Taskflow: A General-Purpose Parallel and Heterogeneous Task Programming System

作     者：Huang, Tsung-Wei Lin, Dian-Lun Lin, Yibo Lin, Chun-Xun 

作者机构：Univ Utah Dept Elect & Comp Engn Salt Lake City UT 84112 USA Peking Univ Dept Comp Sci Beijing 100871 Peoples R China MathWorks Natick MA USA 

出 版 物：《IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS》 (IEEE Trans Comput Aided Des Integr Circuits Syst)

年 卷 期：2022年第41卷第5期

页      面：1448-1452页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Electronic design automation parallel programming 

摘      要：Taskflow tackles the long-standing question: How can we make it easier for developers to program parallel and heterogeneous computer-aided design (CAD) applications with high performance and simultaneous high productivity? Taskflow introduces a new powerful task graph programming model to assist developers in the implementation of parallel and heterogeneous algorithms with complex control flow. We develop an efficient system runtime to solve many of the new scheduling challenges arising out of our models and optimize the performance across latency, energy efficiency, and throughput. Taskflow has demonstrated promising performance on both micro-benchmarks and real-world applications. As an example, Taskflow solved a large-scale circuit placement problem up to 17% faster, with 1.3x fewer memory, 2.1x less power consumption, and 2.9x higher throughput than two industrial-strength systems, oneTBB and StarPU, on a machine of 40 CPUs and 4 GPUs.