Comparing
ChipKerchner:fixRVVSHGEMM
(a4abf78
) withdevelop
(79a1f38
)0%
- Untouched
- 62
Benchmarks
Passed
test_daxpy[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-d]+1%
24.4 µs24.1 µs
test_daxpy[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-z]+1%
26 µs25.7 µs
test_nrm2[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[1000-d]+1%
30.8 µs30.5 µs
test_daxpy[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-d]+1%
32.6 µs32.3 µs
test_nrm2[100-dz]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[100-dz]+1%
29.1 µs28.9 µs
test_nrm2[1000-dz]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[1000-dz]+1%
35.7 µs35.4 µs
test_daxpy[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-c]+1%
25.3 µs25.1 µs
test_dot[100]
benchmark/pybench/benchmarks/bench_blas.py::test_dot[100]+1%
22.6 µs22.4 µs
test_daxpy[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-s]+1%
27.7 µs27.5 µs
test_daxpy[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-c]+1%
32.9 µs32.7 µs
test_dgemv[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-s]+1%
104 µs103.3 µs
test_dgemv[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-c]+1%
149.8 µs149 µs
test_dgemv[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-d]+1%
141.1 µs140.3 µs
test_dot[1000]
benchmark/pybench/benchmarks/bench_blas.py::test_dot[1000]0%
28.6 µs28.5 µs
test_daxpy[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[100-s]0%
24.2 µs24 µs
test_nrm2[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_nrm2[100-d]0%
38.1 µs37.9 µs
test_daxpy[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_daxpy[1000-z]0%
40.8 µs40.6 µs
test_dgbmv[1-100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-z]0%
42.3 µs42.1 µs
test_syrk[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-d]0%
340.8 µs339.6 µs
test_gesv[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-d]0%
395.4 µs394.1 µs
test_dgbmv[1-100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-s]0%
37.4 µs37.3 µs
test_syrk[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-c]0%
473.5 µs472.3 µs
test_dgbmv[1-100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-c]0%
40.4 µs40.3 µs
test_dgbmv[1-100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-100-d]0%
38 µs38 µs
test_gesdd[mn0-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn0-d]0%
120 µs119.9 µs
test_dgbmv[1-1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-s]0%
75.1 µs75 µs
test_syrk[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-s]0%
213.6 µs213.5 µs
test_dgbmv[1-1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-z]0%
119 µs118.9 µs
test_gemm[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-s]0%
273.4 µs273.3 µs
test_gemm[100-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-d]0%
471.5 µs471.3 µs
test_dgemv[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[100-z]0%
231.2 µs231.1 µs
test_syrk[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[100-z]0%
856.7 µs856.4 µs
test_gesv[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-d]0%
93.3 ms93.3 ms
test_gesv[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-z]0%
938.7 µs938.4 µs
test_dgemv[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-d]0%
13.9 ms13.9 ms
test_gemm[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-c]0%
659.8 µs659.7 µs
test_dgemv[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-s]0%
7 ms7 ms
test_gemm[100-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[100-z]0%
1.2 ms1.2 ms
test_gesdd[mn1-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn1-s]0%
65.2 ms65.2 ms
test_syrk[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-c]0%
227.5 ms227.5 ms
test_gesv[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-c]0%
188.6 ms188.6 ms
test_dgemv[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-z]0%
26.3 ms26.3 ms
test_syrk[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-d]0%
130.4 ms130.4 ms
test_gemm[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-z]0%
875.6 ms875.6 ms
test_syrk[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-z]0%
476.4 ms476.4 ms
test_gemm[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-c]0%
426 ms426 ms
test_gesv[1000-z]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-z]0%
353.6 ms353.6 ms
test_gesv[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[1000-s]0%
52.6 ms52.6 ms
test_gesdd[mn1-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn1-d]0%
93.8 ms93.8 ms
test_syev[50-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[50-s]0%
1.3 ms1.3 ms
test_gemm[1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-d]0%
239.4 ms239.4 ms
test_syrk[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syrk[1000-s]0%
65.4 ms65.4 ms
test_gesv[100-c]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-c]0%
695.4 µs695.5 µs
test_gemm[1000-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gemm[1000-s]0%
117.4 ms117.4 ms
test_syev[200-s]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[200-s]0%
49.1 ms49.1 ms
test_syev[200-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[200-d]0%
58.6 ms58.6 ms
test_dgemv[1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgemv[1000-c]0%
14.8 ms14.8 ms
test_syev[50-d]
benchmark/pybench/benchmarks/bench_blas.py::test_syev[50-d]0%
1.4 ms1.4 ms
test_gesv[100-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesv[100-s]0%
256.8 µs256.9 µs
test_dgbmv[1-1000-d]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-d]0%
83.6 µs83.7 µs
test_dgbmv[1-1000-c]
benchmark/pybench/benchmarks/bench_blas.py::test_dgbmv[1-1000-c]0%
99.6 µs99.7 µs
test_gesdd[mn0-s]
benchmark/pybench/benchmarks/bench_blas.py::test_gesdd[mn0-s]0%
109.1 µs109.4 µs
Commits
Click on a commit to change the comparison rangeBase
develop
79a1f38
+0.23%
Fix _Float16 casting issue and reduce LMUL for certain vector instruction from m2 to m1.
a4abf78
4 days ago
by ChipKerchner