From 5fc07aa26faba56b815156fc84d852e80219fe50 Mon Sep 17 00:00:00 2001 From: Gian Marco Iodice Date: Wed, 15 May 2019 17:08:02 +0100 Subject: COMPMID-2338: Remove CLGEMMInterleave4x4 and CLGEMMTranspose1xW Change-Id: I527fc97eac51308de601e5d1d50e75e4d89c5ee5 Signed-off-by: Gian Marco Iodice Reviewed-on: https://review.mlplatform.org/c/1158 Tested-by: Arm Jenkins Reviewed-by: Giuseppe Rossini Comments-Addressed: Arm Jenkins --- docs/00_introduction.dox | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'docs/00_introduction.dox') diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox index 57d8c4a3f2..03e889d14a 100644 --- a/docs/00_introduction.dox +++ b/docs/00_introduction.dox @@ -272,8 +272,8 @@ v19.05 Public major release - @ref NEDepthConcatenateLayer - @ref CLWidthConcatenateLayer - @ref CLDepthConcatenateLayer - - @ref CLGEMMInterleave4x4 - - @ref CLGEMMTranspose1xW + - CLGEMMInterleave4x4 + - CLGEMMTranspose1xW - Support different quantization info in CLConcatLayer. - Add checks on different input/output quantization info were not supported. - Tensors have different quantization information. @@ -688,7 +688,7 @@ v17.09 Public major release - @ref CLDirectConvolutionLayerKernel / @ref CLDirectConvolutionLayer - @ref CLFlattenLayer - @ref CLFloorKernel / @ref CLFloor - - @ref CLGEMMTranspose1xW + - CLGEMMTranspose1xW - @ref CLGEMMMatrixVectorMultiplyKernel - @ref CLL2NormalizeLayerKernel / @ref CLL2NormalizeLayer - @ref CLQuantizationLayerKernel @ref CLMinMaxLayerKernel / @ref CLQuantizationLayer @@ -766,7 +766,7 @@ v17.03.1 First Major public release of the sources v17.03 Sources preview - New OpenCL kernels / functions: - @ref CLGradientKernel, @ref CLEdgeNonMaxSuppressionKernel, @ref CLEdgeTraceKernel / @ref CLCannyEdge - - GEMM refactoring + FP16 support: @ref CLGEMMInterleave4x4Kernel, @ref CLGEMMTranspose1xWKernel, @ref CLGEMMMatrixMultiplyKernel, @ref CLGEMMMatrixAdditionKernel / @ref CLGEMM + - GEMM refactoring + FP16 support: CLGEMMInterleave4x4Kernel, CLGEMMTranspose1xWKernel, @ref CLGEMMMatrixMultiplyKernel, @ref CLGEMMMatrixAdditionKernel / @ref CLGEMM - @ref CLGEMMMatrixAccumulateBiasesKernel / @ref CLFullyConnectedLayer - @ref CLTransposeKernel / @ref CLTranspose - @ref CLLKTrackerInitKernel, @ref CLLKTrackerStage0Kernel, @ref CLLKTrackerStage1Kernel, @ref CLLKTrackerFinalizeKernel / @ref CLOpticalFlow @@ -1232,20 +1232,20 @@ recommended to follow one of the options outlined below. @subsubsection S3_5_1_ubuntu_on_windows Bash on Ubuntu on Windows -The best and easiest option is to use -Ubuntu on Windows. +The best and easiest option is to use +Ubuntu on Windows. This feature is still marked as *beta* and thus might not be available. However, if it is building the library is as simple as opening a *Bash on Ubuntu on Windows* shell and following the general guidelines given above. @subsubsection S3_5_2_cygwin Cygwin -If the Windows subsystem for Linux is not available Cygwin +If the Windows subsystem for Linux is not available Cygwin can be used to install and run `scons`. In addition to the default packages installed by Cygwin `scons` has to be selected in the installer. (`git` might also be useful but is not strictly required if you already have got the source -code of the library.) Linaro provides pre-built versions of -GCC cross-compilers +code of the library.) Linaro provides pre-built versions of +GCC cross-compilers that can be used from the Cygwin terminal. When building for Android the compiler is included in the Android standalone toolchain. After everything has been set up in the Cygwin terminal the general guide on building the library -- cgit v1.2.1