projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 269aad4) | patch
Implementation of Generic Permute CL Kernel (#3114)
authorShubham Gupta/System SW /SRI-Bangalore/Engineer/삼성전자 <shub98.gupta@samsung.com>
Mon, 5 Nov 2018 01:11:09 +0000 (06:41 +0530)
committer오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
Mon, 5 Nov 2018 01:11:09 +0000 (10:11 +0900)
commitc6fa1d0429153a35d8fa3cbbcab28c999696f4fa
tree85c88e5a964aa840041e02f4aa5a8b17f4da9bbctree | snapshot
parent269aad4c56ace5bd58e13156767d0888a6649236commit | diff
Implementation of Generic Permute CL Kernel (#3114)

This patch will add generic permute kernel supporting all permutations for nD Tensors
This kernel is required for Reshape and Transpose op

Signed-off-by: shubham <shub98.gupta@samsung.com>
libs/ARMComputeEx/arm_compute/core/CL/kernels/CLPermuteExKernel.h [new file with mode: 0644] blob
libs/ARMComputeEx/arm_compute/runtime/CL/functions/CLPermuteEx.h [new file with mode: 0644] blob
libs/ARMComputeEx/src/core/CL/CLKernelLibrary.cpp diff | blob | history
libs/ARMComputeEx/src/core/CL/cl_kernels/permute_ex.cl [new file with mode: 0644] blob
libs/ARMComputeEx/src/core/CL/kernels/CLPermuteExKernel.cpp [new file with mode: 0644] blob
libs/ARMComputeEx/src/runtime/CL/functions/CLPermuteEx.cpp [new file with mode: 0644] blob
Domain: Machine Learning / ML Framework;