Computationally intensive algorithms such as Deep Neural Networks (DNNs) are becoming killer applications for edge devices. Porting heavily data-parallel algorithms on resource-constrained and battery-powered devices poses several challenges related to memory footprint, computational throughput, and energy efficiency. Low-bitwidth and mixed-precision arithmetic have been proven to be valid strategies for tackling these problems. We present Dustin, a fully programmable compute cluster integrating 16 RISC-V cores capable of 2- to 32-bit arithmetic and all possible mixed-precision permutations. In addition to a conventional Multiple-Instruction Multiple-Data (MIMD) processing paradigm, Dustin introduces a Vector Lockstep Execution Mode (VLEM) to minimize power consumption in highly data-parallel kernels. In VLEM, a single leader core fetches instructions and broadcasts them to the 15 follower cores. Clock gating Instruction Fetch (IF) stages and private caches of the follower cores leads to 38\% power reduction with minimal performance overhead (<3%). The cluster, implemented in 65 nm CMOS technology, achieves a peak performance of 58 GOPS and a peak efficiency of 1.15 TOPS/W.

翻译：诸如深度神经网络（DNN）等高计算密集型算法正成为边缘设备的杀手级应用。将高度数据并行的算法移植到资源受限且依赖电池供电的设备上，会面临内存占用、计算吞吐量和能效等多重挑战。低位宽与混合精度运算已被证明是解决这些问题的有效策略。本文提出Dustin——一款全可编程计算集群，集成16个RISC-V内核，支持2至32比特运算及所有可能的混合精度组合。除传统的多指令多数据（MIMD）处理范式外，Dustin引入了向量锁步执行模式（VLEM），以最小化高度数据并行内核的功耗。在VLEM模式下，单个主核负责取指令并将其广播至15个从核。对从核的指令获取（IF）级与私有缓存进行时钟门控，可在性能损失极小（<3%）的情况下降低38%的功耗。该集群采用65 nm CMOS工艺实现，峰值性能达58 GOPS，峰值能效为1.15 TOPS/W。