BlogDocs

Small GEMM improvements for AArch64 with SVE(#4887)

Merged
Merging
goplanid:develop
(
4894c54
) into
develop
(
4850275
)
0%
IMPROVEMENTS
0
REGRESSIONS
0
UNTOUCHED
62
NEW
0
DROPPED
0
IGNORED
0

Benchmarks

Passed

test_dgemv[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-d]
+1%
145.9 µs
145 µs
test_dgbmv[1-100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-s]
0%
36.3 µs
36.2 µs
test_nrm2[100-dz]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[100-dz]
0%
27 µs
26.9 µs
test_dgbmv[1-100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-d]
0%
36.9 µs
36.8 µs
test_daxpy[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-s]
0%
23.8 µs
23.7 µs
test_daxpy[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-c]
0%
32.2 µs
32.1 µs
test_gesv[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-z]
0%
936.4 µs
935.1 µs
test_dgemv[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-s]
0%
108.6 µs
108.5 µs
test_dot[1000]
benchmark/pybench/benchmarks/bench_blas.py::test_dot[1000]
0%
28.4 µs
28.4 µs
test_dgbmv[1-100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-z]
0%
41 µs
41 µs
test_gesv[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-s]
0%
257.2 µs
256.9 µs
test_syrk[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-z]
0%
855 µs
854.4 µs
test_dgbmv[1-100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-c]
0%
39.3 µs
39.3 µs
test_dgemv[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-z]
0%
229.6 µs
229.5 µs
test_gesdd[mn0-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn0-s]
0%
107.6 µs
107.5 µs
test_gesv[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-d]
0%
93.3 ms
93.3 ms
test_syrk[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-d]
0%
340.8 µs
340.7 µs
test_dgemv[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-d]
0%
14.7 ms
14.7 ms
test_dgbmv[1-1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-s]
0%
73.8 µs
73.8 µs
test_dgbmv[1-1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-z]
0%
117.7 µs
117.7 µs
test_gemm[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-z]
0%
1.2 ms
1.2 ms
test_gesv[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-c]
0%
188.6 ms
188.6 ms
test_gesv[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-s]
0%
52.6 ms
52.6 ms
test_syev[50-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[50-s]
0%
1.3 ms
1.3 ms
test_syrk[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-s]
0%
65.4 ms
65.4 ms
test_gesdd[mn1-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn1-d]
0%
92.7 ms
92.7 ms
test_syrk[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-c]
0%
472.9 µs
472.9 µs
test_gemm[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-c]
0%
426 ms
426 ms
test_syrk[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-c]
0%
227.5 ms
227.5 ms
test_gemm[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-s]
0%
117.4 ms
117.4 ms
test_syrk[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-d]
0%
130.4 ms
130.4 ms
test_gesv[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-z]
0%
353.4 ms
353.3 ms
test_gesdd[mn1-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn1-s]
0%
63.8 ms
63.8 ms
test_dgemv[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-z]
0%
26.3 ms
26.3 ms
test_syrk[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-z]
0%
476.4 ms
476.4 ms
test_syev[200-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[200-d]
0%
58.4 ms
58.4 ms
test_gemm[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-z]
0%
875.6 ms
875.6 ms
test_syev[50-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[50-d]
0%
1.4 ms
1.4 ms
test_gemm[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-d]
0%
239.4 ms
239.4 ms
test_daxpy[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-z]
0%
40 µs
40 µs
test_dgemv[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-c]
0%
14.8 ms
14.8 ms
test_dgemv[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-s]
0%
7.7 ms
7.7 ms
test_syev[200-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[200-s]
0%
48.5 ms
48.5 ms
test_gesdd[mn0-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn0-d]
0%
118 µs
118 µs
test_gemm[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-d]
0%
470.4 µs
470.5 µs
test_gemm[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-c]
0%
658.7 µs
658.9 µs
test_gemm[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-s]
0%
271.7 µs
271.8 µs
test_dgbmv[1-1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-c]
0%
98.5 µs
98.6 µs
test_syrk[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-s]
0%
212.8 µs
212.9 µs
test_daxpy[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-d]
0%
23.7 µs
23.7 µs
test_gesv[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-c]
0%
694.1 µs
694.7 µs
test_nrm2[1000-dz]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[1000-dz]
0%
35 µs
35 µs
test_nrm2[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[1000-d]
0%
30.1 µs
30.1 µs
test_daxpy[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-s]
0%
27.2 µs
27.2 µs
test_dgbmv[1-1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-d]
0%
82.5 µs
82.6 µs
test_gesv[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-d]
0%
394.3 µs
395.1 µs
test_daxpy[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-z]
0%
25.3 µs
25.3 µs
test_daxpy[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-d]
0%
31.6 µs
31.7 µs
test_nrm2[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[100-d]
-1%
33.7 µs
33.9 µs
test_daxpy[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-c]
-1%
24.5 µs
24.6 µs
test_dot[100]
benchmark/pybench/benchmarks/bench_blas.py::test_dot[100]
-1%
22.4 µs
22.7 µs
test_dgemv[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-c]
-2%
148.5 µs
152.2 µs

Commits

Click on a commit to change the comparison range
base
develop
4850275
0%
Improve TN case with further unrolling
4894c54
17 days ago
by goplanid
ResourcesHomePricingDocsBlogGitHubChangelog
Getting StartedSample repositoryExplore repositoriesSupport
AboutCareersTwitterDiscordContact UsTerms of ServicePrivacy Policy
Copyright © 2024 CodSpeed Technology SAS. All rights reserved.