Rajalakshmi Srinivasaraghavan 0571c3187b POWER10: Rename mma builtins ... The LLVM and GCC teams agreed to rename the __builtin_mma_assemble_pair and __builtin_mma_disassemble_pair built-ins to __builtin_vsx_assemble_pair and __builtin_vsx_disassemble_pair respectively. This patch is to make corresponding changes in dgemm kernel. Also made changes in inputs to those builtins to avoid some potential typecasting issues. Reference gcc commit id:77ef995c1fbcab76a2a69b9f4700bcfd005d8e62		2021-02-26 20:56:34 -06:00
..
alpha	Add implementations of ssum/dsum and csum/zsum	2019-03-30 22:05:11 +01:00
arm	Typo fix	2021-02-23 13:14:35 +01:00
arm64	Add workaround for NVIDIA HPC	2021-01-12 16:51:35 +01:00
generic	Add the support for RISC-V Vector.	2020-10-15 16:09:02 +08:00
ia64	Add ia64 implementation of ?sum	2019-03-30 22:18:03 +01:00
mips	Add msa support for loongson	2020-12-09 10:28:46 +08:00
mips64	Add msa support for loongson	2020-12-09 10:28:46 +08:00
power	POWER10: Rename mma builtins	2021-02-26 20:56:34 -06:00
riscv64	Refs #2899	2020-11-10 09:38:04 +08:00
simd	fix the CI failure of lack the head	2020-11-12 17:35:17 +08:00
sparc	Work around DOT and SWAP test failures	2020-12-06 19:15:37 +01:00
x86	Enable COOPERLAKE build target	2020-08-13 06:18:00 +08:00
x86_64	Update omatcopy_rt.c	2021-02-24 09:34:14 +01:00
zarch	s390x: fix cscal and zscal implementations	2020-09-21 13:10:05 +02:00
CMakeLists.txt	Fix building "generic" TRMM kernel with CMake	2021-01-14 10:00:49 +01:00
Makefile	Amend SkylakeX options to support the NVIDIA compiler	2020-12-19 22:11:49 +01:00
Makefile.L1	Conditionally add -mfma to compiler options where needed	2020-12-17 11:34:05 +01:00
Makefile.L2	Implementation of BF16 based gemv	2020-10-29 02:08:23 +08:00
Makefile.L3	Add msa support for loongson	2020-12-09 10:28:46 +08:00
Makefile.LA	Support NO_LAPACK=1 to build the lib without LAPACK functions.	2011-03-04 11:51:32 +08:00
setparam-ref.c	Add msa support for loongson	2020-12-09 10:28:46 +08:00