aboutsummaryrefslogtreecommitdiff
path: root/src/runtime
AgeCommit message (Expand)Author
2018-11-02COMPMID-746 Allow NEDirectConvolution to work without biases for QS.Michalis Spyrou
2018-11-02COMPMID-773: Add CL/NEON Harris Corners benchmark testsAlex Gilday
2018-11-02COMPMID-750: Enabled support for U8 and S8 datatypes in NEGEMMLowpAArch64V8P4...Pablo Tello
2018-11-02APPBROWSER-366: Add DepthwiseConvolutionLayer(fp16 only) support.Frank Lei
2018-11-02COMPMID-719: NEWinogradLayer reordering using NEPermute.Pablo Tello
2018-11-02COMPMID-767 : Propagate hints to subgraph.Georgios Pinitas
2018-11-02COMPMID-617 Add validation to NEConvolutionLayerGiorgio Arena
2018-11-02APPBROWSER-356: Implement GCArithmeticAddition Operatorzhenglin
2018-11-02COMPMID-617: Adds CLFullyConnectionLayer validation supportGeorgios Pinitas
2018-11-02APPBROWSER-230, APPBROWSER-300: Rename GCScheduler enqueue to dispatch, sync ...Joel Liang
2018-11-02APPBROWSER-359: Sync tensor in GC benchmark testsJoel Liang
2018-11-02APPBROWSER-341: Add ResizeNearest operator supportFrank Lei
2018-11-02Fix destruction order of singleton objects and resolve hang GLES issue.Ioan-Cristian Szabo
2018-11-02APPBROWSER-304,342: Add exclude padding support for OpenGL ES implementation ...Xinghang Zhou
2018-11-02APPBROWSER-340: Implement NormalizePlanarYUV operatorzhenglin
2018-11-02COMPMID-750: Fix assembly kernel interfacesGeorgios Pinitas
2018-11-02COMPMID-556: Fix NEConvolutionLayer for fully connected convolution.Georgios Pinitas
2018-11-02COMPMID-556 - Enabled optimized path for Bifrost in CLGEMMGian Marco
2018-11-02COMPMID-556: Fix bugs around NEDirectConvolutionLayerGeorgios Pinitas
2018-11-02COMPMID-556 - Fix examplesGian Marco
2018-11-02COMPMID-556 Fixed validate for Dot product MatrixMultiplyCoreAnthony Barbier
2018-11-02COMPMID-617 Add validation methods to KernelsMichalis Spyrou
2018-11-02COMPMID-556: Rename Error to Status and inverse logicGeorgios Pinitas
2018-11-02IVGCVSW-631 Neon support for Softmax beta parameter (F32 only)Pablo Palmier
2018-11-02COMPMID-617 Add window validation to CLDirectConvolutionLayerGiorgio Arena
2018-11-02COMPMID-728 - Added validation for transposeGian Marco
2018-11-02APPBROWSER-313: Performance improvement for softmax layerJoel Liang
2018-11-02COMPMID-661: Convolution quantized (#32)Chunosov
2018-11-02COMPMID-617: Add validate support for NEON ArithmeticLayerIoan-Cristian Szabo
2018-11-02COMPMID-632: Make sure we hit the dot product kernel for cpu 0xd0f on the fas...Pablo Tello
2018-11-02COMPMID-722 - Support for vector-matrix in GEMMLowp (NEON)Gian Marco
2018-11-02COMPMID-556: Added a rounding policy to the quantize functionJaroslaw Rzepecki
2018-11-02COMPMID-700: Adds CPPPermute functionGeorgios Pinitas
2018-11-02COMPMID-687: Winograd refactoringPablo Tello
2018-11-02COMPMID-661: Vectorize im2col and add lws heuristics for convolution kernels #46Anthony Barbier
2018-11-02COMPMID-692 Consistent names for the interfacesGiorgio Arena
2018-11-02COMPMID-706 - Add GEMMLowp output stage for scaling by a fixed point numberGian Marco
2018-11-02COMPMID-617: Add validate support for NEON PixelWiseMultiplicationIoan-Cristian Szabo
2018-11-02COMPMID-687: Winograd layer.Pablo Tello
2018-11-02COMPMID-661: QASYMM8 support for fully connected layer.Georgios Pinitas
2018-11-02COMPMID-617: Add validate support for NEON BatchNormalizationLayer.Ioan-Cristian Szabo
2018-11-02COMPIMID-553: MobileNet use case.Georgios Pinitas
2018-11-02Fix border handler for CLDepthwiseConvolution3x3Diego Lopez Recas
2018-11-02COMPMID-713: Address failures in OCLGrind for CLDirectConvolutionGeorgios Pinitas
2018-11-02COMPMID-661 Add Bifrost lws heuristics for several depthwise_convolution kern...Anthony Barbier
2018-11-02COMPMID-617: Add validation to NEON functions.Georgios Pinitas
2018-11-02COMPMID-632: Integrated Assembly kernel GEMM U8 for Arm Cortex-A53.Michalis Spyrou
2018-11-02COMPMID-697 - Rework GEMMLowp interface on OpenCLGian Marco
2018-11-02COMPMID-699 - Add NEON functions for im2col and col2imGian Marco
2018-11-02COMPMID-632: Integrated Assembly kernel GEMM S8 for Arm Cortex-A53.Pablo Tello