Avatar for the OpenMathLib user
OpenMathLib
OpenBLAS
BlogDocsChangelog

riscv64: wire TRSM, complex SYMV, and complex GEMM copy RVV kernels

#5807
Comparing
mengzhuo:no_gen
(
7ad237f
) with
develop
(
3da0ff7
)
CodSpeed Performance Gauge
+18%
Improvement
14
Untouched
48

Benchmarks

62 total
test_nrm2[100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+46%
37.7 µs25.8 µs
test_dot[100]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+25%
22.5 µs18 µs
test_daxpy[100-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+19%
24.2 µs20.4 µs
test_daxpy[100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+18%
24.3 µs20.6 µs
test_daxpy[100-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+17%
25.3 µs21.6 µs
test_daxpy[100-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+17%
26 µs22.3 µs
test_dot[1000]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+16%
28.4 µs24.5 µs
test_daxpy[1000-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+16%
27.7 µs24 µs
test_daxpy[1000-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+15%
32.6 µs28.4 µs
test_nrm2[100-dz]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+14%
28.9 µs25.3 µs
test_nrm2[1000-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+14%
30.6 µs26.8 µs
test_daxpy[1000-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+13%
32.9 µs29.2 µs
test_nrm2[1000-dz]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+11%
35.5 µs31.9 µs
test_daxpy[1000-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+10%
40.7 µs37 µs
test_dgbmv[1-100-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+10%
37.4 µs34 µs
test_dgbmv[1-100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+10%
38 µs34.6 µs
test_dgbmv[1-100-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+9%
40.4 µs37.1 µs
test_dgbmv[1-100-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+9%
42.3 µs38.9 µs
test_dgbmv[1-1000-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+5%
75.2 µs71.3 µs
test_dgbmv[1-1000-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+4%
83.7 µs80.2 µs
test_dgbmv[1-1000-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+4%
99.7 µs96.3 µs
test_gesdd[mn0-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+3%
111.3 µs107.8 µs
test_dgbmv[1-1000-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+3%
118.9 µs115.6 µs
test_gesdd[mn0-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+3%
122.6 µs119.2 µs
test_dgemv[100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+2%
141.7 µs138.6 µs

Commits

Click on a commit to change the comparison range
Base
develop
3da0ff7
+17.64%
riscv64: wire TRSM, complex SYMV, and complex GEMM copy RVV kernels
7ad237f
12 days ago
by mengzhuo
© 2026 CodSpeed Technology
Home Terms Privacy Docs