Efficient algorithms for task mapping on heterogeneous CPU/GPU platforms for fast completion time

Li，Zexin1; Zhang，Yuqun1; Ding，Ao1; Zhou，Husheng2; Liu，Cong2

2021-03-01

10.1016/j.sysarc.2020.101936

JOURNAL OF SYSTEMS ARCHITECTURE   影响因子和分区

1383-7621

1873-6165

In GPU-based embedded systems, the problem of computation and data mapping for multiple applications while minimizing the completion time is quite challenging due to large size of the policy space. To achieve fast competition time, a fine-grain mapping framework that explores a set of critical factors is needed for heterogeneous embedded systems. In this paper, we present a theoretical framework that yields a sub-optimal solution via three practical mapping algorithms with low time complexity. We evaluate such algorithms upon StarPU with a large set of popular benchmarks. Experimental results demonstrate that algorithms proposed by the original EMSOFT paper can achieve up to 30% faster completion time compared to state-of-the-art mapping techniques, and can perform consistently well across different workloads. We further extend such algorithms to minimize the completion time and enhance the runtime performance of complex heterogeneous applications under resource-limited infrastructure. We also extend the evaluation by deploying StarPU under multiple setups with an additional benchmark testing suite for simulating real-world runtime neural networks. Experimental results demonstrate that our extended algorithm can achieve much faster completion time (averagely 30% to 37% under multiple resource-constraint scenarios) compared to the state-of-the-art mapping techniques.

GPU Heterogeneous scheduling Data-size-based prediction Neural network runtime acceleration

SCI ; EI

英语

第一 ; 通讯

National Natural Science Foundation of China[61902169] ; Shenzhen Peacock Plan, China[KQTD2016112514355531] ; Science and Tech-nology Innovation Committee Foundation of Shenzhen, China[JCYJ20170817110848086]

Computer Science

Computer Science, Hardware & Architecture ; Computer Science, Software Engineering

WOS:000697350100011

ELSEVIER

20205209694443

Conformal mapping ; Complex networks ; Embedded systems

Semiconductor Devices and Integrated Circuits:714.2 ; Computer Circuits:721.3 ; Computer Systems and Equipment:722

COMPUTER SCIENCE

Web of Science

1.Department of Computer Science and Engineering,Southern University of Science and Technology,Guangdong,Shenzhen,China
2.Department of Computer Science,The University of Texas at Dallas,United States

Li，Zexin,Zhang，Yuqun,Ding，Ao,et al. Efficient algorithms for task mapping on heterogeneous CPU/GPU platforms for fast completion time[J]. JOURNAL OF SYSTEMS ARCHITECTURE,2021,114.

Li，Zexin,Zhang，Yuqun,Ding，Ao,Zhou，Husheng,&Liu，Cong.(2021).Efficient algorithms for task mapping on heterogeneous CPU/GPU platforms for fast completion time.JOURNAL OF SYSTEMS ARCHITECTURE,114.

Li，Zexin,et al."Efficient algorithms for task mapping on heterogeneous CPU/GPU platforms for fast completion time".JOURNAL OF SYSTEMS ARCHITECTURE 114(2021).