projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 9480d1e) | patch
Fix deadlock when access two acl_cl at once (#6500)
author오형석/On-Device Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
Tue, 13 Aug 2019 00:40:56 +0000 (09:40 +0900)
committerGitHub Enterprise <noreply-CODE@samsung.com>
Tue, 13 Aug 2019 00:40:56 +0000 (09:40 +0900)
commit51671b098692a133d86624afc5455c6e01ef9302
tree93a3f935790cf418e38b7178a0632db04aa98cd8tree | snapshot
parent9480d1e941db531242562bac5bfd2cc370c2b755commit | diff
Fix deadlock when access two acl_cl at once (#6500)

To avoid deadlock when operation need to access two acl_cl at once (source, target), introduce access function to access two tensor

Signed-off-by: Hyeongseok Oh <hseok82.oh@samsung.com>
runtimes/neurun/backend/acl_cl/kernel/ConcatLayer.cc diff | blob | history
runtimes/neurun/backend/acl_cl/operand/Object.cc diff | blob | history
runtimes/neurun/backend/acl_cl/operand/Object.h diff | blob | history
Domain: Machine Learning / ML Framework;