Modulo SDC scheduling with recurrence minimization in high-level synthesis
Modulo SDC scheduling with recurrence minimization in high-level synthesis
复制标题
高级综合中具有递归最小化的模 SDC 调度
DOI：
10.1109/fpl.2014.6927490
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
J. Anderson
中科院分区：
文献类型：
--
作者：
Andrew Canis;S. Brown;J. Anderson
LOOP管道是一种高级合成调度技术，它与循环迭代重叠以实现更高的性能。但是，工业设计通常具有跨识别依赖性施加的资源限制和其他约束。多个约束之间的相互作用可能会对HLS Modulo调度算法提出挑战，如果无法正确处理，该算法可能会导致无法达到最小可能的启动间隔的循环管道计划。我们根据SDC公式提出了一种新颖的Modulo调度程序，该计划包括一个回溯机制，以正确处理多个调度限制，并仍然达到最小可能的启动间隔。 SDC公式的优点是成为数学框架，该框架支持灵活的约束，这些框架可用于更复杂的循环管道。此外，我们描述了如何在模量调度过程中专门应用关联表达转换，以重组复杂的循环中的复发以实现更好的调度。我们将我们的技术与HLS中现有的Modulo计划中的现有工作进行了比较，并将其与最先进的商业工具进行了比较。在一套基准套件上，我们表明我们的调度程序和提议的优化可以导致Geomean壁挂时间缩短32％，而先前的工作与29％相比，与商业工具相比。
Loop pipelining is a high-level synthesis scheduling technique that overlaps loop iterations to achieve higher performance. However, industrial designs often have resource constraints and other constraints imposed by cross-iteration dependencies. The interaction between multiple constraints can pose a challenge for HLS modulo scheduling algorithms, which, if not handled properly can lead to a loop pipeline schedule that fails to achieve the minimum possible initiation interval. We propose a novel modulo scheduler based on an SDC formulation that includes a backtracking mechanism to properly handle multiple scheduling constraints and still achieve the minimum possible initiation interval. The SDC formulation has the advantage of being a mathematical framework that supports flexible constraints that are useful for more complex loop pipelines. Furthermore, we describe how to specifically apply associative expression transformations during modulo scheduling to restructure recurrences in complex loops to enable better scheduling. We compared our techniques to existing prior work in modulo scheduling in HLS and also compared against a state-of-art commercial tool. Over a suite of benchmarks, we show that our scheduler and proposed optimizations can result in a geomean wall-clock time reduction of 32% versus prior work and 29% versus a commercial tool.