diff options
| author | Sheri Zhang <sheri.zhang@arm.com> | 2020-10-26 15:46:37 +0000 |
|---|---|---|
| committer | Sheri Zhang <sheri.zhang@arm.com> | 2020-11-12 15:11:49 +0000 |
| commit | 824061d9910ebb42cbe46b677c0b843db212c9a2 (patch) | |
| tree | f94398a9b84d892afe673543456b9e7084ef5dce | |
| parent | 2d1a835b68eb27a800838fc2b563b12eddf2c19f (diff) | |
| download | ComputeLibrary-824061d9910ebb42cbe46b677c0b843db212c9a2.tar.gz | |
COMPMID-3881: Update remove OpenCL padding 20.11 documentation
Signed-off-by: Sheri Zhang <sheri.zhang@arm.com>
Change-Id: Id6768534c762d8c29a9e1de745a711fa718761cf
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4286
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
| -rw-r--r-- | docs/00_introduction.dox | 40 |
1 files changed, 39 insertions, 1 deletions
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index c1c9af467d..2ecb13fc40 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -104,7 +104,9 @@ v20.11 Public major release - @ref CLSoftmaxLayer - @ref CLLogSoftmaxLayer - @ref GCSoftmaxLayer - - Removed padding from: + - New OpenCL kernels / functions: + - @ref CLGEMMLowpQuantizeDownInt32ScaleByFixedPointKernel + - Removed padding from NEON kernels: - @ref NEComplexPixelWiseMultiplicationKernel - @ref NENonMaximaSuppression3x3Kernel - @ref NERemapKernel @@ -123,6 +125,42 @@ v20.11 Public major release - @ref NEReductionOperationKernel - @ref NEGEMMLowpMatrixAReductionKernel - @ref NEGEMMLowpMatrixBReductionKernel + - Removed padding from OpenCL kernels: + - @ref CLBatchConcatenateLayerKernel + - @ref CLElementwiseOperationKernel + - @ref CLBatchNormalizationLayerKernel + - @ref CLPoolingLayerKernel + - @ref CLWinogradInputTransformKernel + - @ref CLGEMMLowpMatrixMultiplyNativeKernel + - @ref CLGEMMLowpMatrixAReductionKernel + - @ref CLGEMMLowpMatrixBReductionKernel + - @ref CLGEMMLowpOffsetContributionOutputStageKernel + - @ref CLGEMMLowpOffsetContributionKernel + - @ref CLWinogradOutputTransformKernel + - @ref CLGEMMLowpMatrixMultiplyReshapedKernel + - @ref CLFuseBatchNormalizationKernel + - @ref CLDepthwiseConvolutionLayerNativeKernel + - @ref CLDepthConvertLayerKernel + - @ref CLCopyKernel + - @ref CLDepthwiseConvolutionLayer3x3NHWCKernel + - @ref CLActivationLayerKernel + - @ref CLWinogradFilterTransformKernel + - @ref CLWidthConcatenateLayerKernel + - @ref CLWidthConcatenate4TensorsKernel + - @ref CLWidthConcatenate2TensorsKernel + - @ref CLLogits1DMaxShiftExpSumKernel + - @ref CLLogits1DNormKernel + - @ref CLHeightConcatenateLayerKernel + - @ref CLGEMMMatrixMultiplyKernel + - @ref CLGEMMLowpQuantizeDownInt32ScaleKernel + - @ref CLGEMMLowpQuantizeDownInt32ScaleByFloatKernel + - @ref CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel + - @ref CLDepthConcatenateLayerKernel + - @ref CLGEMMLowpQuantizeDownInt32ScaleByFixedPointKernel + - Removed OpenCL kernels / functions: + - CLGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPointKernel + - CLGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel + - CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel - Deprecated OpenCL kernels / functions (If a kernel is used only by the function that is being deprecated, the kernel is deprecated together): - CLLocallyConnectedLayer - CLLocallyConnectedMatrixMultiplyKernel |