aboutsummaryrefslogtreecommitdiff
path: root/src/core/NEON/kernels
AgeCommit message (Expand)Author
2020-01-28COMPMID-2985 add data_layout to PoolingLayerInfoSang-Hoon Park
2020-01-24COMPMID-2809 Added support for QASYMM8_SIGNED in NEUpsampleLayerLuca Foschiani
2020-01-23COMPMID-2772: Add support for QASYMM8_SIGNED in NEPoolingLayerManuel Bottini
2020-01-23COMPMID-2923 Integrate arm_gemm per channel quantizationMichalis Spyrou
2020-01-23COMPMID-3022 Fix NEON QASYMM8 Reduction OperationMichalis Spyrou
2020-01-17COMPMID-2985 change PoolingLayerInfo to structSang-Hoon Park
2020-01-16COMPMID-2994: Add support QASYMM8_SIGNED in NEComparisonOperationKernelmorgolock
2020-01-16COMPMID-2766: Add support for QASYMM8_SIGNED in NEDepthwiseConvolutionLayerMichele Di Giorgio
2020-01-15COMPMID-2819: Retain layout in NEIm2ColKernelGeorgios Pinitas
2020-01-14COMPMID-3006 (Nightly) Build failureMichalis Spyrou
2020-01-10COMPMID-2800: Add support for QASYMM8_SIGNED in NEDepthwiseConvolutionLayer3x...Michele Di Giorgio
2020-01-10COMPMID-2819: Fix offset in NEReductionOperationKernel.Pablo Tello
2020-01-10COMPMID-2799 Add support for QASYMM8_SIGNED in NECastLuca Foschiani
2020-01-09COMPMID-2753: Add support for QASYMM8_SIGNED in CL kernels/functionsManuel Bottini
2020-01-09COMPMID-2994: Add support QASYMM8_SIGNED in NEElementwiseMaxmorgolock
2020-01-08MLCE-139 add align_corners parameter to NEScaleSang-Hoon Park
2020-01-08COMPMID-2819: Fix data layout in NEScaleKernel for nhwc.Georgios Pinitas
2020-01-06COMPMID-2801: Add support for QASYMM8_SIGNED in NEDirectConvolutionLayerOutpu...Michele Di Giorgio
2020-01-06COMPMID-2999: Nighliy Build Failure [655] - Bare metal build for armv7Michele Di Giorgio
2019-12-30COMPMID-2979 Remove padding from NEWinogradLayermorgolock
2019-12-20COMPMID-2773 [NE] add support for QASYMM8_SIGNED to QuantizationLayerSang-Hoon Park
2019-12-20COMPMID-2608: Enable quantization with multiplier greater than 1 on NEONMichele Di Giorgio
2019-12-20COMPMID-2807: Add support for QASYMM8_SIGNED in NEGEMMMatrixVectorMultiplyKernelMichele Di Giorgio
2019-12-20COMPMID-2819: Retain data layout in NESpaceToDepth and NEDepthToSpaceGeorgios Pinitas
2019-12-20COMPMID-2819: Restrict cases where optimized NEPadLayer runs.Georgios Pinitas
2019-12-20COMPMID-2775 [NE] add support for QASYMM8_SIGNED to SoftmaxLayerSang-Hoon Park
2019-12-20COMPMID-2767 [NEON] add support for QASYMM8_SIGNED to DequantizationLayerSang-Hoon Park
2019-12-19COMPMID-2980 (Nightly) armv7a build failuresMichalis Spyrou
2019-12-19COMPMID-2819: Retain configuration step data layout to avoid side-effects.Pablo Tello
2019-12-19COMPMID-2819: Retain configuration step data layout to avoid side-effects.Georgios Pinitas
2019-12-18COMPMID-2819: Update data type auto_init in Elementwise kernels.Georgios Pinitas
2019-12-17COMPMID-2819: Perform sqrt in double domain for L2 pooling.Georgios Pinitas
2019-12-13COMPMID-2811: QASYMM8_SIGNED support in NEPixelwiseMultiplication.Pablo Tello
2019-12-11COMPMID-2819: Remove invalid check in NEDirectConvolutionLayerOutputStageKernelGeorgios Pinitas
2019-12-11COMPMID-2754: Add support for QASYMM8_SIGNED in NE kernels/functions.Georgios Pinitas
2019-12-11COMPMID-2841: Enable aarch32 buildsGeorgios Pinitas
2019-12-05COMPMID-2798 Add support for QASYMM8_SIGNED in NEArithmeticSubtractionMichalis Spyrou
2019-12-05COMPMID-2796: Add support for QASYMM8_SIGNED in NEActivationLayer and NEPRelu...Michalis Spyrou
2019-12-04COMPMID-2305: NEDepthwiseConvolution 3x3: support for QUANT8_PER_CHANNEL_SYMMGiuseppe Rossini
2019-12-04COMPMID-2764: Add support for QASYMM8_SIGNED in NEConvolutionLayer.Georgios Pinitas
2019-12-04COMPMID-2797 Add support for QASYMM8_SIGNED in NEArithmeticAdditionMichalis Spyrou
2019-12-03COMPMID-2819: Fix output stage kernel dispatch selection.Georgios Pinitas
2019-11-27COMPMID-2805: Add QASYMM8_SIGNED support in NEGEMMLowpOutputStageGeorgios Pinitas
2019-11-25IVGBENCH-1661: Segfault on FP16 for NEONGeorgios Pinitas
2019-11-25COMPMID-2700: Use NEON wrapper on SoftmaxLayerManuel Bottini
2019-11-21COMPMID-2920: NEInstanceNormalization fails on NHWC validationsManuel Bottini
2019-11-12COMPMID-2895: Remove QASYMM8_PER_CHANNEL data typeGeorgios Pinitas
2019-11-12COMPMID-2671 use Signed32 for default output data type of ArgMinMaxSang-Hoon Park
2019-11-08COMPMID-2452: Fix 32-bit per-channel convolution for NEON.Georgios Pinitas
2019-11-08COMPMID-2576: Fuse activation in Winograd output transform.Pablo Tello
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-20 20:16:16 +0000