You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
 
Martin Kroeker b716c0ef01
Add workaround for NVIDIA HPC
4 years ago
..
alpha Add implementations of ssum/dsum and csum/zsum 6 years ago
arm Support NVIDIA HPC compiler 4 years ago
arm64 Add workaround for NVIDIA HPC 4 years ago
generic Add the support for RISC-V Vector. 5 years ago
ia64 Add ia64 implementation of ?sum 6 years ago
mips Add msa support for loongson 5 years ago
mips64 Add msa support for loongson 5 years ago
power Optimize swap function for POWER10 4 years ago
riscv64 Refs #2899 5 years ago
simd fix the CI failure of lack the head 5 years ago
sparc Work around DOT and SWAP test failures 5 years ago
x86 Enable COOPERLAKE build target 5 years ago
x86_64 Disable FMA intrinsics in the srot kernel when the compiler is PGI/NVIDIA 4 years ago
zarch s390x: fix cscal and zscal implementations 5 years ago
CMakeLists.txt Change "HALF" and "sh" to "BFLOAT16" and "sb" 5 years ago
Makefile Amend SkylakeX options to support the NVIDIA compiler 4 years ago
Makefile.L1 Conditionally add -mfma to compiler options where needed 5 years ago
Makefile.L2 Implementation of BF16 based gemv 5 years ago
Makefile.L3 Add msa support for loongson 5 years ago
Makefile.LA Support NO_LAPACK=1 to build the lib without LAPACK functions. 14 years ago
setparam-ref.c Add msa support for loongson 5 years ago