2025/05/06 by H.J. Pu, Huanzhi Pu, Pu, Huanzhi +16 · 1 voice
Computer Science · #Advanced Data Storage Technologies #CUDA #Computer Graphics and Visualization Techniques #FOS: Computer and information sciences #General-purpose computing on graphics processing units #Hardware Architecture (cs.AR) #Path (computing) #Programming paradigm #SPMD #Software #Speedup #cs.AR
paper · pdf · doi:10.48550/arxiv.2505.03102
openalex publication_date 2025/05/06 · arxiv published 2025/05/06 · arxiv updated 2025/05/06 · openalex created_date 2025/10/16 · openalex updated_date 2026/08/05
RISC-V GPUs present a promising path for supporting GPU applications. Traditionally, GPUs achieve high efficiency through the SPMD (Single Program Multiple Data) programming model. However, modern GPU programming increasingly relies on warp-level features, which diverge from the conventional SPMD paradigm. In this paper, we explore how RISC-V GPUs can support these warp-level features both through hardware implementation and via software-only approaches. Our evaluation shows that a hardware implementation achieves up to 4 times geomean IPC speedup in microbenchmarks, while software-based solutions provide a viable alternative for area-constrained scenarios.