OpenBLAS

Commit Graph

Author	SHA1	Message	Date
Sunita Nadampalli	19c8f615dc	OpenBLAS: aarch64: Add neoverse-v1/n2 architecture specifics	4 years ago
Jia-Chen	b610d2de37	optimize cgemm on ARM cortex A53 & cortex A55	4 years ago
Bine Brank	a8f62a347b	fix UNROLL_MN and add to targets for SVE	4 years ago
Bine Brank	a1fea1fe2a	sgemm v2x8 SVE kernel	4 years ago
Bine Brank	abe1ce3434	strmm sve v1x8 kernel	4 years ago
Bine Brank	0de36f7b5c	trmm sve copy fucntions for single precision	4 years ago
Bine Brank	86ae89bf33	add sgemm kernel and copy functions for sgemm and ssymm	4 years ago
Martin Kroeker	454edd741c	Merge pull request #3425 from binebrank/arm_sve_dgemm Add dgemm kernel for arm64 SVE	4 years ago
Jia-Chen	5c1cd5e0c2	MOD: add comments to a53 zgemm kernel	4 years ago
Jia-Chen	9f59b19fcd	MOD: optimize zgemm on cortex-A53/cortex-A55	4 years ago
Bine Brank	531a28b6a0	removed unused code (compiler warnings)	4 years ago
Bine Brank	9b9cb90bb1	modify Makefile for SVE copy	4 years ago
Bine Brank	b58d4f31ab	some clean-up & commentary	4 years ago
Bine Brank	e6ed4be02e	symm SVE copy rutines	4 years ago
Jia-Chen	302f22693a	MOD: optimize normal DGEMM on ARMV8 cortex-A53 & cortex-A55	4 years ago
Bine Brank	3c7eed0e53	add remaining trmm copy rutines for SVE	4 years ago
Bine Brank	7d996b1c36	dtrmm_utcopy sve function	4 years ago
Bine Brank	ab7917910d	add v2x8 kernel + fix sve dtrmm	4 years ago
Bine Brank	7093372e32	add ARMV8SVE target	4 years ago
Bine Brank	a8fbdbac34	fix sve dgemm kernel + sve dtrmm	4 years ago
Bine Brank	746b4f0f17	added SVE ncopy and tcopy	4 years ago
Bine Brank	1a10d3e09d	add sve dgemm prototype	4 years ago
Martin Kroeker	22bf5c27ba	Add basic support for the Fujitsu A64FX (#3415 ) * Add initial support for Fujitsu A64FX as generic ARMV8	4 years ago
Martin Kroeker	8c20ca345a	Use Neoverse's current mix of ThunderX2 kernels for Vortex as well	4 years ago
Martin Kroeker	90cc944625	Move alphaI to x22 to leave x18 unused (reserved on OSX)	4 years ago
Martin Kroeker	590fbff06e	move alpha to x19/x20 to leave x18 unused for OSX	4 years ago
Martin Kroeker	380940271b	Move temp to x21 to leave x18 unused (reserved on OSX)	4 years ago
Martin Kroeker	7d75177446	Move temp to x21 to leave x18 unused (reserved on OSX)	4 years ago
Martin Kroeker	0a4ac4b585	Use x21 for I to leave x18 unused (reserved on OSX)	4 years ago
Martin Kroeker	7d4a221579	Remove unused TEMP2 and reshuffle to leave x18 unused (reserved on OSX)	4 years ago
User User-User	39ef0880ae	copy conf	4 years ago
Gilles Gouaillardet	9d292d37b2	arm64: add the missing d9 register to the clobber list Refs. numpy/numpy#18422 Signed-off-by: Gilles Gouaillardet <gilles@rist.or.jp>	4 years ago
CodesWithWolves	d2bda3b56a	Remove Unnecessary/Erroneous Reads In sgemm_tcopy_16.S COPY1x8 Macro There appears to have been some code leak when copying from the COPY2x8 macro above where we're reading 8 bytes into d4-d7 directly after reading 4 bytes into s4-s7. These 32 bytes in d4-7 are unused and can possibly overrun the boundary of allocated memory -- Valgrind detected this which is what dragged my attention to it for a 128,1 copy. Additionally, there is no need to update the addresses stored in A0-A7 as the only possible paths after running this macro will overwrite A0-7 if looping to the next 8 rows, or overwrite A0-3 if moving to 4 rows -- in which case A4-7 are unused.	4 years ago
Martin Kroeker	b716c0ef01	Add workaround for NVIDIA HPC	5 years ago
Martin Kroeker	2efa3b70dc	Add workaround for NVIDIA HPC	5 years ago
Martin Kroeker	49959d4f1c	Add workaround for NVIDIA HPC	5 years ago
Martin Kroeker	0f27a03607	Add workaround for NVIDIA HPC mishandling of the asm DOT kernels	5 years ago
Martin Kroeker	c2a8ebfe69	Add workaround for NVIDIA HPC mishandling of the asm DOT kernels	5 years ago
Ashwin Sekhar T K	1b2508362b	arm64: Fix nrm2 for input vectors with Inf Fix double precision nrm2 kernels returning NaN when the input vectors contain Inf/-Inf.	5 years ago
Martin Kroeker	8631e2976a	Temporarily revert to the old nrm2 kernels	5 years ago
Martin Kroeker	2768bc1764	Temporarily revert to the old nrm2 kernels	5 years ago
Martin Kroeker	6f4698ee1f	Temporarily revert to the old nrm2 kernel	5 years ago
Martin Kroeker	e1b7123bbe	Merge pull request #2867 from Qiyu8/usimd-floatdot Optimize the performance of dot by using universal intrinsics in X86/ARM	5 years ago
User User-User	d2333e7842	aarch64 fix std=c18 compilation	5 years ago
Qiyu8	60e6c68e38	Adapt ARM architect	5 years ago
Martin Kroeker	775a87242d	Rename KERNEL.SILICON to KERNEL.VORTEX	5 years ago
Martin Kroeker	80794fe8fd	Create KERNEL.SILICON	5 years ago
Ashwin Sekhar T K	4e1be0e481	ARM64: Add THUNDERX3T110 Target	5 years ago
ZhangDanfeng	bc6fd20a40	fix INIT8x4 Signed-off-by: ZhangDanfeng <467688405@qq.com>	5 years ago
ZhangDanfeng	9b7877ccf1	sgemm copy source init Signed-off-by: ZhangDanfeng <467688405@qq.com>	5 years ago

1 2 3 4

167 Commits (afa0cece5cbca7ce9c749b3101ac36b15518508e)