Hardware vs. Software Implementation of Warp-Level Features in Vortex RISC-V GPU
By: Huanzhi Pu , Rishabh Ravi , Shinnung Jeong and more
Potential Business Impact:
Makes computer graphics run much faster.
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.
Similar Papers
Decoupled Control Flow and Data Access in RISC-V GPGPUs
Hardware Architecture
Makes computer graphics chips faster for AI.
Optimal Software Pipelining and Warp Specialization for Tensor Core GPUs
Programming Languages
Makes computer graphics run much faster.
Accelerating Gravitational $N$-Body Simulations Using the RISC-V-Based Tenstorrent Wormhole
Distributed, Parallel, and Cluster Computing
Speeds up space simulations and saves energy.