COMPMID-1987: 19.02 Release notes
Change-Id: I7799e9e7ec4f68222fc7bc6ac8536e4b5cea1107
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
Reviewed-on: https://review.mlplatform.org/671
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox
index aeb8a3d..f722836 100644
--- a/docs/00_introduction.dox
+++ b/docs/00_introduction.dox
@@ -239,6 +239,86 @@
@subsection S2_2_changelog Changelog
v19.02 Public major release
+ - Various bug fixes.
+ - Various optimisations.
+ - New Neon kernels / functions:
+ - @ref NETileKernel / @ref NETile
+ - @ref NEFuseBatchNormalizationKernel / @ref NEFuseBatchNormalization
+ - @ref NEElementwiseOperationKernel
+ - @ref NEElementwiseMax
+ - @ref NEElementwiseMin
+ - @ref NEElementwiseSquaredDiff
+ - @ref NESelectKernel / @ref NESelect
+ - @ref NESplit
+ - @ref NESlice
+ - @ref NEUnstack
+ - @ref NEStridedSliceKernel / @ref NEStridedSlice
+ - @ref NEElementwiseUnaryKernel
+ - @ref NERsqrtLayer
+ - @ref NEExpLayer
+ - @ref NEReverseKernel / @ref NEReverse
+ - @ref NEArgMinMaxLayer
+ - @ref NEStackLayerKernel / @ref NEStackLayer
+ - @ref NERangeKernel / @ref NERange
+ - @ref NEPadLayer
+ - @ref NEMemsetKernel
+ - @ref NEGatherKernel / @ref NEGather
+ - @ref NEElementwiseComparison
+ - @ref NEElementwiseComparisonStatic
+ - @ref NEComparisonOperationKernel
+ - @ref NEElementwiseDivision
+ - New OpenCL kernels / functions:
+ - @ref CLSelectKernel / @ref CLSelect
+ - @ref CLTileKernel / @ref CLTile
+ - @ref CLComparisonKernel / @ref CLComparison
+ - @ref CLArgMinMaxLayer
+ - @ref CLElementwiseMax
+ - @ref CLElementwiseMin
+ - @ref CLElementwiseSquaredDiff
+ - @ref CLStackLayerKernel / @ref CLStackLayer
+ - @ref CLReverse / @ref CLReverseKernel
+ - @ref CLRsqrtLayer
+ - @ref CLExpLayer
+ - @ref CLElementWiseUnaryLayerKernel
+ - @ref CLGEMMReshapeLHSMatrixKernel
+ - @ref CLGEMMReshapeRHSMatrixKernel
+ - @ref CLGEMMMatrixMultiplyReshapedKernel
+ - @ref CLRangeKernel / @ref CLRange
+ - @ref CLUnstack
+ - @ref CLGatherKernel / @ref CLGather
+ - @ref CLGEMMLowpMatrixMultiplyReshapedKernel
+ - New CPP kernels / functions:
+ - @ref CPPDetectionOutputLayer
+ - @ref CPPTopKV / @ref CPPTopKVKernel
+ - @ref CPPNonMaximumSuppression
+ - Added new examples:
+ - graph_ssd_mobilenet.cpp
+ - graph_mobilenet_v2.cpp
+ - graph_resnet12.cpp
+ - graph_srcnn955.cpp
+ - graph_vgg_vdsr.cpp
+ - graph_inception_resnet_v1.cpp
+ - Add 4D tensors support to
+ - @ref NESoftmaxLayer
+ - Fused activation in @ref CLWinogradConvolutionLayer
+ - Extented @ref NEPermute to support more cases
+ - Added NEON/SVE GEMM Hybrid kernels
+ - Added u8 and s8 hybrid assembly kernels
+ - Introduced GEMM strategy name in NEGEMMAssemblyWrapper
+ - Improved @ref CLTuner
+ - Fused the bias addition within @ref CLGEMM
+ - Added support for QASYMM8 LOGISTIC activation in @ref NEActivationLayer
+ - Added NHWC data layout support to:
+ - @ref NEScale for F16
+ - @ref CLNormalizationLayer IN_MAP_2D for FP32/FP16
+ - @ref NEL2NormalizeLayer for FP32/FP16
+ - @ref NENormalizationLayer IN_MAP_2D for FP32/FP16
+ - @ref CLROIAlignLayer
+ - @ref CLGenerateProposalsLayer
+ - Added QASYMM8 support to the following kernels:
+ - @ref NEArithmeticAdditionKernel
+ - @ref NEScale
+ - Added new tests and improved validation and benchmarking suites.
- Deprecated functions/interfaces
- Usage of inner_border_right and inner_border_top has been deprecated in @ref CLDeconvolutionLayer and @ref NEDeconvolutionLayer