aboutsummaryrefslogtreecommitdiff
path: root/src/runtime
AgeCommit message (Expand)Author
2018-11-02COMPMID-1276 - Allow GEMM to work with 3D input tensorGian Marco Iodice
2018-11-02COMPMID-1359: (Nightly) CLCannyEdge failuresMichele Di Giorgio
2018-11-02COMPMID-1188 - Fixed get_convolution_method in CLConvolutionLayerGian Marco Iodice
2018-11-02COMPMID-1124: Validate CLLSTMGeorgios Pinitas
2018-11-02COMPMID-1440: Access original B in gemm assembly when not pretransposed.Georgios Pinitas
2018-11-02COMPMID-1434: Fix NEWinograd for NHWC and sub-tensorsGeorgios Pinitas
2018-11-02COMPMID-1386: Add FC convert weights on NEONGeorgios Pinitas
2018-11-02COMPMID-1401 Implement NEFullyConnectedLayer for QASYMM8Giorgio Arena
2018-11-02COMPMID-1347: Simplified CPUInfo enumAnthony Barbier
2018-11-02COMPMID-1419: Make NEGEMMAssemblyDispatch dynamically typed instead of templatedAnthony Barbier
2018-11-02COMPMID-1405: Create our own gemm_native kernel / function.Anthony Barbier
2018-11-02COMPMID-1347: Fixed fallback CPUInfo populate function and added latest CPUsAnthony Barbier
2018-11-02COMPMID-1386: Add support for converting weights for CL.Georgios Pinitas
2018-11-02COMPMID-1364: Add support for NHWC in NEDepthConcatenateLayerGeorgios Pinitas
2018-11-02COMPMID-1357: Stop passing around raw pointers in NEWinogradConvolutionAnthony Barbier
2018-11-02COMPMID-1357: Port NEWinogradConvolution to use NEGEMMAssemblyDispatchAnthony Barbier
2018-11-02COMPMID-1365: Add support for NHWC in CLDepthConcatenateLayerGeorgios Pinitas
2018-11-02COMPMID-1188: Fixes LSTM IO dimension requirements.Georgios Pinitas
2018-11-02COMPMID-1381: Fix nightly build failure on armv7Anthony Barbier
2018-11-02COMPMID-1381: Cleaned up the AssemblyHelper interfaceAnthony Barbier
2018-11-02COMPMID-1226 Extend CLMeanStdDev to support FP32 / FP16Michalis Spyrou
2018-11-02COMPMID-1388: Change default CLTuner to the one for the detected GPUGeorgios Pinitas
2018-11-02COMPMID-1167: Validation for NEDepthwiseConvolutionLayerAbe Mbise
2018-11-02COMPMID-1188 : Rename TNOX to Mali-G76Georgios Pinitas
2018-11-02COMPMID-1246: Fixed typo in MidgardTuner.h filenameAnthony Barbier
2018-11-02COMPMID-1124 : Fixes in CLLSTM layerGeorgios Pinitas
2018-11-02COMPMID-1339 - Implementing Winograd Convolution Layer 1x5 and 5x1 kernels on...Gian Marco Iodice
2018-11-02COMPMID-1246 Change CLLSTM in order to match android testsMichalis Spyrou
2018-11-02COMPMID-1246 Fix CLDeconvolution arguments when calculatingMichalis Spyrou
2018-11-02COMPMID-1355: OpenMP compilation is broken.Georgios Pinitas
2018-11-02COMPMID-970 : Remove QS8 / QS16 supportVidhya Sudhan Loganathan
2018-11-02COMPMID-1352: Disable support for 4D softmax layer.Georgios Pinitas
2018-11-02COMPMID-811 Add NHWC data format support for CL depthwise convolutionGiorgio Arena
2018-11-02COMPMID-1201 - Implementing Winograd Convolution Layer 1x3 and 3x1 kernels on...Gian Marco Iodice
2018-11-02COMPMID-1334 (Nightly) Fix std::bad_alloc error in 32-bit NEON runsGiorgio Arena
2018-11-02COMPMID-1345: Switched from using mutexes to atomics in the CPP SchedulerAnthony Barbier
2018-11-02COMPMID-809: Add NHWC data format on CLGEMMConvolutionLayer.Georgios Pinitas
2018-11-02COMPMID-1253: Nightly: Fix Canny Edge NEON failingMichele Di Giorgio
2018-11-02COMPMID-1293: Handle aligned allocationsGeorgios Pinitas
2018-11-02COMPMID-1287: Extending NEWinogradLayer test suitePablo Tello
2018-11-02COMPMID-1067 NEON RNN FP32 / FP16Michalis Spyrou
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
generated by cgit v1.2.1 (git 2.23.0) at 2024-06-17 14:04:10 +0000