aboutsummaryrefslogtreecommitdiff
path: root/src
AgeCommit message (Expand)Author
2019-11-08COMPMID-2576: Fuse activation in Winograd output transform.Pablo Tello
2019-11-06COMPMID-2308: NEConvolutionLayer: support QUANT8_SYMM_PER_CHANNEL filtersGeorgios Pinitas
2019-11-06COMPMID-2862: remove forward declaration of ReductionOperationSang-Hoon Park
2019-11-01COMPMID-2549: Add GLES Runtime Context interfaces.Georgios Pinitas
2019-11-01COMPMID-2672: add comments for OpenCL helper macrosSang-Hoon Park
2019-10-31COMPMID-2266: [CL] add support for Log SoftmaxSang-Hoon Park
2019-10-30COMPMID-1671: Allow fp mixed precision in CLFCLayer.Georgios Pinitas
2019-10-30COMPMID-2707: add keep_dims parameter to Reduction OperationSang-Hoon Park
2019-10-30COMPMID-2306: CLDepthwiseConvolution: support for QUANT8_PER_CHANNEL_SYMMMichele Di Giorgio
2019-10-29COMPMID-1889: Fuse bias addition and output stage in CLFCLayer.Georgios Pinitas
2019-10-28MLCE-146: VTS failures A55Pablo Tello
2019-10-26COMPMID-2588: Optimize the output detection kernel required by MobileNet-SSD ...Giuseppe Rossini
2019-10-25COMPMID-2481: Add InputQuantizationInfo!=OutputQuantization Info tests for De...Manuel Bottini
2019-10-24COMPMID-2501: Support multiplier > 1 during QASYMM8 requantization for Quanti...Manuel Bottini
2019-10-23COMPMID-2515: Merge optimized depthwise convolution to the generic depthwise ...Manuel Bottini
2019-10-23COMPMID-2577: Fuse bias addition and activation in gemm assembly kernelsGeorgios Pinitas
2019-10-22COMPMID-2452: Fix CLDepthwiseConvolutionLayerNativeKernelMichele Di Giorgio
2019-10-21COMPMID-2708 NEDepthwiseConvolution Generic: support for QUANT8_PER_CHANNEL_SYMMGiorgio Arena
2019-10-21COMPMID-2744 [CL] add support for 9x9 quantized direct convolutionSang-Hoon Park
2019-10-18COMPMID-2486: Fix bare metal buildsMichalis Spyrou
2019-10-18Revert "COMPMID-1816: Use parallel reduction on 0 axis in CL ARG_MIN/ARG_MAX"Manuel Bottini
2019-10-18Revert "COMPMID-2742: [CL] ArgMinMax clCreateKernel error"Manuel Bottini
2019-10-17COMPMID-2486: Remove/add disabled compiler warningsMichalis Spyrou
2019-10-17COMPMID-2813: Update the heuristic in CLDepthWiseConvolutionLayerGian Marco Iodice
2019-10-16COMPMID-2265 add support for Log Softmax to NEONSang-Hoon Park
2019-10-16COMPMID-2486: Remove disabled compiler warningsMichalis Spyrou
2019-10-16COMPMID-2741: [CL] GEMMMatrixMultiplyReshaped clCreateKernel ErrorGeorgios Pinitas
2019-10-15COMPMID-2205: CL runtime context.Pablo Tello
2019-10-15COMPMID-2600: Implement a new and generic depthwise convolution for CL QASYMM...Michele Di Giorgio
2019-10-14COMPMID-2742: [CL] ArgMinMax clCreateKernel errorManuel Bottini
2019-10-11COMPMID-2743: Mark 9x9 quantized direct convolutions as unsupported in CLGeorgios Pinitas
2019-10-11COMPMID-2697: Dynamic Tensors Type2 test caseGeorgios Pinitas
2019-10-11COMPMID-2452: Remove unnecessary checks from CLWinogradOutputTransformKernelMichele Di Giorgio
2019-10-08COMPMID-2486: Remove disabled compiler warningsMichalis Spyrou
2019-10-07COMPMID-2452: Mismatches FP16 in CL InstanceNormalizationManuel Bottini
2019-10-04COMPMID-2572: Update the heuristic in CLGEMM for FP16Gian Marco Iodice
2019-10-04COMPMID-1816: Use parallel reduction on 0 axis in CL ARG_MIN/ARG_MAXManuel Bottini
2019-10-03COMPMID-2685: [CL] Use Weights managerMichalis Spyrou
2019-10-02COMPMID-2661: Implement complex function dynamic tensor support.Georgios Pinitas
2019-10-02COMPMID-2257: Add support for QASYMM8 in NEGenerateProposalsMichele Di Giorgio
2019-10-01COMPMID-2699: Add support for QASYMM16 in NEQuantizationLayerMichele Di Giorgio
2019-10-01COMPMID-2313: Implement CL INSTANCE_NORMALIZATION functionManuel Bottini
2019-10-01COMPMID-2693 Weights manager to mark the initial weights as unsuedMichalis Spyrou
2019-10-01COMPMID-2645: Detection Post-Process fixesGeorgios Pinitas
2019-10-01INFPRF-609:Performance Issue of the Latest ArmCLgiuros01
2019-10-01COMPMID-2601 [CL] add mixed precision support to PoolingLayerSang-Hoon Park
2019-10-01COMPMID-2592 Create a new kernel for CLPad with SYMMETRIC and REFLECT modeGiorgio Arena
2019-10-01COMPMID-2581: Fuse batch normalization with convolution and depthwise convolu...giuros01
2019-09-30COMPMID-2452: Dot product optimizations on merge/transformsGeorgios Pinitas
2019-09-30COMPMID-2671: Change ArgMinMax NEON/CL output type to Signed32Michele Di Giorgio
generated by cgit v1.2.1 (git 2.23.0) at 2024-04-29 15:40:44 +0000