Improve performance on edges of GEMM for RISC-V#5674

Merged

martin-frbg merged 23 commits intoOpenMathLib:developfrom

ChipKerchner:fasterRVVEdges

Apr 11, 2026

Commits on Mar 11, 2026

Merge remote-tracking branch 'origin/develop' into HEAD
ChipKerchner
committed

Commits on Mar 12, 2026

Commits on Mar 13, 2026

Commits on Mar 14, 2026

Commits on Mar 16, 2026

Commits on Mar 17, 2026

Commits on Mar 18, 2026

More global optimzation and clean up.
ChipKerchner
committed

Commits on Mar 19, 2026

Merge remote-tracking branch 'origin/develop' into fasterRVVEdges
ChipKerchner
committed
Avoid greater than 4 segment load and store penalties by using 2. Fix mf2 length.
ChipKerchner
committed

Commits on Mar 20, 2026

Only initialize unused variables to prevent GCC warnings.
ChipKerchner
committed

Commits on Mar 22, 2026

Fix typo.
ChipKerchner
committed

Commits on Mar 24, 2026

Fix another typo.
ChipKerchner
committed

Commits on Mar 30, 2026

Convert 2X LMUL1 instructions to 1X LMUL2. Improved FP64 GEMM edges - up to more than 3X faster.
ChipKerchner
committed

Commits on Mar 31, 2026

Remove shadow variable.
ChipKerchner
committed