diff options
author | morgolock <pablo.tello@arm.com> | 2020-11-20 11:03:33 +0000 |
---|---|---|
committer | Pablo Marquez Tello <pablo.tello@arm.com> | 2020-11-21 09:02:36 +0000 |
commit | 0052078c7329a1bef7705c7d1e7603075e2a1a20 (patch) | |
tree | 272f0acaac8bde7dbc54c5c5fd472503502126f9 | |
parent | 26314d27c0ddfc175776da8ffc258b30d7f7ddf0 (diff) | |
download | ComputeLibrary-0052078c7329a1bef7705c7d1e7603075e2a1a20.tar.gz |
Update Release Notes 20.11
Change-Id: I0ca2928783d24a8fddd01f15ade796149be3434f
Signed-off-by: morgolock <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4165
Reviewed-by: SiCong Li <sicong.li@arm.com>
Tested-by: Georgios Pinitas <georgios.pinitas@arm.com>
-rw-r--r-- | docs/00_introduction.dox | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index 6b341fb0f0..3321b39992 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -87,6 +87,8 @@ If there is more than one release in a month then an extra sequential number is @subsection S2_2_changelog Changelog v20.11 Public major release + - Performance regressions can be noted when executing Depthwise Convolution on Neon with a multiplier > 1. + This is planned to be resolved in 21.02 release. - Added new data type S32 support for: - @ref NEArithmeticSubtraction - @ref NEArithmeticSubtractionKernel @@ -106,6 +108,13 @@ v20.11 Public major release - @ref GCSoftmaxLayer - New OpenCL kernels / functions: - @ref CLGEMMLowpQuantizeDownInt32ScaleByFixedPointKernel + - @ref CLLogicalNot + - @ref CLLogicalAnd + - @ref CLLogicalOr + - New NEON kernels / functions: + - @ref NELogicalNot + - @ref NELogicalAnd + - @ref NELogicalOr - Removed padding from NEON kernels: - @ref NEComplexPixelWiseMultiplicationKernel - @ref NENonMaximaSuppression3x3Kernel |