arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.09112cs.PLcs.AR
收藏

改写历史:重新利用领域专用粗粒度可重构阵列

Rewriting History: Repurposing Domain-Specific CGRAs

Jackson Woodruff, Thomas Koehler, Alexander Brauckmann, Chris Cummins, Sam Ainsworth, Michael F. P. O'Boyle

AI总结:

本文提出首个灵活CGRA编译器FlexC,通过数据流改写与等式饱和技术使领域专用CGRAs支持原本不支持的操作,在超2000个内核上实现2.2倍内核覆盖提升和3倍加速。

摘要:

粗粒度可重构阵列(CGRAs)是领域专用器件,兼具FPGA的灵活性与ASIC的性能。然而,领域受限也带来风险:所设计的芯片可能无法加速足够多的当前及未来软件,从而难以证明其硬件成本是合理的。我们提出FlexC,这是首个灵活的CGRA编译器,使CGRAs能够适配其原本不原生支持的操作。FlexC采用数据流改写,将代码中不受支持的区域替换为CGRA支持的等价操作。我们使用等式饱和(equality saturation)技术,该技术能够高效探索大规模重写规则空间,从而在程序空间中有效搜索受支持的程序。我们将FlexC应用于超过2,000个循环内核,面向四种不同的研究型CGRAs和300个生成的CGRAs进行编译,结果表明可加速的循环内核数量增加了2.2倍,在原本无法被加速器支持的内核上,相比Arm A5 CPU实现了3倍加速。

英文摘要:

Coarse-grained reconfigurable arrays (CGRAs) are domain-specific devices promising both the flexibility of FPGAs and the performance of ASICs. However, with restricted domains comes a danger: designing chips that cannot accelerate enough current and future software to justify the hardware cost. We introduce FlexC, the first flexible CGRA compiler, which allows CGRAs to be adapted to operations they do not natively support. FlexC uses dataflow rewriting, replacing unsupported regions of code with equivalent operations that are supported by the CGRA. We use equality saturation, a technique enabling efficient exploration of a large space of rewrite rules, to effectively search through the program-space for supported programs. We applied FlexC to over 2,000 loop kernels, compiling to four different research CGRAs and 300 generated CGRAs and demonstrate a 2.2$\times$ increase in the number of loop kernels accelerated leading to 3$\times$ speedup compared to an Arm A5 CPU on kernels that would otherwise be unsupported by the accelerator.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑