HiMap: Fast and Scalable High-Quality Mapping on CGRA via Hierarchical Abstraction
HiMap: Fast and Scalable High-Quality Mapping on CGRA via Hierarchical Abstraction
复制标题
HiMap：通过分层抽象在 CGRA 上实现快速且可扩展的高质量地图
DOI：
10.23919/date51398.2021.9473916
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
L. Thiele
中科院分区：
文献类型：
--
作者：
D. Wijerathne;Zhaoying Li;A. Pathania;T. Mitra;L. Thiele
粗粒度可重构阵列（CGRA）由于在可重构性、性能和能效之间取得了很好的平衡而成为一种很有前途的硬件加速器。CGRA性能在很大程度上依赖于一个高质量的编译器来将应用程序内核映射到体系结构上。不幸的是，最先进的编译器无法在可接受的编译时间内生成高质量的映射，特别是随着CGRA大小的增加。我们提出了HiMap——一种快速和可扩展的CGRA映射方法——它也擅长为现有和新兴应用领域中流行的多维内核生成接近最优的解决方案。HiMap的效率和可伸缩性背后的关键策略是利用循环迭代依赖关系中的规律性，方法是在分层映射中使用虚拟收缩数组作为中间抽象层。实验结果证实，HiMap可以生成达到CGRA性能极限的应用程序映射。与最先进的映射相比，HiMap在性能和能源效率方面分别提高了17.3倍和5倍。对于64x64 CGRA， HiMap的近最佳映射编译时间不到15分钟，而现有方法需要几天才能生成次等映射。
Coarse-Grained Reconfigurable Array (CGRA) has emerged as a promising hardware accelerator due to the excellent balance among reconfigurability, performance, and energy efficiency. The CGRA performance strongly depends on a high-quality compiler to map the application kernels on the architecture. Unfortunately, the state-of-the-art compilers fall short in generating high quality mapping within an acceptable compilation time, especially with increasing CGRA size. We propose HiMap - a fast and scalable CGRA mapping approach - that is also adept at producing close-to-optimal solutions for multi-dimensional kernels prevalent in existing and emerging application domains. The key strategy behind HiMap's efficiency and scalability is to exploit the regularity in the loop iteration dependencies by employing a virtual systolic array as an intermediate abstraction layer in a hierarchical mapping. Experimental results confirm that HiMap can generate application mappings that hit the performance envelope of the CGRA. HiMap offers 17.3x and 5x improvement in performance and energy efficiency of the mappings compared to the state-of-the-art. The compilation time of HiMap for near-optimal mappings is less than 15 minutes for 64x64 CGRA while existing approaches take days to generate inferior mappings.
DOI：
10.1145/3240765.3240838
发表时间：
2018-11
期刊：
2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
影响因子：
--
作者：
J. Cong;Jie Wang
通讯作者：
J. Cong;Jie Wang