OpenBLAS

78 MB

Tree: f59eb5f8bc

Author	SHA1	Message	Date
Chris Sidebottom	84a268b6ca	Use SVE zgemm/cgemm on Arm(R) Neoverse(TM) V1 core This patch removes the prefetches from cgemm/zgemm which improves the performance similar to sgemm/dgemm did in #3868, this means I'm happy to enable this on any applicable cores. I also replicated the unrolling the copies from sgemm and dgemm.	2 years ago
Chris Sidebottom	aea2a4622b	Use latest non-SVE kernels in ARMV8SVE These are generally better and, in some cases, include threading which helps in the cores we're targeting here.	2 years ago
Chris Sidebottom	ec334e69dc	Use SVE kernel for SGEMM/DGEMM on Arm(R) Neoverse(TM) V1 This re-spins #3869 with some additional copy unrolling which helps maintain SYRK performance. After #3868, the SVE kernels represent a pretty good boost. This re-uses ARMV8SVE as a base and I'm going to incrementally move everything to use ARMV8SVE in additional patches (as well as fix up anything that's not already in ARMV8SVE).	3 years ago
Bine Brank	19d435b1b3	update armv8sve + contributors	4 years ago
Bine Brank	f33543d029	combine zchemm into single file	4 years ago
Bine Brank	d30157d891	update configuration of kernels for A64FX and ARMV8SVE	4 years ago
Bine Brank	a8f62a347b	fix UNROLL_MN and add to targets for SVE	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	7093372e32	add ARMV8SVE target	4 years ago