From 93e743fbe7d52f4c41fcd90762fc38b95be802f7 Mon Sep 17 00:00:00 2001 From: Omar Al Khatib Date: Tue, 2 Jan 2024 14:45:07 +0000 Subject: Optimize CpuSoftmaxKernel for axis != 0 and neon kernels Resolves: COMPMID-6501 Signed-off-by: Omar Al Khatib Change-Id: I0abd3cbb5f861301f407c443988fb7efaa205b5d Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11056 Tested-by: Arm Jenkins Reviewed-by: Gunes Bayir Comments-Addressed: Arm Jenkins Benchmark: Arm Jenkins --- docs/user_guide/release_version_and_change_log.dox | 2 ++ 1 file changed, 2 insertions(+) (limited to 'docs/user_guide') diff --git a/docs/user_guide/release_version_and_change_log.dox b/docs/user_guide/release_version_and_change_log.dox index bc7d2cb126..2d46737e96 100644 --- a/docs/user_guide/release_version_and_change_log.dox +++ b/docs/user_guide/release_version_and_change_log.dox @@ -44,6 +44,8 @@ If there is more than one release in a month then an extra sequential number is v24.04 Public major release - Optimize start-up time of @ref NEConvolutionLayer for some input configurations where GeMM is selected as the convolution algorithm - Optimize @ref NEConvolutionLayer for input tensor size > 1e7 bytes and weight tensor height > 7 + - Performance optimizations: + - Optimize @ref NESoftmaxLayer for axis != 0 by natively supporting higher axes up to axis 3. v24.02.1 Public patch release - Fix performance regression in fixed-format kernels -- cgit v1.2.1