- 205ba24 Added S64/U64 support for the input in CLCast by Pablo Marquez Tello · 1 year, 2 months ago
- 8e2dede Add Bias to MatMul Kernels and add support for use in Fully Connected Layer by Mohammed Suhail Munshi · 1 year, 2 months ago
- 5153fe4 Fix unsupported configuration in CLFullyConnected validation by Gunes Bayir · 1 year, 2 months ago
- c9eeee5 Fix nightly failures in MatMulLowpNativeKernel when using bounded activation functions by Mohammed Suhail Munshi · 1 year, 2 months ago
- 00474e9 Implement FP32/16 MatMul Lhs T Rhs T/NT kernel using MMUL extension by Gunes Bayir · 1 year, 2 months ago
- 8c49f16 Add helpers to set CKW tensor components as OpenCL kernel arguments by Jakub Sujak · 1 year, 2 months ago
- a2bb80e Use MatMul in fully connected layer with dynamic weights when supported by Mohammed Suhail Munshi · 1 year, 2 months ago
- c952596 Implement FP32/FP16 MatMul NT/T kernel using the MMUL extension by Ramy Elgammal · 1 year, 3 months ago
- a8d8058 Implement FP32/FP16 MatMul NT/NT kernel using the MMUL extension by SiCong Li · 1 year, 3 months ago
- 94abde4 Add Fused Activation to OpenCL MatMul by Mohammed Suhail Munshi · 1 year, 3 months ago
- 043613f Break up Utils.h a bit to reduce unused code being included everywhere by Matthew Bentham · 1 year, 3 months ago
- f1aeab9 Break up arm_compute/core/Types.h a bit by Matthew Bentham · 1 year, 3 months ago
- 48c0ed9 Fix ScaleKernel validate method. by Pablo Marquez Tello · 1 year, 4 months ago
- e9b3ee2 Connect CLMatMul function to quantized kernels and resolve NE BatchMatMul int_8 failures by Jakub Sujak · 1 year, 4 months ago
- 352c07d Implement OpenCL MatMul heuristic for Arm® Mali™-G710 by Gian Marco Iodice · 1 year, 4 months ago
- 60ab4e6 Fix export_to_cl_image issue in the fp16 GeMM implementation by Gian Marco Iodice · 1 year, 4 months ago
- 7a0f1bd Add fp16 GeMM heuristic for Arm® Mali™-G710 by Gian Marco Iodice · 1 year, 4 months ago
- 5e99a3e Add quantized CL MatMul kernel for LHS NT, RHS T by Jakub Sujak · 1 year, 4 months ago
- f16eed9 Change fp16 GeMM heuristic for Arm® Mali™-G77 by Gian Marco Iodice · 1 year, 4 months ago
- 905a3c1 Improve Winograd performance on OpenCL by Gian Marco Iodice · 1 year, 4 months ago
- 467daef Implement CL kernel for a native batched matmul Quantized - LHS transposed, RHS transposed by Omar Al Khatib · 1 year, 5 months ago
- 9d0c4de Add quantized CL MatMul kernels for Lhs NT/T, Rhs NT by Gunes Bayir · 1 year, 5 months ago
- 1ed6a14 Align naming convention of ClMatMul by Jakub Sujak · 1 year, 5 months ago
- 617ed50 Support dynamic weights for Fully Connected layers on GPU by Jakub Sujak · 1 year, 5 months ago
- f26ea2f Implement MatMul Function by Ramy Elgammal · 1 year, 5 months ago
- f9a547c Work around CLScale compiler-specific issue by SiCong Li · 1 year, 5 months ago
- bbeef72 Add Texture Pipe Support for Matmul Lhs T/NT Rhs NT kernels by Gunes Bayir · 1 year, 5 months ago
- 8918b23 Implement OpenCL MatMul for Lhs T Rhs T/NT FP32/16 by Gunes Bayir · 1 year, 5 months ago
- 14d7b53 Implementation of RSQRT for quantized int8 by Ramy Elgammal · 1 year, 7 months ago
- 2b6ebfe Implement OpenCL MatMul for Lhs NT Rhs T/NT FP32/16 by Ramy Elgammal · 1 year, 6 months ago
- 47f177e Fix LWS search space used by CLTuner by SiCong Li · 1 year, 6 months ago
- 227db8d Add an option to use lowest for max-pooling by Adnan AlSinan · 1 year, 6 months ago
- 1b6377b Add broadcast batched matmul validation cases by SiCong Li · 1 year, 8 months ago
- 13bab71 Fix ClGemm crashes on unsupported data types by SiCong Li · 1 year, 8 months ago
- 1b2f868 Fix CL DirectConvolutionLayer validate tests by SiCong Li · 1 year, 8 months ago
- 3cce35d Extend cl image support to input and output tensors by Gian Marco Iodice · 1 year, 8 months ago
- b7e8626 Optimize CL Scale/Resize Quantized by removing (de)quant. code by Gunes Bayir · 1 year, 8 months ago
- a5cb79f Update the ClConv2d heuristic by Gian Marco Iodice · 1 year, 8 months ago
- 8a2d7ce Extend Transposed Conv. for tiles with N0>1 by Gunes Bayir · 1 year, 8 months ago
- 8468371 Make CLReshape kernel window based on dst instead of src by Ramy Elgammal · 1 year, 8 months ago
- a0ae8d2 Optimize Transposed Convolution for CL backend (Quantized) by Gunes Bayir · 1 year, 9 months ago
- 3274172 Add CLAMP operator to Dynamic Fusion interface by Jakub Sujak · 1 year, 9 months ago
- 21a0a4e Fix build error resulting from incorrect header path by Jakub Sujak · 1 year, 9 months ago
- df6a3b0 Use heuristics for setting dynamic fusion direct conv2d tile sizes by Ramy Elgammal · 1 year, 9 months ago
- 76335eb Implement the OpenCL kernel to compute the indirect convolution by Gian Marco Iodice · 1 year, 9 months ago
- 5d01681 Implement address precalculation for indirect conv2d - OpenCL by Gian Marco Iodice · 1 year, 9 months ago
- 31df05a Remove dynamic fusion prototype with tests and examples by SiCong Li · 1 year, 10 months ago
- ec0113d Optimize Transposed Convolution for CL backend (FP32/16) by Gunes Bayir · 1 year, 10 months ago
- 3394f3e Rework direct convolution heuristic on OpenCL by Gian Marco Iodice · 2 years ago
- ad9a7ed Rework DepthwiseConvolution heuristic on OpenCL by Gian Marco Iodice · 2 years ago
- 3bedd2f Improve start-up time in gemmlowp reshaped rhs only. by Adnan AlSinan · 1 year, 11 months ago
- db14af6 Update GEMM reshaped rhs only heuristic by Gian Marco Iodice · 1 year, 11 months ago
- b5368fb Force CL kernel compilation with 64 registers by Viet-Hoa Do · 1 year, 11 months ago
- 047e5d0 Fix validation in validate_image2d_support_on_rhs by Gian Marco Iodice · 2 years ago
- 4478e1c Rework heuristic in ClConv2d by Gian Marco Iodice · 2 years ago
- d11de98 Add a macro guard in all OpenCL kernels in gemmlowp.cl by Gian Marco Iodice · 2 years ago
- 1257131 Enable Winograd-based conv2d when IFM>=8 on Gpu by Gian Marco Iodice · 2 years ago
- 9ee8a3e Revert "Fix performance regression in ClConv2D" by Ramy Elgammal · 2 years ago
- e54d8c0 Fix performance regression in ClConv2D by Gian Marco Iodice · 2 years ago
- cec1af5 Fix performance regression in Conv2D on OpenCL by Adnan AlSinan · 2 years, 1 month ago
- cc03419 Disable unsafe FP optimizations in Winograd Output Transform by Gunes Bayir · 2 years, 1 month ago
- 0105ce5 Fix LeNet-f16 convolution regression by Adnan AlSinan · 2 years, 1 month ago
- e572dff Add GemmLowp MMUL Reshaped Only Rhs Support for QASYMM8/QASYMM8_SIGNED by Freddie Liardet · 2 years, 3 months ago
- e871207 Update ClConv2D heuristic to use direct convolution by Adnan AlSinan · 2 years, 1 month ago
- 4bfc70e Add Gemm MMUL Reshaped Only Rhs Support for FP32/FP16 by Gunes Bayir · 2 years, 9 months ago
- 2cc50b3 Extended direct conv 2d interface for tuning the OpenCl kernel by Gian Marco Iodice · 2 years, 3 months ago
- d8804fd Fix OpenCL Winograd output transform by Gian Marco Iodice · 2 years, 2 months ago
- 0c68704 Fix performance regression in Winograd Output Transform (OpenCL) by Gian Marco Iodice · 2 years, 2 months ago
- fdb5342 Disable unsafe FP optimizations causing accuracy issues by Gunes Bayir · 2 years, 3 months ago
- 4e9f568 Fix inclusion guard for dynamic fusion module by SiCong Li · 2 years, 4 months ago
- b63b119 Integrate Dynamic Fusion patches by SiCong Li · 2 years, 7 months ago
- 5e549fa Add CLPool3d Int8 Support by Mohammed Suhail Munshi · 2 years, 5 months ago
- 0a486cf Enable dynamic cl tuning for dynamically fused kernels by SiCong Li · 2 years, 5 months ago
- ca364df Include missing embedded headers by SiCong Li · 2 years, 5 months ago
- 16c5697 Add DirectConvolution2D kernel component for dynamic fusion by Gunes Bayir · 2 years, 5 months ago
- 892b70a Fix embedded kernel header inclusion for dynamic fusion by Giorgio Arena · 2 years, 5 months ago
- 3751569 Implementation of ClPooling3d by ramelg01 · 2 years, 6 months ago
- 232c452 Merge kernel prototype patch by Giorgio Arena · 2 years, 6 months ago
- 51d7119 Fix performance regression on Arm(R) Mali(TM)-G71 by Gian Marco Iodice · 2 years, 6 months ago
- 89aa4eb Improve start-up time for concatenation layers by ramelg01 · 2 years, 7 months ago
- 616f8eb Fix performance regression on the first layer of convolution-based model by Gian Marco Iodice · 2 years, 7 months ago
- bb6877a Improve start-up time for winograd_output_transform_*_nhwc by ramelg01 · 2 years, 7 months ago
- 6863fa0 Remove deprecated remap functions. by Adnan AlSinan · 2 years, 7 months ago
- 2a86a30 Improve start-up time for winograd_input_transform_*_nhwc by ramelg01 · 2 years, 7 months ago
- ba8690b Improve start-up time for winograd_filter_transform_*_nhwc by ramelg01 · 2 years, 7 months ago
- 451c309 Revert "Rework gemm_mm_reshaped_only_rhs_ kernels with new macros" by Ramy Elgammal · 2 years, 7 months ago
- 10e88a7 Rework gemm_mm_reshaped_only_rhs_ kernels with new macros by Gian Marco Iodice · 2 years, 9 months ago
- 0bae3ee Fix heuristic in ClConv2D by Gian Marco Iodice · 2 years, 7 months ago
- b181263 Enabled support for QASYMM8 in ClCastKernel by Pablo Marquez Tello · 2 years, 8 months ago
- c4270cf Add tests for FP Cpu Pooling where pool region is completely outside the input by SiCongLi · 2 years, 8 months ago
- 3e155a5 Rework gemm_reshape_lhs_ with new macros by Adnan AlSinan · 2 years, 9 months ago
- 3012435 Remove padding from ClDirectConv2dKernel by Adnan AlSinan · 2 years, 9 months ago
- 8d07127 Use #if directive instead of regular condition in CLDirectConv2D by Giorgio Arena · 2 years, 9 months ago
- 78baa48 Improve start-up direct convolution on OpenCL by Gian Marco Iodice · 2 years, 9 months ago
- 4fb5670 Rework gemm_reshape_rhs_(nt,t) with new macros by Gian Marco Iodice · 2 years, 10 months ago
- 9cca592 Improve start-up timer for GeMM (floating-point): by ramelg01 · 2 years, 10 months ago
- e330fb4 Improve start-up timer for ClIm2Col by Giorgio Arena · 2 years, 9 months ago
- 3177861 Fix PostOp dependency by SiCongLi · 2 years, 10 months ago
- 17975a6 Improve start-up time for ClScale by Adnan AlSinan · 2 years, 10 months ago
- d928735 Add validate tests for CLConvolutionLayer and CLGEMMConvolutionLayer with post ops by SiCongLi · 2 years, 10 months ago