CuPBoP: Making CUDA a Portable Language
Open Access
- 21 June 2024
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 29 (4) , 1-25
Abstract
CUDA is designed specifically for NVIDIA GPUs and is not compatible with non-NVIDIA devices. Enabling CUDA execution on alternative backends could greatly benefit the hardware community by fostering a more diverse software ecosystem. To address the need for portability, our objective is to develop a framework that meets key requirements, such as extensive coverage, comprehensive end-to-end support, superior performance, and hardware scalability. Existing solutions that translate CUDA source code into other high-level languages, however, fall short of these goals. In contrast to these source-to-source approaches, we present a novel framework, CuPBoP , which treats CUDA as a portable language in its own right. Compared to two commercial source-to-source solutions, CuPBoP offers a broader coverage and superior performance for the CUDA-to-CPU migration. Additionally, we evaluate the performance of CuPBoP against manually optimized CPU programs, highlighting the differences between CPU programs derived from CUDA and those that are manually optimized. Furthermore, we demonstrate the hardware scalability of CuPBoP by showcasing its successful migration of CUDA to AMD GPUs. To promote further research in this field, we have released CuPBoP as an open-source resource.Keywords
Funding Information
- National Science Foundation (#2016701)
- Ministry of Science and ICT under the ITRC support program (IITP-2023-RS-2022-00156295)
This publication has 39 references indexed in Scilit:
- HIPLZ: Enabling performance portability for exascale systemsConcurrency and Computation: Practice and Experience, 2023
- Evaluation of Intel's DPC++ Compatibility Tool in heterogeneous computingJournal of Parallel and Distributed Computing, 2022
- pocl: A Performance-Portable OpenCL ImplementationInternational Journal of Parallel Programming, 2014
- Boosting CUDA Applications with CPU–GPU Hybrid ComputingInternational Journal of Parallel Programming, 2013
- From opencl to high-performance hardware on FPGAS2012
- Swan: A tool for porting CUDA programs to OpenCLComputer Physics Communications, 2011
- A real-time multigrid finite hexahedra method for elasticity simulation using CUDASimulation Modelling Practice and Theory, 2011
- Rodinia: A benchmark suite for heterogeneous computing2009
- The OpenCL specification2009
- LLVM: A compilation framework for lifelong program analysis & transformation2004