projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 2f22dd6) | patch
Use CLKernellibraryEx on our own kernels (#2675)
author이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 <chunseok.lee@samsung.com>
Wed, 12 Sep 2018 05:39:48 +0000 (14:39 +0900)
committerGitHub Enterprise <noreply-CODE@samsung.com>
Wed, 12 Sep 2018 05:39:48 +0000 (14:39 +0900)
commitd00211fcb17da2e203646ad88d85525b28a2003a
treeb447297532c11011a4d0e6cb59f88c6f33fcad68tree | snapshot
parent2f22dd6b1ae97ed0380887ed78337870ce70f5c7commit | diff
Use CLKernellibraryEx on our own kernels (#2675)

* Use CLKernellibraryEx on our own kernels

- Change  CLKernellibrary to CLKernellibraryEx
- add initilaization of CLKernellibraryEx before creating kernel
FIXME: please suggest better way

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
* CLKernellibraryEx initialization on Compilation_finish

- Remove initialization on kernel's configure step
- Add initialization on Compilation_finish

Signed-off-by: Chunseok Lee <chunseok.lee@samsung.com>
libs/ARMComputeEx/src/core/CL/kernels/CLCastKernel.cpp diff | blob | history
libs/ARMComputeEx/src/core/CL/kernels/CLGatherKernel.cpp diff | blob | history
libs/ARMComputeEx/src/core/CL/kernels/CLPixelWiseDivisionKernel.cpp diff | blob | history
libs/ARMComputeEx/src/core/CL/kernels/CLReduceMaxKernel.cpp diff | blob | history
libs/ARMComputeEx/src/core/CL/kernels/CLReductionMeanKernel.cpp diff | blob | history
libs/ARMComputeEx/src/core/CL/kernels/CLStridedSliceKernel.cpp diff | blob | history
libs/ARMComputeEx/src/core/CL/kernels/CLTopKV2Kernel.cpp diff | blob | history
runtimes/pure_arm_compute/src/compilation.cc diff | blob | history
Domain: Machine Learning / ML Framework;