- cb0010b COMPMID-1102 : Enable the use of 4x4 tile sizes in neon implementation of winograd conv. by Vidhya Sudhan Loganathan · 6 years ago
- a8a4d9e COMPMID-959: Fixed typo in CLPermute::validate() by Anthony Barbier · 6 years ago
- 73d4aef COMPMID-948: Add validation to NEL2NormalizeLayer by John Richardson · 6 years ago
- 18557bb COMPMID-1152 OCLGrind: invalid read in pooling_layer_MxN_nhwc by Michalis Spyrou · 6 years ago
- 7b94c3e COMPMID-1139: Fix SIGSEGV in arm_compute_benchmark by Georgios Pinitas · 6 years ago
- b2d9ebb COMPMID-1149: (OCLGrind) Invalid read dwc_3x3 by Georgios Pinitas · 6 years ago
- 8422558 COMPMID-1150 : (OCLGrind) Kernel compilation error and assertion by Georgios Pinitas · 6 years ago
- 393fa4c COMPMID-814: NEScale NHWC support by Georgios Pinitas · 6 years ago
- 3e3b371 COMPMID-959: bugfix: CLDeconvolutionLayer::validate fails if bias==NULL (#439) by wr0112358 · 6 years ago
- 1b4cbc0 COMPMID-1142: (OCLGrind) Invalid read in batchnormalization_layer_nhwc by Georgios Pinitas · 6 years ago
- 01a214a COMPMID-1001 - Make the GEMM validation test more generic by Isabella Gottardi · 6 years ago
- 59631a1 COMPMID-1104 Add fast math hint in the graph API by Giorgio Arena · 6 years ago
- b8fc60f COMPMID-1086: Optimizing GCGEMM - Add helpers to get target GPU information by Michele Di Giorgio · 6 years ago
- 62385bc COMPMID-948: Add validation to CLL2NormalizeLayer by John Richardson · 6 years ago
- 657bdb3 COMPMID-1050 CL/NEON: Create a function to convert the 2D weights of FC layer from NHWC to NCHW and viceversa by Giorgio Arena · 6 years ago
- 3d1489d COMPMID-605: Transition buffer memory manager by Georgios Pinitas · 6 years ago
- 750641d COMPMID-1052 - Rework validate method in CLGEMM by Gian Marco Iodice · 6 years ago
- aa3240d COMPMID-959: Fixed Clang-tidy error by Anthony Barbier · 6 years ago
- e250389 COMPMID-810 Add NHWC data format support for NEON convolution by Michalis Spyrou · 6 years ago
- 79ffade COMPMID-1112: Enabled multithreading transforms in Winograd. by Pablo Tello · 6 years ago
- 7f4a819 COMPMID-597: Port HOGMultiDetection to new framework by John Richardson · 6 years ago
- 71ac9c0 COMPMID-1134: Fixing the Window reconstruction in gemm_native by Anthony Barbier · 6 years ago
- 5c2fb3f COMPMID-997: Add support for node's name in GraphAPI. by Georgios Pinitas · 6 years ago
- cac13b1 COMPMID-1097: Port mobilenet to NHWC by Georgios Pinitas · 6 years ago
- ad0c738 COMPMID-1068 Create validate method to CLDepthWiseConvolution by Giorgio Arena · 6 years ago
- d8cde85 COMPMID-959: Assembly kernel marks weights as unused when pretranspose by Georgios Pinitas · 6 years ago
- bb36a8e COMPMID-922 - CLGEMM FP16 optimizations - part2 by Gian Marco Iodice · 6 years ago
- 4dcb583 COMPMID-1122: Store the cl_context only in one place by Anthony Barbier · 6 years ago
- d24af8a COMPMID-1125: Add support for FP16 in CLDepthwiseConvolution by Michele Di Giorgio · 6 years ago
- 932b561 COMPMID-959: Perform pretranspose if allowed on NEON assembly by Georgios Pinitas · 6 years ago
- 4497e81 COMPMID-1123 - Enabling Winograd 2x2,3x3 and Winograd 4x4,3x3 without fast_math by Gian Marco Iodice · 6 years ago
- e043767 COMPMID-920: Introduce prepare() stage by Georgios Pinitas · 6 years ago
- 535fedd COMPMID-1117: TransposeAccessWindow leads to high padding by Georgios Pinitas · 6 years ago
- 7217563 COMPMID-1107: Add support for ChannelShuffle in CL by Michele Di Giorgio · 6 years ago
- c0f5443 COMPMID-808 Add NHWC data format support for NEON direct convolution by Giorgio Arena · 6 years ago
- 3c520c5 COMPMID-1089 CLPoolingLayer fix padding and add output shape computation to ShapeCalculator by Giorgio Arena · 6 years ago
- 6c42127 COMPMID-1105: Fix mismatches conv layer when using NativeGemm with multiple threads by Pablo Tello · 6 years ago
- 7657224 COMPMID-926 Add depth multiplier support to NEON/CL/GLES depthwise convolution by Giorgio Arena · 6 years ago
- e74b201 COMPMID-805 Add NHWC data format support for CL pooling by Michalis Spyrou · 6 years ago
- 2213d4b COMPMID-1096 - Add fast_math flag to CLConvolutionLayer by Gian Marco Iodice · 6 years ago
- ae70072 COMPMID-959: Fail when graph is already registered by Georgios Pinitas · 6 years ago
- edf357c COMPMID-1085 : runtime_error thrown by QASYMM8 CLGEMMConvolutionLayer::validate by Vidhya Sudhan Loganathan · 6 years ago
- b3b1e0b COMPMID-1010: Remove RSH profiler header by Georgios Pinitas · 6 years ago
- 57dac84 COMPMID-806 Add NHWC data format support format for NEON pooling by Michalis Spyrou · 6 years ago
- 6b06953 COMPMID-1087: Fix CLHOGDetector failure. by John Richardson · 6 years ago
- 9fb1159 COMPMID-1074: Rename WinograLayer.cpp to WinogradConvolutionLayer.cpp by Georgios Pinitas · 6 years ago
- 2b3129e COMPMID-1041 NEON Winograd: update function to use GEMM function by Michalis Spyrou · 6 years ago
- 99d4095 COMPMID-1023: Import memory for OpenCL by Georgios Pinitas · 6 years ago
- cda0c38 COMPMID-1080 - Fix CLFullyConnectedLayer validate() tests failing by Gian Marco Iodice · 6 years ago
- 84ce1f9 COMPMID-718 : Winograd: add validate method and tests by Vidhya Sudhan Loganathan · 6 years ago
- 3ca9786 COMPMID-718 : Winograd: add validate method and tests by Vidhya Sudhan Loganathan · 6 years ago
- bf3c662 COMPMID-803: Add NHWC data format support for CL batch normalisation by Michele Di Giorgio · 6 years ago
- 164b65d COMPMID-1043: Rework GCGEMMMatrixMultiplyKernel interface and allow auto initialization of the tensors by Michele Di Giorgio · 6 years ago
- 0cbb927 COMPMID-804: Add NHWC data format support for NEON batch normalisation by Michele Di Giorgio · 6 years ago
- 82b5148 COMPMID-959: Sets memory manager to CLWinograd by Georgios Pinitas · 6 years ago
- fda901f COMPMID-1078 Fix CL DepthwiseConvolutionLayer QASYMM8 failing validation by Giorgio Arena · 6 years ago
- f485a10 COMPMID-802 Fix NEIm2Col NHWC by Giorgio Arena · 6 years ago
- 48c19f1 COMPMID-959 Refactor OpenCL interceptors to use lambda functions by Anthony Barbier · 6 years ago
- d727e85 COMPMID-855: Get the library to work on non Mali GPUs by Anthony Barbier · 6 years ago
- e52a300 COMPMID-1026 - Add support for 4x4 output tile in CLWinogradConvolutionLayer by Gian Marco Iodice · 6 years ago
- dd03870 COMPMID-1037 Add support for F(4x4, 5x5) in CLWinogradOutputTransformKernel by Giorgio Arena · 6 years ago
- bb54e4e COMPMID-797 Integrate Mobilenet QASYMM8 with new graph. by Giorgio Arena · 6 years ago
- 4d33630 COMPMID-987: Make beta and gamma optional in BatchNormalization by Michele Di Giorgio · 6 years ago
- 1cd4149 COMPMID-577: Implement CL validation for GaussianPyramid by Sanghoon Lee · 6 years ago
- c9c62c2 COMPMID-1056 - Optimizing CLGEMMMatrixMultiplyKernel refactoring the inner loop by Gian Marco Iodice · 6 years ago
- 7da55aa COMPMID-959: Add accessors for the OpenCL program cache by Anthony Barbier · 6 years ago
- fd68311 COMPMID-922 - CLGEMM FP16 optimizations - part1 by Gian Marco Iodice · 6 years ago
- dfca60b COMPMID-811 Add NHWC data format support for CL depthwise convolution QASYMM8 by Giorgio Arena · 6 years ago
- fe5ef38 COMPMID-1037 Add support for F(4x4, 5x5) in CLWinogradInputTransformKernel by Giorgio Arena · 6 years ago
- f0cefbf COMPMID-959 - Fixing subtensor validation by Gian Marco Iodice · 6 years ago
- ecb1c62 COMPMID-959: Fixed order of init/destruction of CLSymbols / CLKernelLibrary by Anthony Barbier · 6 years ago
- 56e8e86 COMPMID-1031: Use LWS hints for G51, G51BIG, G51LIT, and TNOX by Sam Laynton · 6 years ago
- e7e96e0 COMPMID-1054 Update RSH's GEMM to add batch+multi support by Michalis Spyrou · 6 years ago
- 1ed1fc6 COMPMID-812 Add NHWC data format support for NEON depthwise convolution (optimized case). by Giorgio Arena · 6 years ago
- 9373c8b COMPMID-1037 Add support for F(4x4, 5x5) in CLWinogradFilterTransformKernel by Giorgio Arena · 6 years ago
- fc1d1e2 COMPMID-959: Add FP32 support to GLES GEMMConvolution by Michele Di Giorgio · 6 years ago
- a72300a COMPMID-1051 - Fix validate method in NEGEMMConvolutionLayer by Gian Marco Iodice · 6 years ago
- 95a3f55 COMPMID-959: Disabled winograd on Arm Cortex-A53 while we're working on a fix by Anthony Barbier · 6 years ago
- 5f0124d COMPMID-959: Fixed clang-tidy formatting, made GLES builds fail for standalone=1 by Anthony Barbier · 6 years ago
- ae3c8ab COMPMID-584: Add validation to channel_combine kernels by Ioan-Cristian Szabo · 7 years ago
- 156fcf3 COMPMID-802 Add NHWC data format support for NEON im2col. by Giorgio Arena · 6 years ago
- 8de9261 COMPMID-585: Port OpticalFlow to new validation by John Richardson · 6 years ago
- a1be5ba COMPMID-959: Number of threads was overwritten in benchmark_graph tests by Anthony Barbier · 6 years ago
- 50b2254 COMPMID-959 Removed assert on cpuid because valgrind always passes '-1' by Anthony Barbier · 6 years ago
- 247f52c COMPMID-1013 - Create WinogradInfo data structure by Gian Marco Iodice · 6 years ago
- eb8a399 COMPMID-994 : Check cl_arm_printf is supported in the CLScheduler by Vidhya Sudhan Loganathan · 6 years ago
- 3ebef32 COMPMID-949: Optimizing CLDepthwiseConvolution3x3Kernel for FP16 by Michele Di Giorgio · 6 years ago
- 4d9379a COMPMID-1040: Added support for nullptr bias tensor in NEWinogradLayer by Andrew Mundy · 6 years ago
- 3f217ec COMPMID-908 - Merge Activation layer with Convolution Layer (NEON. CL, GLES) by Isabella Gottardi · 6 years ago
- d9eb275 COMPMID-797: Switch to new graph. by Georgios Pinitas · 6 years ago
- c0d1c86 COMPMID-734: CLTuner rework by Georgios Pinitas · 6 years ago
- 7fad9b1 COMPMID-1021: CPUInfo refactoring. by Pablo Tello · 6 years ago
- 1562be3 COMPMID-998: Release unused trainable parameters. by Georgios Pinitas · 6 years ago
- 684cb0f COMPMID-596: Port HOGDetector to new validation by John Richardson · 6 years ago
- 7da29b6 COMPMID-1017: Implement dilated convolution in NEON, OpenCL, and GC by Alex Gilday · 6 years ago
- f92cb23 COMPMID-959: Collapse window in activation layer for GLES. by Georgios Pinitas · 6 years ago
- 81b28c4 COMPMID-1032 - Fixing bug in CLGEMM when is_interleaved_transposed=true by Gian Marco Iodice · 6 years ago
- 61b4fca COMPMID-959 Fix clang-tidy issue by Anthony Barbier · 6 years ago
- ceff0f9 COMPMID-1016: Optimize kernel reconfiguration by Georgios Pinitas · 6 years ago
- 7f7936a COMPMID-959 Fix race condition on info.thread_id in OpenMP scheduler (#399) by Simone Pellegrini · 6 years ago