projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 78fc3d3) | patch
[newrt] Do not mmap for CPU tensor allocation (#1951)
author이한종/동작제어Lab(SR)/Engineer/삼성전자 <hanjoung.lee@samsung.com>
Mon, 16 Jul 2018 08:28:12 +0000 (17:28 +0900)
committer이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 <chunseok.lee@samsung.com>
Mon, 16 Jul 2018 08:28:12 +0000 (17:28 +0900)
commitf42bbc3205e858db563f001977804128934c00da
treea69161f8a07bb3855b973be7cf13bb0a75949a73tree | snapshot
parent78fc3d3f789de7a19180c063d171c5943aecbfc0commit | diff
[newrt] Do not mmap for CPU tensor allocation (#1951)

* [newrt] Do not mmap for CPU tensor allocation

For CPU tensor memory we do not have to mmap for tensors, just allocate
with plain heap memory with `new`.

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
* Add comment for cpu tensor allocation

Signed-off-by: Hanjoung Lee <hanjoung.lee@samsung.com>
runtimes/new_runtime/src/internal/cpu.h diff | blob | history
Domain: Machine Learning / ML Framework;