DEEPTOOLS: Compiler and Execution Runtime Extensions for RAPiD AI Accelerator
- Authors
- Venkataramani, Swagath; Choi, Jung wook; Srinivasan, Vijayalakshmi; Wang, Wei; Zhang, Jintao; Schaal, Marcel; Serrano, Mauricio J.; Ishizaki, Kazuaki; Inoue, Hiroshi; Ogawa, Eri; Ohara, Motiyoshi; Chang, Leland; Gopalakrishnan, Kailash
- Issue Date
- Sep-2019
- Publisher
- IEEE COMPUTER SOC
- Keywords
- Deep Learning; Machine learning accelerators; Software stack for AI
- Citation
- IEEE MICRO, v.39, no.5, pp.102 - 111
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE MICRO
- Volume
- 39
- Number
- 5
- Start Page
- 102
- End Page
- 111
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/147127
- DOI
- 10.1109/MM.2019.2931584
- ISSN
- 0272-1732
- Abstract
- The ubiquitous adoption of systems specialized for AI requires bridging two seemingly conflicting challenges-the need to deliver extreme processing efficiencies while employing familiar programming interfaces, making them compelling even for nonexpert users. We take a significant first step towards this goal and present an end-to-end software stack for the RAPID AI accelerator developed by IBM Research. We present a set of software extensions, called DEEPTOOLS, that leverage and work within popular deep learning frameworks. DEEPTOOLS requires no additional user input and enables aggressive, accelerator-specific performance optimization akin to a full, custom framework. DEEPTOOLS has two key components: 1) a compiler runtime called DeepRT, which automatically identifies how best to execute a given DNN graph on RAPID and constructs the requisite program binaries; and 2) an execution runtime called RAPiDLiB, which triggers and manages the execution of compute and data-transfer operations on RAPID. We integrate DEEPTOOLS with TensorFlow and map popular DNNs (AlexNet, VGG, ResNet, LSTM) to RAPID. We demonstrate substantial improvement in performance over hand-tuned mappings.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.