projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 0fbe4a3) | patch
[neurun] Revise MemoryAllocator (#3386)
author김용섭/동작제어Lab(SR)/Engineer/삼성전자 <yons.kim@samsung.com>
Tue, 30 Oct 2018 06:07:18 +0000 (15:07 +0900)
committer오형석/동작제어Lab(SR)/Staff Engineer/삼성전자 <hseok82.oh@samsung.com>
Tue, 30 Oct 2018 06:07:18 +0000 (15:07 +0900)
commitb168dc604b791ca1b7347de3d5ee777d9a634505
treef54bdd57063cff48c6e8b94486a1cfc5f4d7ce04tree | snapshot
parent0fbe4a38d64c08350d87dcf0898d12c4caa1fa06commit | diff
[neurun] Revise MemoryAllocator (#3386)

- MemoryBlock -> Block
- base_offset -> offset
- Remove mem_id concept
- Introduce graph::operand::Index instead of uint32_t
- Apply above changes to symbols of MemoryAllocator
- Apply above changes to tests of MemoryAllocator
- Append Logging

Signed-off-by: Yongseop Kim <yons.kim@samsung.com>
runtimes/neurun/src/backend/cpu/MemoryAllocator.cc diff | blob | history
runtimes/neurun/src/backend/cpu/MemoryAllocator.h diff | blob | history
runtimes/neurun/src/backend/cpu/TensorBuilder.cc diff | blob | history
runtimes/neurun/src/backend/cpu/TensorBuilder.h diff | blob | history
runtimes/neurun/test/backend/cpu/MemoryAllocator.cc diff | blob | history
Domain: Machine Learning / ML Framework;