15 Commits

Author	SHA1	Message	Date
Chris Sidebottom	578e7dae85	Fix bf16->f32 conversion for NEOVERSEV1 and NEOVERSEN2 targets ... This fixes an issue originally introduced with the BGEMM kernel. I've updated the tests to run with `beta=1.0` so as to test loading and updating from C. Alongside this, the tests now return sensible return values to reduce the risk of them being ignored. Also fixed a bug in `generic/gemv_t.c` resulting in weird outputs for `bgemv`.	2025-10-06 18:05:58 +00:00
Chris Sidebottom	ea2faf0c9a	Add optimized BGEMM for NEOVERSEN2 target ... This re-uses the existing NEOVERSEN2 8x4 `sbgemm` kernel to implement `bgemm`.	2025-07-24 10:59:28 +00:00
Annop Wongwathanarat	e11744a411	Use SVE kernel for S/DGEMVN for SVE machines	2025-04-22 09:40:13 +00:00
Annop Wongwathanarat	ec146157d3	Use SVE kernel for S/DGEMVT for SVE machines	2025-04-09 20:38:14 +00:00
Ye Tao	38ee7c9301	Add dispatch of SBGEMVNKERNEL for NEOVERSEN2 and NEOVERSEV2	2025-03-03 11:32:05 +00:00
Annop Wongwathanarat	edaf51dd99	Add sbgemv_t_bfdot kernel for ARM64 ... This improves performance for sbgemv_t by up to 100x on NEOVERSEV1. The geometric mean speedup is ~61x for M=N=[2,512].	2025-02-28 12:31:50 +00:00
Martin Kroeker	3345007d8f	retire the thunderx2 NRM2 kernels due to reported inaccuracies and NAN	2024-12-05 21:12:06 +01:00
Martin Kroeker	09ace3cf23	Merge pull request #3846 from lilh9598/sbgemm_opt ... Improve the performance of sbgemm_tcopy on neoversen2	2023-03-26 19:04:57 +02:00
Chris Sidebottom	fd4f52c797	Add SVE implementation for sdot/ddot ... This adds an SVE implementation to sdot/ddot when available, falling back to the previous Advanced SIMD kernel where there's no SVE implementation for the kernel. All the targets were essentially treating `dot_thunderx2t99.c` as the Advanced SIMD implementation so I've renamed it to better fit with the feature detection.	2022-12-01 12:07:50 +00:00
lilianhuang	fdac8a97c1	Add sbgemm_ncopy_8 and sbgemm_tcopy_4	2022-11-29 04:46:14 -05:00
Honglin Zhu	79066b6bf3	Change file name to match the norm and delete useless code.	2022-10-28 17:09:39 +08:00
Honglin Zhu	b00d5b9746	New sbgemm implementation for Neoverse N2 ... 1. Use UZP instructions but not gather load and scatter store instructions to get lower latency. 2. Padding k to a power of 4.	2022-10-26 15:09:41 +08:00
Honglin Zhu	55d686d41e	neoverse n2 sbgemm: ... implement ncopy tcopy kernel_8x4	2022-06-29 10:14:21 +08:00
Honglin Zhu	04593bb27c	neoverse n2 sbgemm: init file	2022-06-29 10:14:21 +08:00
Sunita Nadampalli	19c8f615dc	OpenBLAS: aarch64: Add neoverse-v1/n2 architecture specifics	2022-01-07 00:28:17 +00:00