riscv64: wire TRSM, complex SYMV, and complex GEMM copy RVV kernels #5807
+93
−73
CodSpeed HQ / CodSpeed Performance Analysis
succeeded
May 20, 2026 in 0s
Performance Gate Passed
⚠️ Different runtime environments detected
Some benchmarks with significant performance changes were compared across different runtime environments,
which may affect the accuracy of the results.
A heads-up, this is a breaking change and it might affect your current performance baseline a bit. But here's the exciting part - it's packed with new, cool features and promises improved result stability 🥳!
Curious about what's new? Visit our releases page to delve into all the awesome details about this new version.
⚡ 14 improved benchmarks
✅ 48 untouched benchmarks
Performance Changes
| Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|
| ⚡ | test_daxpy[100-c] |
25.3 µs | 21.6 µs | +17.2% |
| ⚡ | test_daxpy[100-d] |
24.3 µs | 20.6 µs | +18.15% |
| ⚡ | test_nrm2[100-d] |
37.7 µs | 25.8 µs | +46.39% |
| ⚡ | test_daxpy[100-s] |
24.2 µs | 20.4 µs | +18.58% |
| ⚡ | test_nrm2[100-dz] |
28.9 µs | 25.3 µs | +14.22% |
| ⚡ | test_nrm2[1000-d] |
30.6 µs | 26.8 µs | +14.07% |
| ⚡ | test_daxpy[100-z] |
26 µs | 22.3 µs | +16.8% |
| ⚡ | test_nrm2[1000-dz] |
35.5 µs | 31.9 µs | +11.41% |
| ⚡ | test_daxpy[1000-c] |
32.9 µs | 29.2 µs | +12.75% |
| ⚡ | test_daxpy[1000-d] |
32.6 µs | 28.4 µs | +15.06% |
| ⚡ | test_daxpy[1000-s] |
27.7 µs | 24 µs | +15.52% |
| ⚡ | test_daxpy[1000-z] |
40.7 µs | 37 µs | +10.19% |
| ⚡ | test_dot[1000] |
28.4 µs | 24.5 µs | +15.99% |
| ⚡ | test_dot[100] |
22.5 µs | 18 µs | +24.57% |
Tip
Curious why this is faster? Comment @codspeedbot explain why this is faster on this PR, or directly use the CodSpeed MCP with your agent.
Comparing mengzhuo:no_gen (7ad237f) with develop (3da0ff7)
Loading