DAP: A 507-GMACs/J 256-Core Domain Adaptive Processor for Wireless Communication and Linear Algebra Kernels in 12-nm FINFET

Kuan-Yu Chen, Chi-Sheng Yang, Yu-Hsiu Sun, Chien-Wei Tseng, Morteza Fayazi, Xin He, Siying Feng, Yufan Yue, Trevor N. Mudge, Ronald G. Dreslinski, Hun-Seok Kim, David T. Blaauw

Abstract: We present domain adaptive processor (DAP), a programmable systolic-array processor designed for wireless communication and linear algebra workloads. DAP uses a globally homogeneous but locally heterogeneous architecture, uses decode-less reconfiguration instructions for data streaming, enables single-cycle data communication between functional units (FUs), and features lightweight nested-loop control for periodic execution. Our design demonstrates how configuration flexibility and rapid program loading enable a wide range of communication workloads to be mapped and swapped in less than a microsecond, supporting continually evolving communication standards such as 5G. A prototype chip of DAP with 256 cores is fabricated in a 12-nm FINFET process and has been verified. The measurement results show that DAP achieves 507 GMACs/J and a peak performance of 264 GMACs.