Commit Graph

14 Commits

Author SHA1 Message Date
Vincent Rabaud
7463e9b8bb Even faster CV_PAUSE on SkyLake and above.
No need to loop as RDTSC is 3/4 times faster than _mm_pause.
2022-12-19 14:15:34 +01:00
Vincent Rabaud
b7b08fa0c3 Fix slower CV_PAUSE on SkyLake and above.
This is fixing https://github.com/opencv/opencv/issues/22852
2022-12-15 14:18:57 +01:00
Alexander Alekhin
62414e3073 core(parallel): suppress TSAN warning 2021-10-04 10:46:32 +00:00
Vincent Rabaud
847b16fb76 Disable thread sanitization when CV_USE_GLOBAL_WORKERS_COND_VAR is not set.
This fixes #19463
2021-02-09 14:12:39 +01:00
Alexander Alekhin
e83438c23d core(build): fix i386 compilation 2020-01-26 00:00:25 +00:00
Alexander Alekhin
816f82682b core(trace/itt): avoid calling __itt_thread_set_name() by default
- don't override current application thread names
- set name for own threads only
2019-12-07 21:41:15 +00:00
mipsopen-fwu
b1ea91d8bd Merge pull request #15422 from mipsopen-fwu:msa-dev
* Added MSA implementations for mips platforms. Intrinsics for MSA and build scripts for MIPS platforms are added.

Signed-off-by: Fei Wu <fwu@wavecomp.com>

* Removed some unused code in mips.toolchain.cmake.

Signed-off-by: Fei Wu <fwu@wavecomp.com>

* Added comments for mips toolchain configuration and disabled compiling warnings for libpng.

Signed-off-by: Fei Wu <fwu@wavecomp.com>

* Fixed the build error of unsupported opcode 'pause' when mips isa_rev is less than 2.

Signed-off-by: Fei Wu <fwu@wavecomp.com>

* 1. Removed FP16 related item in MSA option defines in OpenCVCompilerOptimizations.cmake.
2. Use CV_CPU_COMPILE_MSA instead of __mips_msa for MSA feature check in cv_cpu_dispatch.h.
3. Removed hasSIMD128() in intrin_msa.hpp.
4. Define CPU_MSA as 150.
Signed-off-by: Fei Wu <fwu@wavecomp.com>

* 1. Removed unnecessary CV_SIMD128_64F guarding in intrin_msa.hpp.
2. Removed unnecessary CV_MSA related code block in dotProd_8u().

Signed-off-by: Fei Wu <fwu@wavecomp.com>

* 1. Defined CPU_MSA_FLAGS_ON as "-mmsa".
2. Removed CV_SIMD128_64F guardings in intrin_msa.hpp.

Signed-off-by: Fei Wu <fwu@wavecomp.com>

* Removed unused msa_mlal_u16() and msa_mlal_s16 from msa_macros.h.

Signed-off-by: Fei Wu <fwu@wavecomp.com>
2019-09-20 19:52:48 +03:00
Alexander Alekhin
7dc162cb42 core: fix mm_pause() for non-SSE i386 builds
replaced to safe binary compatible 'rep; nop' asm instruction
2018-04-09 18:37:35 +03:00
Alexander Alekhin
491502a349 core: fix parallel_for data race 2018-02-16 21:13:48 +03:00
luz.paz
5718d09e39 Misc. modules/ typos
Found via `codespell`
2018-02-12 07:09:43 -05:00
Alexander Alekhin
914f57f28d core(parallel_for): fix data race 2018-02-06 18:19:50 +03:00
Alexander Alekhin
b10fedde56 core(parallel_for): cleanup
remove 'dont_wait' (can be replaced with has_wake_signal)
2018-02-06 16:10:41 +03:00
Sayed Adel
4e1d396ce1 core:ppc Add yield support 2018-01-31 04:03:35 +00:00
Alexander Alekhin
c49d5d5252 core: fix pthreads performance
OpenCV pthreads-based implementation changes:
- rework worker threads pool, allow to execute job by the main thread too
- rework synchronization scheme (wait for job completion, threads 'pong' answer is not required)
- allow "active wait" (spin) by worker threads and by the main thread
- use _mm_pause() during active wait (support for Hyper-Threading technology)
- use sched_yield() to avoid preemption of still working other workers
- don't use getTickCount()
- optional builtin thread pool profiler (disabled by compilation flag)
2018-01-26 04:09:11 +00:00