aboutsummaryrefslogtreecommitdiff
path: root/src/core/CL/cl_kernels
AgeCommit message (Collapse)Author
2018-11-02COMPMID-1176: Add FP16 support in CLDeconvolutionLayer.Georgios Pinitas
Change-Id: Ic82ca002220fa31d8618a55084ff1dfc2585bea7 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/131944 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Vidhya Sudhan Loganathan <vidhyasudhan.loganathan@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-959: Fix CLChannelShuffleMichele Di Giorgio
Change-Id: I1ea4db4e1ba37a736445ba991eeb08c247a6a61e Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/131393 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-1044: Optimizing GCGEMM - Support for not reshaped GEMM on GLESMichele Di Giorgio
Change-Id: I22fe80393ec70e4501a4f9f9cad14014029d035d Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/129134 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-1137 OpenCL concatenate widthMichalis Spyrou
Change-Id: I40faba421281b1cf080fa6a825d04a4366cdaeb0 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/130700 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-1150 : (OCLGrind) Kernel compilation error and assertionGeorgios Pinitas
-Multiple definitions of COLS_MTX_B in gemm.cl one for FP32 and one for FP16. -GEMMTranspose1xWKernel invalid check fro small window sizes. Change-Id: I9c7ddd3577aec9afc702731ca27a1e10d6eddb81 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/131023 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-1050 CL/NEON: Create a function to convert the 2D weights of FC ↵Giorgio Arena
layer from NHWC to NCHW and viceversa Change-Id: If77ffeb92b6eb883e5d2d2c97c2c4d1d23d17c8d Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/129257 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-922 - CLGEMM FP16 optimizations - part2Gian Marco Iodice
This patch improves of ~30 % GEMM fp16 when the reshape is required The results have been reported at the following confluence page: https://confluence.arm.com/display/MLENG/GEMM+FP16+performance%3A+ACL+18.05 Change-Id: I8233095a7e9ab06f1f915782a25dd41653b49140 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/128254 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-1125: Add support for FP16 in CLDepthwiseConvolutionMichele Di Giorgio
Change-Id: I4838f5a8e4c33ed646cd05e0bb682fca635a29a3 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/130469 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
2018-11-02COMPMID-1107: Add support for ChannelShuffle in CLMichele Di Giorgio
Change-Id: I56d2a02b316f0c69ff1fd7220e732f775414fe69 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/129709 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-926 Add depth multiplier support to NEON/CL/GLES depthwise convolutionGiorgio Arena
Change-Id: I03f32c62350e5ea43e77bb15fc5a832d83719e3b Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/126657 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-805 Add NHWC data format support for CL poolingMichalis Spyrou
Change-Id: I3d91fde78b971aba3f6349f633cd9b1c50e5cacf Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/124712 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-1096 - Add fast_math flag to CLConvolutionLayerGian Marco Iodice
COMPMID-1103 - CLWinogradConvolutionLayer mismatches Change-Id: Iceaa9482a1790ec39d2720c220261aaea8043978 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/129398 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-803: Add NHWC data format support for CL batch normalisationMichele Di Giorgio
Change-Id: Ie37588f60b9cfc7b1d09b1e8628fcfb4b17e0717 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/123834 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-1078 Fix CL DepthwiseConvolutionLayer QASYMM8 failing validationGiorgio Arena
Change-Id: Id540490e5faf11c466ff039a20880eeedd6e5ec7 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/128612 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
2018-11-02COMPMID-1026 - Add support for 4x4 output tile in CLWinogradConvolutionLayerGian Marco Iodice
The performance achieved can be found at the following confluence page: https://confluence.arm.com/display/MLENG/GEMM-based+convolution+vs+Winograd-based+convolution+on+OpenCL Change-Id: I4b690cfdd4eb4ff0cd17b14fdd49ccaa1d1dc85c Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/127729 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-1037 Add support for F(4x4, 5x5) in CLWinogradOutputTransformKernelGiorgio Arena
Change-Id: I0b126f03028f08687497b0d79d2e2764f7ed07c8 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/128001 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-987: Make beta and gamma optional in BatchNormalizationMichele Di Giorgio
Currently we have beta and gamma compulsory in Batch normalization. There are network that might not need one or both of those. Thus these should be optional with beta(offset) defaulting to zero and gamma(scale) to 1. Will also reduce some memory requirements. Change-Id: I15bf1ec14b814be2acebf1be1a4fba9c4fbd3190 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/123237 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-1056 - Optimizing CLGEMMMatrixMultiplyKernel refactoring the inner loopGian Marco Iodice
Results reported at: https://confluence.arm.com/display/MLENG/GEMM+FP32+performance%3A+ACL+18.05 Change-Id: I3246c4f19c4d21a7d6a44e4593bc5caffc016f81 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/127838 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-922 - CLGEMM FP16 optimizations - part1Gian Marco Iodice
This patch improves of ~20% GEMM fp16. The results has been reported at the following confluence page: https://confluence.arm.com/display/MLENG/GEMM+FP32+performance%3A+ACL+18.05 I am aware with few cases we have a bit of degradation. However this cases are memory bound anyway (Fully connected layer cases) Change-Id: I183cbb7fba55a0b5eb86532c4dca5efe096096b0 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/128044 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-811 Add NHWC data format support for CL depthwise convolution QASYMM8Giorgio Arena
Change-Id: I89de432f3fbcba7abf9e1d4f8396a4334b4fa2c2 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/118324 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-1037 Add support for F(4x4, 5x5) in CLWinogradInputTransformKernelGiorgio Arena
Change-Id: Iac26936f46d0f7cdd9d2f8393b0092cd5a223c45 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/127675 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-1037 Add support for F(4x4, 5x5) in CLWinogradFilterTransformKernelGiorgio Arena
Change-Id: I6dd639bf5df9bc0c133996f75bdee767f70a6cfb Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/127469 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-584: Add validation to channel_combine kernelsIoan-Cristian Szabo
Change-Id: I67fe3fcea08704d9f4b04d22fe34db83b2697b87 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110562 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-585: Port OpticalFlow to new validationJohn Richardson
Change-Id: Ia36bd11ca27420d3059eea15df81b237900149ec Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/125175 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: John Richardson <john.richardson@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-994 : Check cl_arm_printf is supported in the CLSchedulerVidhya Sudhan Loganathan
Introduced static and dynamic checks before using printf vendor extension features (callbacks and buffers) Change-Id: Ib38cb3d8591bbb482d02a41918f4b52efde75267 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/126751 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-949: Optimizing CLDepthwiseConvolution3x3Kernel for FP16Michele Di Giorgio
Change-Id: I2af6544eab17004c5b3de56557cb2cc5efecc915 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/122181 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
2018-11-02COMPMID-596: Port HOGDetector to new validationJohn Richardson
Change-Id: I73231fc71c5166268e6c909b7930b7e034f3794e Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/118876 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-1017: Implement dilated convolution in NEON, OpenCL, and GCAlex Gilday
Change-Id: If4626ec9e215e14dffe22e80812da5bac84a52e2 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/125734 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-1032 - Fixing bug in CLGEMM when is_interleaved_transposed=trueGian Marco Iodice
The bug concerned the collapse of the window in CLGEMMMatrixMultiplyKernel Change-Id: I5043bf37b72eeb615ebe7fb3f2c8e72d006bf341 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/126262 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-1019 Implement copy function CLMichalis Spyrou
Change-Id: Ica17528bf6c812d9caf9d66c612c11434ec1dc69 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/125542 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-1008: Fix Doxygen issuesAlex Gilday
Change-Id: Ie73d8771f85d1f5b059f3a56f1bbd73c98e94a38 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/124723 Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-1009 Support 4x4 output tile for Winograd Filter Transform on OpenCL.Giorgio Arena
Change-Id: I68c6453e0f192de659582404f109a89616b9fbb9 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/124811 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-935 - Implementing Convolution with Winograd on OpenCL (part 4)Gian Marco Iodice
Implemented Winograd Output Transform (2x2,3x3) on OpenCL Implemented CLWinogradConvolutionLayer on OpenCL Change-Id: I6a113fc5f052ca07f878d2b800d2ab003f84af65 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/125148 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-853 Fuse CL DepthwiseConvolution with Activation for QASYM8Giorgio Arena
Change-Id: I287908f76af458ad4b4d865d353dc37e33877250 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/120839 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-935 - Implementing Convolution with Winograd on OpenCL (part 2)Gian Marco Iodice
Implemented Winograd Filter Transform 3x3 on OpenCL Change-Id: I8f2b2dd938c5c000ef7ce392a37fb7b8b4202a4e Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/122708 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-935 Implementing Convolution with Winograd on OpenCL (part 3)Giorgio Arena
Change-Id: I51f92f30602fb0a02314f344fa67061f448694bf Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/122793 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-935 - Implementing Convolution with Winograd on OpenCL (Part 1)Gian Marco
This patch enables GEMM to execute multiple batches in parallel https://confluence.arm.com/display/MLENG/Winograd%3A+batched+GEMM Change-Id: I66222db041dd35e82af11fbb262fd1ebd3ca4b2f Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/120866 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-765: Fix incorrect comma position in DepthwiseConv cl kernel.Georgios Pinitas
Change-Id: Ica047a92d3ab199ffc65a512b9ba10e865639dfe Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/121806 Reviewed-by: Les Bell <les.bell@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-927: Adding support for FP16 in CLDepthwiseConvolutionLayer3x3Michele Di Giorgio
Change-Id: Ie5f299c7a7fbe3062cee22bb2b4ae5df818fe490 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/121178 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-582: Add validation to channel_extract kernels.Ioan-Cristian Szabo
Change-Id: I5022d02f06f9d849dad76e3d9b8e48632c236429 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/121191 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-853 Use tile 2 for CL depthwise convolution QASYM8Giorgio Arena
Change-Id: I91f6a0b057f5eb84c6ac7db5abbc05c7520ed5d2 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/120760 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-939 Fix mismatches and finalize CLSoftmaxLayer optimizationGiorgio Arena
Change-Id: I4404f91a270e0ba7bbb7451c4c43a485fd4a3f6c Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/121105 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-938: OCLgrind: Mismatches in depthwise convolution on BifrostGeorgios Pinitas
Invalid conversions in oclgrind when clamp is used. Removed call to clamp in CL kernel and replace with convert_sat. Change-Id: I3cd9b87dc10c65d307fbf6eb0aec1b671fba6e97 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/121062 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-882 - Optimizing GEMMLowp on OpenCL reshaping matricesGian Marco
This new optimization allows to achieve 36.3 % of MAC utilisation on Mate 9 @ 1GHz. The performance have been reported here https://confluence.arm.com/display/MLENG/GEMMLowp+performance%3A+ACL+18.02 Change-Id: I71b6a217068763dfdc11bbf3574ee0eb94f93679 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/118531 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-905 Optimize CLSoftmaxLayer for QASYMM8Giorgio Arena
Change-Id: I3512d67b8a72b17db1381842ca42780e39cc511c Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/120605 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-765 Move direct convolution output stage to the right fileGiorgio Arena
Change-Id: Ifb4d27ba05aa618babb79b1f8e95fbfa689c5f3a Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/120792 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-856: CL Depthwise Convolution QASYMM8 supportGeorgios Pinitas
Change-Id: Ic6097e7cf160e8b829fb521b7b99d9a57d9799d3 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/118774 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-905 Asymm functions support for all vec sizesGiorgio Arena
Change-Id: Ie0c5885a60771f728f80a8c4bdb7f1e4085fa3ee Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/120267 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-828 - Add support for pool widths 4, 5 & 6 and for non square data ↵Isabella Gottardi
sizes - Part 2 (CL) Change-Id: I004906b9b1f11158fe17b4aa2640a7f4685fb929 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/118462 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-897 Merge batch normalization with bounded reluGiorgio Arena
Change-Id: I9a607fe620f795cdea1a99fdd3f5f8c2fc76f980 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/119234 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-16 12:16:10 +0000