Releases: luhenry/netlib
Releases · luhenry/netlib
Add dgemm, dgemv, sgemv, dscal, and sscal with offsets
v0.1.11 v0.1.11
Add support for offsets to dgemm
v0.1.10 v0.1.10
Accelerate dgemv[N] and sgemv[N]
v0.1.9 v0.1.9
Add accelerated sgemv, sscal, dgemm[N,N] and dgemm[N,T].
| Benchmark | Mode | Threads | Samples | Score | Score Error (99.9%) | Unit | Param: k | Param: m | Param: n | Param: trans | Param: transa | Param: transb | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | blas | thrpt | 1 | 6 | 10131111.71 | 367218.35 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | f2j | thrpt | 1 | 6 | 17325598.32 | 236924.26 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | vector | thrpt | 1 | 6 | 52312539.90 | 5357404.80 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | blas | thrpt | 1 | 6 | 97.82 | 1.66 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | f2j | thrpt | 1 | 6 | 102.66 | 6.70 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | vector | thrpt | 1 | 6 | 120.95 | 0.72 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | blas | thrpt | 1 | 6 | 10074357.58 | 79485.83 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | f2j | thrpt | 1 | 6 | 10944039.07 | 193783.47 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | vector | thrpt | 1 | 6 | 43714182.97 | 365517.92 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | blas | thrpt | 1 | 6 | 111.74 | 2.11 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | f2j | thrpt | 1 | 6 | 89.22 | 0.31 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | vector | thrpt | 1 | 6 | 152.71 | 1.68 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2017227.01 | 65697.32 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 918506.73 | 1015.25 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 1309057.46 | 93137.59 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 76707.48 | 1604.32 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10429.31 | 625.28 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 13636.47 | 2645.98 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 83707.82 | 313.00 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 17631.07 | 115.88 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 31084.49 | 615.11 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2288.07 | 361.88 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 162.92 | 18.97 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 256.28 | 10.38 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 79952.73 | 2528.44 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9663.57 | 437.51 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 12847.20 | 1584.69 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2104.47 | 192.66 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 106.10 | 0.20 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 133.98 | 20.84 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2167.37 | 62.67 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 168.63 | 3.91 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 284.45 | 5.72 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 100.71 | 1.92 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 1.67 | 0.01 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 2.61 | 0.03 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2039338.23 | 7389.38 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 925139.49 | 12826.17 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 1321563.96 | 156393.95 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 78544.37 | 1301.40 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10796.42 | 8.71 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 43610.83 | 159.41 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 83870.03 | 3278.79 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9991.97 | 117.48 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 14409.26 | 847.37 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1775.73 | 2979.60 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 102.48 | 1.23 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 346.36 | 18.75 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 80997.74 | 513.36 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9711.92 | 17.30 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 14402.85 | 2114.16 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2084.52 | 67.51 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 106.81 | 0.42 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 414.34 | 0.60 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2162.09 | 117.43 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 98.08 | 0.19 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 159.99 | 23.68 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 91.91 | 43.33 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 1.03 | 0.01 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 3.57 | 0.28 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1912911.34 | 22205.76 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 920954.50 | 2652.09 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 1281248.75 | 55521.69 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 62639.37 | 568.70 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9844.24 | 530.24 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 13207.31 | 1953.10 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 83048.36 | 2225.20 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 16754.45 | 103.82 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 30249.06 | 545.96 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2348.82 | 43.28 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 153.34 | 1.54 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 302.24 | 2.05 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 68252.08 | 843.54 | ops/s | 10 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9128.31 | 11.00 | ops/s | 10 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 13630.49 | 999.59 | ops/s | 10 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1810.91 | 84.17 | ops/s | 1000 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 69.12 | 0.37 | ops/s | 1000 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBench... |
v0.1.7
| Benchmark | Mode | Threads | Samples | Score | Score Error (99.9%) | Unit | Param: k | Param: m | Param: n | Param: trans | Param: transa | Param: transb | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | blas | thrpt | 1 | 6 | 10246033.56 | 324590.30 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | f2j | thrpt | 1 | 6 | 17422407.12 | 159847.18 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | vector | thrpt | 1 | 6 | 53372341.22 | 1533737.07 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | blas | thrpt | 1 | 6 | 97.38 | 5.59 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | f2j | thrpt | 1 | 6 | 106.23 | 1.68 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | vector | thrpt | 1 | 6 | 122.64 | 0.50 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | blas | thrpt | 1 | 6 | 10435249.72 | 74396.98 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | f2j | thrpt | 1 | 6 | 10834780.28 | 278495.34 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | vector | thrpt | 1 | 6 | 44321846.77 | 1263146.16 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | blas | thrpt | 1 | 6 | 120.62 | 4.65 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | f2j | thrpt | 1 | 6 | 87.96 | 1.84 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | vector | thrpt | 1 | 6 | 151.89 | 1.62 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2021958.63 | 78348.54 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 918603.13 | 7038.17 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 918298.89 | 5131.31 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 76528.69 | 3239.31 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10360.86 | 705.81 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 10193.12 | 56.41 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 82407.62 | 811.14 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 17616.07 | 214.34 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 17628.58 | 50.29 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2406.41 | 158.77 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 168.40 | 2.01 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 166.03 | 2.20 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 78797.92 | 1708.58 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9643.74 | 447.37 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 9643.09 | 428.93 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1947.12 | 643.80 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 105.75 | 1.84 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 105.94 | 0.43 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1435.52 | 1370.58 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 169.56 | 0.23 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 169.58 | 0.41 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 101.73 | 6.28 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 1.67 | 0.11 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 1.59 | 0.33 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2051378.77 | 29749.48 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 930267.55 | 2350.46 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 1168010.57 | 198909.60 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 78719.86 | 2263.80 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10799.45 | 17.99 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 43889.68 | 383.42 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 82370.74 | 2338.18 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10032.36 | 100.98 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 13187.77 | 2747.76 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2548.44 | 61.18 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 103.18 | 0.54 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 349.60 | 12.05 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 78464.03 | 2395.29 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9698.28 | 12.84 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 12438.11 | 758.77 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2121.77 | 75.43 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 106.49 | 1.80 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 415.38 | 3.20 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1890.07 | 77.75 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 98.27 | 1.14 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 137.40 | 2.00 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 102.58 | 2.11 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 1.03 | 0.01 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 3.47 | 0.16 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1895217.54 | 101053.21 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 922431.17 | 1022.94 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 916376.97 | 3629.74 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 59787.87 | 7594.98 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9859.37 | 753.44 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 9929.31 | 503.22 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 79905.21 | 7760.42 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 16800.46 | 66.67 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 16796.62 | 104.18 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2404.82 | 88.87 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 153.55 | 2.57 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 151.95 | 2.01 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 67836.56 | 2714.85 | ops/s | 10 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9102.08 | 17.28 | ops/s | 10 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 9353.27 | 557.99 | ops/s | 10 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1756.23 | 496.27 | ops/s | 1000 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 69.87 | 3.92 | ops/s | 1000 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vec... |
Improves performance of dspmv, dspr, dsyr, and sdot
| Benchmark | Mode | Threads | Samples | Score | Score Error (99.9%) | Unit | Param: k | Param: m | Param: n | Param: trans | Param: transa | Param: transb | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | blas | thrpt | 1 | 6 | 9891830.622 | 1028065.96 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | f2j | thrpt | 1 | 6 | 17318477.350 | 359818.65 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | vector | thrpt | 1 | 6 | 44742539.869 | 18923558.24 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | blas | thrpt | 1 | 6 | 96.853 | 11.44 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | f2j | thrpt | 1 | 6 | 106.407 | 4.43 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | vector | thrpt | 1 | 6 | 121.109 | 6.17 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | blas | thrpt | 1 | 6 | 9954784.951 | 173474.76 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | f2j | thrpt | 1 | 6 | 10859531.956 | 15222.60 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | vector | thrpt | 1 | 6 | 47541964.333 | 600666.13 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | blas | thrpt | 1 | 6 | 111.008 | 12.33 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | f2j | thrpt | 1 | 6 | 89.610 | 0.39 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | vector | thrpt | 1 | 6 | 155.458 | 0.76 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2047546.577 | 12526.45 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 923563.891 | 6930.27 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 922385.764 | 14522.30 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 78249.491 | 457.42 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10646.235 | 744.95 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 10732.174 | 384.81 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 82551.452 | 2137.37 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 17799.175 | 48.49 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 17778.241 | 62.63 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2424.799 | 995.14 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 171.261 | 3.06 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 171.975 | 1.18 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 80907.458 | 1471.73 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9834.701 | 23.26 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 9834.416 | 63.73 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1879.319 | 1764.10 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 106.984 | 1.04 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 106.900 | 0.70 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2168.814 | 70.41 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 171.909 | 1.55 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 172.358 | 0.75 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 106.865 | 1.63 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 1.713 | 0.02 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 1.661 | 0.18 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2063000.639 | 13726.63 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 937191.069 | 3797.43 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 1137394.041 | 4013.79 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 79769.902 | 682.91 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10898.293 | 6.75 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 26585.125 | 399.26 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 81745.215 | 4755.09 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10026.385 | 251.08 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 13146.593 | 151.41 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2615.017 | 386.57 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 105.069 | 0.51 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 219.903 | 7.32 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 81429.819 | 731.09 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9782.387 | 19.98 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 12203.720 | 1882.68 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2204.799 | 89.43 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 107.516 | 0.68 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 250.123 | 2.58 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2184.589 | 67.15 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 98.956 | 0.91 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 117.876 | 1.28 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 99.506 | 50.37 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 1.047 | 0.00 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 2.185 | 0.05 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1938319.922 | 8216.59 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 925870.239 | 4411.42 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 922341.430 | 2018.15 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 63373.857 | 328.00 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10038.596 | 619.56 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 10088.526 | 749.38 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 82053.302 | 2790.34 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 17243.272 | 1084.71 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 16992.581 | 32.94 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2399.037 | 812.39 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 157.014 | 3.05 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 154.813 | 5.45 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 68170.5... |
v0.1.4: Release version 0.1.4
| Benchmark | Mode | Threads | Samples | Score | Score Error (99.9%) | Unit | Param: k | Param: m | Param: n | Param: trans | Param: transa | Param: transb | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | blas | thrpt | 1 | 6 | 10328662.50 | 167933.39 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | f2j | thrpt | 1 | 6 | 17276172.55 | 194877.38 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | vector | thrpt | 1 | 6 | 48170174.19 | 309585.24 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | blas | thrpt | 1 | 6 | 87.06 | 12.16 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | f2j | thrpt | 1 | 6 | 106.24 | 3.88 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DaxpyBenchmark | vector | thrpt | 1 | 6 | 121.42 | 1.29 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | blas | thrpt | 1 | 6 | 9971174.02 | 70502.50 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | f2j | thrpt | 1 | 6 | 10790365.04 | 56293.53 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | vector | thrpt | 1 | 6 | 32507396.01 | 462653.36 | ops/s | 100 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | blas | thrpt | 1 | 6 | 112.21 | 7.88 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | f2j | thrpt | 1 | 6 | 88.53 | 2.60 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DdotBenchmark | vector | thrpt | 1 | 6 | 132.07 | 5.83 | ops/s | 10000000 | |||||
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2042637.85 | 8542.60 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 923011.41 | 1136.49 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 921666.51 | 4647.82 | ops/s | 10 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 78147.69 | 386.24 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10171.39 | 276.29 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 10259.97 | 32.87 | ops/s | 1000 | 10 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 82944.62 | 422.25 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 17731.58 | 129.65 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 17638.89 | 83.05 | ops/s | 10 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2495.89 | 80.93 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 167.11 | 4.35 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 163.95 | 12.00 | ops/s | 1000 | 1000 | 10 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 78734.43 | 4195.57 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9802.36 | 26.60 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 9622.01 | 538.65 | ops/s | 10 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1616.66 | 965.03 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 106.44 | 0.81 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 106.68 | 0.41 | ops/s | 1000 | 10 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2111.52 | 148.09 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 171.32 | 0.34 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 171.44 | 0.14 | ops/s | 10 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 105.51 | 0.81 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 1.60 | 0.23 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 1.66 | 0.03 | ops/s | 1000 | 1000 | 1000 | N | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2054290.08 | 13240.66 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 936262.08 | 2093.58 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 1163587.20 | 17250.06 | ops/s | 10 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 79484.61 | 768.98 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10841.49 | 15.91 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 25887.80 | 1341.88 | ops/s | 1000 | 10 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 83362.52 | 2769.93 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10094.88 | 22.52 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 12025.65 | 180.84 | ops/s | 10 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2597.56 | 98.58 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 103.06 | 0.48 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 215.88 | 11.00 | ops/s | 1000 | 1000 | 10 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 79787.90 | 1608.62 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9753.82 | 29.97 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 12516.77 | 1782.32 | ops/s | 10 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1613.01 | 2603.21 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 107.18 | 0.29 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 243.14 | 13.07 | ops/s | 1000 | 10 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2144.77 | 121.60 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 99.29 | 0.43 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 115.72 | 18.19 | ops/s | 10 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 105.16 | 1.03 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 1.03 | 0.01 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 2.07 | 0.22 | ops/s | 1000 | 1000 | 1000 | T | N | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1930441.88 | 5692.22 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 926376.89 | 1562.97 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 920685.85 | 3918.77 | ops/s | 10 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 62923.75 | 243.08 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 10077.18 | 1095.50 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 9981.89 | 616.41 | ops/s | 1000 | 10 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 81954.14 | 1084.29 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 16855.39 | 96.91 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 17299.23 | 1284.96 | ops/s | 10 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 2421.07 | 445.05 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 150.69 | 6.03 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 152.34 | 0.51 | ops/s | 1000 | 1000 | 10 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 68111.31 | 2490.68 | ops/s | 10 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 9324.40 | 569.98 | ops/s | 10 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | vector | thrpt | 1 | 6 | 9325.47 | 533.31 | ops/s | 10 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | blas | thrpt | 1 | 6 | 1897.84 | 50.92 | ops/s | 1000 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchmarks.DgemmBenchmark | f2j | thrpt | 1 | 6 | 73.31 | 2.28 | ops/s | 1000 | 10 | 1000 | N | T | |
| dev.ludovic.blas.benchm... |