diff options
| author | Pablo Tello <pablo.tello@arm.com> | 2018-02-14 12:47:30 +0000 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:47:18 +0000 |
| commit | f6c572ce404c8ac99b0b00c65b757fbadab33dc1 (patch) | |
| tree | 0678208f2f333312095d0780c821097196091f87 /docs | |
| parent | 91d20d95df35961d3eb5de497007d98576118d19 (diff) | |
| download | ComputeLibrary-f6c572ce404c8ac99b0b00c65b757fbadab33dc1.tar.gz | |
COMPMID-784: Productise Winograd.
a) Added support for kernel size 5.
b) Templatised data type for transforms and batched gemms kernels.
Change-Id: Idb83dda7a5eec19e015888ab31902bd791913297
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/120540
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/00_introduction.dox | 11 |
1 files changed, 9 insertions, 2 deletions
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index 787b38dde0..c7faea7122 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -189,6 +189,13 @@ If there is more than one release in a month then an extra sequential number is @subsection S2_2_changelog Changelog +v18.02 Public maintenance release + - New NEON kernels / functions + - @ref arm_compute::NEWinogradLayerTransformInputKernel / @ref arm_compute::NEWinogradLayer + - @ref arm_compute::NEWinogradLayerTransformOutputKernel / @ref arm_compute::NEWinogradLayer + - @ref arm_compute::NEWinogradLayerTransformWeightsKernel / @ref arm_compute::NEWinogradLayer + - Renamed arm_compute::NEWinogradLayerKernel into @ref arm_compute::NEWinogradLayerBatchedGEMMKernel + v18.01 Public maintenance release - Various bug fixes - Added some of the missing validate() methods @@ -205,7 +212,7 @@ v18.01 Public maintenance release - @ref arm_compute::GCGEMMInterleave4x4Kernel - @ref arm_compute::GCGEMMTranspose1xWKernel - @ref arm_compute::GCIm2ColKernel - - Refactored NEON Winograd (@ref arm_compute::NEWinogradLayerKernel) + - Refactored NEON Winograd (arm_compute::NEWinogradLayerKernel) - Added @ref arm_compute::NEDirectConvolutionLayerOutputStageKernel - Added QASYMM8 support to the following NEON kernels: - @ref arm_compute::NEDepthwiseConvolutionLayer3x3Kernel @@ -256,7 +263,7 @@ v17.12 Public major release - @ref arm_compute::NEGEMMLowpOffsetContributionKernel / @ref arm_compute::NEGEMMLowpMatrixAReductionKernel / @ref arm_compute::NEGEMMLowpMatrixBReductionKernel / @ref arm_compute::NEGEMMLowpMatrixMultiplyCore - @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel / @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint - @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8ScaleKernel / @ref arm_compute::NEGEMMLowpQuantizeDownInt32ToUint8Scale - - @ref arm_compute::NEWinogradLayerKernel / @ref arm_compute::NEWinogradLayer + - @ref arm_compute::NEWinogradLayer / arm_compute::NEWinogradLayerKernel - New OpenCL kernels / functions - @ref arm_compute::CLGEMMLowpOffsetContributionKernel / @ref arm_compute::CLGEMMLowpMatrixAReductionKernel / @ref arm_compute::CLGEMMLowpMatrixBReductionKernel / @ref arm_compute::CLGEMMLowpMatrixMultiplyCore |