poster

CuPBoP: A Framework to Make CUDA Portable

Authors:

Hyesoon KimAuthors Info & Claims

PPoPP '23: Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming

Pages 444 - 446

https://doi.org/10.1145/3572848.3577504

Published: 21 February 2023 Publication History

Get Access

Abstract

CUDA, as one of the most popular choices for GPU programming, can be executed only on NVIDIA GPUs. To execute CUDA on non-NVIDIA devices, researchers have proposed to translate CUDA to other programming languages. However, this approach cannot achieve high coverage due to the challenges in source-to-source translation.

We propose a framework, CuPBoP, that executes CUDA programs on non-NVIDIA devices without relying on other programming languages. CuPBoP consists of two parts. The compilation part applies transformations on CUDA host/kernel IRs. The runtime part consists of the runtime libraries for CUDA built-in functions. For the CPU backends, compared with the existing frameworks, CuPBoP achieves the highest coverage on all CPUs that we evaluate (x86, aarch64, RISC-V).

We make CuPBoP publicly available to inspire more works in this area ¹.

References

[1]

2020. HIP-CPU. https://github.com/ROCm-Developer-Tools/HIP-CPU

Google Scholar

[2]

2022. NVIDIA document. https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#special-registers

Google Scholar

[3]

Shuai Che, Michael Boyer, Jiayuan Meng, David Tarjan, Jeremy W Sheaffer, Sang-Ha Lee, and Kevin Skadron. 2009. Rodinia: A benchmark suite for heterogeneous computing. In 2009 IEEE international symposium on workload characterization (IISWC). Ieee, 44--54.

Digital Library

Google Scholar

[4]

Ruobing Han, Jaewon Lee, Jaewoong Sim, and Hyesoon Kim. 2022. COX: Exposing CUDA Warp-Level Functions to CPUs. ACM Transactions on Architecture and Code Optimization (TACO) (2022).

Google Scholar

[5]

Chris Lattner. 2008. LLVM and Clang: Next generation compiler technology. In The BSD conference, Vol. 5. 1--20.

Google Scholar

[6]

NVIDIA. 2012. NVVM. https://docs.nvidia.com/cuda/nvvm-ir-spec/index.html#abstract

Google Scholar

[7]

James Reinders, Ben Ashbaugh, James Brodman, Michael Kinsner, John Pennycook, and Xinmin Tian. 2021. Data parallel C++: mastering DPC++ for programming of heterogeneous systems using C++ and SYCL. Springer Nature.

Google Scholar

[8]

John A Stratton, Vinod Grover, Jaydeep Marathe, Bastiaan Aarts, Mike Murphy, Ziang Hu, and Wen-mei W Hwu. 2010. Efficient compilation of fine-grained SPMD-threaded programs for multicore CPUs. In Proceedings of the 8th annual IEEE/ACM international symposium on Code generation and optimization. 111--119.

Digital Library

Google Scholar

[9]

John A Stratton, Sam S Stone, and Wen-Mei W Hwu. 2008. MCUDA: An efficient implementation of CUDA kernels for multi-core CPUs. In International Workshop on Languages and Compilers for Parallel Computing. Springer, 16--30.

Digital Library

Google Scholar

[10]

Yao Zhang, Mark Sinclair, and Andrew A Chien. 2013. Improving performance portability in OpenCL programs. In International Super-computing Conference. Springer, 136--150.

Crossref

Google Scholar

Cited By

View all

Tian SScogland TChapman BDoerfert J(2023)OpenMP Kernel Language Extensions for Performance Portable GPU CodesProceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis10.1145/3624062.3624164(876-883)Online publication date: 12-Nov-2023
https://dl.acm.org/doi/10.1145/3624062.3624164

Index Terms

CuPBoP: A Framework to Make CUDA Portable
1. Computing methodologies
  1. Parallel computing methodologies

Recommendations

Vectorizing Unstructured Mesh Computations for Many-core Architectures
PMAM'14: Proceedings of Programming Models and Applications on Multicores and Manycores

Achieving optimal performance on the latest multi-core and many-core architectures depends more and more on making efficient use of the hardware's vector processing capabilities. While auto-vectorizing compilers do not require the use of vector ...
Vectorizing Unstructured Mesh Computations for Many-core Architectures
PMAM'14: Proceedings of Programming Models and Applications on Multicores and Manycores

Achieving optimal performance on the latest multi-core and many-core architectures depends more and more on making efficient use of the hardware's vector processing capabilities. While auto-vectorizing compilers do not require the use of vector ...
A performance study of general-purpose applications on graphics processors using CUDA

Graphics processors (GPUs) provide a vast number of simple, data-parallel, deeply multithreaded cores and high memory bandwidths. GPU architectures are becoming increasingly programmable, offering the potential for dramatic speedups for a variety of ...

Comments

Information & Contributors

Information

Published In

PPoPP '23: Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming

February 2023

480 pages

ISBN:9798400700156

DOI:10.1145/3572848

General Chair:
Maryam Mehri Dehnavi
University of Toronto
,
Program Chairs:
Milind Kulkarni
Purdue University
,
Sriram Krishnamoorthy
Google

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 21 February 2023

Check for updates

Author Tags

Qualifiers

Poster

Conference

PPoPP '23

Sponsor:

PPoPP '23: The 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming

February 25 - March 1, 2023

QC, Montreal, Canada

Acceptance Rates

Overall Acceptance Rate 230 of 1,014 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
254
Total Downloads

Downloads (Last 12 months)152
Downloads (Last 6 weeks)8

Reflects downloads up to 27 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Tian SScogland TChapman BDoerfert J(2023)OpenMP Kernel Language Extensions for Performance Portable GPU CodesProceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis10.1145/3624062.3624164(876-883)Online publication date: 12-Nov-2023
https://dl.acm.org/doi/10.1145/3624062.3624164

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Vectorizing Unstructured Mesh Computations for Many-core Architectures

Vectorizing Unstructured Mesh Computations for Many-core Architectures

A performance study of general-purpose applications on graphics processors using CUDA