aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2018-11-02COMPMID-791: Adds support of QASYMM8 in NEDepthwiseConvolution3x3Georgios Pinitas
Change-Id: I1a9ed6c3420ddf8978aeaad48d9915333b006b49 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116374 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-849: Changed default toolchain to Clang on AndroidAnthony Barbier
Change-Id: I345aa8455f53980b6e17c0963a8b593a1dbe38be Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116764 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02IVGCVSW-847 Fix {NEON/CL}PoolingLayerKernel configDiego Lopez Recas
Also, add validation test that hits the discovered failure for CL. Change-Id: I5573e0a3f169b85d5fb7299e7c48d74be7165208 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/112717 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-753 Add benchmarks for ActivationLayers used in MobileNetGiorgio Arena
Change-Id: Iafc16409430274d5126f0fb054b0de5de6b6ca8f Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116635 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-751 QASYMM8 ActivationLayer optimisation: don't requantize if not ↵Giorgio Arena
necessary Change-Id: Iea8a21f7c71025bfde6fdf7c7a7c92ba749b189b Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116673 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-832: Clean up tests.Georgios Pinitas
Removes QS8 and QS16 tests from benchmarks. Change-Id: Idf82d33159b2066d50ac2d454140938e43160779 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116626 Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-751 Processing 8 elements makes computation up to 80us faster on ↵Giorgio Arena
MobileNet QASYMM8 dwc layers Change-Id: I30eaea3f3625086e311ad201ef73a8f06a01e382 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116521 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-839 Added method to clear the Kernel Library's program cacheAnthony Barbier
Change-Id: If2e14c19f16686a2a8e05832845f8bfcf0f0cdaf Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116537 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-835: Valgrind make UNIT/Utils/RoundFloatToNearestUp fail on aarch64Pablo Tello
Workaround for Valgrind round() issue on aarch64. Valgrind's call to std::round(-4.500000) == -4.000000 instead of 5.00000. I think there is a bug in valgrind's code for aarch64 where the rounding mode is not properly setup and that's the reason why round to zero is used all the time. Change-Id: If8fbee98e022856fcc48e454f7afd447f1f193e9 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116457 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-752 Creating an example for QASYMM8 MobileNetGiorgio Arena
Change-Id: Ic76b3b6adaff8c84ba4d2ca5283d9291c69344f0 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114466 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-769 Add asymmetric padding support in NEON kernels.Michalis Spyrou
- NEDirectConvolutionLayer - NEDepthwiseConvolutionLayer3x3 Change-Id: Id4d7d17ee334639c059015a290b8fc34712706ee Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115430 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-816 - Enabled CLConvolutionLayer to use CLGEMM function insteadGian Marco
of CLGEMMMatrixMultiplyKernel kernel. Change-Id: If035fa3d1fb3ff4012442bcd908c370d21aa6657 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115990 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-830 Fix hang in arm_compute_benchmark NEONMichalis Spyrou
Problem seems to happen when calling clfinish inside the CLScheduler destructor. Removed destructor and now calling sync() in benchmarks main.cpp. Change-Id: Ibb36a0d19aa03349d291407a1fb8266dce3ec75b Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116288 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-752: DATA_UPDATE Add MobilenetV1 QASYMM8 data.Georgios Pinitas
Change-Id: Icbb569acdfb5cd9d669341921d585297a5840bb3 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/116192 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-765 - Reduced to 4 the batch size for AlexNetGian Marco
This patch also removed QS8 AlexNet benchmarking for NEON and set the flag weights_reshaped to false for CL Change-Id: I8db21b007c3b25b870e9072f8e02e36d1c1281c9 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115999 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-785: Add QASYMM8 support for pooling layerGeorgios Pinitas
Adds generic pooling case for QASYMM8 Change-Id: I37d38a92ca61651e915fbbbb6da88e180390b4ab Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115439 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-765: Fixed unused variable warningAnthony Barbier
Change-Id: I244954f748169cefcf71409bc9fdbc45de816ba5 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115878 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-786: Remove all the fill() calls in benchmarksAnthony Barbier
Filling buffers with random data takes a significant amount of time and in most cases doesn't affect the performance We will therefore only keep fill() in the functions for which it matters Change-Id: Ica34fe09941f27d6f0417f33176847febf722bc3 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115892 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-782 Port examples to the new formatMichalis Spyrou
Change-Id: Ib178a97c080ff650094d02ee49e2a0aa22376dd0 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115717 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-565 - Implement reference and CL/NEON validation for ↵Sanghoon Lee
CustomConvolutionSeparable Change-Id: I81fae268d158aec882dbeadb5597dc9f7274d865 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115347 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-800: Display build_information() at the beginning of the runsAnthony Barbier
Change-Id: Iba1e2f021f19351edf849239d10fb9f3788a67c8 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115743 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-753 Add benchmarks for GEMM/GEMMLowp used in AlexNetGiorgio Arena
Change-Id: Ie680065fe98c2fcdefad1fd5240f0a951df6e4cf Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115779 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02IVGCVSW-863 calculate_max_window..() family takes ValidRegionDiego Lopez Recas
Change-Id: I91e39713ffa580e9d2213988ad3517a8a41bf4e8 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114013 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02APPBROWSER-376: Work around for scale validation error.Frank Lei
Use "vec2 scale" instead of scale_x/scale_y to work around this issue. Change-Id: Ieae55327596fdb853d7b625262fec3a3a84f577c Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115143 Reviewed-by: Joel Liang <joel.liang@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Frank Lei <frank.lei@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-742: Add image input support for Harris Corners testsAlex Gilday
Change-Id: I4833eec0734776d8683fe867bb4f4d827f1a2fb7 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115503 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-471 Implement Deconvolution on OpenCLMichalis Spyrou
Change-Id: Ie00c6b08a51d30c5ce2637d40ee3d165b8a68686 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/110311 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-727 - Implement reference and CL/NEON validation for ↵Sanghoon Lee
CustomConvolutionRectangle Change-Id: I108a48ad5e6dc3f331fd5ceb38ced8ccdb31d81a Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/113130 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-771 Allow examples to be profiledAnthony Barbier
Change-Id: I180281e796e1670b9ad391d82d66ecde0119ef78 Note: this is for internal use only which is why I think the hackiness of RunExample.cpp is acceptable. Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115154 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-784: Removed no longer needed file winograd_shim_nchw.hppPablo Tello
Change-Id: If72b649fce21d0b8b9c28a1b064c4cf5adb06c15 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115502 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-753 Add benchmarks for QASYMM8 depthwise convolution layers used in ↵Giorgio Arena
MobileNet Change-Id: I72cdf54477838b01bc5fa1281b0b587646f1902b Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115396 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-784: Winograd refactoringPablo Tello
Removed the code that created a subtensor and imported memory from the workspace in the function run() method. The subtensor is no longer needed because we perform the reordering of the tensors with NEPermute. The call to the method winograd::Winograd2x2_3x3GEMM<TOut, TIn>::reshape_output() will transform the results from the winograd domain into the spatial domain and this will be stored in the member _output_nhwc. Change-Id: Iae09d26c7587cd2eed98968c3ce214e20031038e Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115483 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-765: Fix HarrisCorners data type in benchmarksGeorgios Pinitas
Change-Id: I23865486ef413c4d2495c537df4b1393b0e822df Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115395 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-783: Segfault in OCLGrindGeorgios Pinitas
Enforce clFinish to be called on destruction of the CLScheduler to ensure that no leftovers are in the queue which might lead to the retain of the queue and its deferred destruction. Change-Id: Ic71933f65cdccd74f4f01a6e2ec1a049995f5b50 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115389 Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02APPBROWSER-298: Remove the old shader common codeJoel Liang
Remove token pasting operator support for GLES shader Remove cs_shdaers/helpers.h (The old GLES shader common code) Remove class BufferParam. We don't need to pass the buffer_data_type_shift to GLES shader. Change-Id: Ic4fa6b2fb7647b8f69759f6077ae4a5b483cc04d Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115448 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Frank Lei <frank.lei@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID: GEMMTranspose1xW tests.Pablo Tello
Change-Id: I62a7a1871b93fafc65eb58fa550bc86179bdffe7 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/112489 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-589: Port HOGDescriptor to new validationJohn Richardson
Change-Id: I2021612e61de1b82aaeb49249d06929c7fceb15f Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115216 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-759 - CLGEMM optimization for McVail benchmarksGian Marco
This patch introduces an optimization for CLGEMM on Bifrost architectures which can bring to 40% of FMA utilization on config 3 of McVail. The new CLGEMM does not require any reshape of matrix A and matrix B. This patch also adds the auto-config in CLConvolutionLayer and CLGEMM and extends the interface for NEGEMM and CLGEMM. Change-Id: Ibb354eda45e9ca64b14a99700fb21dff5989dda9 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/113716 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02APPBROWSER-373: Rewrite the convolution_layer.cs with the new common codezhenglin
Change-Id: I4aa3999159f0448592f5f704ebcd37b26f9b1e51 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115279 Reviewed-by: Joel Liang <joel.liang@arm.com> Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02APPBROWSER-374: Rewrite the dropout.cs with the common codezhenglin
Change-Id: Ic2be14d626856faa4496c588154ef5cfb66d4e2c Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115282 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Joel Liang <joel.liang@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-746 Allow NEDirectConvolution to work without biases for QS.Michalis Spyrou
Renamed BiasAccumulateKernel to OutputStage. If no bias is provided when the input is quantized, the kernel simply downscales the input. Throw error if no bias is provided and input is floating point. Change-Id: I645a4ee9c6014b0547778fdd92c9ec72ef2f0aab Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114158 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02APPBROWSER-375: Rewrite the transpose.cs with the new common codezhenglin
Change-Id: I373e349ac35ff52ebcc895723d8aa61b754519d4 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115283 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Joel Liang <joel.liang@arm.com>
2018-11-02APPBROWSER-372: Rewrite the direct_convolution5x5.cs with the new common codeJoel Liang
Change-Id: Ie2f398d62dea97e9201f77d22c9f0796db297b63 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115280 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Zhenglin Li <zhenglin.li@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02APPBROWSER-370: Rewrite the normalization_layer.cs with the new common codezhenglin
Change-Id: I717d0ebbae5102da039b9295649aed8056e4cdfd Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114960 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Joel Liang <joel.liang@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com>
2018-11-02COMPMID-773: Add CL/NEON Harris Corners benchmark testsAlex Gilday
Change-Id: Idf452cfa0428a36f2d718a6d438d6e59897e1e99 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/115061 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-579: Port Derivative to new validationJohn Richardson
Change-Id: Iecbfa3ebab890c778fb475403466d6fb168e9968 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/113357 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02APPBROWSER-371: Rewrite the direct_convolution3x3.cs with the new common codeJoel Liang
Change-Id: I82a3ec133193433ba9ed3efcb49c51a2b95b16c0 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114962 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Zhenglin Li <zhenglin.li@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02APPBROWSER-369: Rewrite the gemm.cs with the new common codezhenglin
Change-Id: I9db00c846fa7fc223a22ab775025dfdea587ade8 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114957 Reviewed-by: Joel Liang <joel.liang@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-750: Enabled support for U8 and S8 datatypes in ↵Pablo Tello
NEGEMMLowpAArch64V8P4Kernel Change-Id: If32cbdc65f2e1441595cae5b4824a9b4357c8bf6 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/113467 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-765 Merge pull request #325 from lukeiwanski/feature/no_exceptionsAnthony Barbier
ARM_COMPUTE_NO_EXCEPTIONS macro guard Cherry-picked public merge request from Codeplay Change-Id: Id819177fcc86a64dc4e82eefe46b2f646619e8c0 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114924 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02APPBROWSER-366: Add DepthwiseConvolutionLayer(fp16 only) support.Frank Lei
Change-Id: I051b7e56b60bf1a55cdf014539ef71346d3aee26 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/114737 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-28 05:09:17 +0000