ec6b354c32
use /usr/bin/env perl
2021-02-24 14:07:20 +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
0d140e61ac
Fix wrong grouping of dcombssq
2020-10-23 15:53:40 +02:00
4c45cd6294
fix missing split of sladiv1/dladiv/ilaenv2stage by build type
2020-10-23 15:31:25 +02:00
4ad33c46b0
Add back symbols that got dropped when splitting by type
2020-10-19 20:37:52 +02:00
5b9ebe4f8a
Merge pull request #2919 from isuruf/export
...
Fix exporting some lapack and cblas symbols
2020-10-19 08:14:27 +02:00
14b1d33933
Fix exporting some lapack and cblas
2020-10-18 22:45:58 -05:00
a5c667b55c
Need a space when redirecting to file
...
Following two commands have two completely different meanings
perl ./gensymbol objcopy x86_64 _ 0 0 0 0 0 0 "" "64_" 1 0 1 1 1 1 > objcopy.def
perl ./gensymbol objcopy x86_64 _ 0 0 0 0 0 0 "" "64_" 1 0 1 1 1 1> objcopy.def
2020-10-18 09:40:31 -05:00
b5d30b390d
Fix build issues with bfloat16
...
This patch fixes compilation errors due to recent renaming from SH to SB
with BUILD_BFLOAT16.
2020-10-13 11:00:22 -05:00
ae1ab5bfdf
Change "HALF" and "sh" to "BFLOAT16" and "sb"
2020-10-12 00:03:21 +02:00
d33de97d60
Adapt to having only a subset of variable types supported
2020-10-11 14:36:45 +02:00
6a83c591d6
Adapt for having only a subset of variable types
2020-10-11 14:34:12 +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
9ae154ba89
Patch for building on Summit
2020-07-20 23:30:28 -04:00
41fc6f3cd2
Added missing exported symbols.
2020-06-13 22:37:39 +02:00
ba2c5b404d
When building with flang, use it also for the final link step to get dependencies right
2020-06-09 16:09:34 +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
67cc4b9e16
Fix warnings in clang and export symbol
2020-04-15 19:15:23 -05:00
41e802443a
libname: treat FreeBSD and DragonFly like linux and sunos
...
There is no difference in the way libnames are handle between FreeBSD
and linux or sunos. FreeBSD and DragonFly prefers having sonames as well
2020-04-03 06:20:42 +02:00
23f322f997
Do not run any cleanup if the program is exiting anyway
...
From keno's PR #2350 - this avoids the potential hang in blas_thread_shutdown where we may wait for threads to exit while they are waiting on the loader lock from DllMain
2020-01-19 13:28:27 +01:00
375b1875c8
[WIP] Update LAPACK to 3.9.0 ( #2353 )
...
* Update make.inc entries for LAPACK 3.9.0
Reference-LAPACK PR 347 changed some variable names and relative paths
* Update LAPACK to 3.9.0
* Add new functions from LAPACK 3.9.0
* Add new functions from LAPACK 3.9.0
* Restore LOADER command
as it makes it easier to specify pthread as needed
* Restore LOADER
* Restore EIG/LIN prefixes in cmdbase
* add binary path to lapack_testing.py call
* Restore OpenMP version check
* Restore OpenMP version check
* Restore fix for out-of-bounds array accesses
from #2096
2020-01-01 13:18:53 +01:00
fab49e49e5
Move most lapack 3.7/3.8 additions to the embedded_underscores list
...
to allow linktest to pass with a compiler that adds a second underscore to such names
2019-10-24 21:26:20 +02:00
b89d9762a2
Change install_name on osx to match linux
2019-07-08 17:14:35 -05:00
8ba9e2a61a
Also call CloseHandle on each thread, as well as on the event so as to not leak thread handles.
2019-03-19 11:21:44 +01:00
4ad694eda1
Fix for #2063 : The DllMain used in Cygwin did not run the thread memory
...
pool cleanup upon THREAD_DETACH which is needed when compiled with
USE_TLS=1.
2019-03-19 09:26:50 +01:00
adb419ed67
With the Intel compiler on Linux, prefer ifort for the final link step
...
icc has known problems with mixed-language builds that ifort can handle just fine. Fixes #1956
2019-02-14 22:57:30 +01:00
6f77af2eef
Add `$(LDFLAGS)` to `$(CC)` and `$(FC)` invocations within `exports/Makefile`
2018-09-21 09:19:51 +00:00
6463bffd59
Haiku supporting patches
2018-08-02 20:49:14 +02:00
43e592ceb3
Add -lm for Android.
...
Conflicts:
exports/Makefile
2018-05-24 21:02:42 +08:00
24f8d5b624
Add DragonFly to exports/Makefile
...
Its exclusion was an oversight on my part.
2018-04-06 17:30:10 -07:00
8da6b6ae52
Allow building on OpenBSD
...
With this change, OpenBLAS builds and all tests pass on OpenBSD 6.2
using Clang. Tested on x86-64 only, with and without DYNAMIC_ARCH=1.
2018-04-02 10:48:22 -07:00
2d52f0f4c3
update cmakefiles for lapack 3.8.0
2017-11-23 21:22:01 +01:00
3be5c3d343
Update LAPACK to 3.8.0
2017-11-23 18:13:35 +01:00
9268314290
Fix gensymbol script
2017-11-06 21:12:38 -06:00
00c42dc815
Merge pull request #1314 from martin-frbg/nofortran-fix-2
...
Rewrite NOFORTRAN conditionals
2017-09-26 10:34:18 +02:00
79e754e548
Rewrite NOFORTRAN conditionals
...
... so that they do not trigger accidentally when NOFORTRAN is empty/unset
2017-09-25 23:45:14 +02:00
2922c15f36
Merge pull request #1302 from martin-frbg/nofortran-fix
...
Remove default FEXTRALIBS in NOFORTRAN case
2017-09-14 11:54:20 +02:00
3a245a376f
Remove default FEXTRALIBS in NOFORTRAN case
2017-09-14 09:21:04 +02:00
dddedbab5d
More canonical installation on Cygwin:
...
* The DLL is named cygopenblas.dll, not libopenblas.dll
* The import lib (still called libopenblas.dll.a) is installed
2017-09-07 14:18:56 +02:00
3b0624d50f
Build shared library on Android without SONAME versioning
...
Android does not support versioned SONAME entries, ref. #1173
2017-05-10 13:08:13 +02:00
90dd190a6d
Build shared library for Android.
2017-04-11 12:01:18 +08:00
26a614fdd1
Whitespace cleanup/reformatting
2017-03-09 15:30:43 -08:00
7ae64f4f9c
Add `csymv` and `zsymv` into `@lapackobjs2` for exporting
2017-03-09 15:22:40 -08:00
a8bb5003de
removed blas_thread_shutdown from gensymbol
2017-01-08 08:51:30 +01:00
abc3304587
fix for appveyor test
2017-01-07 14:27:08 +01:00
a836fe8ec1
updated exports/gensymbol for lapack-3.7.0
2017-01-07 13:20:28 +01:00
efaf30d536
Wrap CURDIR and DESTDIR in quotes
2016-05-03 21:31:32 +02:00
fb8968fb83
Refs #707 . Bugfix for previous commit.
2016-02-11 05:14:53 +08:00
dae6b82a71
Refs #707 . Add BUILD_LAPACK_DEPRECATED flag in Makefile.rule.
...
If you want to build LAPACK deprecated functions since LAPACK 3.6.0
make BUILD_LAPACK_DEPRECATED=1
2016-02-11 04:22:53 +08:00
aaa8551c57
Merge pull request #749 from lotheac/illumos_fixes
...
illumos fixes
2016-01-26 08:42:20 -06:00
Harmen Stoppels
Chen, Guobing
Martin Kroeker
Isuru Fernando
Rajalakshmi Srinivasaraghavan
Wileam Phan
Simon Märtens
Baptiste Daroussin
Erik M. Bray
Elliot Saba
Zoltán Mizsei
Zhang Xianyi
Alex Arslan
martin
Zhang Xianyi
Werner Saar
Ivan Ukhov