DEEPTOOLS: Compiler and Execution Runtime Extensions for RAPiD AI Accelerator

被引：18

作者：

Venkataramani, Swagath ^{[1
]}

Choi, Jungwook ^{[1
]}

Srinivasan, Vijayalakshmi ^{[1
]}

Wang, Wei ^{[1
]}

Zhang, Jintao ^{[1
]}

Schaal, Marcel ^{[1
]}

Serrano, Mauricio J. ^{[1
]}

Ishizaki, Kazuaki ^{[1
]}

Inoue, Hiroshi ^{[1
]}

Ogawa, Eri ^{[1
]}

Ohara, Motiyoshi ^{[1
]}

Chang, Leland ^{[1
]}

Gopalakrishnan, Kailash ^{[1
]}

机构：

[1] Ibm Res Labs, Yorktown Hts, NY 10598 USA

来源：

IEEE MICRO | 2019年 / 39卷 / 05期

关键词：

Deep Learning; Machine learning accelerators; Software stack for AI;

D O I：

10.1109/MM.2019.2931584

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

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.

引用

页码：102 / 111

页数：10

共 11 条

[1]

Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265

[2]

Chen TQ, 2018, PROCEEDINGS OF THE 13TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P579

[3] Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks [J].

Chen, Yu-Hsin ;

Krishna, Tushar ;

Emer, Joel S. ;

Sze, Vivienne .

IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2017, 52 (01) :127-138

[4]

Cyphers Scott, 2018, ARXIV180108058

[5]

Fleischer B, 2018, SYMP VLSI CIRCUITS, P35, DOI 10.1109/VLSIC.2018.8502276

[6] A Configurable Cloud-Scale DNN Processor for Real-Time AI [J].

Fowers, Jeremy ;

Ovtcharov, Kalin ;

Papamichael, Michael ;

Massengill, Todd ;

Liu, Ming ;

Lo, Daniel ;

Alkalay, Shlomi ;

Haselman, Michael ;

Adams, Logan ;

Ghandi, Mahdi ;

Heil, Stephen ;

Patel, Prerak ;

Sapek, Adam ;

Weisz, Gabriel ;

Woods, Lisa ;

Lanka, Sitaram ;

Reinhardt, Steven K. ;

Caulfield, Adrian M. ;

Chung, Eric S. ;

Burger, Doug .

2018 ACM/IEEE 45TH ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2018, :1-14

[7] In-Datacenter Performance Analysis of a Tensor Processing Unit [J].

Jouppi, Norman P. ;

Young, Cliff ;

Patil, Nishant ;

Patterson, David ;

Agrawal, Gaurav ;

Bajwa, Raminder ;

Bates, Sarah ;

Bhatia, Suresh ;

Boden, Nan ;

Borchers, Al ;

Boyle, Rick ;

Cantin, Pierre-luc ;

Chao, Clifford ;

Clark, Chris ;

Coriell, Jeremy ;

Daley, Mike ;

Dau, Matt ;

Dean, Jeffrey ;

Gelb, Ben ;

Ghaemmaghami, Tara Vazir ;

Gottipati, Rajendra ;

Gulland, William ;

Hagmann, Robert ;

Ho, C. Richard ;

Hogberg, Doug ;

Hu, John ;

Hundt, Robert ;

Hurt, Dan ;

Ibarz, Julian ;

Jaffey, Aaron ;

Jaworski, Alek ;

Kaplan, Alexander ;

Khaitan, Harshit ;

Killebrew, Daniel ;

Koch, Andy ;

Kumar, Naveen ;

Lacy, Steve ;

Laudon, James ;

Law, James ;

Le, Diemthu ;

Leary, Chris ;

Liu, Zhuyuan ;

Lucke, Kyle ;

Lundin, Alan ;

MacKean, Gordon ;

Maggiore, Adriana ;

Mahony, Maire ;

Miller, Kieran ;

Nagarajan, Rahul ;

Narayanaswami, Ravi .

44TH ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA 2017), 2017, :1-12

[8] A Compiler for Deep Neural Network Accelerators to Generate Optimized Code for a Wide Range of Data Parameters from a Hand-crafted Computation Kernel [J].

Ogawa, Eri ;

Ishizaki, Kazuaki ;

Inoue, Hiroshi ;

Venkataramani, Swagath ;

Choi, Jungwook ;

Wang, Wei ;

Srinivasan, Vijayalakshmi ;

Ohara, Moriyoshi ;

Gopalakrishnan, Kailash .

2019 IEEE SYMPOSIUM IN LOW-POWER AND HIGH-SPEED CHIPS (COOL CHIPS 22), 2019,

[9]

Rotem N., 2018, GLOW GRAPH LOWERING

[10] SCALEDEEP: A Scalable Compute Architecture for Learning and Evaluating Deep Networks [J].

Venkataramani, Swagath ;

Ranjan, Ashish ;

Banerjee, Subarno ;

Das, Dipankar ;

Avancha, Sasikanth ;

Jagannathan, Ashok ;

Durg, Ajaya ;

Nagaraj, Dheemanth ;

Kaul, Bharat ;

Dubey, Pradeep ;

Raghunathan, Anand .

44TH ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA 2017), 2017, :13-26

← 1 2 →