GitHub Actions run on branch ChipKerchner:RVV_Narrow_Accumulate_FP16_GEMM - OpenMathLib/OpenBLAS - CodSpeed

Blog Docs Changelog

GitHub Actions run

CPU Simulation

5 days ago 1cc377e ChipKerchner:RVV_Narrow_Accumulate_FP16_GEMM pull_request

Compare

Base

Search a run

Head

Added ability to accumulate in FP16. Convert BF16 to FP32. For FP16 and BF16 GEMM in RISC-V (BF16 now works for pre-RVA23)

#5640

ChipKerchner:RVV_Narrow_Accumulate_FP16_GEMM

5 days ago

CPU Simulation

Suggested base runs: • •

62 total

test_gemm[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

875.6 ms

test_daxpy[100-z]

benchmark/pybench/benchmarks/bench_blas.py

25.8 µs

test_daxpy[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

40.6 µs

test_daxpy[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

32.7 µs

test_daxpy[100-s]

benchmark/pybench/benchmarks/bench_blas.py

24 µs

test_daxpy[100-c]

benchmark/pybench/benchmarks/bench_blas.py

25.2 µs

test_daxpy[100-d]

benchmark/pybench/benchmarks/bench_blas.py

24.2 µs

test_gesdd[mn0-d]

benchmark/pybench/benchmarks/bench_blas.py

120.2 µs

test_daxpy[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

32.2 µs

test_dgemv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

26.3 ms

test_dgbmv[1-100-c]

benchmark/pybench/benchmarks/bench_blas.py

40.3 µs

test_dgemv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

14.8 ms

test_daxpy[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

27.4 µs

test_dgemv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

104.1 µs

test_dgbmv[1-1000-z]

benchmark/pybench/benchmarks/bench_blas.py

118.9 µs

test_dgbmv[1-1000-d]

benchmark/pybench/benchmarks/bench_blas.py

83.6 µs

test_gemm[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

117.4 ms

test_dgbmv[1-1000-s]

benchmark/pybench/benchmarks/bench_blas.py

75.1 µs

test_gesdd[mn0-s]

benchmark/pybench/benchmarks/bench_blas.py

109.1 µs

test_dgemv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

141.5 µs

test_gesv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

257 µs

test_gesdd[mn1-d]

benchmark/pybench/benchmarks/bench_blas.py

93.8 ms

test_dgbmv[1-1000-c]

benchmark/pybench/benchmarks/bench_blas.py

99.6 µs

test_gemm[100-d]

benchmark/pybench/benchmarks/bench_blas.py

471.1 µs

test_dgbmv[1-100-z]

benchmark/pybench/benchmarks/bench_blas.py

42.1 µs

© 2026 CodSpeed Technology

Home Terms Privacy Docs