projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 82fc272) | patch
Generic EmbeddingLookup kernel to handle tensors upto rank=4 (#3794)
authorShubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 <shub98.gupta@samsung.com>
Mon, 10 Dec 2018 01:28:33 +0000 (06:58 +0530)
committer오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
Mon, 10 Dec 2018 01:28:33 +0000 (10:28 +0900)
commit7b2fad2cf613584ba448d166c718ce18e164fd39
tree6469b6188c3650ea7f5a2033fb894a900c4a07f7tree | snapshot
parent82fc272297d68ef21a2190826e322b443e0bfaddcommit | diff
Generic EmbeddingLookup kernel to handle tensors upto rank=4 (#3794)

This patch unifies the 3 different embedding lookup kernel into
one kernel so as to make a generic cl to support upto 4d tensors.

Signed-off-by: shubham <shub98.gupta@samsung.com>
libs/ARMComputeEx/src/core/CL/CLKernelLibrary.cpp diff | blob | history
libs/ARMComputeEx/src/core/CL/cl_kernels/embedding_lookup.cl diff | blob | history
libs/ARMComputeEx/src/core/CL/kernels/CLEmbeddingLookupKernel.cpp diff | blob | history
Domain: Machine Learning / ML Framework;