Improve performance on edges of GEMM for RISC-V
#5674Comparing
ChipKerchner:fasterRVVEdges
(b0ee407
) withdevelop
(b95729f
)0%
- Untouched
- 62
Benchmarks
62 total
test_syev[200-s]
benchmark/pybench/benchmarks/bench_blas.py+2%
49.1 ms48.1 ms
test_gesdd[mn1-s]
benchmark/pybench/benchmarks/bench_blas.py+1%
65.2 ms64.8 ms
test_gesv[100-d]
benchmark/pybench/benchmarks/bench_blas.py0%
394.9 µs393.9 µs
test_gemm[100-z]
benchmark/pybench/benchmarks/bench_blas.py0%
1.2 ms1.2 ms
test_gesv[100-c]
benchmark/pybench/benchmarks/bench_blas.py0%
696.3 µs695.6 µs
test_gemm[1000-d]
benchmark/pybench/benchmarks/bench_blas.py0%
239.4 ms239.3 ms
test_syev[50-d]
benchmark/pybench/benchmarks/bench_blas.py0%
1.4 ms1.4 ms
test_dgemv[1000-s]
benchmark/pybench/benchmarks/bench_blas.py0%
7 ms7 ms
test_gesv[1000-d]
benchmark/pybench/benchmarks/bench_blas.py0%
93.3 ms93.3 ms
test_gesv[1000-c]
benchmark/pybench/benchmarks/bench_blas.py0%
188.6 ms188.6 ms
test_gemm[1000-z]
benchmark/pybench/benchmarks/bench_blas.py0%
875.6 ms875.5 ms
test_syev[200-d]
benchmark/pybench/benchmarks/bench_blas.py0%
58.6 ms58.6 ms
test_gesv[1000-s]
benchmark/pybench/benchmarks/bench_blas.py0%
52.6 ms52.6 ms
test_syrk[1000-z]
benchmark/pybench/benchmarks/bench_blas.py0%
476.4 ms476.4 ms
test_syrk[1000-s]
benchmark/pybench/benchmarks/bench_blas.py0%
65.4 ms65.4 ms
test_dgemv[1000-z]
benchmark/pybench/benchmarks/bench_blas.py0%
26.3 ms26.3 ms
test_syrk[1000-c]
benchmark/pybench/benchmarks/bench_blas.py0%
227.5 ms227.5 ms
test_syrk[1000-d]
benchmark/pybench/benchmarks/bench_blas.py0%
130.3 ms130.4 ms
test_gemm[1000-c]
benchmark/pybench/benchmarks/bench_blas.py0%
426 ms426 ms
test_gesdd[mn1-d]
benchmark/pybench/benchmarks/bench_blas.py0%
93.8 ms93.8 ms
test_gesv[1000-z]
benchmark/pybench/benchmarks/bench_blas.py0%
353.6 ms353.6 ms
test_dgemv[1000-d]
benchmark/pybench/benchmarks/bench_blas.py0%
13.9 ms13.9 ms
test_dgemv[1000-c]
benchmark/pybench/benchmarks/bench_blas.py0%
14.8 ms14.8 ms
test_syev[50-s]
benchmark/pybench/benchmarks/bench_blas.py0%
1.3 ms1.3 ms
test_gemm[1000-s]
benchmark/pybench/benchmarks/bench_blas.py0%
117.4 ms117.5 ms
Commits
Click on a commit to change the comparison rangeBase
develop
b95729f
-0.02%
Fast performing edges for FP32 GEMM of RVV.
376d3a1
4 days ago
by ChipKerchner-0.07%
Add bool types for C.
6d6af1d
4 days ago
by ChipKerchner-0.45%
Add K-unrolling to M = 8. Other small changes.
9c16449
3 days ago
by ChipKerchner+0.1%
Unroll K for N less than or equal to 4.
fda433f
2 days ago
by ChipKerchner-0.01%
Common unroll code.
eb9bbcc
2 days ago
by ChipKerchner+0.02%
Preserve K.
b0ee407
2 days ago
by ChipKerchner