (additionally
to the length) of each shard to the shard size.
Before this change the following code behaves in
an unexpected way:
```
shards := encoder.Split(buffer)
// ...
shards[0] = shards[0][:cap(shards[0])
```
Instead of restoring the length of `shards[0]` to
the shard size, it assigns the entire memory of `buffer`
to `shards[0]`.
2019-09-27 16:30:26 -07:00
7890684129
Improve quick check for case when dataOnly is true ( #105 )
2019-06-25 16:30:44 +02:00
ec2eb9fb8c
Split: Reduce memory allocation ( #103 )
...
* [Split] Reduce memory allocation in Split function
2019-06-25 16:28:24 +02:00
0883d2f011
Only enable AVX512 on AMD64
...
Fixes #102
2019-05-26 12:12:55 +02:00
a373324398
Fixed upper bound check for data shard cli argument in example encoders and file permission issue. ( #98 )
2019-04-07 17:36:31 +02:00
a9588190c0
Optimize pure Go version. ( #96 )
...
* Optimize pure Go version.
* Update docs. Add Go 1.12 CI
* Avoid dst bounds check when using noasm ~ 40-50% faster.
* Convert multiply table to a slice whenever used.
* Split on 32 byte boundaries instead of 16 byte.
2019-03-08 10:49:27 +01:00
09979cdf93
Start documentation with method name.
...
Replaces #92
2019-02-15 15:31:43 +01:00
2b210cf086
Update README.md
...
Remove dead link
2019-02-10 22:49:25 +01:00
79aee05119
AVX512 accelerated version resulting in a 4x speed improvement over AVX2 ( #91 )
...
The performance on AVX512 has been accelerated for Intel CPUs. This gives speedups on a per-core basis of up to 4x compared to AVX2 as can be seen in the following table:
```
$ benchcmp avx2.txt avx512.txt
benchmark AVX2 MB/s AVX512 MB/s speedup
BenchmarkEncode8x8x1M-72 1681.35 4125.64 2.45x
BenchmarkEncode8x4x8M-72 1529.36 5507.97 3.60x
BenchmarkEncode8x8x8M-72 791.16 2952.29 3.73x
BenchmarkEncode8x8x32M-72 573.26 2168.61 3.78x
BenchmarkEncode12x4x12M-72 1234.41 4912.37 3.98x
BenchmarkEncode16x4x16M-72 1189.59 5138.01 4.32x
BenchmarkEncode24x8x24M-72 690.68 2583.70 3.74x
BenchmarkEncode24x8x48M-72 674.20 2643.31 3.92x
```
2019-02-10 11:17:23 +01:00
8885f3a1c7
Feature/ppc support ( #88 )
...
Add accelerated PPC support.
2018-12-18 20:39:59 +01:00
278ba25f43
Pre-slice input.
2018-11-16 00:23:56 +01:00
454fd91890
Maintenance updates. ( #86 )
...
* Add gcc go build tags.
* Update Travis.
* Fix typo
2018-11-12 13:25:55 +01:00
925cb01d65
Fix several typos in matrix_test.go ( #80 )
2018-07-04 19:30:09 +02:00
3133c51b91
Added link to ocaml-reed-solomon-erasure to README.md ( #79 )
2018-06-30 10:15:29 +02:00
7d9453e171
Update README.md
2018-05-04 15:02:00 +02:00
0b30fa71cc
Merge pull request #75 from ernado/patch-1
...
Fix typo in README.md
2017-12-19 14:34:37 +01:00
19a926a71b
Fix typo in README.md
2017-12-15 19:01:33 +03:00
6db5e38e85
Merge pull request #74 from klauspost/align-blocks
...
Split blocks into size divisible by 16, add WithAutoGoroutines
2017-12-10 21:00:05 +01:00
f5e73dcfe2
Split blocks into size divisible by 16
...
Older systems (typically without AVX2) are more sensitive to misaligned load+stores.
Add parameter to automatically set the number of goroutines.
name old time/op new time/op delta
Encode10x2x10000-8 18.4µs ± 1% 16.1µs ± 1% -12.43% (p=0.000 n=9+9)
Encode100x20x10000-8 692µs ± 1% 608µs ± 1% -12.10% (p=0.000 n=10+10)
Encode17x3x1M-8 1.78ms ± 5% 1.49ms ± 1% -16.63% (p=0.000 n=10+10)
Encode10x4x16M-8 21.5ms ± 5% 19.6ms ± 4% -8.74% (p=0.000 n=10+9)
Encode5x2x1M-8 343µs ± 2% 267µs ± 2% -22.22% (p=0.000 n=9+10)
Encode10x2x1M-8 858µs ± 5% 701µs ± 5% -18.34% (p=0.000 n=10+10)
Encode10x4x1M-8 1.34ms ± 1% 1.16ms ± 1% -13.19% (p=0.000 n=9+9)
Encode50x20x1M-8 30.3ms ± 4% 25.0ms ± 2% -17.51% (p=0.000 n=10+8)
Encode17x3x16M-8 26.9ms ± 1% 24.5ms ± 4% -9.13% (p=0.000 n=8+10)
name old speed new speed delta
Encode10x2x10000-8 5.45GB/s ± 1% 6.22GB/s ± 1% +14.20% (p=0.000 n=9+9)
Encode100x20x10000-8 1.44GB/s ± 1% 1.64GB/s ± 1% +13.77% (p=0.000 n=10+10)
Encode17x3x1M-8 10.0GB/s ± 5% 12.0GB/s ± 1% +19.88% (p=0.000 n=10+10)
Encode10x4x16M-8 7.81GB/s ± 5% 8.56GB/s ± 5% +9.58% (p=0.000 n=10+9)
Encode5x2x1M-8 15.3GB/s ± 2% 19.6GB/s ± 2% +28.57% (p=0.000 n=9+10)
Encode10x2x1M-8 12.2GB/s ± 5% 15.0GB/s ± 5% +22.45% (p=0.000 n=10+10)
Encode10x4x1M-8 7.84GB/s ± 1% 9.03GB/s ± 1% +15.19% (p=0.000 n=9+9)
Encode50x20x1M-8 1.73GB/s ± 4% 2.09GB/s ± 4% +20.59% (p=0.000 n=10+9)
Encode17x3x16M-8 10.6GB/s ± 1% 11.7GB/s ± 4% +10.12% (p=0.000 n=8+10)
2017-11-18 22:00:55 +01:00
e52c150f96
Fix some small typos in README ( #71 )
2017-11-18 16:17:31 +01:00
3610933d2f
Use AVX2 SIMD assembly instructions in favor of BYTE sequences. ( #73 )
...
* Use AVX2 SIMD assembly instructions in favor of BYTE sequences.
2017-11-18 16:17:10 +01:00
6bb6130ff6
Add laste new feature to doc.
2017-10-01 14:06:06 +02:00
61c22eab55
Cauchy Matrix option ( #70 )
...
* Experimental Cauchy Matrix
Experimental support for Cauchy style matrix
http://web.eecs.utk.edu/~plank/plank/papers/CS-05-569.pdf
All matrices appear reversible.
* Remove Go 1.5 and 1.6 from CI tests.
* Fix comment.
* Increase max number of goroutines+docs.
2017-10-01 14:02:11 +02:00
ddcafc661e
Allow reconstructing into pre-allocated memory. ( #66 )
...
This changes the interface of Reconstruct and ReconstructData to accept
slices of zero length but sufficient capacity for shards to reconstruct,
and reslices them instead of allocating new memory.
2017-09-20 21:08:24 +02:00
87ba8262ab
Add Go 1.9 to Travis.
2017-08-26 11:54:10 +02:00
985e396eec
Asmfmt.
2017-08-26 11:51:49 +02:00
c71640765a
Update docs before release, when #62 is ready. ( #63 )
...
* Update docs before release, when #62 is ready.
* Update README.md
2017-08-26 11:48:42 +02:00
7b88f42e61
Add NEON support for ARM64 ( #62 )
...
* Add support for arm64 using NEON instructions
Specifically using the PMULL/PMULL2 polynomial multiplication instructions followed by a reduction step (actually two steps).
* Add ARM performance numbers
* Formatting for performance table
* Refactoring of NEON version and 256-bit wide version
* Expand test slice beyond 32 (for AVX2 and NEON) and test galMulSliceXor explicitly.
* Fix ARM code with missing function.
* Fix missing newline
2017-08-26 11:47:42 +02:00
d78bf472d8
add Update parity function ( #60 )
...
Add Update parity function
2017-08-20 11:42:39 +02:00
dc6af2dce5
Minor cleanup ( #61 )
...
* Remove some benchmarks
* Format tables a bit.
* Doc cleanup
2017-08-13 22:38:27 +02:00
48a4fd05f1
fix unnecessary memory alloc in Split ( #59 )
...
Split divided the data into `DataShards` blocks and allocates all parity blocks.
This change adds a check whether the capacity of data is large enough to hold all
data and parity blocks. It only allocates parity blocks if necessary.
2017-07-22 16:16:58 +02:00
Klaus Post