3 people 48b2496ca6 perf(rvv): fuse FP32 L2 widening multiply and accumulation ...

Replace separate widening multiplication and FP64 addition with
widening FMA in the unmasked and masked FP32 L2 norm kernels.

Finite FP32 products are exactly representable in FP64, so this
preserves numerical results without changing the accumulation order.
Tail and mask undisturbed policies are retained.

Co-authored-by: Yang Wang <yangwang@iscas.ac.cn>
Co-authored-by: Yuansheng <yuansheng@isrc.iscas.ac.cn>

2026-09-20 15:15:55 +08:00

..

armpl

Merge pull request #28664 from pratham-mcw:armpl_dft_opt

2026-05-14 10:56:21 +03:00

carotene

Fixed numerous Clang -Wextra-semi warnings

2026-08-19 18:32:08 -04:00

fastcv

Merge pull request #27252 from asmorkalov:as/extract_hal

2025-04-25 14:56:42 +03:00

ipp

Merge pull request #29332 from Akansha-977/Resize_Refactoring

2026-09-15 15:22:13 +05:30

kleidicv

Merge pull request #28744 from asmorkalov:as/kleidicv_26.03

2026-05-20 22:31:13 +03:00

ndsrvp

Merge branch 4.x

2026-07-09 12:17:24 +03:00

riscv-rvv

perf(rvv): fuse FP32 L2 widening multiply and accumulation

2026-09-20 15:15:55 +08:00