26931

CuPBoP: CUDA for Parallelized and Broad-range Processors

Ruobing Han, Jun Chen, Bhanu Garg, Jeffrey Young, Jaewoong Sim, Hyesoon Kim
Georgia Institute of Technology
arXiv:2206.07896 [cs.DC], (16 Jun 2022)

@misc{https://doi.org/10.48550/arxiv.2206.07896,

   doi={10.48550/ARXIV.2206.07896},

   url={https://arxiv.org/abs/2206.07896},

   author={Han, Ruobing and Chen, Jun and Garg, Bhanu and Young, Jeffrey and Sim, Jaewoong and Kim, Hyesoon},

   keywords={Distributed, Parallel, and Cluster Computing (cs.DC), Hardware Architecture (cs.AR), FOS: Computer and information sciences, FOS: Computer and information sciences},

   title={CuPBoP: CUDA for Parallelized and Broad-range Processors},

   publisher={arXiv},

   year={2022},

   copyright={arXiv.org perpetual, non-exclusive license}

}

Download Download (PDF)   View View   Source Source   

748

views

CUDA is one of the most popular choices for GPU programming, but it can only be executed on NVIDIA GPUs. Executing CUDA on non-NVIDIA devices not only benefits the hardware community, but also allows data-parallel computation in heterogeneous systems. To make CUDA programs portable, some researchers have proposed using source-to-source translators to translate CUDA to portable programming languages that can be executed on non-NVIDIA devices. However, most CUDA translators require additional manual modifications on the translated code, which imposes a heavy workload on developers. In this paper, CuPBoP is proposed to execute CUDA on non-NVIDIA devices without relying on any portable programming languages. Compared with existing work that executes CUDA on non-NVIDIA devices, CuPBoP does not require manual modification of the CUDA source code, but it still achieves the highest coverage (69.6%), much higher than existing frameworks (56.6%) on the Rodinia benchmark. In particular, for CPU backends, CuPBoP supports several ISAs (e.g., X86, RISC-V, AArch64) and has close or even higher performance compared with other projects. We also compare and analyze the performance among CuPBoP, manually optimized OpenMP/MPI programs, and CUDA programs on the latest Ampere architecture GPU, and show future directions for supporting CUDA programs on non-NVIDIA devices with high performance
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: