GNNHLS: Evaluating Graph Neural Network Inference via High-Level Synthesis

被引：2

作者：

Zhao, Chenfeng ^{[1
]}

Dong, Zehao ^{[1
]}

Chen, Yixin ^{[1
]}

Zhang, Xuan ^{[1
]}

Chamberlain, Roger D. ^{[1
]}

机构：

[1] Washington Univ, McKelvey Sch Engn, St Louis, MO 63110 USA

来源：

2023 IEEE 41ST INTERNATIONAL CONFERENCE ON COMPUTER DESIGN, ICCD | 2023年

关键词：

field-programmable gate arrays; graph neural networks; high-level synthesis;

D O I：

10.1109/ICCD58817.2023.00092

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

We present GNNHLS, an open-source framework to comprehensively evaluate GNN inference acceleration on FPGAs via HLS, containing a software stack for data generation and baseline deployment and FPGA implementations of 6 well-tuned GNN HLS kernels. Evaluating on 4 graph datasets with distinct topologies and scales, the results show that GNNHLS achieves up to 50.8x speedup and 423x energy reduction relative to the CPU baselines. Compared with the GPU baselines, GNNHLS achieves up to 5.16x speedup and 74.5x energy reduction.

引用

页码：574 / 577

页数：4

共 50 条

[21] Two-Level Graph Neural Network
Ai, Xing
Sun, Chengyu
Zhang, Zhihong
Hancock, Edwin R.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (04) : 4593 - 4606
[22] Learning to Compare Hardware Designs for High-Level Synthesis
Bai, Yunsheng
Sohrabizadeh, Atefeh
Ding, Zijian
Liang, Rongjian
Li, Weikai
Wang, Ding
Ren, Haoxing
Sun, Yizhou
Cong, Jason
PROCEEDINGS OF THE 2024 ACM/IEEE INTERNATIONAL SYMPOSIUM ON MACHINE LEARNING FOR CAD, MLCAD 2024, 2024,
[23] Tensor Optimization for High-Level Synthesis Design Flows
Siracusa, Marco
Ferrandi, Fabrizio
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2020, 39 (11) : 4217 - 4228
[24] A review of high-level synthesis for dynamically reconfigurable FPGAs
Zhang, XJ
Ng, KW
MICROPROCESSORS AND MICROSYSTEMS, 2000, 24 (04) : 199 - 211
[25] Global Analysis of C Concurrency in High-Level Synthesis
Ramanathan, Nadesh
Constantinides, George A.
Wickerson, John
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2021, 29 (01) : 24 - 37
[26] Aspect-Level Attributed Network Embedding via Variational Graph Neural Networks
Wang, Hengliang
Mu, Kedian
DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2020), PT II, 2020, 12113 : 398 - 414
[27] Educational Tool-spaces for Convolutional Neural Network FPGA Design Space Exploration Using High-Level Synthesis
Yarnell, Richard C.
Hossain, Mousam
Medina, Raul Graterol
Pindoria, Ayush
Ghimire, Sujan
Chowdhury, Muhtasim Alam
Salehi, Soheil
Bai, Yu
Demara, Ronald F.
PROCEEDING OF THE GREAT LAKES SYMPOSIUM ON VLSI 2024, GLSVLSI 2024, 2024, : 343 - 346
[28] Probabilistic Scheduling in High-Level Synthesis
Cheng, Jianyi
Wickerson, John
Constantinides, George A.
2021 IEEE 29TH ANNUAL INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES (FCCM 2021), 2021, : 195 - 203
[29] Separation Logic for High-Level Synthesis
Winterstein, Felix J.
Bayliss, Samuel R.
Constantinides, George A.
ACM TRANSACTIONS ON RECONFIGURABLE TECHNOLOGY AND SYSTEMS, 2016, 9 (02)
[30] Translation Validation of High-Level Synthesis
Kundu, Sudipta
Lerner, Sorin
Gupta, Rajesh K.
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2010, 29 (04) : 566 - 579

← 1 2 3 4 5 →