PANORAMA: divide-and-conquer approach for mapping complex loop kernels on CGRA
PANORAMA: divide-and-conquer approach for mapping complex loop kernels on CGRA
复制标题
PANORAMA：在 CGRA 上映射复杂循环内核的分而治之方法
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
T. Mitra
中科院分区：
文献类型：
--
作者：
D. Wijerathne;Zhaoying Li;Thilini Kaushalya Bandara;T. Mitra
CGRA非常适合作为硬件加速器，因为它具有功率效率和可重新配置性。然而，他们的潜力是有限的编译器无法有效地映射到架构复杂的循环内核。我们提出了PANORAMA，这是一种快速且可扩展的编译器，基于分而治之的方法，为表示循环体的复杂数据流图（DFG）生成到更大CGRA的质量映射。与最先进的技术相比，PANORAMA将映射循环的吞吐量提高了2.6倍，编译时间加快了8.7倍。
CGRAs are well-suited as hardware accelerators due to power efficiency and reconfigurability. However, their potential is limited by the inability of the compiler to map complex loop kernels onto the architectures effectively. We propose PANORAMA, a fast and scalable compiler based on a divide-and-conquer approach to generate quality mapping for complex dataflow graphs (DFG) representing loop bodies onto larger CGRAs. PANORAMA improves the throughput of the mapped loops by up to 2.6x with 8.7x faster compilation time compared to the state-of-the-art techniques.