Commit Graph

171 Commits

Author SHA1 Message Date
Alexander Alekhin
eb54e5c55c core: generalize and fix x86 'cpuid' calls 2018-02-13 15:35:04 +03:00
luz.paz
5718d09e39 Misc. modules/ typos
Found via `codespell`
2018-02-12 07:09:43 -05:00
Alexander Alekhin
bbfa239036 Merge pull request #10706 from alalek:exception_opencv_version 2018-02-01 18:32:13 +00:00
Alexander Alekhin
c8930cc279 opencv_version: dump detected HW features 2018-01-27 17:08:29 +00:00
Alexander Alekhin
f6fd3abd31 core: add OpenCV version information into Exception messages 2018-01-27 13:51:16 +00:00
Alexander Alekhin
7d67d60fb1 cmake(opt): AVX512_SKX 2017-12-29 07:18:11 +00:00
Maksim Shabunin
7349b8f5ce Build for embedded systems 2017-12-11 13:27:37 +03:00
Mattia Rizzolo
d026d7dcfb
Fix build for non-linux architectures but still glibc-based
Exampls of these are gnu/kfreebsd and gnu/hurd, both available as
unofficial Debian ports.

They don't define __linux__ (as they are non-linux…) but still define
__GLIBC__, so check on that.

Signed-off-by: Mattia Rizzolo <mattia@mapreri.org>
2017-10-17 00:45:27 +02:00
Sayed Adel
d077778074 Added support for VSX 2017-10-09 00:32:29 +00:00
pengli
e340ff9c3a Merge pull request #9114 from pengli:dnn_rebase
add libdnn acceleration to dnn module  (#9114)

* import libdnn code

Signed-off-by: Li Peng <peng.li@intel.com>

* add convolution layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add pooling layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add softmax layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add lrn layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add innerproduct layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add HAVE_OPENCL macro

Signed-off-by: Li Peng <peng.li@intel.com>

* fix for convolution ocl

Signed-off-by: Li Peng <peng.li@intel.com>

* enable getUMat() for multi-dimension Mat

Signed-off-by: Li Peng <peng.li@intel.com>

* use getUMat for ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* use CV_OCL_RUN macro

Signed-off-by: Li Peng <peng.li@intel.com>

* set OPENCL target when it is available

and disable fuseLayer for OCL target for the time being

Signed-off-by: Li Peng <peng.li@intel.com>

* fix innerproduct accuracy test

Signed-off-by: Li Peng <peng.li@intel.com>

* remove trailing space

Signed-off-by: Li Peng <peng.li@intel.com>

* Fixed tensorflow demo bug.

Root cause is that tensorflow has different algorithm with libdnn
to calculate convolution output dimension.

libdnn don't calculate output dimension anymore and just use one
passed in by config.

* split gemm ocl file

split it into gemm_buffer.cl and gemm_image.cl

Signed-off-by: Li Peng <peng.li@intel.com>

* Fix compile failure

Signed-off-by: Li Peng <peng.li@intel.com>

* check env flag for auto tuning

Signed-off-by: Li Peng <peng.li@intel.com>

* switch to new ocl kernels for softmax layer

Signed-off-by: Li Peng <peng.li@intel.com>

* update softmax layer

on some platform subgroup extension may not work well,
fallback to non subgroup ocl acceleration.

Signed-off-by: Li Peng <peng.li@intel.com>

* fallback to cpu path for fc layer with multi output

Signed-off-by: Li Peng <peng.li@intel.com>

* update output message

Signed-off-by: Li Peng <peng.li@intel.com>

* update fully connected layer

fallback to gemm API if libdnn return false

Signed-off-by: Li Peng <peng.li@intel.com>

* Add ReLU OCL implementation

* disable layer fusion for now

Signed-off-by: Li Peng <peng.li@intel.com>

* Add OCL implementation for concat layer

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>

* libdnn: update license and copyrights

Also refine libdnn coding style

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
Signed-off-by: Li Peng <peng.li@intel.com>

* DNN: Don't link OpenCL library explicitly

* DNN: Make default preferableTarget to DNN_TARGET_CPU

User should set it to DNN_TARGET_OPENCL explicitly if want to
use OpenCL acceleration.

Also don't fusion when using DNN_TARGET_OPENCL

* DNN: refine coding style

* Add getOpenCLErrorString

* DNN: Use int32_t/uint32_t instread of alias

* Use namespace ocl4dnn to include libdnn things

* remove extra copyTo in softmax ocl path

Signed-off-by: Li Peng <peng.li@intel.com>

* update ReLU layer ocl path

Signed-off-by: Li Peng <peng.li@intel.com>

* Add prefer target property for layer class

It is used to indicate the target for layer forwarding,
either the default CPU target or OCL target.

Signed-off-by: Li Peng <peng.li@intel.com>

* Add cl_event based timer for cv::ocl

* Rename libdnn to ocl4dnn

Signed-off-by: Li Peng <peng.li@intel.com>
Signed-off-by: wzw <zhiwen.wu@intel.com>

* use UMat for ocl4dnn internal buffer

Remove allocateMemory which use clCreateBuffer directly

Signed-off-by: Li Peng <peng.li@intel.com>
Signed-off-by: wzw <zhiwen.wu@intel.com>

* enable buffer gemm in ocl4dnn innerproduct

Signed-off-by: Li Peng <peng.li@intel.com>

* replace int_tp globally for ocl4dnn kernels.

Signed-off-by: wzw <zhiwen.wu@intel.com>
Signed-off-by: Li Peng <peng.li@intel.com>

* create UMat for layer params

Signed-off-by: Li Peng <peng.li@intel.com>

* update sign ocl kernel

Signed-off-by: Li Peng <peng.li@intel.com>

* update image based gemm of inner product layer

Signed-off-by: Li Peng <peng.li@intel.com>

* remove buffer gemm of inner product layer

call cv::gemm API instead

Signed-off-by: Li Peng <peng.li@intel.com>

* change ocl4dnn forward parameter to UMat

Signed-off-by: Li Peng <peng.li@intel.com>

* Refine auto-tuning mechanism.

- Use OPENCV_OCL4DNN_KERNEL_CONFIG_PATH to set cache directory
  for fine-tuned kernel configuration.
  e.g. export OPENCV_OCL4DNN_KERNEL_CONFIG_PATH=/home/tmp,
  the cache directory will be /home/tmp/spatialkernels/ on Linux.

- Define environment OPENCV_OCL4DNN_ENABLE_AUTO_TUNING to enable
  auto-tuning.

- OPENCV_OPENCL_ENABLE_PROFILING is only used to enable profiling
  for OpenCL command queue. This fix basic kernel get wrong running
  time, i.e. 0ms.

- If creating cache directory failed, disable auto-tuning.

* Detect and create cache dir on windows

Signed-off-by: Li Peng <peng.li@intel.com>

* Refine gemm like convolution kernel.

Signed-off-by: Li Peng <peng.li@intel.com>

* Fix redundant swizzleWeights calling when use cached kernel config.

* Fix "out of resource" bug when auto-tuning too many kernels.

* replace cl_mem with UMat in ocl4dnnConvSpatial class

* OCL4DNN: reduce the tuning kernel candidate.

This patch could reduce 75% of the tuning candidates with less
than 2% performance impact for the final result.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>

* replace cl_mem with umat in ocl4dnn convolution

Signed-off-by: Li Peng <peng.li@intel.com>

* remove weight_image_ of ocl4dnn inner product

Actually it is unused in the computation

Signed-off-by: Li Peng <peng.li@intel.com>

* Various fixes for ocl4dnn

1. OCL_PERFORMANCE_CHECK(ocl::Device::getDefault().isIntel())
2. Ptr<OCL4DNNInnerProduct<float> > innerProductOp
3. Code comments cleanup
4. ignore check on OCL cpu device

Signed-off-by: Li Peng <peng.li@intel.com>

* add build option for log softmax

Signed-off-by: Li Peng <peng.li@intel.com>

* remove unused ocl kernels in ocl4dnn

Signed-off-by: Li Peng <peng.li@intel.com>

* replace ocl4dnnSet with opencv setTo

Signed-off-by: Li Peng <peng.li@intel.com>

* replace ALIGN with cv::alignSize

Signed-off-by: Li Peng <peng.li@intel.com>

* check kernel build options

Signed-off-by: Li Peng <peng.li@intel.com>

* Handle program compilation fail properly.

* Use std::numeric_limits<float>::infinity() for large float number

* check ocl4dnn kernel compilation result

Signed-off-by: Li Peng <peng.li@intel.com>

* remove unused ctx_id

Signed-off-by: Li Peng <peng.li@intel.com>

* change clEnqueueNDRangeKernel to kernel.run()

Signed-off-by: Li Peng <peng.li@intel.com>

* change cl_mem to UMat in image based gemm

Signed-off-by: Li Peng <peng.li@intel.com>

* check intel subgroup support for lrn and pooling layer

Signed-off-by: Li Peng <peng.li@intel.com>

* Fix convolution bug if group is greater than 1

Signed-off-by: Li Peng <peng.li@intel.com>

* Set default layer preferableTarget to be DNN_TARGET_CPU

Signed-off-by: Li Peng <peng.li@intel.com>

* Add ocl perf test for convolution

Signed-off-by: Li Peng <peng.li@intel.com>

* Add more ocl accuracy test

Signed-off-by: Li Peng <peng.li@intel.com>

* replace cl_image with ocl::Image2D

Signed-off-by: Li Peng <peng.li@intel.com>

* Fix build failure in elementwise layer

Signed-off-by: Li Peng <peng.li@intel.com>

* use getUMat() to get blob data

Signed-off-by: Li Peng <peng.li@intel.com>

* replace cl_mem handle with ocl::KernelArg

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(build): don't use C++11, OPENCL_LIBRARIES fix

* dnn(ocl4dnn): remove unused OpenCL kernels

* dnn(ocl4dnn): extract OpenCL code into .cl files

* dnn(ocl4dnn): refine auto-tuning

Defaultly disable auto-tuning, set OPENCV_OCL4DNN_ENABLE_AUTO_TUNING
environment variable to enable it.

Use a set of pre-tuned configs as default config if auto-tuning is disabled.
These configs are tuned for Intel GPU with 48/72 EUs, and for googlenet,
AlexNet, ResNet-50

If default config is not suitable, use the first available kernel config
from the candidates. Candidate priority from high to low is gemm like kernel,
IDLF kernel, basick kernel.

* dnn(ocl4dnn): pooling doesn't use OpenCL subgroups

* dnn(ocl4dnn): fix perf test

OpenCV has default 3sec time limit for each performance test.
Warmup OpenCL backend outside of perf measurement loop.

* use ocl::KernelArg as much as possible

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(ocl4dnn): fix bias bug for gemm like kernel

* dnn(ocl4dnn): wrap cl_mem into UMat

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(ocl4dnn): Refine signature of kernel config

- Use more readable string as signture of kernel config
- Don't count device name and vendor in signature string
- Default kernel configurations are tuned for Intel GPU with
  24/48/72 EUs, and for googlenet, AlexNet, ResNet-50 net model.

* dnn(ocl4dnn): swap width/height in configuration

* dnn(ocl4dnn): enable configs for Intel OpenCL runtime only

* core: make configuration helper functions accessible from non-core modules

* dnn(ocl4dnn): update kernel auto-tuning behavior

Avoid unwanted creation of directories

* dnn(ocl4dnn): simplify kernel to workaround OpenCL compiler crash

* dnn(ocl4dnn): remove redundant code

* dnn(ocl4dnn): Add more clear message for simd size dismatch.

* dnn(ocl4dnn): add const to const argument

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(ocl4dnn): force compiler use a specific SIMD size for IDLF kernel

* dnn(ocl4dnn): drop unused tuneLocalSize()

* dnn(ocl4dnn): specify OpenCL queue for Timer and convolve() method

* dnn(ocl4dnn): sanitize file names used for cache

* dnn(perf): enable Network tests with OpenCL

* dnn(ocl4dnn/conv): drop computeGlobalSize()

* dnn(ocl4dnn/conv): drop unused fields

* dnn(ocl4dnn/conv): simplify ctor

* dnn(ocl4dnn/conv): refactor kernelConfig localSize=NULL

* dnn(ocl4dnn/conv): drop unsupported double / untested half types

* dnn(ocl4dnn/conv): drop unused variable

* dnn(ocl4dnn/conv): alignSize/divUp

* dnn(ocl4dnn/conv): use enum values

* dnn(ocl4dnn): drop unused innerproduct variable

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(ocl4dnn): add an generic function to check cl option support

* dnn(ocl4dnn): run softmax subgroup version kernel first

Signed-off-by: Li Peng <peng.li@intel.com>
2017-10-02 15:38:00 +03:00
Alexander Alekhin
597b3f4456 Merge pull request #9580 from mshabunin:fix-static-6 2017-09-09 19:31:21 +00:00
Maksim Shabunin
248e2c7d47 Fixed some issues found by static analysis 2017-09-08 12:22:12 +03:00
Pavel Vlasov
37ab318657 Compatibility improvement with old IPP versions (tested on 9.0.1);
Manual IPP dispatcher simplification;
2017-09-08 11:08:24 +03:00
Zoltán Mizsei
6258ff36bc Haiku build fix 2017-08-26 11:37:59 +02:00
Pavel Vlasov
a57718e1ac ICV2017u3 package update;
- Optimizations set change. Now IPP integrations will provide code for SSE42, AVX2 and AVX512 (SKX) CPUs only. For HW below SSE42 IPP code is disabled.
- Performance regressions fixes for IPP code paths;
- cv::boxFilter integration improvement;
- cv::filter2D integration improvement;
2017-08-23 14:24:43 +03:00
Alexander Alekhin
dcc63d7408 Merge pull request #9248 from alalek:alloc_refactoring 2017-08-03 16:25:29 +00:00
Alexander Alekhin
b46e741c95 core(alloc): drop unused code, use memalign() functions instead of hacks
valgrind provides better detection without memory buffer hacks
2017-07-27 18:10:41 +03:00
Alexander Alekhin
d35422b523 core(tls): hide assertions from Thread Sanitizer 2017-07-27 17:31:51 +03:00
Alexander Alekhin
68ef903a7c core(tls): don't use tlsSlots without synchronization 2017-07-26 22:45:55 +03:00
Alexander Alekhin
602f047fe8 build: replace WIN32 => _WIN32 2017-07-25 13:30:48 +03:00
Alexander Alekhin
a4a47b538c build: detect Android via '__ANDROID__' macro
https://sourceforge.net/p/predef/wiki/OperatingSystems
2017-07-10 12:43:59 +03:00
Maksim Shabunin
a769d69a9d Fixed several issues found by static analysis 2017-06-28 18:06:18 +03:00
Alexander Alekhin
006966e629 trace: initial support for code trace 2017-06-26 17:07:13 +03:00
Alexander Alekhin
3e3e2dd512 android: make optional "cpufeatures", build fixes for NDK r15 2017-06-21 13:34:19 +03:00
Alexander Alekhin
a3189e36c0 Merge pull request #8753 from RyuheiMori:fix-cpu-feature-detection-on-android 2017-06-12 16:08:08 +00:00
Alexander Alekhin
3dee87b697 update CPU detection on ANDROID patch 2017-06-11 05:06:49 +00:00
Maksim Shabunin
f71ea4dfe9 Merge pull request #8816 from mshabunin:sprintf-fix
Fixed snprintf for VS 2013 (#8816)

* Fixed snprintf for VS 2013

* snprintf: removed declaration from header, changed implementation

* cv_snprintf corrected according to comments

* update snprintf patch
2017-06-08 21:53:16 +02:00
Alexander Alekhin
16ea72e6b9 build: fix snprintf() usage 2017-05-22 22:24:17 +03:00
Ryuhei Mori
bb3a416320 Fix cpu features detection on android 2017-05-19 21:19:13 +08:00
Alexander Alekhin
17eef4d8a9 Merge pull request #8596 from nnorwitz:nnorwitz 2017-05-12 19:48:28 +00:00
nnorwitz
256b6bb3db Don't blow out the stack. Use a smaller buffer and prevent buffer overruns with snprintf. 2017-05-03 16:56:09 +03:00
Pavel Vlasov
35c7216846 IPP for OpenCV 2017u2 initial enabling patch; 2017-04-20 20:26:30 +03:00
Vadim Pisarevsky
a57d144076 Merge pull request #7462 from alalek:cpu_multi_target 2017-03-21 19:51:32 +00:00
Alexander Alekhin
ec7f74f7b4 core(TLS): add cleanup() method 2017-02-21 16:08:23 +03:00
Fangjun KUANG
526220a171 Fix typos in the documentation (#8226)
* fix typos.

* Fix typos.

* Fix typos.

* Fix typos.

* Fix typos.
2017-02-21 12:48:15 +03:00
Alexander Alekhin
e16227b53c cmake: support multiple CPU targets 2017-02-13 19:52:59 +03:00
Philippe Renon
e79f83e573 calib3d: fix missing cv::redirectError symbol error
happens on msys2 with gcc 6.2.0
see also http://stackoverflow.com/questions/38552221/undefined-reference-to-cvredirecterror-while-creating-shared-build-of-opencv-3
2016-11-15 08:56:01 +01:00
Pavel Vlasov
349d5ba012 --perf_instrument parameter now has int type and 0, 1, 2 modes (1 - simple trees, 2 - expanded trees for functions with same name but different calling address);
Maximum depth limit var was added to the instrumentation structure;

Trace names output console output fix: improper tree formatting could happen;
Output in case of error was added;

Custom regions improvements;

Improved timing and weight calculation for parallel regions; New TC (threads counter) value to indicate how many different threads accessed particular node;

parallel_for, warnings fixes and ReturnAddress code from Alexander Alekhin;
2016-11-08 10:18:05 +03:00
Alexander Alekhin
10d18a315c instrumentation: minor refactoring, wrap OpenCL
- calculate ticksTotal instead of ticksMean
- local / global width is based on ticksTotal value
- added instrumentation for OpenCL program compilation
- added instrumentation for OpenCL kernel execution
2016-09-08 16:13:44 +03:00
mpkh
01d2e7af71 fix building on FreeBSD
resolve undeclared identifier close error
2016-08-22 17:17:06 +04:00
Pavel Vlasov
a462d76a95 Implementations instrumentation framework for OpenCV performance system; 2016-08-17 16:26:03 +03:00
Pavel Vlasov
8bcec7d77f IPP enabling fix and typo fix; 2016-08-12 10:11:47 +03:00
Tomoaki Teshima
b2ad7cd9c0 add feature to convert FP32(float) to FP16(half)
* check compiler support
  * check HW support before executing
  * add test doing round trip conversion from / to FP32
  * treat array correctly if size is not multiple of 4
  * add declaration to prevent warning
  * make it possible to enable fp16 on 32bit ARM
  * let the conversion possible on non-supported HW, too.
  * add test using both HW and SW implementation
2016-05-21 21:31:33 +09:00
Alexander Alekhin
c7ccde69a8 fix TLS implementation (closes #5967) 2016-01-14 14:38:37 +03:00
Maksim Shabunin
84f37d352f HAL moved back to core 2015-12-17 12:33:23 +03:00
Maksim Shabunin
b4bcdd10a1 HAL: improvements
- added new functions from core module: split, merge, add, sub, mul, div, ...
- added function replacement mechanism
- added example of HAL replacement library
2015-12-03 14:43:37 +03:00
Bert
d3b0bda011 Update system.cpp
FreeBSD compilation fix
2015-11-13 11:03:34 +03:00
Vadim Pisarevsky
3942b1f362 Merge pull request #5340 from alalek:ocl_off 2015-11-10 16:53:36 +00:00
Pavel Vlasov
89eee6ca99 Fixes for IPP integration:
dotProd_16s - disabled for IPP 9.0.0;
filter2D - fixed kernel preparation;
morphology - conditions fix and disabled FilterMin and FilterMax for IPP 9.0.0;
GaussianBlur - disabled for CV_8UC1 due to buffer overflow;
integral - disabled for IPP 9.0.0;

IppAutoBuffer class was added;
2015-10-12 10:51:28 +03:00
Pavel Vlasov
6a0d3b06f2 IPPInitSingelton initialization guards; 2015-10-01 17:48:49 +03:00