aboutsummaryrefslogtreecommitdiff
path: root/src/core/CL/cl_kernels
AgeCommit message (Expand)Author
2018-11-02COMPMID-706 - Add GEMMLowp output stage for scaling by a fixed point numberGian Marco
2018-11-02COMPMID-684: 2D In-Map normalization support for CLGeorgios Pinitas
2018-11-02COMPMID-661: QASYMM8 support for fully connected layer.Georgios Pinitas
2018-11-02COMPMID-713: Address failures in OCLGrind for CLDirectConvolutionGeorgios Pinitas
2018-11-02COMPMID-712: OCLGrind CLSoftmaxLayer quantized failuresGeorgios Pinitas
2018-11-02COMPMID-714: Resolve failures in OCLGrind for CLPhaseGeorgios Pinitas
2018-11-02COMPMID-697 - Rework GEMMLowp interface on OpenCLGian Marco
2018-11-02COMPMID-556 Improved indentation and error handling in format_doxygen.pyAnthony Barbier
2018-11-02COMPMID-556 Add saturation to 8-bit activation. This prevents undefined overflowRob Hughes
2018-11-02COMPMID-661: Fix scale border issue (#38)Daniil Efremov
2018-11-02COMPMID-661: Optimize FC layer with 2 new Bifrost kernels and LWS tuning (#33)Anton Lokhmotov
2018-11-02COMPMID-661: Add QASYMM8 support (and basic tests) to CLDepthwiseConvolution3...Dmitry Savenko
2018-11-02COMPMID-556: Fixes bias in CLDirectConvolutionLayer to be int32.Georgios Pinitas
2018-11-02COMPMID-661: issue# 23 Scale border fix (#26)Daniil Efremov
2018-11-02APPBROWSER-298, APPBROWSER-306: Reimplement the common code of compute shaderJoel Liang
2018-11-02COMPMID-556: Fix CLNormalization issues.Georgios Pinitas
2018-11-02COMPMID-661: Fix rounding in average pooling for uint8.Georgios Pinitas
2018-11-02COMPMID-661: softmax-uint8 implementation (#16)Chunosov
2018-11-02COMPMID-631: Merge branches/gles_compute branchAnthony Barbier
2018-11-02COMPMID-661: Fix beta in softmax_layer kernelGeorgios Pinitas
2018-11-02COMPMID-661: Add avgpool-uint8 support. Optimize avgpool-fp32 for Bifrost. (#13)Anton Lokhmotov
2018-11-02COMPMID-661: softmax-fp32 optimisation (#14)Chunosov
2018-11-02COMPMID-661: directconv-uint8 (#20)Chunosov
2018-11-02Allow running without cl_khr_fp16Matthew Bentham
2018-11-02COMPMID-647: Exclude padding pixels from averaging factor.Georgios Pinitas
2018-11-02IVGCVSW-619: Support for Cl u8 bounded ReluMichel Iwaniec
2018-11-02COMPMID-648: Fix initial value for MAX pooling for QS types in CL.Georgios Pinitas
2018-11-02COMPMID-643: Add bias to CLDepthwiseConvolution.Georgios Pinitas
2018-11-02COMPMID-640: FullyConnectedLayer failures on both NEON/CLGeorgios Pinitas
2018-11-02COMPMID-556: Fix CLPoolingLayer checksGeorgios Pinitas
2018-11-02IVGCVSW-601: support for asymetric padding in cl conv and depthwise convJaroslaw Rzepecki
2018-11-02IVGCVSW-632 CL support for Softmax beta parameterPablo Palmier
2018-11-02COMPMID-606 - Fix for S8 failuresGian Marco Iodice
2018-11-02COMPMID417 - Fix illegal scalar access in color_convert.clGian Marco Iodice
2018-11-02COMPMID-545 add CL printf supportsteniu01
2018-11-02COMPMID-417 - Added validation for FP16 CLBatchNormalizationLayerGian Marco Iodice
2018-11-02COMPMID-424 Implemented reference implementation and tests for WarpAffineIsabella Gottardi
2018-11-02COMPMID-417: Fix CL compiler warningsMoritz Pflanzer
2018-11-02COMPMID-541: Fix padding in CLMinMaxLocationKernelMoritz Pflanzer
2018-11-02COMPMID-515: L2 Pooling for FP32/FP16 in CL.Georgios Pinitas
2018-11-02COMPMID-516 Increase tolerance rate of Scale, Conv, fully connected and GEMMsteniu01
2018-11-02COMPMID-452 CL Generic Depthwise Convolution implementation.Giorgio Arena
2018-11-02COMPMID-522 - Added support for GlobalPooling in CLPoolingLayer and CLFlatten...Gian Marco Iodice
2018-11-02COMPMID-417: Fix CLNonLinearFilterGeorgios Pinitas
2018-11-02COMPMID-462: Implement TensorReshape for NEON and CL.Georgios Pinitas
2018-11-02COMPMID-448: Implement CL Quantization/Dequantization Layer.Michele Di Giorgio
2018-11-02COMPMID-477 - Optimized CLDirectConvolution1x1 for BifrostGian Marco Iodice
2018-11-02COMPMID-417 Fix ROIPoolingSiCong Li
2018-11-02COMPMID-519: Add support for Lower and Upper Bounded RELU for CL/NEONGeorgios Pinitas
2018-11-02COMPMID-424 Implemented reference implementation, new output valid region and...Isabella Gottardi