6a99fcce94
Use _Atomic instead of volatile for thread safety where C11 is supported
...
Suggested by dodomorandi in #660
2018-03-10 00:03:49 +01:00
7646974227
Limit the additional locking from PRs 1052,1299 to non-OpenMP multithreading
2018-02-21 11:45:33 +01:00
8866e393a2
Revert "Add locks only for non-OPENMP multithreading"
2018-02-20 17:17:12 +01:00
3119b2ab4c
Add locks only for non-OPENMP multithreading
...
to migitate performance problems caused by #1052 and #1299 as seen in #1461
2018-02-20 12:17:18 +01:00
8f5f614615
On Cygwin use mmap instead of Windows native allocation functions, which are not fork-safe.
2018-02-06 12:23:27 +01:00
f5fc109fbd
Perform blas_thread_shutdown with pthread_atfork() on Cygwin
...
Even if we're directly using the win32 threading driver and not pthreads,
pthread_atfork still works fine to register a pre-fork handler, and is
necessary to restore the threading server to a pre-initialized state.
2018-02-06 12:23:27 +01:00
e388459a27
Merge pull request #1419 from brada4/develop
...
Initialize unitialized values for repeated calls
2018-01-31 23:48:34 +01:00
e5752ff9b3
take out unused variables
2018-01-20 11:42:31 +01:00
8a0b086b28
add missing bracket for old glibc (cppcheck)
2018-01-12 22:35:48 +01:00
42285d8e70
Merge pull request #1410 from brada4/develop
...
Address warnings #1357
2018-01-06 20:02:46 +01:00
8aafa0473c
address last warnings as seen by gcc7
2018-01-01 20:57:12 +01:00
11a627c54e
remove surplus parentheses to silence clang5
2018-01-01 20:56:26 +01:00
cc9500db41
Merge pull request #1403 from brada4/develop
...
Address few more warnings
2017-12-30 14:51:34 +01:00
bfc2a88594
remove unused buffer
2017-12-22 00:55:40 +01:00
177b78c8b4
Issue1388 ( #1389 )
...
* Calculation of chunk range limits was ignoring num_cpu
bug introduced by me in #1262 - should fix #1388
* Calculation of range limits was ignoring num_cpu
bug introduced by me in #1262
* Calculation of chunk range limits was ignoring num_cpu
bug introduced by me in #1262
* Calculation of chunk range limits was ignoring num_cpu
bug introduced by me in #1262
* Calculation of chunk range limits was ignoring num_cpu
bug introduced by me in #1262
* Calculation of chunk range limits was ignoring num_cpu
bug introduced by me in #1262
2017-12-09 22:29:03 +01:00
281a2b952f
warning cleanup ( #1380 )
...
* dead increments in driver/level2
* dead increments in kernel/generic
* part dead increments in kernel/x86_64
2017-12-05 19:54:10 +01:00
c49c6b237d
Merge pull request #1382 from martin-frbg/dtrmv-1332
...
Work around errors in multithreaded dtrmv
2017-12-05 19:53:23 +01:00
28ae3ca76f
Limit MAX_CPU to 1024 for now
...
Some Linux distributions (notably SuSE) have raised CPU_SETSIZE to 4096, apparently disregarding API limitations.
From #1348 , the highest value to survive array initialization (on a desktop system) is 3232, and 1024 - which is the
more usual CPU_SETSIZE limit, was demonstrated to work fine on an actual bignuma system.
2017-12-05 12:54:15 +01:00
b414283f48
Disable gemv unrolling
...
as a (hopefully temporary) workaround for #1332
2017-12-03 22:41:54 +01:00
ef95cd471f
elminate unread variable, after reiteration 3 of them (clang4)
2017-11-25 02:54:37 +01:00
e14d50d86e
eliminate Wunused-const gcc7 warning
2017-11-24 19:13:24 +01:00
07e7c36dac
Handle shmem init failures in cpu affinity setup code
...
Failures to obtain or attach shared memory segments would lead to an exit without explanation of the exact cause.
This change introduces a more verbose error message and tries to make the code continue without setting cpu affinity.
Fixes #1351
2017-11-18 23:57:44 +01:00
2a6fef9a55
Try to handle shmget or shmat failing
...
also replaces one verbatim sched_yield with the YIELDING macro for consistency as suggested in #1351
2017-11-09 23:16:13 +01:00
db72ad8f6a
Merge pull request #1320 from timmoon10/develop
...
2D thread distribution for multi-threaded GEMMs
2017-10-08 23:31:33 +02:00
514d237257
Merge pull request #1279 from xsacha/develop
...
CMake improvements
2017-10-06 21:13:45 +02:00
30486a356c
Reduce number of data partitions in n.
2017-10-04 12:37:49 -07:00
9de52b489a
Cleaning up and documenting multi-threaded GEMM code.
2017-10-03 16:32:08 -07:00
860dcfc703
Use 2D thread distribution for small GEMMs.
...
Allows maximum use of available cores if one of M and N is small and the other is large.
2017-10-03 13:43:39 -07:00
6aaa107865
Reducing threads for multi-threaded GEMMs on small matrices.
2017-09-27 19:25:33 -07:00
ba1f91f17b
Convert another caller of "allocation" to LOCK_COMMAND
...
... as the "allocation" code jumped to now does UNLOCK_COMMAND instead of blas_unlock
2017-09-09 20:30:33 +02:00
f460776f0f
Fix thread data races
2017-09-09 19:07:06 +02:00
e882f3d6f3
Fix thread data race in memory.c
2017-09-09 18:58:38 +02:00
37858d1146
Fix threading usage in CMake: s/SMP/USE_THREAD/
2017-08-19 15:07:42 +10:00
2f12ea017b
No strncasecmp with MSVC
2017-08-08 00:07:25 +05:30
719fcc56b0
Merge pull request #1262 from martin-frbg/xmv_thread-splitting
...
Make sure that range limit of last thread never exceeds data size
2017-08-06 14:11:44 +02:00
ebb04e3265
Merge pull request #1259 from isuruf/cmake
...
CMake Improvements
2017-08-02 15:31:05 +02:00
0ba64cee60
Update trmv_thread.c
2017-08-02 12:03:54 +02:00
c4e5ba1bfe
Make sure that range_n of last thread never exceeds the actual data size when splitting the workload
2017-08-02 00:37:58 +02:00
a6f533b248
Revert "Fix calculated range limit exceeding actual data size for last thread"
2017-08-01 19:28:08 +02:00
d245caa49a
Support out-of-source build
2017-08-01 15:16:14 +05:30
e70a6b92bf
Merge pull request #1257 from martin-frbg/cgroups-prereq
...
Rework __GLIBC_PREREQ checks to avoid breaking non-glibc builds
2017-08-01 11:23:03 +02:00
63cfa32691
Rework __GLIBC_PREREQ checks to avoid breaking non-glibc builds
2017-07-31 21:02:43 +02:00
585c0010a5
Fix range limit exceeding actual data size in last step
2017-07-28 00:27:02 +02:00
857f61bc5d
Fix range limit exceeding data size in last step
2017-07-28 00:21:53 +02:00
9332042d5f
Fix range exceeding actual data size in quick_divide
2017-07-28 00:13:24 +02:00
c4af196a2d
Honor cgroup/cpuset limits when enumerating cpus
2017-07-25 22:47:34 +02:00
480e697681
Revert "Honor cgroup/cpuset limits when enumerating cpus" ( #1246 )
2017-07-24 16:17:50 +02:00
80373ea039
More fixes for silly misedits
2017-07-15 12:48:42 +02:00
d12b75a6c4
Fixup braces lost in previous edit
2017-07-15 11:53:28 +02:00
7294fb1d9d
Merge branch 'develop' into cgroups
2017-07-15 10:40:42 +02:00
Martin Kroeker
Erik M. Bray
Andrew
Tim Moon
Sacha Refshauge
Isuru Fernando