diff options
Diffstat (limited to 'docs/00_introduction.dox')
-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 |