aboutsummaryrefslogtreecommitdiff
path: root/src/runtime
AgeCommit message (Expand)Author
2018-11-02COMPMID-1145: (API) Introduce prepare() stage (NEON/CL/GLES)Georgios Pinitas
2018-11-02COMPMID-1180: Add support for bucket multi-threading (Part2)Anthony Barbier
2018-11-02COMPMID-911: Allow GEMM to work with 3D tensorsIsabella Gottardi
2018-11-02COMPMID-1222 Implementing CLArithmeticDivision - FP32 / FP16Michalis Spyrou
2018-11-02COMPMID-1162: Enable NHWC data layout support for NEWinogradConvolutionLayer ...Pablo Tello
2018-11-02COMPMID-1160 Turn Graph hints into heuristicsGiorgio Arena
2018-11-02COMPMID-1278: Make intermediate tensors resizable in CLSoftmaxLayer::validate()Michele Di Giorgio
2018-11-02COMPMID-1156: Allow memory reusage when trying to reallocate a smaller CLTensorMichele Di Giorgio
2018-11-02COMPMID-817: Tuner: Port kernels to new design.Georgios Pinitas
2018-11-02COMPMID-1257: Allow retaining weights in CLDeconvolutionLayerMichele Di Giorgio
2018-11-02COMPMID-1244: Allow retaining weights in CLGEMMConvolutionLayer and CLFullyCo...Michele Di Giorgio
2018-11-02COMPMID-1251 - Update GEMM's heuristic selection on OpenCLGian Marco Iodice
2018-11-02COMPMID-1209: Enable memory manager for the GEMM workspace bufferGeorgios Pinitas
2018-11-02COMPMID-813 Add NHWC data format support for CL scaleMichalis Spyrou
2018-11-02COMPMID-1180: Add support for bucket multi-threading (Part 1)Anthony Barbier
2018-11-02COMPMID-1182: printf doesn't workGeorgios Pinitas
2018-11-02COMPMID-568: Implement Canny edge function for CL/NEONAbe Mbise
2018-11-02COMPMID-1168: enabling memory manager for _gemm_output gives wrong resultsGeorgios Pinitas
2018-11-02COMPMID-1038: stoi and stoul cleanup.Pablo Tello
2018-11-02COMPMID-1176: Add FP16 support in CLDeconvolutionLayer.Georgios Pinitas
2018-11-02COMPMID-1163: NEON Scale NHWC failuresGeorgios Pinitas
2018-11-02COMPMID-959 - Fix Validate in Convolution LayerIsabella Gottardi
2018-11-02COMPMID-993 Implement CL LSTM functionMichalis Spyrou
2018-11-02COMPMID-1106 Add fast math support in NEWinogradConvolutionLayerGiorgio Arena
2018-11-02COMPMID-814: Add validate method to scale.Georgios Pinitas
2018-11-02COMPMID-1166: Fixed alpha/beta mixup for some merges.David Mansell
2018-11-02COMPMID-1137 OpenCL concatenate widthMichalis Spyrou
2018-11-02COMPMID-792 - Re-enabled Winograd on NEON in all graph examples.Gian Marco Iodice
2018-11-02COMPMID-1102 : Enable the use of 4x4 tile sizes in neon implementation of win...Vidhya Sudhan Loganathan
2018-11-02COMPMID-959: Fixed typo in CLPermute::validate()Anthony Barbier
2018-11-02COMPMID-948: Add validation to NEL2NormalizeLayerJohn Richardson
2018-11-02COMPMID-814: NEScale NHWC supportGeorgios Pinitas
2018-11-02COMPMID-959: bugfix: CLDeconvolutionLayer::validate fails if bias==NULL (#439)wr0112358
2018-11-02COMPMID-1086: Optimizing GCGEMM - Add helpers to get target GPU informationMichele Di Giorgio
2018-11-02COMPMID-948: Add validation to CLL2NormalizeLayerJohn Richardson
2018-11-02COMPMID-1050 CL/NEON: Create a function to convert the 2D weights of FC layer...Giorgio Arena
2018-11-02COMPMID-605: Transition buffer memory managerGeorgios Pinitas
2018-11-02COMPMID-1052 - Rework validate method in CLGEMMGian Marco Iodice
2018-11-02COMPMID-810 Add NHWC data format support for NEON convolutionMichalis Spyrou
2018-11-02COMPMID-1068 Create validate method to CLDepthWiseConvolutionGiorgio Arena
2018-11-02COMPMID-959: Assembly kernel marks weights as unused when pretransposeGeorgios Pinitas
2018-11-02COMPMID-922 - CLGEMM FP16 optimizations - part2Gian Marco Iodice
2018-11-02COMPMID-1122: Store the cl_context only in one placeAnthony Barbier
2018-11-02COMPMID-1125: Add support for FP16 in CLDepthwiseConvolutionMichele Di Giorgio
2018-11-02COMPMID-959: Perform pretranspose if allowed on NEON assemblyGeorgios Pinitas
2018-11-02COMPMID-1123 - Enabling Winograd 2x2,3x3 and Winograd 4x4,3x3 without fast_mathGian Marco Iodice
2018-11-02COMPMID-920: Introduce prepare() stageGeorgios Pinitas
2018-11-02COMPMID-1107: Add support for ChannelShuffle in CLMichele Di Giorgio
2018-11-02COMPMID-808 Add NHWC data format support for NEON direct convolutionGiorgio Arena
2018-11-02COMPMID-926 Add depth multiplier support to NEON/CL/GLES depthwise convolutionGiorgio Arena
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-18 20:17:05 +0000