projects / platform / core / ml / nnfw.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 744b699) | patch
[enco] Support constant folding (#2441)
author박종현/동작제어Lab(SR)/Staff Engineer/삼성전자 <jh1302.park@samsung.com>
Thu, 29 Nov 2018 05:25:48 +0000 (14:25 +0900)
committerGitHub Enterprise <noreply-CODE@samsung.com>
Thu, 29 Nov 2018 05:25:48 +0000 (14:25 +0900)
commite52135f16010e55eac0af7ea7ccfe65835ea7eef
treecf9b06ace3900a5dd1610b5f7d7bbf654955635ctree | snapshot
parent744b69963317c1eee4e818717fb3d9780f05f9bacommit | diff
[enco] Support constant folding (#2441)

This commit introduces constant folding pass into the enco compilation
pipeline.

Note that the current implementation supports folding over "copy"
instruction only.

Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
contrib/enco/core/src/Backend.cpp diff | blob | history
contrib/enco/core/src/Transforms/ConstantFolding.cpp [new file with mode: 0644] blob
contrib/enco/core/src/Transforms/ConstantFolding.h [new file with mode: 0644] blob
Domain: Machine Learning / ML Framework;