Improving Scalability of Exact Modulo Scheduling with Specialized Conflict-Driven Learning

Improving Scalability of Exact Modulo Scheduling with Specialized Conflict-Driven Learning
复制标题

通过专门的冲突驱动学习提高精确模调度的可扩展性

DOI:
10.1145/3316781.3317842
复制
发表时间:
2019
期刊:
The 56th Annual Design Automation Conference (DAC
影响因子:
--
通讯作者:
Zhang, Zhiru
Zhang, Zhiru
中科院分区:
--
文献类型:
--
作者:
Dai, Steve;Zhang, Zhiru

文献摘要

参考文献

被引文献

相似文献

循环流水线是高级综合中的一个重要优化,它支持循环迭代的高吞吐量流水线执行。然而,目前的管道调度方法从根本上依赖于基于自组织优先级函数的不精确启发式算法,缺乏对实现最佳吞吐量的保证。为了解决这一问题,我们提出了一种基于整数差分约束和布尔可满足性的调度算法来精确处理各种管道调度约束。我们的技术利用了冲突驱动的学习和特定问题的专门化,以最优而有效地获得流水线解决方案。实验表明,与基于整数线性规划的技术相比,我们的方法实现了显著的加速。
Loop pipelining is an important optimization in high-level synthesis to enable high-throughput pipelined execution of loop iterations. However, current pipeline scheduling approach relies on fundamentally inexact heuristics based on ad hoc priority functions and lacks guarantee on achieving the best throughput. To address this shortcoming, we propose a scheduling algorithm based on system of integer difference constraints (SDC) and Boolean satisfiability (SAT) to exactly handle various pipeline scheduling constraints. Our techniques take advantage of conflict-driven learning and problem-specific specialization to optimally yet efficiently derive pipelining solutions. Experiments demonstrate that our approach achieves notable speedup in comparison to integer linear programming based techniques.
高级综合中具有递归最小化的模 SDC 调度
DOI: 10.1109/fpl.2014.6927490
发表时间: 2014
期刊: 2014 24th International Conference on Field Programmable Logic and Applications (FPL)
影响因子: --
作者:
Andrew Canis;S. Brown;J. Anderson
通讯作者: J. Anderson
DOI: 10.1145/3174243.3174268
发表时间: 2018-02
期刊: Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays
影响因子: --
作者:
Steve Dai;Gai Liu;Zhiru Zhang
通讯作者: Steve Dai;Gai Liu;Zhiru Zhang
DOI: --
发表时间: 1997
期刊: ACM-SIGPLAN Symposium on Programming Language Design and Implementation
影响因子: --
作者:
A. Eichenberger;E. Davidson
通讯作者: E. Davidson