IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
12,163 Commits 38 Branches 54 Tags
7e724565b5d40bbd9bd483ba81041b9b224291ad
Commit Graph
885 Commits
Author SHA1 Message Date
Zhang Yi 7e724565b5 [CPU] Use parallel_nt_static for MLAS threading (#19297) 2023-08-22 10:38:07 +00:00
Zhang Yi 53c47aaa91 [CPU]Fix mlas threadpool of MlasExecuteThreaded (#19292) 2023-08-22 12:49:38 +04:00
Wanglei Shen 7c273dc2c5 fix SDL issue (CID 1518459) (#19287) 2023-08-21 20:24:59 +08:00
Wanglei Shen 61fcf3855a fix SDL issue (CID 1518457) (#19289) 
* fix SDL issue (CID 1518457)

* update for comments
 2023-08-21 17:43:09 +08:00
Anton Voronov 4f29e60742 FIxed is_on_constant_path() using in all places (#19239) 
* Fixed matmul weights check in snippets_mark_skipped

* fix

* ConvertMatMulToFC: is_on_constant_path fix

* [TESTS] added SplitMatMulConcat subgraph test

* MarkDequantizationSubgraph: is_on_constant_path fix
 2023-08-18 14:01:07 +04:00
Maksim Kutakov 74c237de2e [CPU] Remove skip for the first inPlace base edge (#19185) 2023-08-16 11:49:04 +04:00
Maksim Kutakov d13dff06f3 [CPU] Disable gather inPlace for out of range indices (#19159) 2023-08-16 10:32:31 +04:00
yanlan song 13f8ff4a40 fix rt_info meta parse race condition (#19196) 
* fix a possible race condition

Signed-off-by: fishbell <bell.song@intel.com>

* clang

Signed-off-by: fishbell <bell.song@intel.com>

* reimpl

Signed-off-by: fishbell <bell.song@intel.com>

* add cases

Signed-off-by: fishbell <bell.song@intel.com>

* implement test in 2.0

Signed-off-by: fishbell <bell.song@intel.com>

* clean up unchanged files

Signed-off-by: fishbell <bell.song@intel.com>

* add pragma once

Signed-off-by: fishbell <bell.song@intel.com>

---------

Signed-off-by: fishbell <bell.song@intel.com>
 2023-08-15 15:33:01 +00:00
Gorokhov Dmitriy 5ff67fca40 [CPU][ARM] Fixed execution mode behavior (#19192) 2023-08-15 16:46:05 +04:00
Egor Duplenskii 37a6848f26 [CPU][ARM][FP16] Prefer Convert over Reorder for conversion (#19148) 2023-08-15 09:11:50 +04:00
Aleksandr Voron e48b2dfc34 [CPU][ARM] Set FP16 inference precision by default for non-convolution networks on ARM (#19069) 2023-08-14 22:22:39 +04:00
Egor Duplenskii 680333b2db [CPU][ARM] Enable FP16 precision for CumSum node (#19176) 2023-08-14 15:22:43 +00:00
Anton Voronov 87f9b2bdf8 [CPU] Fixed checks in snippets_mark_skipped for MatMul weights (#19141) 2023-08-14 16:04:35 +04:00
Maksim Kutakov 4996d1f034 TensorMemoryBlob: sync data handle on alloc call (#19149) 2023-08-14 13:22:11 +04:00
Egor Duplenskii f09d2e2666 [CPU][ARM] Perf fixes for FP16 precision (#18973) 2023-08-14 09:22:03 +04:00
Ilya Lavrenov 6067ab17ba Aligned target and files (libraries) names (#19161) 2023-08-13 11:31:44 +04:00
Wanglei Shen 0368474c8a fix manually setting Pcore+Ecore manually when model prefers Pcore only (#19160) 2023-08-12 18:19:02 +08:00
Gorokhov Dmitriy 2bdb7bd23e [CPU] FullyConnected acceleration with 8bit weights decompression on SPR (#19111) 2023-08-11 14:14:32 +04:00
Ilya Lavrenov a251346031 [CPU] Give different output name for dnnl (#19136) 
* Give different output name for dnnl

* Apply suggestions from code review

added prefix to library name
 2023-08-11 13:54:44 +04:00
Ilya Lavrenov cc5ab26a95 Remove explicit CRT options from MLAS (#19115) 2023-08-11 13:03:12 +04:00
Anton Voronov 2a3132941c [FIX][CPU] Convert CF: added convert childs number check (#19022) 
* [FIX][CPU] Convert CF: added convert childs number check

* code style fix

* WIP: [CPU][TESTS] Convert CF: Added subgraph test with two outputs for Convert node

* MatMulDecompressConvertTest refactoring + instances fixes

* removed KeepConstAndDecompressionForMatMul pass and added cpu callback for KeepConstAndDecompression

* MatMulDecompressConvertTest2: added graphs and small problem description

* small review fix
 2023-08-11 12:10:00 +04:00
Sun Xiaoxia 0ed1749ad9 [CPU] Removed socket id=-1 workaround on macOS (#18779) 2023-08-11 10:38:21 +04:00
Wanglei Shen 2ed5e50bd1 [CPU] Update stream info for mixing MAIN_CORE_PROC and HYPER_THREADING_PROC (#18863) 2023-08-11 10:31:31 +04:00
Zhang Yi 7d192c9239 Update mlas with i32 build fix (#19107) 2023-08-10 13:38:16 +04:00
Aleksandr Voron 19b3f062af [CPU] Replace memory_order_relaxed with release/acquire in UpdateNodesBase class (#19028) 2023-08-09 13:28:44 +04:00
Wanglei Shen 2b1f8939cb [CPU][ARM] Fix unused variable issue for PR 18818 (#19062) 2023-08-08 17:19:23 +00:00
Vladislav Golubev 4733c32e75 [CPU] Fix initSupportedPrimitiveDescriptors for conv_dw_conv case (#19045) 2023-08-08 15:40:00 +00:00
Aleksandr Voron a246003b79 [CPU][ARM] Reshape tensors for ACLConvertExecutor (#18578) 2023-08-08 14:56:49 +04:00
Wanglei Shen e733b0466c [CPU] Update streams calculation for latency mode on MacOS (#18818) 2023-08-08 10:53:48 +04:00
Anton Voronov eacdc24d54 [CPU] Transpose constant folding on cpu plug-in side for MatMul op (#18877) 2023-08-07 22:17:08 +04:00
Zhang Yi 648351ba39 [CPU] Disable mlas with webassembly (#19005) 2023-08-07 09:19:42 +04:00
Edward Shogulin b76fc24824 [LPT] Unexpected quantisation level fix (#18888) 
* [LPT] Unexpected quantisation level support

* [LPT] Unexpected quantisation level support - extension for weights

* [LPT] Unexpected quantisation level support - extension for weights + tests

* refactoring: compilation fix
 2023-08-04 15:02:12 +01:00
Gorokhov Dmitriy 80a807e26c [CPU] FullyConnected op acceleration with 8bit weights decompression (#18915) 2023-08-04 09:34:48 +04:00
Alexandra Sidorova 0f253c5986 [Snippets] Optimized second attempt of SplitDimensionM optimization (#18745) 2023-08-03 16:27:51 +04:00
Yuan Hu d445f9ec95 [CPU] Added unit tests for custom shape infer (#17162) 2023-08-03 12:41:27 +04:00
Nesterov Alexander 040951bfa1 [ARM CPU] Skip autobatch tests on arm32 arch (#18937) 2023-08-03 11:30:38 +04:00
Aleksandr Voron 8846b5ddd0 [CPU] Disabled MLAS FC impl on ARM (#18947) 
Fixes regression introduced in PR18879
 2023-08-03 08:59:31 +04:00
Nesterov Alexander f3bafef128 [ARM CPU] Add ACL deconvolution operation (#18655) 2023-08-02 21:02:01 +00:00
Alexandra Sidorova 5b82c6f08d [Snippets][CPU] Enabled MHA tokenization for quant and bf16 cases (#18403) 2023-08-02 21:16:27 +04:00
Aleksandr Voron 7b4a7e5eb4 [CPU][ARM] MLAS Transpose executor (#18879) 2023-08-02 12:48:09 +00:00
Ilya Lavrenov 7be660e551 Fixed CPU build (#18805) 2023-08-02 16:28:00 +04:00
Wanglei Shen 0cad2f1324 [CPU] Move streams calculation before transformation pipeline (#18911) 2023-08-02 11:38:34 +00:00
Pawel Raasz 9067a1fead Review NMS, MatrixNms shape inference (#18869) 
* Review NMS shape inference

* Fix test issues

* Review MatrixNms shape inference

* Unregister NMS with dynamic output from CPU plugin
 2023-08-01 19:44:55 +04:00
Chen Xu 74a608592a [CPU] Fix Reduce node bug regarding fusing with low precision (#18835) 2023-08-01 11:56:36 +00:00
Chenhu Wang 0608ece0ae [CPU] MVN kernel: fixed tails processing on SSE (#18893) 2023-08-01 09:29:18 +00:00
Pawel Raasz 6cc8661efe Review preprocessing ops convert color i420 nv12 color classes for shape inference aspects (#18870) 
* Review I420 convert shape inference

* Review NV12 convert shape inference
 2023-08-01 12:05:21 +04:00
Yury Gaydaychuk 61be577822 [CPU][Commit slider] Add commit to preprocess args (#18677) 2023-07-31 19:57:50 +04:00
Vladislav Golubev 2b5ca40eb6 [CPU] MatMul: move i8 compressed weights constant folding to the plugin (#18718) 
- Reused LPT pass for ConstantFold pass disabling for decompression subgraph
- GraphOptimizer: added FuseFCAndWeightsDecompression transformation
- Transformation pipeline adapted to the MatMuls with compressed weights
- Added MoveFCReshapeToWeights CPU transformation
 2023-07-31 12:44:09 +04:00
Aleksandr Voron e9991982bb [CPU][ARM] FP16 inference precision support (#18394) 2023-07-31 10:34:22 +04:00
Vladislav Golubev 5e846a0433 [CPU] Extensions shape inference issue fix (#18824) 2023-07-28 15:02:38 +04:00