bec9d9f63d
Merge pull request #3335 from guowangy/small-matrix-latest
...
Add GEMM optimization for small matrix and single/double kernel for skylakex
2021-08-29 22:33:33 +02:00
4c766cd11f
Fix a small syntax error. A ( was accidently deleted.
2021-08-11 12:08:34 -04:00
c28560129f
Check the total number of arguments passed insead of if the ARGV# is defined. This fixes a problem when compling openblas as a subproject of another code.
2021-08-11 12:00:07 -04:00
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.
2021-08-05 02:59:36 +00:00
fee5abd84b
Small Matrix: support cmake build
2021-08-04 08:50:15 +00:00
0b8f7c8c10
Add cmake support for LOONGARCH64
2021-08-02 10:00:41 +08:00
47ba85f314
Fix regex to match kernels suffixed with cpuname too
2021-07-22 17:24:15 +02:00
30f23be0f9
Rework setting of -mfma to only apply it where necessary
2021-07-22 12:00:03 +02:00
91e2b11d3c
add to cmake listings too
2021-06-20 15:32:42 +02:00
13fa9f737d
Modify defines for CR and RC to work around name collision on Windows
2021-06-16 12:17:25 +02:00
db50b24a4a
Add entries for the new Householder Reconstruction functions from 3.9.1
2021-05-02 19:55:15 +02:00
40000d1f64
Add entries for Householder reconstruction functions from 3.9.1
2021-05-02 19:21:59 +02:00
725432efaa
pass NO_AVX512 macro def
2021-04-07 00:10:41 +08:00
d7a77091a3
Addressed issue #3100 , removing an unnecessary write to the include directory
2021-02-10 12:11:17 +00:00
33b5670122
Merge pull request #3096 from martin-frbg/fixclangcmake
...
Fix Cooperlake/DYNAMIC_ARCH builds with clang on Windows
2021-02-02 13:33:15 +01:00
95e19e2e23
fix case in compiler name check
...
Co-authored-by: xoviat <49173759+xoviat@users.noreply.github.com>
2021-02-02 10:53:46 +01:00
99ac042702
remove spurious lines (probably editor malfunction)
2021-02-01 21:02:53 +01:00
774b9f8653
handle AppleClang in Cooperlake support condition
2021-02-01 20:18:53 +01:00
eb1d2344f7
Fix compiler version check for Intel Cooperlake support (clang-cl does not accept -dumpversion)
2021-02-01 19:45:25 +01:00
0cc36770f1
Merge pull request #3073 from xoviat/embedded
...
add embedded option
2021-01-31 18:02:41 +01:00
cb61d3b46b
Add DYNAMIC_LIST support for ARM64
2021-01-25 13:13:20 +01:00
b60de4447a
add cortex-m platform
2021-01-19 08:57:44 -06:00
89ae305e11
Workaround for cmake having its own C_COMPILER variable
2021-01-13 12:30:26 +01:00
ec4d77c47c
Add -mfma for HAVE_FMA3 in the non-DYNAMIC_ARCH case as well
2020-11-13 09:16:34 +01:00
a29338aaa6
Remove extraneous quotes that caused a cmake policy warning
2020-11-07 20:27:42 +01:00
438a8e5624
Fix placement of getarch call and spurious cpu property accumulation in DYNAMIC_ARCH builds
2020-11-07 20:26:12 +01:00
0155cd53a3
Add -msse3 where needed for DYNAMIC_ARCH builds
2020-11-03 23:45:49 +01:00
a9f9354296
Fix target test
2020-11-02 23:17:46 +01:00
b9bc76aec4
Add files via upload
2020-11-02 22:43:50 +01:00
e5f8c2bf8a
typo fix
2020-11-01 22:25:43 +01:00
6baf8af658
Disable EXPRECISION for the combination of DYNAMIC_CORE and GENERIC target
2020-11-01 22:11:48 +01:00
a7b1f9b1bb
Implementation of BF16 based gemv
...
1. Add a new API -- sbgemv to support bfloat16 based gemv
2. Implement a generic kernel for sbgemv
3. Implement an avx512-bf16 based kernel for sbgemv
Signed-off-by: Chen, Guobing <guobing.chen@intel.com>
2020-10-29 02:08:23 +08:00
eddc65c7b7
Add POWER10 support flag (unconditionally for now)
2020-10-20 01:09:49 +02:00
f5902ab0a1
Support cross-compiling for Apple Vortex
2020-10-18 19:10:58 +02:00
f64243ff57
Add compiler options for sse/sse2/ssse3/sse4.1
2020-10-16 10:47:06 +02:00
786c0a3ce8
Add sse options for use of intrinics with older compilers
2020-10-16 10:41:53 +02:00
756802df61
Merge pull request #2890 from martin-frbg/s-d-sum
...
Revert special handling of Windows xNRM2 and enable C+intrinsics kern…
2020-10-14 09:02:03 +02:00
75e3a92df6
Add express -mavx and -msse options (and fix a stray = for cooperlake)
2020-10-14 01:01:58 +02:00
e3a29f6b58
Change "HALF" and "sh" to "BFLOAT16" and "sb"
2020-10-12 00:07:37 +02:00
68e6823d36
Adapt for supporting only a subset of variable types
2020-10-11 15:01:32 +02:00
88928650c4
Merge pull request #2883 from martin-frbg/issue2872
...
Minor CMAKE fixes
2020-10-11 10:30:33 +02:00
82a497ec5d
restore PRESCOTT default for DYNAMIC_LIST
2020-10-11 00:43:09 +02:00
de27e4f5fb
Stop DYNAMIC_ARCH build if the toplevel source contains a stray config_kernel.h from a gmake build
...
This is unlikely to happen in practice, but if it does, the rogue file would get included instead of the dynamically generated version for each target_core, leading to very confusing errors like "invalid operands (undefined UND and ABS sections)" in compilation of the assembly kernels as macros like PREFETCH would remain undefined
2020-10-11 00:40:22 +02:00
e1b7123bbe
Merge pull request #2867 from Qiyu8/usimd-floatdot
...
Optimize the performance of dot by using universal intrinsics in X86/ARM
2020-10-10 12:10:25 +02:00
f32d34a015
add sse3 compiler flag
2020-10-10 10:36:15 +08:00
a5feea6611
make BLAS3_MEM_ALLOC_THRESHOLD configurable on non-Windows
2020-10-04 23:01:06 +02:00
2367726578
Remove redundant status message
2020-09-30 23:28:49 +02:00
c4aeeeb9f4
Activate all BUILD_ options if none was specified
2020-09-15 23:15:34 +02:00
91c84e1c01
Merge pull request #2796 from Guobing-Chen/BF16_dot_coversion_apis
...
Add bfloat16 based dot and conversion with single/double
2020-09-14 15:00:19 +02:00
26792d2096
Copy BUILD_* directives to the compiler options to allow ifdef in tests
2020-09-13 21:47:55 +02:00
deaeb6c5b8
Add bfloat16 based dot and conversion with single/double
...
1. Added bfloat16 based dot as new API: shdot
2. Implemented generic kernel and cooperlake-specific (AVX512-BF16) kernel for shdot
3. Added 4 conversion APIs for bfloat16 data type <=> single/double: shstobf16 shdtobf16 sbf16tos dbf16tod
shstobf16 -- convert single float array to bfloat16 array
shdtobf16 -- convert double float array to bfloat16 array
sbf16tos -- convert bfloat16 array to single float array
dbf16tod -- convert bfloat16 array to double float array
4. Implemented generic kernels for all 4 conversion APIs, and cooperlake-specific kernel for shstobf16 and shdtobf16
5. Update level1 thread facilitate functions and macros to support multi-threading for these new APIs
6. Fix Cooperlake platform detection/specify issue when under dynamic-arch building
7. Change the typedef of bfloat16 from unsigned short to more strict uint16_t
Signed-off-by: Chen, Guobing <guobing.chen@intel.com>
2020-09-04 02:31:25 +08:00
68b1713c30
Merge pull request #2811 from martin-frbg/issue2806
...
Make NO_AVX512 option override the AVX512 compile test in CMAKE builds as well
2020-09-01 17:19:14 +02:00
0a4c5c4c44
Merge pull request #2807 from martin-frbg/issue2804
...
Work around ARMV8 build-time cpu detection problems on non-Linux systems
2020-08-31 23:44:56 +02:00
5feb087c05
Handle Apple labeling armv8 as arm64 rather than aarch64
2020-08-31 20:02:08 +02:00
7c0977c267
Add OpenMP dependency to pkgconfig file if needed
2020-08-22 13:53:44 +02:00
bd3207b4b4
Update system.cmake
2020-08-19 22:51:10 +02:00
b8ebfc9335
Update system.cmake
2020-08-19 22:30:19 +02:00
7c1986640b
fallback from cooperlake to skylake if gcc<10
2020-08-19 20:48:39 +02:00
71d33c952d
Typo fix
2020-08-19 17:44:23 +02:00
6a3c074786
-march=cooperlake requires gcc10
2020-08-19 17:22:12 +02:00
430f741b30
-march=cooperlake requires gcc10
2020-08-19 17:17:53 +02:00
e740c4873d
Enable COOPERLAKE build target
...
Enable new build target platform -- COOPERLAKE. This target platform
supports all the SKYLAKEX supported ISAs + avx512bf16. So all the
SKYLAKEX specific kernels/drivers and related code are now extended
to be also active on COOPERLAKE. Besides, new BF16 related kernels
are active under this target.
2020-08-13 06:18:00 +08:00
cb097beba2
Merge pull request #2741 from martin-frbg/issue2739
...
Adjust A53 SGEMM parameters to reflect recent switch to 8x8 kernel
2020-07-29 10:01:14 +02:00
64e2e4aaf3
missing braces
2020-07-27 20:19:22 +00:00
921ec4e9e2
Adjust A53 SGEMM parameters to reflect move to 8x8 kernel
2020-07-27 19:54:46 +00:00
4e1be0e481
ARM64: Add THUNDERX3T110 Target
2020-07-26 23:32:24 -07:00
9e21a100e3
Add trivial check for stdatomic.h
2020-07-20 22:52:09 +00:00
9d000ecaa2
include CheckLanguage module
2020-07-16 22:36:35 +00:00
a847d00366
handle missing lack of fortran compiler more gracefully
2020-07-16 22:17:39 +00:00
6eaeb01263
Merge pull request #2658 from RajalakshmiSR/p10
...
powerpc: Add support for future processor
2020-06-23 00:02:37 +02:00
6876221cf3
Remove optimization level limit for flang again and add -fno-unroll-loops for AOCC flang 2.x instead
2020-06-14 17:40:24 +02:00
1dd712131e
Fix spelling of flang option -Mrecursive and add -Kieee
2020-06-14 00:09:31 +02:00
9fe930f205
powerpc: Add support for future processor
...
This is the initial patch to support build infrastructure
for POWER10 architecture.
2020-06-11 15:47:20 -05:00
3ce469a34f
Limit optimization level to O1 for flang and add -frecursive
2020-06-09 16:11:13 +02:00
79cd69fea4
Merge pull request #2644 from martin-frbg/cmake-maxstack
...
Add CMAKE support for MAX_STACK_ALLOC setting
2020-06-05 08:33:48 +02:00
bb12c2c854
Limit MAX_STACK_ALLOC availability to non-Wndows
2020-06-04 19:07:27 +02:00
6e97df7b47
Add CMAKE support for MAX_STACK_ALLOC setting
2020-06-04 14:45:31 +02:00
4db00121dc
Disable EXPRECISION and add -lm on OSX (same as the BSDs and Linux)
2020-05-31 12:39:36 +02:00
cd10b35fe9
Handle trailing spaces and empty condition variables
2020-05-09 13:42:33 +02:00
5dd14e3d48
Make building the bfloat16 functions conditional on option BUILD_HALF ( #2590 )
...
* make building the bfloat16 BLAS functions conditional on BUILD_HALF
* pass the BUILD_HALF option to gensymbol
* Pass BUILD_HALF as a compiler define for dynamic_arch builds
2020-05-01 09:58:30 +02:00
3bd56846bb
Silence a debug message
2020-04-27 16:27:09 +02:00
e7bbdfdf84
Have CMAKE parse conditional lines in KERNEL files
...
Supports ifeq and ifneq, but requires both to have an else branch
2020-04-27 15:20:03 +02:00
70869d571f
Quote include paths for getarch to protect any embedded spaces
2020-04-24 10:30:44 +02:00
4f70512b97
Update kernel.cmake
2020-04-19 08:10:26 +02:00
d0737b0142
Update kernel.cmake
2020-04-18 21:36:28 +02:00
a83a59b038
Use generic kernels for ishama,shasum,shdot,shrot
2020-04-18 15:53:51 +02:00
0a19bd813c
Use generic codes for shamax and shcopy
2020-04-18 12:52:51 +02:00
f361de30a3
Use generic axpy.c for SHAXPY as x86 lacks saxpy.c
2020-04-18 11:07:16 +02:00
9f6d6f6cb6
use saxpy.c instead of axpy.S for SHAXPY
2020-04-17 22:27:58 +02:00
22bb50fb81
cmake fixes
2020-04-17 13:35:17 -05:00
7eb55504b1
RFC : Add half precision gemm for bfloat16 in OpenBLAS
...
This patch adds support for bfloat16 data type matrix multiplication kernel.
For architectures that don't support bfloat16, it is defined as unsigned short
(2 bytes). Default unroll sizes can be changed as per architecture as done for
SGEMM and for now 8 and 4 are used for M and N. Size of ncopy/tcopy can be
changed as per architecture requirement and for now, size 2 is used.
Added shgemm in kernel/power/KERNEL.POWER9 and tested in powerpc64le and
powerpc64. For reference, added a small test compare_sgemm_shgemm.c to compare
sgemm and shgemm output.
This patch does not cover OpenBLAS test, benchmark and lapack tests for shgemm.
Complex type implementation can be discussed and added once this is approved.
2020-04-14 14:55:08 -05:00
a05243d0f2
ifort and pgfort need "recursive" for compiling LAPACK as well
...
as shown in Reference-LAPACK issue 401 (their PR 403)
2020-04-01 15:38:07 +02:00
8c7c1395da
Merge pull request #2521 from martin-frbg/cm-avx512
...
Use proper extension on the avx512 testcase filename
2020-03-22 01:03:42 +01:00
1d9773b800
Use proper extension on the avx512 testcase filename
...
The need to call it .tmp existed only when it was generated by a tmpfile call, and the "-x c" option to tell the compiler it is actually a C source is not universally supported (this broke the test with clang-cl at least)
2020-03-20 23:05:53 +01:00
6d54c94760
Make ifort on Windows create lowercase symbols with appended underscore
...
tentative fix for #2472
2020-03-20 01:08:10 +01:00
21f6c4b5a9
fixes #2480
2020-03-02 17:22:28 +01:00
c623a965f9
Add Neoverse-N1 core
...
The implementation is a hybird of the ARMV8 one with some of the
improved TX2 rountines along with specifying -march=v8.2-a
2020-02-29 03:22:04 +00:00
ca4f7dceff
Add parameters for EMAG8180 DYNAMIC_ARCH support with cmake
2020-02-24 20:23:18 +01:00
1ddf9f1067
Add EMAG8180 to arm64 DYNAMIC_ARCH list for cmake
2020-02-24 20:16:18 +01:00
7f0d523b42
Make BUFFER_SIZE configurable
2020-02-09 23:32:57 +01:00
Martin Kroeker
cianciosa
Wangyang Guo
gxw
User User-User
刘雨培
Jake Arkinstall
xoviat
Chen, Guobing
Qiyu8
Ashwin Sekhar T K
Rajalakshmi Srinivasaraghavan
Rajalakshmi Srinivasaraghavan
مهدي شينون (Mehdi Chinoune)
Ali Saidi