2b967590a0
bugfix in dynamic.c
2016-04-25 09:08:38 +02:00
aa744dfa59
Update memory.c
2016-03-22 20:02:37 +08:00
61cf8f74d9
Fix access violation on Windows while static linking
2016-03-22 19:14:54 +08:00
68eb4fa329
Add missing openblas_env makefile.
2016-03-09 14:52:47 -05:00
05196a8497
Refs #716 . Only call getenv at init function.
2016-03-09 12:50:07 -05:00
1edf30b790
Change Opteron(SSE3) to Opteron_SSE3 at dyanmaic core name.
2016-03-01 20:13:08 +08:00
6b85dbb6dc
Refs #696 . Turn off stack limit setting on Linux.
...
I cannot reproduce SEGFAULT of lapack-test with default stack size
on ARM Linux.
2016-02-24 14:21:42 -05:00
935356c34f
Update dynamic.c and cpuid_x86.c for Intel Avoton.
...
Second part of "support Intel Avoton via Nehalem kernel"
2016-02-02 13:42:55 -05:00
f5df444ceb
Merge pull request #762 from jeromerobert/bug760
...
Let openblas_get_num_threads return the number of active threads
2016-01-26 08:45:16 -06:00
aaa8551c57
Merge pull request #749 from lotheac/illumos_fixes
...
illumos fixes
2016-01-26 08:42:20 -06:00
0d87c1ffb6
Let openblas_get_num_threads return the number of active threads
...
... not the number of allocated threads.
Close #760
2016-01-26 13:04:16 +01:00
e737e32fd1
RLIMIT_NPROC doesn't exist on illumos
2016-01-22 18:55:51 +02:00
97cd4b8aee
illumos fixes to memory.c
2016-01-22 18:55:43 +02:00
0d22551a6b
increase the stack size limit in the constructor
2015-11-20 09:23:01 +01:00
fbc21266e6
Minor C code fixes in driver/
2015-11-09 14:15:49 +05:30
839395fc25
Detect AMD Trinity and Richland.
2015-10-29 02:53:29 +08:00
6040858b22
Fix #673
...
Add lacking headers declarations when compiling for Android ARM7
2015-10-27 13:55:24 +01:00
70642fe4ed
Refs #668 . Raise the signal when pthread_create fails.
...
Thank James K. Lowden for the patch.
2015-10-26 19:02:51 -05:00
2feef49fa8
Merge branch 'develop' into cmake
...
Conflicts:
driver/others/memory.c
2015-10-26 14:54:34 -05:00
1ce054fcb3
Refs #669 . Fixed the build bug with gcc on Mac OS X.
2015-10-22 11:07:35 -05:00
94b125255f
Merge branch 'develop' into cmake
...
Conflicts:
driver/others/memory.c
2015-10-13 04:46:08 +08:00
11ac4665c8
Fixed #654 . Make sure the gotoblas_init function is run before all other static initializations.
2015-10-05 14:14:32 -05:00
cc7cab8a45
Detect other Intel Skylake cores.
...
http://users.atw.hu/instlatx64/
2015-09-09 10:47:17 -05:00
61ae47eb99
Ref #632 . Support Intel Skylake by Haswell kernels.
2015-09-09 11:07:33 -04:00
d3e2f0a1af
add missing barriers
...
should fix issue #597
2015-08-16 15:37:02 +02:00
f874465bb8
Use cmake to build OpenBLAS GENERIC Target on MSVC x86 64-bit.
...
Disable CBLAS and LAPACK.
2015-08-10 14:10:44 -05:00
dcd5ba4443
Merge branch 'cmake' of https://github.com/hpanderson/OpenBLAS into hpanderson_cmake
2015-07-22 04:06:39 +08:00
a11555c715
Support Android NDK armeabi-v7a-hard ABI. (-mfloat-abi=hard)
...
e.g.
make HOSTCC=gcc CC=arm-linux-androideabi-gcc NO_LAPACK=1 TARGET=ARMV7
In Android NDK, it uses armeabi-v7a-hard ABI.
TARGET_CFLAGS += -mhard-float -D_NDK_MATH_NO_SOFTFP=1
TARGET_LDFLAGS += -Wl,--no-warn-mismatch -lm_hard
For more information, please check hard-float example at
android_ndk/tests/device/hard-float/jni/.
2015-05-20 21:57:27 -05:00
51ff17d46e
Add AMD Excavator target.
2015-05-13 16:16:30 -05:00
ebb9eba987
Fix build with ALLOC_SHM=0 (Android NDK)
...
Refactor such that you can build with ALLOC_SHM=0. HughTLB
implicity depends on ALLOC_SHM=1. This patch allows
building for Android NDK r10d.
2015-05-10 00:10:26 -07:00
9798481979
Refs #478 , #482 . Fix segfault bug for gemv_t with MAX_ALLOC_STACK flag.
...
For gemv_t, directly use malloc to create the buffer.
2015-04-13 19:45:27 -05:00
8977b3f235
Refs #529 . Support Intel Broadwell by Haswell kernels.
2015-04-02 11:08:03 -05:00
e95d64333a
Refs #519 . Avoid calling strncpy.
2015-03-19 15:57:22 -05:00
b6438dedea
Fix issue #508
...
Fix race condition during shutdown causing a crash in
gotoblas_set_affinity().
2015-03-18 13:22:43 +01:00
5ae8993752
Added intrinsics for MSVC.
2015-02-25 11:52:51 -06:00
84d90d6ed8
Fixed some compiler errors/warnings for clang.
2015-02-25 11:52:25 -06:00
0d8e227ea7
Changed strategy for setting preprocessor definitions.
...
Instead of generating separate object files for each permutation of
defines for a source file, GenerateNamedObjects now writes an entirely
new source file and inserts the defines as #define c statements.
This solves a problem I ran into with ar.exe where it was refusing to
link objects that had the same filename despite having different paths.
2015-02-24 12:26:33 -06:00
4662a0b13a
Changed generate functions to iterate through a list of float types.
...
This will generate obj files for SINGLE/DOUBLE/COMPLEX/DOUBLE COMPLEX.
2015-02-15 17:44:37 -06:00
c94fe71278
Removed incoming-stack-boundary for MSVC.
...
Made float type optional for GenerateNamedObjects.
Called GenerateNamedObjects for a couple of driver/others files that
needed NAME/CNAME set.
2015-02-11 10:54:14 -06:00
7fa5c4e2fd
Fixed some case issues with ARCH.
...
Added some kernel and driver/others objects.
2015-02-08 15:29:18 -06:00
cfa9392ffa
Fix openblas_get_num_threads and openblas_get_num_procs bug with single thread.
2015-02-08 01:30:23 -06:00
2828f6630c
Added SMP sources to COMMONOBJS.
2015-02-04 14:01:36 -06:00
65a847cd36
Introduce openblas_get_num_threads and openblas_get_num_procs
2015-02-03 12:23:41 -05:00
7194424fef
Added missing common objects to the library.
2015-02-02 15:21:29 -06:00
5057a4b4df
Added openblas add_library call that uses DBLAS_OBJS ojbects.
2015-01-30 15:21:21 -06:00
3e8ea7a351
Added COMMONOBJS to driver/others CMakeLists.txt.
2015-01-30 14:06:14 -06:00
8d9b196e0d
Moved loop over define combos into a function.
...
This function takes a set of sources and a set of preprocessor
definitions. It will iterate over the sources and build an object
file for each combination of preprocessor definitions for each
source file.
2015-01-30 12:14:44 -06:00
0dc559ed30
bugfix in dynamic.c
2014-12-28 17:15:42 +01:00
4319769b79
added target processor STEAMROLLER
2014-12-28 20:16:46 +08:00
2fb02626da
Update organization info.
2014-11-25 15:28:58 +08:00
695e0fa649
#463 fixed a compiling bug on AIX.
2014-11-10 14:39:56 +08:00
a64fe9bcc9
added optimized sgemv_n kernel for sandybridge
2014-09-06 08:41:53 +02:00
2021d0f9d6
experimentally removed expensive function calls
2014-09-05 15:05:53 +02:00
f7eb81a846
Fix link error on Linux/musl.
...
get_nprocs() is a GNU convenience function equivalent to POSIX2008
sysconf(_SC_NPROCESSORS_ONLN); the latter should be available in unistd.h
on any current *nix. (OS X supports this call since 10.5, and FreeBSD
currently supports it. But this commit does not change FreeBSD or OS X
versions.)
2014-08-03 15:06:30 -07:00
793175be3a
added experimental support for big numa machines
2014-08-02 13:40:16 +02:00
c94762bb56
Refs #401 . Added NO_AVX2 flag for old binutils (e.g. RHEL6)
2014-07-16 08:38:25 +08:00
552119c484
Fixed #407 . Support outputing the CPU corename on runtime.
...
The user can use char * openblas_get_config() or char * openblas_get_corename().
2014-07-08 12:48:08 +08:00
50e99a52ea
added definitions for PILEDRIVER and HASWELL
2014-07-06 12:08:27 +02:00
7a8949e0ce
Merge branch 'develop' of https://github.com/TimothyGu/OpenBLAS into TimothyGu-develop
...
Conflicts:
driver/others/memory.c
2014-06-28 20:51:31 +08:00
6c2ead30f0
Remove all trailing whitespace except lapack-netlib
...
Signed-off-by: Timothy Gu <timothygu99@gmail.com>
2014-06-27 12:05:18 -07:00
f41f03ab83
fix #394 . this cleans up some handles after using them, and doesn't disable ALL process privileges upon success
2014-06-27 12:16:57 -04:00
438002204d
Ref #393 : fix for INTERFACE64=0 and ARCH_X86 in divtable
2014-06-21 12:29:23 +02:00
53bfa51ee0
Ref #385 : fixed warnings in dynamic.c
2014-06-12 18:17:08 +02:00
a86d349a51
Ref #380 : enhancements for dynamic_arch
2014-06-12 14:20:03 +02:00
a35a1a9ae7
changed makefiles for lapack development
2014-05-07 11:33:02 +02:00
2c556f093a
Add cast to function pointer to remove warning
2014-02-25 11:08:32 +01:00
3b027d2528
Do not reference pthread_atfork in non-SMP_SERVER mode
2014-02-25 11:08:32 +01:00
49bd98f410
Do not reference pthread_atfork under windows
2014-02-19 19:25:48 +01:00
138a841390
FIX #294 : make OpenBLAS thread-pool resilient to fork via pthread_atfork
2014-02-19 19:01:15 +01:00
046e4013cb
Revert "Refs #294 . Used pthread_atfork to avoid hang after a Unix fork."
...
This reverts commit 3617c22a56
2014-02-19 18:32:54 +01:00
3617c22a56
Refs #294 . Used pthread_atfork to avoid hang after a Unix fork.
...
The problem is the mutex we used in blas_server. Thus, we must clear
the mutex before the fork and re-init them at parent and child process.
If you used OpenMP, GOMP has the same problem by now. Please try other OpenMP
implemantation.
2014-02-18 15:36:04 +08:00
8c7687b419
Refs #338 . Added OPENBLAS_VERBOSE environment variable on runtime
...
By default, OpenBLAS doesn't output the warning message. You can set
OPENBLAS_VERBOSE (e.g. export OPENBLAS_VERBOSE=1) to enable the warning
message on runtime.
2014-01-24 02:05:59 +08:00
ab69443bd4
Refs #332 . Added addtional Intel Ivy Bridge and Haswell CPU-id.
2014-01-05 23:44:29 +08:00
b263e096af
Refs #307 . Delete debug printf.
2013-12-31 15:53:13 +08:00
0b6e13b689
Merge remote branch 'origin/develop' into haswell
2013-12-01 13:38:11 +01:00
5c648a8984
Merge remote branch 'origin/develop' into haswell
2013-12-01 11:25:33 +01:00
5048a80032
Refs #283 . Fixed the incorrect usage of long data type for Windows 64.
2013-11-14 13:46:42 +08:00
a2942456ef
Refs #307 . Fixed the hang bug when free OpenBLAS dll in Windows.
2013-11-13 10:00:18 +08:00
eae4cfa3f6
Avoid failure on qemu guests declaring an Athlon CPU without 3dnow!
...
The present patch verifies that, on machines declaring an Athlon CPU model and
family, the 3dnow and 3dnowext feature flags are indeed present. If they are
not, it fallbacks on the most generic x86 kernel. This prevents crashes due to
illegal instruction on qemu guests with a weird configuration.
Closes #272
2013-08-28 14:29:42 +02:00
2638370844
Init code base for Intel Haswell.
2013-08-13 00:54:59 +08:00
673e453b3f
Enable bulldozer kernels.
2013-08-05 16:07:54 +08:00
143cca4dd5
Merge branch 'develop' into bulldozer
2013-08-05 15:51:53 +08:00
534c5ec919
Fixed #261 . Use strncmp instead of a comparing trick.
2013-07-29 16:48:35 +08:00
5b504d6c23
Refs #263 . Rollback bulldozer and piledriver kernels to barcelona kernels.
2013-07-28 17:39:24 +08:00
72b1edaf1b
Merge branch 'develop' into bulldozer
...
Conflicts:
kernel/x86_64/KERNEL.BULLDOZER
2013-07-28 06:38:25 +02:00
4471c77905
Fixed #261 . Use strncmp instead of a comparing trick.
2013-07-26 23:43:54 +08:00
2a7503e563
Refs #225 . Fixed a bug in GEMM OpenMP threading.
2013-07-15 09:56:19 +08:00
c19a488af2
create openblas_get_parallel to retrieve information which
...
parallelization model is used by OpenBLAS.
2013-07-11 21:39:19 +08:00
f54f5bac9e
Refs #248 . Fixed the LSB compatiable issue for BLAS only.
...
For example, make CC=lsbcc NO_LAPACK=1.
2013-07-09 15:38:03 +08:00
5d3312142a
Refs #221 #246 . Fixed the overflowing stack bug in mutlithreading BLAS3.
...
When NUM_THREADS(MAX_CPU_NUNBERS) is very large ,e.g. 256.
typedef struct {
volatile BLASLONG working[MAX_CPU_NUMBER][CACHE_LINE_SIZE * DIVIDE_RATE];
} job_t;
job_t job[MAX_CPU_NUMBER];
The job array is equal 8MB.
Thus, We use malloc instead of stack allocation.
2013-07-08 01:07:05 +08:00
886cbaf4e4
Support AMD Piledriver by bulldozer kernels.
2013-07-06 12:06:43 -03:00
32dbeb636d
Refs #221 . Set stack limit to 16MB to prevent a SEGFAULT bug on Mac OS X with DYNAMIC_ARCH=1 & NUM_THREADS=256.
2013-07-02 14:17:55 +08:00
88ef307cef
Refs #241 . Add Haswell support (using sandybridge optimizations)
2013-06-30 22:35:14 +08:00
65ffead0cf
Refs #124 . Check XSAVE flag on x86 CPU.
2013-06-06 22:50:43 +08:00
f1ce74ffdd
Improved the print when OS don't support AVX.
2013-03-02 14:15:54 +08:00
d744c9590a
In OpenMP threading, preallocate the thread buffer instead of allocating the buffer every time. This patch improved the performance slightly.
2013-03-01 14:36:47 +08:00
3cc6ae793e
Refs #174 . Return sb pointer when OpenMP or Windows.
2013-02-26 00:48:21 +08:00
5155e3f509
Refs #174 . Fixed the overflowing buffer bug of multithreading hbmv and sbmv.
...
Instead of using thread 0 buffer, each thread uses its own sb buffer.
Thus, it can avoid overflowing thread 0 buffer.
2013-02-13 16:05:58 +08:00
5c8bf6ae0e
Merge branch 'bulldozer' into develop
2013-02-10 01:19:42 +08:00
6ae2f868fd
Set the affinity. Only use 1 core of each module on bulldozer.
2013-02-09 18:19:02 +01:00
Werner Saar
Theoractice
theoractice
Zhang Xianyi
Martin Kroeker
Jerome Robert
Lauri Tirkkonen
Ralph Campbell
j-bo
Yichao Yu
Grazvydas Ignotas
powderluv
Ton van den Heuvel
Hank Anderson
Erik Schnetter
Isaac Dunham
Timothy Gu
Jameson Nash
Olivier Grisel
Sébastien Villemot
grisuthedragon
Dan Luu