IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
13,725 Commits 38 Branches 54 Tags
032ac898e21c4008fb8c8dc2da5778c1b3ab4afe
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Roman Lyamin 0e7248430c [Transformations] Support precision conversion for PriorBox (#21702) 2023-12-18 11:19:59 +04:00
Roman Lyamin 6a50ea3c74 [GPU] Using a cpu impl type for NMS in a dynamic case (#21648) 2023-12-14 17:22:01 +04:00
Roman Lyamin 01b4faf47f [GPU] Enable CPU pinning for compilation tasks executor (#21261) 2023-11-28 09:40:00 +04:00
Roman Lyamin 50b6c5f0d7 [GPU] Fix for SoftmaxKernel_bf in dynamic case (#20769) 2023-10-31 09:02:03 +04:00
Roman Lyamin 7eb53586f5 [GPU] Added WA for MarkDequantizationSubgraph to work correctly in the plugin (#20767) 2023-10-30 17:58:34 +00:00
Roman Lyamin 5c6b7a5ed4 [GPU] Allow softmax_bf kernel for axis=X 4d case (#20699) 2023-10-30 09:11:32 +04:00
Roman Lyamin 59fe0a05a4 [GPU] Fix for reorder fusing in fuse_constant_transposes pass (#20651) 2023-10-24 09:21:30 +04:00
Roman Lyamin fe9d5607ed [GPU] Fixed data generation for f16 fusion tests (#20247) 
* [GPU] Fixed data generation for f16 fusion tests

* [GPU] Temporary tolerance increase for failed tests on iGPU

* [GPU] Temporary skip or tolerance increase for failed tests on dGPU
 2023-10-17 11:17:07 +04:00
Roman Lyamin b345f3c324 [GPU] Fix high latency for LLMs on dGPU (#20328) 2023-10-11 14:42:33 +04:00
Roman Lyamin 99de7818be [GPU] Extended SupportedFusedOps for Concatenation (#20096) 2023-10-09 14:28:37 +04:00
Roman Lyamin 1ba8005688 [GPU] Disabling redundant copying of constant weights (#18949) 2023-09-26 18:43:57 +04:00
Roman Lyamin 2e88aa0770 [GPU] Added int32 weights support for reorder_weights kernels (#20015) 2023-09-25 09:23:47 +04:00
Roman Lyamin a800d3e4f4 [GPU] Update weights reorder output shape for fully_connected (#19925) 2023-09-21 09:26:42 +04:00
Roman Lyamin 5ba60f845e [GPU] Added zero input support for Pad (#19720) 2023-09-14 09:59:53 +04:00
Roman Lyamin 188434e969 [GPU] image_2d_weights_winograd_6x3_s1 formats fix (#19205) 2023-08-16 08:59:43 +04:00
Roman Lyamin 9be28328bf Added giy_xs_os_xsv2_osv8__ao32 format to to_weights_layout map (#19181) 2023-08-15 08:49:50 +04:00
Roman Lyamin 575f497c8b [GPU] Fix data race in CompilationContext (#19103) 2023-08-10 00:50:49 +00:00
Roman Lyamin 2d5a4e20ec [GPU] Fix premature termination of async compilation task in tests (#19035) 2023-08-09 12:47:06 +04:00
Roman Lyamin 7d89c93ded [GPU] Added gi_yxs_os_yxsv2_osv16 format to to_weights_layout map (#19074) 2023-08-09 12:03:48 +04:00
Roman Lyamin d00c7d30f9 [GPU] Reorder weights refactoring (#17787) 2023-06-23 16:01:55 +04:00
Roman Lyamin cca8cf15ef [GPU] softmax_kernel_items_class_optimized fix (#18178) 2023-06-23 16:00:11 +04:00
Roman Lyamin 63a5ec5762 [GPU] Several fixes for format traits (#18018) 2023-06-14 14:33:58 +04:00
Roman Lyamin ad03c631b9 [GPU] Added os_is_yx_osv16_isv2 format (#17476) 2023-05-12 15:11:09 +04:00
Roman Lyamin fbc14a2efb [GPU] Coverity fixes (#17241) 2023-04-27 22:14:27 +04:00
Roman Lyamin 656428bc4f [GPU] Skip kernel logic for Concat fix (#16885) 2023-04-13 15:55:05 +04:00
Roman Lyamin f8aacf3b19 [GPU] Small fix for gather_nonzero (#16858) 2023-04-12 09:15:49 +04:00
Roman Lyamin 2312ec79a2 [GPU] Skip failing lstm tests (#16868) 2023-04-12 02:10:42 +02:00
Roman Lyamin 234fe92931 [GPU] MVN 1d dynamic batch case fix (#16826) 2023-04-11 09:42:51 +04:00
Roman Lyamin 132b657977 [GPU] Added GatherND dynamic support and changed logic for empty tensor support (#16690) 2023-04-07 09:19:05 +04:00
Roman Lyamin 38c8a3d15b [GPU] Added custom canonicalize_shapes for Gather (#16733) 2023-04-06 10:50:57 +04:00
Roman Lyamin 5113a5538c [GPU] Added shape canonicalization mechanism (#16166) 2023-03-27 15:02:06 +04:00
Roman Lyamin b8e1dea345 [GPU] Fix binary_convolution non-constant weights (#15898) 
* [GPU] Fix binary_convolution non-constant weights

* [GPU] Remove unused checks related to allowInputReordering
 2023-03-10 14:36:12 +04:00
Roman Lyamin 681faadce3 [GPU] Added shape agnostic kernels for GatherElements and Tile (#15798) 
* [GPU] Added shape agnostic kernel for GatherElements

* [GPU] Added shape agnostic kernel for Tile
 2023-03-08 08:34:24 +04:00
Roman Lyamin 24b0baa0d1 [GPU] Added support mixed input formats for Select (#16009) 2023-03-02 09:19:02 +04:00
Roman Lyamin 1070a3b6c1 [GPU] Added fp16 support for GatherTree (#15983) 2023-02-28 09:54:56 +04:00
Roman Lyamin efb51b058c [GPU] Added operator== for cldnn primitives (#15736) 2023-02-17 19:09:12 +04:00
Roman Lyamin 803a927e70 [GPU] Added shape agnostic kernel support for Range + fix dynamic tests (#15640) 2023-02-13 17:14:29 +04:00
Roman Lyamin 75735ca597 [GPU] Added ScatterUpdate shape agnostic kernel (#15579) 2023-02-10 07:06:30 +01:00
Roman Lyamin 23b863ffe8 [GPU] Added ScatterNDUpdate shape agnostic kernel (#15567) 2023-02-08 16:27:34 +01:00
Roman Lyamin 014a35c3ce [GPU] Added strided_slice shape agnostic kernel (#15477) 2023-02-06 13:03:00 +04:00
Roman Lyamin 36df508baf [GPU] Added shape agnostic ref kernels for Select and Activation (#15016) 
* [GPU] Added Select shape agnostic support

* [GPU] Added Activation shape agnostic support
 2023-02-02 10:08:36 +04:00
Roman Lyamin 2d9a213ed6 [GPU] Added NV12toBGR single plane surface tests (#15417) 2023-02-01 18:26:39 +04:00
Roman Lyamin 4089ee0899 [GPU] Added WA for currently unsupported scale_shift_opt agnostic kernel (#15341) 2023-01-27 16:47:35 +04:00
Roman Lyamin 8e073819c3 [GPU] Added shape agnostic ref kernel for Reduce and Quantize (#15183) 
* [GPU] Added shape agnostic ref kernel for quantize

* [GPU] Added shape agnostic ref kernel for Reduce
 2023-01-25 14:25:13 +04:00
Roman Lyamin eb9946bd25 [GPU] Added support dynamic sizes/scales inputs for Interpolate (#14074) 2022-11-28 09:10:12 +04:00
Roman Lyamin fce64834d2 [GPU] PReLU broadcast 1d slope case fix (#13951) 2022-11-14 11:03:10 +04:00
Roman Lyamin 5eae673220 [MO TESTS] PReLU tests fix (#13960) 2022-11-11 23:39:17 +04:00
Roman Lyamin 4dd75a1b8b [GPU] Added Pad/Interpolate dynamic support and MVN dynamic tests (#13874) 
* [GPU] Pad dynamic

* [GPU] Added MVN dynamic tests

* [GPU] Interpolate dynamic
 2022-11-10 15:33:45 -08:00
Roman Lyamin 34b76584f7 [GPU] AvgPool/MaxPool dynamic support (#13754) 2022-11-07 15:46:17 +04:00
Roman Lyamin 6c7f1f8792 [GPU] Fix performance drop on new API (#13767) 2022-11-03 18:34:14 +04:00
Roman Lyamin 2b5dd4fac8 [GPU] Pooling refactoring (#13664) 2022-11-03 14:53:32 +04:00
Roman Lyamin 478939ea9e [GPU] GEMM dynamic (#13248) 2022-10-21 16:19:35 +04:00
Roman Lyamin 9c6ad77852 [GPU] FullyConnected dynamic (#13015) 
* [GPU] FullyConnected dynamic

* [GPU] Fix FC OneDNN usage
 2022-10-11 16:51:18 +04:00
Roman Lyamin c173f7e374 [GPU] fully_connected/gemm shape infer support (#12772) 2022-09-01 09:04:55 +04:00
Roman Lyamin 93d82cde4a [GPU] Squeeze/Unsqueeze shape infer support (#12724) 2022-08-31 09:38:39 +04:00
Roman Lyamin fcf20dee86 [GPU] GatherElements shape infer (#12517) 2022-08-25 09:38:53 +04:00
Roman Lyamin e7e6d7883c [GPU] Dynamic input support for Transpose (#12739) 2022-08-25 09:29:24 +04:00
Roman Lyamin 3339d5a372 [GPU] MVN shape infer support and dynamic tests (#12685) 2022-08-24 18:29:15 +04:00
Roman LyaminandSergey Shlyapnikov 19fd77e3d8 [GPU] Broadcast shape infer support (#12588) 
* [GPU] Align broadcast with nGraph operation

* [GPU] Broadcast shape infer support

Co-authored-by: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
 2022-08-24 18:27:15 +04:00
Roman Lyamin f26c3d035a [GPU] Interpolate shape infer support (#12516) 2022-08-22 10:47:07 +04:00
Roman Lyamin 267f2f9c4b [GPU] Tile shape infer support (#12539) 2022-08-22 10:41:46 +04:00
Roman Lyamin 5128f20cfa [GPU] Pad shape infer support (#12654) 
* [GPU] Align Pad parameters with ngraph

* [GPU] Pad shape infer support
 2022-08-22 10:33:15 +04:00
Roman Lyamin 73da7080a3 [GPU] Align StridedSlice parameters with ngraph (#12414) 2022-08-11 18:34:55 +04:00
Roman Lyamin 85e2229a80 [GPU] Align Tile parameters with ngraph (#12345) 2022-08-11 14:08:22 +04:00
Roman Lyamin e98cdcf496 [GPU] Use int64_t type for axis in GatherElements (#12317) 2022-08-11 14:07:08 +04:00
Roman Lyamin 25224eb2c2 [GPU] Use int64_t type for axis in ScatterElementsUpdate (#12323) 2022-07-28 09:17:29 +04:00
Roman Lyamin 31e3c11291 [GPU] Use int64_t type for axis in CumSum (#12306) 2022-07-28 09:16:21 +04:00
Roman Lyamin 5e52d519ea [GPU] Align TopK parameters with ngraph (#12278) 2022-07-28 09:15:41 +04:00
Roman Lyamin e2da32721b [GPU] Use int64_t type for axis in softmax (#12287) 2022-07-26 13:21:43 +04:00
Roman Lyamin 0ee6959537 [GPU] Replacing get_shape() with get_partial_shape() (#10525) 2022-02-21 09:41:24 +03:00
Roman Lyamin d13e04a693 [GPU] convolution_kernel_bfyx_1x1_opt fix (#10338) 2022-02-14 10:32:19 +03:00
Roman Lyamin 7b288d125a [GPU] Gather fusion tests fix (#10308) 2022-02-11 20:57:44 +03:00
Roman Lyamin 0d64afc2c8 [GPU] program_helpers::are_layouts_identical fix (#10109) 2022-02-09 09:27:15 +03:00
Roman Lyamin cf80eda8e0 [GPU] Added handle permute (#9853) 2022-01-27 14:37:55 +03:00
Roman Lyamin baa1a8e59d [GPU] Add batching buffer to new API (#9565) 2022-01-14 16:02:19 +03:00
Roman Lyamin 9f69daf0f3 [GPU] Remove batched key from config (#9451) 2021-12-29 09:58:48 +03:00
Roman Lyamin ecbeff460a [GPU] Fix check binary size in SetBlob (#9418) 2021-12-28 16:12:15 +03:00
Roman Lyamin b050d39f89 [GPU] Add batching surface to new API (#9435) 2021-12-27 09:46:37 +03:00
Roman Lyamin 2068d5838b [GPU] Add I420toRGB/I420toBGR operations (#9204) 2021-12-16 10:27:27 +03:00
Roman Lyamin 7d0d0ea503 [GPU] Add NV12toRGB/NV12toBGR operations (#8838) 2021-12-14 12:01:50 +03:00
Roman Lyamin a46db8a72e [IE CLDNN] Disable bs_fs_yx_bsv16_fsv16 format for int8 convolution (#8220) 2021-10-27 16:33:02 +03:00
Roman Lyamin 03424849fb [GPU] Add separate config for each device (#7421) 2021-10-19 16:51:38 +03:00
Roman Lyamin 17091476d8 [IE CLDNN] Add optional memory access type (#7686) 2021-09-30 10:32:07 +03:00
Roman Lyamin 6ecfbd47e3 [IE CLDNN] clDNNPlugin size fix (#7655) 2021-09-27 14:32:52 +03:00
Roman Lyamin f202c45c46 [IE TESTS] Move locale test to shared folder (#7605) 2021-09-24 10:27:07 +03:00
Roman Lyamin d6ade04fc7 [GPU] Performance improvement for Load Network (#7514) 2021-09-21 11:35:23 +03:00
Roman Lyamin 660c106233 [GPU] Performance counters fix (#7143) 2021-09-17 13:12:25 +03:00
Roman Lyamin c8a5044664 [IE CLDNN] Add Select int32/int16 input support (#5877) 2021-05-28 18:00:51 +03:00
Roman Lyamin 5a42015e76 [IE CLDNN] Memory dependencies fix (#5480) 2021-05-21 13:42:31 +03:00
Roman Lyamin 16d7d01a27 [IE CLDNN] Eltwise b_fs_zyx_fsv16 optimization (#5098) 2021-04-26 15:36:38 +03:00
Roman Lyamin 75f9fcd134 [IE CLDNN] Fix StridedSlice for hbonet (#4493) 2021-03-16 08:26:14 +03:00
Roman Lyamin b637b39179 [IE CLDNN] Fixed MVN-6 with negative axes (#4523) 2021-03-01 12:41:30 +03:00
Roman Lyamin 01535161a6 [IE CLDNN] Added MVN-6 operation (#4190) 2021-02-19 12:24:52 +03:00
Roman Lyamin d406a5af50 [IE CLDNN] Added CTCGreedyDecoderSeqLen operation (#4119) 2021-02-14 11:03:25 +03:00
Roman Lyamin 6b09d5769f [IE CLDNN] Added LogSoftmax-5 operation (#2945) 2020-11-11 08:53:30 +03:00
Roman Lyamin 77365bcb4c [IE CLDNN] Added Round-5 operation (#2838) 2020-10-27 10:56:15 +03:00
Roman Lyamin cc569d2254 [IE CLDNN] Added HSigmoid operation (#2700) 2020-10-18 20:47:22 +03:00
Roman Lyamin 3a9e160031 [IE TESTS] Added single layer tests HSwish (#1861) 2020-08-20 13:32:16 +03:00
Roman Lyamin 15f91be168 [IE CLDNN] Added fsv16 and int8 support in BatchToSpace and SpaceToBatch (#1381) 2020-08-03 15:04:49 +03:00
Roman Lyamin 8245e5b6f4 [IE CLDNN] Added HSwish-4 operation (#1585) 2020-08-03 10:15:43 +03:00