projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 8528a07) | patch
Generic HashTableLookup kernel to handle tensors upto rank=4 (#3798)
authorShubham Gupta/SNAP /SRI-Bangalore/Engineer/삼성전자 <shub98.gupta@samsung.com>
Mon, 10 Dec 2018 01:27:55 +0000 (06:57 +0530)
committer오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
Mon, 10 Dec 2018 01:27:55 +0000 (10:27 +0900)
commit130373b5736deff2bb8e9220e38601805f112fca
tree8b83716550695098b67f6541432d6b647fe80668tree | snapshot
parent8528a073a330c19903522ea32c437bd1f0047714commit | diff
Generic HashTableLookup kernel to handle tensors upto rank=4 (#3798)

This patch unifies the 3 different hashtable 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/hashtable_lookup.cl diff | blob | history
libs/ARMComputeEx/src/core/CL/kernels/CLHashtableLookupKernel.cpp diff | blob | history
Domain: Machine Learning / ML Framework;