Comparing
quic:fix-sgemmdirect-sme1
(04915be
) withdevelop
(3e961c2
)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%
147.6 µs
146.8 µs
test_dgemv[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-c]+1%
149.3 µs
148.5 µs
test_daxpy[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-z]0%
40.1 µs
40 µs
test_dgemv[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-s]0%
110.2 µs
109.8 µs
test_daxpy[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-z]0%
25.3 µs
25.3 µs
test_dgbmv[1-100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-z]0%
41.5 µs
41.4 µs
test_nrm2[1000-dz]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[1000-dz]0%
34.9 µs
34.8 µs
test_daxpy[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-d]0%
31.9 µs
31.8 µs
test_daxpy[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-c]0%
24.6 µs
24.6 µs
test_daxpy[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-d]0%
23.6 µs
23.5 µs
test_dot[1000]
benchmark/pybench/benchmarks/bench_blas.py::test_dot[1000]0%
27.9 µs
27.8 µs
test_daxpy[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-s]0%
26.9 µs
26.9 µs
test_gesv[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-c]0%
693.8 µs
693.1 µs
test_dgbmv[1-100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-s]0%
36.6 µs
36.6 µs
test_syev[50-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[50-d]0%
1.4 ms
1.4 ms
test_syrk[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-s]0%
213 µs
212.9 µs
test_gemm[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-s]0%
272.7 µs
272.6 µs
test_daxpy[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-c]0%
32.2 µs
32.2 µs
test_syrk[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-d]0%
339.3 µs
339.1 µs
test_dgemv[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-d]0%
14.7 ms
14.7 ms
test_dgemv[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-z]0%
230.5 µs
230.5 µs
test_syrk[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-z]0%
855.5 µs
855.4 µs
test_nrm2[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[1000-d]0%
29.8 µs
29.8 µs
test_gesdd[mn1-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn1-d]0%
93.9 ms
93.9 ms
test_gemm[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-z]0%
1.2 ms
1.2 ms
test_gemm[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-c]0%
659 µs
658.9 µs
test_gesv[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-d]0%
93.3 ms
93.3 ms
test_syev[200-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[200-s]0%
49.1 ms
49.1 ms
test_gemm[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-d]0%
470.7 µs
470.7 µs
test_gemm[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-s]0%
117.4 ms
117.4 ms
test_dgemv[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-z]0%
26.3 ms
26.3 ms
test_dgbmv[1-1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-s]0%
74.4 µs
74.4 µs
test_syev[50-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[50-s]0%
1.3 ms
1.3 ms
test_gesdd[mn1-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn1-s]0%
65.2 ms
65.2 ms
test_gemm[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-z]0%
875.6 ms
875.6 ms
test_syrk[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-z]0%
476.4 ms
476.4 ms
test_gemm[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-d]0%
239.4 ms
239.4 ms
test_nrm2[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[100-d]0%
35.4 µs
35.4 µs
test_gesv[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-c]0%
188.6 ms
188.6 ms
test_syrk[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-s]0%
65.4 ms
65.4 ms
test_gemm[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-c]0%
426 ms
426 ms
test_syev[200-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[200-d]0%
58.6 ms
58.6 ms
test_syrk[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-c]0%
227.5 ms
227.5 ms
test_gesv[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-s]0%
52.6 ms
52.6 ms
test_dgemv[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-c]0%
14.8 ms
14.8 ms
test_syrk[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-d]0%
130.3 ms
130.4 ms
test_daxpy[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-s]0%
23.4 µs
23.4 µs
test_gesv[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-z]0%
935.1 µs
935.2 µs
test_syrk[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-c]0%
471.8 µs
471.8 µs
test_nrm2[100-dz]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[100-dz]0%
27.9 µs
27.9 µs
test_dgemv[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-s]0%
7.7 ms
7.7 ms
test_dgbmv[1-1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-c]0%
98.7 µs
98.7 µs
test_gesv[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-z]0%
353.2 ms
353.4 ms
test_dgbmv[1-100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-d]0%
37.3 µs
37.3 µs
test_gesv[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-d]0%
393.8 µs
394 µs
test_dgbmv[1-100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-c]0%
39.4 µs
39.4 µs
test_dgbmv[1-1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-z]0%
118.2 µs
118.3 µs
test_dgbmv[1-1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-d]0%
82.9 µs
83 µs
test_dot[100]
benchmark/pybench/benchmarks/bench_blas.py::test_dot[100]0%
21.8 µs
21.9 µs
test_gesdd[mn0-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn0-s]0%
108.5 µs
108.7 µs
test_gesdd[mn0-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn0-d]0%
119.9 µs
120.2 µs
test_gesv[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-s]0%
256.8 µs
257.5 µs
Commits
Click on a commit to change the comparison rangeBase
develop
3e961c2
0%
Add vector registers to clobber list to prevent compiler optimization.
SME based SGEMMDIRECT kernel uses the vector registers (z) and adding
clobber list informs compiler not to optimize these registers.
04915be
4 months ago
by vaiskv