Martin Kroeker
ebe50458f3
Do not add a -tp to the flags of the nvc compiler if there is one already in CFLAGS
2 years ago
Martin Kroeker
3e64fa72c4
Settings from Makefile(_kernel).conf should be available to DYNAMIC_ARCH kernel builds
2 years ago
Martin Kroeker
ca3b5ae3f0
Pass NO_SVE if set
2 years ago
Martin Kroeker
d16261fbc6
SVE-enabled targets in ARM64 DYNAMIC_ARCH require a recent compiler
2 years ago
Martin Kroeker
57151b97aa
Fix INTERFACE64 builds on riscv and loongarch
2 years ago
Martin Kroeker
62341ac5e1
Fix missing parenthesis
2 years ago
Martin Kroeker
5a294b0c8a
Add -lm on any arm/arm64 BSD, not just FreeBSD
2 years ago
Martin Kroeker
ea6c5f3cf5
Add option RELAPACK_REPLACE
2 years ago
Martin Kroeker
bd30120ba7
Merge pull request #3720 from FlyGoat/mips64
Make it work on general MIPS64 processors
3 years ago
Jiaxun Yang
fae9368f14
Implement DYNAMIC_LIST for MIPS64
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
3 years ago
Jiaxun Yang
a50b29c540
Provide a fallback MIPS64_GENERIC target
It is really dangerous to fallback to Loongson core on other
MIPS64 processors.
Signed-off-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
3 years ago
Martin Kroeker
85fd3c4279
Support compilation with the Cray C and Fortran compilers ( #3712 )
* Add support for the Cray Fortran compiler
3 years ago
Martin Kroeker
d0ba257de0
Merge pull request #3704 from XiWeiGu/loongarch64_dynamic_arch
LoongArch64: Add DYNAMIC_ARCH support
3 years ago
Rajalakshmi Srinivasaraghavan
1d97405c02
POWER: Enable bfloat16 kernels by default
This patch enables bfloat16 kernels by default for POWER processors.
Tested on Linux POWER8, POWER9, POWER10 and AIX POWER10 systems.
3 years ago
gxw
fbfe1daf6e
LoongArch64: Add DYNAMIC_ARCH support
3 years ago
gxw
3573306a69
LoongArch64: Add core LOONGSON2K1000 and LOONGSONGENERIC
3 years ago
Martin Kroeker
407a1a242c
Merge pull request #3670 from martin-frbg/osxvermin
Increase MACOSX_DEPLOYMENT_TARGET to 11 on ARM macs
3 years ago
Martin Kroeker
be5500e704
Merge pull request #3669 from VFerrari/fix_small_matrix_kernel
POWER: fix issues with the small matrix kernel
3 years ago
Martin Kroeker
914c4d0fe8
Add C versions of the CBLAS test sources ( #3656 )
* Add C conversions of the CBLAS tests for NOFORTRAN=1 builds
* Enable CTEST without Fortran and fix passing of BUILD_vartype options to exports/gensymbol
3 years ago
Martin Kroeker
2857987ff6
Increase MACOSX_DEPLOYMENT_TARGET to 11 on ARM macs
3 years ago
VFerrari
2062280c6f
Power: Enable SMALL_MATRIX OPT as default for dynamic arch
3 years ago
Martin Kroeker
8f13ab94d2
Merge pull request #3613 from Rabenda/fix-riscv
Fix riscv64 detect
3 years ago
Martin Kroeker
24e99eca31
Avoid adding -lgfortran with NOFORTRAN
3 years ago
Han Gao
3fc52ebcfb
Fix other arch build in detect.
When CORE is empty, use -march=loongson3a. Fix it.
Signed-off-by: Han Gao <gaohan@uniontech.com>
3 years ago
Niyas Sait
3f5d145cd4
build: minor fixes to build on windows with make
This patch contains following fixes
1. Fix to build without PIC flag
2. Define LAPACK_COMPLEX_STRUCTURE for windows. Builds are failing
without it and changes are consistent with the CMake rules defined
in system.cmake (line 576)
3 years ago
Martin Kroeker
b7873605d4
Use f2c translations of LAPACK when no Fortran compiler is available ( #3539 )
* Add C equivalents of the Fortran routines from Reference-LAPACK as fallbacks, and C_LAPACK variable to trigger their use
3 years ago
Martin Kroeker
499ae5e8f7
Merge pull request #3510 from martin-frbg/issue3505
Fix recent SkylakeX/DYNAMIC_ARCH DGEMM breakage
3 years ago
Martin Kroeker
f1ac59f200
Forward DYNAMIC_ARCH option to Makefile.prebuild
3 years ago
Sunita Nadampalli
19c8f615dc
OpenBLAS: aarch64: Add neoverse-v1/n2 architecture specifics
3 years ago
Martin Kroeker
ed430cd963
Update -tp option for recent nvfortran on x86_64
3 years ago
kavanabhat
eee3381cbe
Fallback for Power kernels
3 years ago
Martin Kroeker
54d321d742
Merge pull request #3466 from rafaelcfsousa/rafael/small_matrix_p10
[POWER] Add small matrix for sgemm/dgemm on Power10
3 years ago
kavanabhat
9a45b5123f
Update Makefile.system
3 years ago
kavanabhat
7b5b93037d
Fix truncated assembler checks
3 years ago
Rafael Cardoso Fernandes Sousa
c78fdcc80d
[POWER] Add support for SMALL_MATRIX_OPT
3 years ago
Martin Kroeker
46947efb83
Ignore compiler support for MIPS MSA if the cpu lacks this capability
3 years ago
Martin Kroeker
9cc0098ce2
Fix potentially wrong HOSTARCH definition in cross-compilation
3 years ago
Martin Kroeker
a6fd497820
Fix nvidia HPC version checks
3 years ago
Martin Kroeker
bb01e26cfe
Adjust compiler options for nvidia hpc 21.9 (and fix a long-standing typo in dynamic_arch settings)
3 years ago
Wangyang Guo
3dc6052c7e
initial support for Sapphire Rapids platform
4 years ago
Martin Kroeker
8e4c209002
Merge pull request #3398 from kavanabhat/aix_p10_gnuas
Big Endian Changes for Power10 kernels
4 years ago
Martin Kroeker
04f3ecd026
Fix minor typo
4 years ago
kavanabhat
9cc95e5657
AIX changes for P10 with GNU Compiler
4 years ago
Alexandru Ardelean
b7bb2e36b8
Makefile.system: adjust mipsel/mips64el ARCH variables
When building for MIPS{64} little-endian variants, the included makefiles
should be the same as for the big-endian.
There are already some adjustments being done for some ARCH names.
This change adds the ones for the `mipsel` and `mips64el` names, so that
the Makefile.mips{64} files get included.
This comes as a result of: https://github.com/openwrt/packages/issues/16649
Signed-off-by: Alexandru Ardelean <ardeleanalex@gmail.com>
4 years ago
Wangyang Guo
76ea8db4da
Small Matrix: enable by default for x86_64 arch
If no customized GEMM_SMALL_M_PERMIT kernel defined, it will just by pass to normal path.
4 years ago
Xianyi Zhang
0a2077901c
Add small marix optimization kernel interface.
make SMALL_MATRIX_OPT=1
5 years ago
gxw
34207bdf5b
Fixed typos about LOONGARCH64
4 years ago
gxw
af0a69f355
Add support for LOONGARCH64
4 years ago
User User-User
9335d42740
add gcc8 version matching
4 years ago
User User-User
b7da75e4fd
WiP CORTEX A55 support
4 years ago