* Benchmark_app python and c/c++ script add op profiling feature
* Fix compile bug about benchmark c/c++ op profiling
* Fix Compile Bug
* Fix issue in PR#12350 : 1. report_type info update; 2. priority of -pc and -pcsort; 3.align format between c++ and python; 4.check 'proportion' for 0 and print N/A; 5.detect the confusing print info
* Fix 8/17 review suggestion
* Fix 8/23 suggestion
* Fix the clang-format issue
* Fix the win-cc issue
* Fix win-cc issue about conversion from 'double' to 'float', possible loss of data
* Push PR by ODT group account
Co-authored-by: Chen Peter <peter.chen@intel.com>
Co-authored-by: Fiona Zhao <fiona.zhao@intel.com>
* Set 'UNDEFINED' as the performancehint default value. Update benchmark app to pass performance hint with none value to MULTI/AUTO plugin.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Using 'UNDEFINED' as the default value of hint in AUTO/MULTI plugin.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Adding a flag instead of adding a default value of hint to check if user configures the performance hint to AUTO/MULTI plugin.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update benchmark python version.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* fix Performance inefficiencies issue caused by previous PR.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: River Li <river.li@intel.com>
* fix benchmark filed to pass on MULTI device when enable num_streams.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Remove part of test cases because MULTI plguin will not check if the unspported property is valid now.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Remove some incorrect config for MULTI test case since MULTI will pass through those unrecognized config without any exception.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Support MULTI to set nstreams to multi target devices by using ov::device:properties.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Support AUTO to set nstreams with multi target devices bu using ov:device::properties.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update format.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
* When set batch_size, disable auto batching
* auto-batch only supprt auto plugin
* Set property allow_auto_batching for devices
* cancel static
* Clean Code
* Add test case for testing allow_auto_batching
* Fix the issue after merging latest master branch code
* Add allow_auto_batching in python benchmark_app
* Fix the quotes issue
* When load_network is set to allow-auto-batching, there is no need to read the value of global
* Fix the clang-format
* Change the location
Co-authored-by: River Li <river.li@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
* WA for Benchmark App: Remote tensor use for internaly dynamic original models (NMS) that turn static due to transformation to legacy op and lack of dynamism support
* Style
* update logic of setting TPUT by default for MULTI and AUTO.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Set config to MULTI instaed of target device when using -d MULTI:target_device in benchmark app.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update logit to check if perfomance hint is set.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update test cases.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Set the correct _so from passthrough executable network when batch plugin is disabel to fix lifecycle coredump.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Same update for AUTO plugin
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
* Fixes for cases when TBB_DIR env var is set
* Don't use make in build_samples.sh script
* First version of Windows installer
* WIndows NSIS installer
* Improved version of debian packages
* Improvements
* Improvements
* Debian packages now look good
* Library versioning
* Fixed tests to run against debian packages
* Fixed frontend tests
* Fixed code style
* FIxed Windows
* Fixed python tests
* Fixed paths in tests
* fdvfdv
* Fixes
* USe versioning only for debian packages
* Relocatable tests
* Fixed
* Fixed all tests
* Fixed clang-format
* Fixed more tests
* Fixed some tests
* Absolute paths in .ci
* Fixes
* Added support of OpenCV 3.4
* Trying to fix gnaUnitTests
* Add some tip description about enable OpenCL for benchmark_app.
Signed-off-by: xipingya <xiping.yan@intel.com>
* Export doesn't work, we need to add -Dopencl_root_hints=[PATH]/OpenCL-CLHPP/include to cmake command.
Signed-off-by: xipingya <xiping.yan@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
* FTZ_and_DAZ_set_for_cpu
* remove DAZ
* fix
* extract to utils
* ie core part changes to add do as property and benchmark_app enable do
* enable brgcov from Luocheng patch
* add debug info
* enable_brgemm_on_avx512
* add python binding
* dlb test
* FTZ_and_DAZ_set_for_cpu
* remove DAZ
* fix
* extract to utils
* ie core part changes to add do as property and benchmark_app enable do
* enable brgcov from Luocheng patch
* add debug info
* enable_brgemm_on_avx512
* add python binding
* dlb test
* revert test code
* revert test code
* enable brgconv f32
* use config to enable brgconv f32
* when brg disabled not init bin-postops
* change prop name for extensive
* use more general field
* fix review comments.
* selectdevice returns MULTI:device in cumulative_throughput
* load multi with throughput and disable cpu helper in cumulative
* disable cpu helper in cumulative_throughput
* add cumulative to bechmark_app help message
* modify benchmark_app.hpp clang-format
* Try to improve gflags
* Try to improve gflags: part 2
* Tried to use dependencies on system
* Use nlohmann_jsonConfig from system
* Enabled nlohmann_json from system
* Improvements
* handle system gflags in developer package
* Simplifications
* Simplify dependency management
* Corrected package names
* Fixed subgraphsDumper configure stage
* Try to fix rhel8
* Try to fix macosx
* Fixed VPUX build
* Fixed aliasing issues
* Suppress some wanrings
* export gflags when build it
* Fixed some LTO
* Try to fix Mac
* revert
* use gflags as private dependency
* Aligned targets in developer package
* Fixed frontends tests build on U20 with LTO
* PAssed
* Don't use pkg_search_module(zlib ..) during cross-compilation
* Removed unused variables
* Fixed finding of zlib during cross-compilation
* Build with system TBB
* Fixes
* Check whether system TBB is available
* Try to fix ONNX Runtime build with system TBB
* Test
* Fixed compilation of threading.cpp
* Fixed unset of cache dirs
* Limit dearch paths of TBB
* Try to enable pip packages with custom TBB
* Fix for TBB 2021.2
* Install only needed TBB libraries
* Install TBB from system to pip package
* Reverted usage of TBBROOT
* Fixed oneTBB case
* Try to fix Android
* Escape some paths
* Added samples path
* Fixed TBBBind usage for case of system TBB
* fix .ncc_style target names
it was breaking configure on system with libclang-12-dev, clang-12,
ninja and cmake 3.17+(ninja complains about duplicate
target). with lower cmake version configure succeeds, but build exits
immediately with error. by replacing ninja with make error becomes
warning(it's still significant, make just skips duplicate rules, i.e.
doesn't check style of some source files, rule duplication is genuine
bug). without libclang-12-dev and clang-12 ENABLE_NCC_STYLE is OFF and
bug is not triggered
* silence uninitialized warning in core_integration
probably it was always initialized before use, but compiler wasn't made
aware of it
* fix function spelling to unbreak code style checks in benchmark_app
* include <thread> for std::this_thread
existing code was relying on namespace pollution by old libstdc++
* replace is_pod with is_standard_layout && is_trivial
is_pod is deprecated, it breaks build on current gcc
Co-authored-by: Serhii Pavlovskyi <spavlovskyi@lohika.com>
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
* Used new config for streams and threads
* Fixed review coments in ba
* format fix
* fixed hello_query_device
* Added STL string io
* fixed tests
* Fixed test
* Fixed build
* fixed format
* Fixed build
* try fix win
* other any io specialization
* Fixed after merge
* renamed streams
* build fixed
* fixed build
* fixed format
* fix for old mac build
* Fixed type of exception
* test fix
* Depricated Any implicit cast
* Fixed test
* fixed gna build
* Fixed warnings in benchmark_app
* Fixed test build
* ncc exception for PrintTo
* Error mesage in test
* Error mesage in test
* fixed build
* Refactored statistics output with JSON support
* Detailed/average reports are added
* stylefix
* Update samples/cpp/benchmark_app/statistics_report.hpp
Co-authored-by: Ivan Vikhrev <ivan.vikhrev@intel.com>
* Linux Fixes
* stylefixes
* data_shape field format is changed
* stylefix
Co-authored-by: Ivan Vikhrev <ivan.vikhrev@intel.com>
* [IE SAMPLES] activated NCC tool for c++ samples
* exclude ov_ncc_naming_style for tests
* fixed NCC hit
* Added support for source files in samples
* changed style of methods for benchmark
* changed style for speech sample
* changed code style
* changed code style for shared_tensor
* benchmark changes
* changed remote_tensors_filling
* fixed notes
* rebase of branch
* Set THROUGHPUT as the default configration for all the plugin and display the config of the plugin.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* updated format.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Update benchmark python API.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Replace str 'THROUGHPUT' with CONFIG_VALUE(THROUGHPUT).
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Using CONFIG_VALUE(THROUGHPUT) replace 'THROUGHPUT' string.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* update code style.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* Move the setting output code into the try block.
Signed-off-by: Wang, Yang <yang4.wang@intel.com>
* auto-batching POC squashed (all commits from auto-batch-2021.3 branch)
(cherry picked from commit d7742f2c747bc514a126cc9a4d5b99f0ff5cbbc7)
* applying/accomodating the API changes after rebase to the master
* replaying modified version of actual batch selection
* eearly experiments with model mem footprint
* changes from rebasing to the latest master
* experimenting with DG1 on the batch size selection, also collecting the mem footprint
* WIP:moving the auto-batching to the icore to let the MULT/AUTO support that, ALLOW_AUTO_BATCHING as a conventional config key. still fials hot device swap
* quick-n-dirty batch footpint vs device total mem
* code style
* testing which models perform badly due to kernels and NOT (batched) footprint
* stub pipeline task to comunicate the readiness rather than promise/future
* quick-n-dirty timeout impl
* explicit _completionTasks,reverting BA to use the timeout
* inputs outputs copies, works with AUTO and demo now
* accomodate the config per device-id, after rebase to the latest master
* allowing the auto-batching only with tput hint to let more conventional tests pass
* fix the pre-mature timeout restaring via waiting for batch1 requests completion
* moved the bacthed request statring ( along with input copies) to the dedicated thread
* [IE CLDNN] Disable bs_fs_yx_bsv16_fsv16 format for int8 convolution
* code style
* increasing the timeout to test the ssd_* models perf (timeout?) issues
* reducing number of output stuff in BA to avoid bloating the logs in experiments
* more aggressive batching for experiments, not limited to 32 and also 4 as a min
* more accurate timeout debugging info
* getting the reqs limitation from the plugin SetConfig as well
* refactor the reshape logic a bit to accomodate CPU for bathcing, also added remeote context
* let the benchamrk_app to consume specific batch values for the auto-batching such as BATCH:GPU(4)
* auto-batching functional test (with results check vs ref) and GPU instance for that
* fixed arithemtic on blobs ptrs
* clang
* handling possible batched network failure
* BATCH as the constants device name in test
* ENABLE_BATCH
* func tests for CPU, also DetectionOutput hetero tests (CPU and GPU)
* DetectionOutput hetero test for the CPU
* reenabling the Auto-Batching in the AUTO
* auto-batching device enabled in the test
* fixed the DO test
* improve the loading loop logic
* brushed the config keys
* allow hetero code-path for explicit device name like BATCH:GPU(4), used in the hetero code-path tests
* fix the test after refactoring
* clang
* moving ThreadSafeQueue to the ie_parallel, as it is re-used in the AUTO/MULTI and BATCH now
* auto-batching hetero test (subgraph with DetectionOutput)
* fixed minor changes that were result of experiments with impl
* code-style
* brushing, disabling CPU's HETERO tests until planned activity for 22.2
* removing home-baked MAX_BATCH_SZIE and swicthing to the official impl by GPU team
* remote blobs tests for the auto-batching (old API)
* brushed names a bit
* CreateContext and LoadNEtwork with context for the Auto-Batching plus remote-blobs tests
* fixed the ieUnitTests with adding CreateContext stub to the MockICore
* clang
* improved remote-blobs tests
* revert the back BA from exeprimenents with AB + device_use_mem
* conformance tests for BATCH, alos batch size 1 is default for BATCH:DEVICE
* remote blobs 2.0 tests, issue with context having the orig device name
* debugging DG1 perf drop (presumably due to non-fitting the device-mem)
* disbaling WA with batch/=2 for excesive mem footptint, leaving only streams 2
* remote blobs 2.0 tests for different tensor sharing types
* converting assert to throw to accomodate legacy API where the lock() was possible to be called
* revert the timeout back to avoid mixing the studies, fixed the footprint calc
* reverting to estimating the max batch by extrapolating from bacth1 size
* more conservative footptint etimation (with bacth1), graceful bacth 1 handling without duplication
* even graceful batch 1 handling without duplication
* WA for MAX_BATCH_SIZE failure, removing batch4 as a min for the auto-batching
* AutoBatchPlugin -> ov_auto_batch_plugin
* WA for gcc 4.8
* clang
* fix misprint
* fixed errors resulted from recent OV's Variant to Any transition
* skip auto-batching for already-batched networks
* AUTO_BATCH_TIMEOUT and tests
* GPU-specific L3
* switched to pure config, also improved ALLOW_AUTO_BATCHING config key handling logic
* debugging device info
* enabling the config tests for the GPU and fixing the Auto-batching tests to pass
* making the default (when not recognized the driver) cache size more aggressive, to accomodate recent HW with old drivers
* skip auto-batching for RNNs and alikes (e.g. single CHW input)
* fixed fallback to the bacth1 and moved HETERO path under condition to avoid bloating
* brushing
* Auto plugin GetMetric support gpu auto-batch
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add test case
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* add comments on test
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* brushing the vars names, alos adding the excpetion handling
* disabling the auto-batching for the networks with non-batched outputs and faster-rcnn and alikes (CVS-74085) to minimize the of #failures
* add try catch
Signed-off-by: Hu, Yuan2 <yuan2.hu@intel.com>
* brushing the code changed in the GPU plugin
* Auto-Batch requests tests
* brushed varibles a bit (ref)
* cleaned debug output from the ie_core
* cleaned cmake for the Auto-Batch
* removed batchN estimation from batch1
* cleaned from debug printf
* comments, cleanup
* WA the mock test errors introduced with merging the https://github.com/myshevts/openvino/pull/13
* Adding back removed batchN estimation from batch1 to debug degradations on DG1 (resulted from too optimistic MAX_BATCH_SIZE?). This partially reverts commit e8f1738ac1.
* brushing ie_core.cpp
* fix 32bit compilation
* Code review: ENABLE_AUTO_BATCH
* consolidate the auot-batching logic in ie_core.cpp into single ApplyAutoBAtching
* renamed brushed the OPTIMAL_BATCH (now with_SIZE) and mimicks the MAX_BATCH_SZIE wrt MODEL_PTR
* default value for the OPTIMAL_BATCH_SIZE
* clang
* accomodate new func tests location
* fix shuffle of headers after clang + copyrights
* fixed misprint made during code refactoring
* moving the common therad-safe containers (like ThreadSafeQueue) to the dedicated dev_api header
* switch from the device name to the OPTIMAL_BATCH_SIZE metric presence as a conditin to consider Auto-Batching
* switching from the unsafe size() and minimizing time under lock
* code style
* brushed the ApplyAutoBatching
* brushed the netric/config names and descriptions
* completed the core intergration tests for the auto-batching
* ExecGraphInfo and check for incorrect cfg
* removed explicit dependencies from cmake file of the plugin
* disabling Auto-Batching thru the tput hint (to preserve current product default), only excplicit like BATCH:GPU used in the tests
Co-authored-by: Roman Lyamin <roman.lyamin@intel.com>
Co-authored-by: Hu, Yuan2 <yuan2.hu@intel.com>
* Merged and compiling
* Fix for dynamic shape type
* review fixes
* renamed blob shape to tensor shape, small improvements
* fix code style
* added parsing of multiple shapes
* store latency per group, add isIdleRequestAvailable() to Infer Queue
* added cached random inputs
* redesign pipeline, added new metrics(avg, max, min), added metrics per groups
* fixed code style
* small improvements
* modified tensor parameters parsing
* modified -i parameter parsing: added possibility to specify input names
* implemented image cashing
* added cashed blobs creating
* added -pcseq flag, modified batch filling, changes fps formula
* improvements
* code formatting
* code formatting2
* apply suggestions from review
* replaced Buffer class with InferenceEngine Blobs
* use batch size in blobs filling
* added shared blob allocator to handle blob's data
* fixed warnings & code style
* allocate blobs
* fix for networks with image info input
* added comments & fixed codestyle
* clear data in free() in SharedBlobAllocator
* remove unnecessary check
* Delimeter is changed to ::
* stylefix
* added layout from string function, small improvements
* modified parsing to enable : in input parameters
* small fixes
* small fixes
* added missed blob allocation, fixes
* [TEST]added support for remote blobs
* fix remote blobs
* new inputs/files output format
* removed vectors resize which caused bugs
* made cl::Buffer type under ifdef, fix inputs filling
* changed batch() function to not throwing exceptions
* removed unused var
* fix code style
* replace empty name in input files with name from net input
* restored old behaviour for static models
* fix code style
* fix warning - made const iterator
* fix warning - remove reference in loop variable
* added random and image_info input types to -i, fix problem with layout
* replaced batch() with getBatchSize() in main
* fix layout, shape, tensor shape parameters parsing
* upd help messages for input, tensor shape and pcseq command
* added buffer for cl output blobs, small fixes
Signed-off-by: ivikhrev <ivan.vikhrev@intel.com>
* added legacy mode
* restore setBlob
* code style formatting
* move collecting latency for groups under flag
* removed not applicable layouts
* added hint to error message when wrong input name in -tensor_shape was specified
* added new metrics to statistics report
* Apply suggestions from code review
* fix binary blobs filling when layout is CN
* apply suggestions
* moved file in the right place after rebase
* improved -pcseq output
* updated args and readme
* removed TEMPLATE plugin registration
* fix -shape arg decsription
* enable providing several -i args as input
* renamed legacy_mode to inference_only and made it default for static models, renamed tensor_shape to data_shape
* upd readme
* use getBlob() in inference only mode
* fix old input type for static case
* fix typo
* upd readme
* move log about benchmark mode to the measuring perfomance step
* added class for latency metrics
* upd readme, fix typos, renamed funcs
* fix warning and upd parsing to avoid error with : in file paths
* fix error on centos : error: use of deleted function ‘std::basic_stringstream<char>::basic_stringstream(const std::basic_stringstream<char>&)
* added check for key in inputs
* renamed input to inputs
* adjust batch size for binary blobs
* replaced warning with exception in bench mode defining
* align measurement cycle with master
Co-authored-by: ivikhrev <ivan.vikhrev@intel.com>
* ov2.0 IE samples modification
apply code style
turn off clang style check for headers order
unify samples a bit
add yuv nv12 reader to format_reader, helloe_nv112 sample
hello_reshape_ssd ov2.0
* sync with PR 8629 preprocessing api changes
* fix for slog << vector<int>
* add operator<< for ov::Version from PR-8687
* Update samples/cpp/hello_nv12_input_classification/main.cpp
Co-authored-by: Mikhail Nosov <mikhail.nosov@intel.com>
* apply code style
* change according to review comments
* add const qualifier
* apply code style
* std::ostream for old inference engine version to make VPU plugin tests happy
* apply code style
* revert changes in print version for old api samples
* keep inference_engine.hpp for not ov2.0 yet samples
* fix merge artifacts
* fix compilation
* apply code style
* Fixed classification sample test
* Revert changes in hello_reshape_ssd sample
* rebase to master, sync with PR-9054
* fix issues found by C++ tests
* rebased and sync with PR-9051
* fix test result parsers for classification tests (except unicode one)
* fix mismatches after merge
* rebase and sync with PR-9144
Co-authored-by: Mikhail Nosov <mikhail.nosov@intel.com>
Co-authored-by: antonrom23 <anton.romanov@intel.com>
18582088138