[ layer ] Lower the computational code of lstmcell_core to BLAS level

nnstreamer / nntrainer

NNtrainer is Software Framework for Training Neural Network Models on Devices.

Apache License 2.0

134 stars 71 forks source link

[ layer ] Lower the computational code of lstmcell_core to BLAS level #2642

Closed skykongkong8 closed 1 week ago

skykongkong8 commented 2 weeks ago

Through this PR, 2 things:

Cleaner code : reduce if/def code block to tensor level
Acceleration : Use SIMD haxpy in fp16 case. Previously it was only using naive loop

taos-ci commented 2 weeks ago

:memo: TAOS-CI Version: 1.5.20200925. Thank you for submitting PR #2642. Please a submit 1commit/1PR (one commit per one PR) policy to get comments quickly from reviewers. Your PR must pass all verificiation processes of cibot before starting a review process from reviewers. If you are new member to join this project, please read manuals in documentation folder and wiki page. In order to monitor a progress status of your PR in more detail, visit http://ci.nnstreamer.ai/.