aboutsummaryrefslogtreecommitdiff
path: root/src/runtime/NEON
AgeCommit message (Expand)Author
2018-11-02COMPMID-1451: Fix allocation of weights in DeconvolutionMichele Di Giorgio
2018-11-02COMPMID-1586: Add support for NHWC CLDeconvolutionLayerMichele Di Giorgio
2018-11-02COMPMID-1621 Deconvolution wrong output calculationMichalis Spyrou
2018-11-02COMPMID-1519: Add support for 3D input/output in CLGEMMLowpOutputStageGeorgios Pinitas
2018-11-02COMPMID-1596 Create UpsampleLayer for NEONMichalis Spyrou
2018-11-02COMPMID-1590: Memory corruption in arm_compute_validation.Pablo Tello
2018-11-02COMPMID-1540 Implement YOLOLayer on NEONMichalis Spyrou
2018-11-02COMPMID-1446 : Add support for 3D output in NEGEMMLowpOutputStageGeorgios Pinitas
2018-11-02COMPMID-1564: Add NEDepthwiseConvolution3x3 for QASYMM8Georgios Pinitas
2018-11-02COMPMID-1532: Add DepthwiseConvolution3x3 FP16 on NEONGeorgios Pinitas
2018-11-02COMPMID-1563: Fix name of NEGEMMInterleavedWrapperAnthony Barbier
2018-11-02COMPMID-1566: Add broadcast to CLArithmeticSubtractionGeorgios Pinitas
2018-11-02COMPMID-1563: Added a tag to ISCheduler::run_workloads to identify workloadsAnthony Barbier
2018-11-02COMPMID-1552: support kernels sizes 1x7, 7x1, 1x5, 5x1 in NEWinogradPablo Tello
2018-11-02COMPMID-1556 - Add ReorgLayer to graph APIGian Marco Iodice
2018-11-02[COMPMID-386] Github: Support SoftmaxLayer on different number of dimensions?giuros01
2018-11-02[COMPMID-1482] Auto-initialize the output tensor of im2col and col2im in NEGE...Giuseppe Rossini
2018-11-02COMPMID-1548: NEON FP16 mismatches on CannyEdge and HarrisCorners.Georgios Pinitas
2018-11-02COMPMID-1528: Add ReorgLayer on NEONGeorgios Pinitas
2018-11-02COMPMID-1514: Add validate to NEFloor and CLFloorGeorgios Pinitas
2018-11-02COMPMID-1247:Integrate kernel size 1x3 & 3x1 support in NEWinogradLayer.Pablo Tello
2018-11-02COMPMID-1469: Add validate in NEGEMMMatrixAdditionKernelGeorgios Pinitas
2018-11-02COMPMID-1304: NEDepthConvert : Add support for FP32 -> FP16 and FP16 -> FP32 ...Michele Di Giorgio
2018-11-02[COMPMID-1301] Add validate() method to NEReshapeLayerGiuseppe Rossini
2018-11-02COMPMID-1246 Fix NEON mobilenet NCHWGiorgio Arena
2018-11-02COMPMID-1534 - Fix GEMM and Magnitude test for FP16Gian Marco Iodice
2018-11-02COMPMID-1534: Fix LSTM/RNN Layers for NEON and FP16Georgios Pinitas
2018-11-02COMPMID-1047 Extract Flatten function from Im2Col for NEONGiorgio Arena
2018-11-02COMPMID-1188: Set all arguments to const in NEDepthwiseConvolutionLayer::vali...Georgios Pinitas
2018-11-02COMPMID-1060 LSTM FP32 NEONMichalis Spyrou
2018-11-02COMPMID-1480 Add support for NHWC QASYMM8/FP32(non-optimized) to NEON Depthwi...Giorgio Arena
2018-11-02COMPMID-1366 Implement NECopyMichalis Spyrou
2018-11-02COMPMID-1498 - Enable grouping in CLGEMMConvolutionLayerGian Marco Iodice
2018-11-02COMPMID-1246 Remove unused window iterator from NERNNLayer.Michalis Spyrou
2018-11-02COMPMID-1485 - Add support for NHWC when running NEGEMMConvolutionLayer with ...Gian Marco Iodice
2018-11-02COMPMID-1342 Add grouping support to CLIm2ColKernelGiorgio Arena
2018-11-02MLCE-13: Sanitizing matrix argument in the Warp.Pablo Tello
2018-11-02COMPMID-1188 - Removed the multiplication by 4 in NEGEMMInterleavedWrapperGian Marco Iodice
2018-11-02COMPMID-1277 - Optimizing CLIm2ColKernel for NHWC.Gian Marco Iodice
2018-11-02COMPMID-1248 Enabled memory manager in NEWinogradConvolutionLayerAnthony Barbier
2018-11-02COMPMID-1406: Refactor gemm_interleaved to use our own types and schedulerAnthony Barbier
2018-11-02COMPMID-872 - Rework NEGEMMConvolutionLayer to use NEGEMMGian Marco Iodice
2018-11-02MLCE-36: FC tranpose weightsGeorgios Pinitas
2018-11-02COMPMID-1188 - Fixed CLGEMMConvolutionLayer/NEGEMMConvolutionLayer for NHWCGian Marco Iodice
2018-11-02COMPMID-1445: Fixed NEON GEMM assembly dispatch for QASYMM8Anthony Barbier
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-1419: Make NEGEMMAssemblyDispatch dynamically typed instead of templatedAnthony Barbier
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-11 11:51:20 +0000