<i>chipStar</i> : Making HIP/CUDA applications cross-vendor portable by building on open standards

We describe chipStar , an open source software stack that enables building unmodified CUDA and HIP programs into binaries that rely solely on open cross-vendor compute standards OpenCL and SPIR-V. The relevant technical aspects of chipStar and the feature mismatches between the CUDA/HIP APIs and OpenCL are discussed along with a set of standard extension proposals to bridge the essential gaps in the future. The key benefit of the software stack is its portability, which is demonstrated by providing performance evaluations on a diversity of less common CPU/GPU platforms including RISC-V/PowerVR and ARM Mali. A comparison against the original AMD HIP platform provides a geometric mean of 0.75, a reasonable price to pay for the enhanced portability. chipStar is now considered mature enough for wider testing and even production use, which is demonstrated by successful porting and competitive performance of GAMESS-GPU-HF, a complex HPC application.

Authors

Institutions

Publication Details

Journal
The International Journal of High Performance Computing Applications
Published
2026-02-14
DOI
https://doi.org/10.1177/10943420261423001
Primary Topic
Parallel Computing and Optimization Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

chipStar : Making HIP/CUDA applications cross-vendor portable by building on open standards

Rahulkumar Gayatri, Michal Babej, Ben Ashbaugh, Colleen Bertoni et al.
The International Journal of High Performance Computing Applications
Parallel Computing and Optimization Techniques
article

chipStar : Making HIP/CUDA applications cross-vendor portable by building on open standards

Rahulkumar Gayatri, Michal Babej, Ben Ashbaugh, Colleen Bertoni, Kevin Harms, Henry Linjamaki, Wael Elwasif, Pekka Jääskeläinen, Philip C. Roth, Jisheng Zhao, Paulius Velesko, Brice Videau, Peng Tu, Jenny Chen, Karol Herbst, Sarbojit Sarkar
article en

Abstract

We describe chipStar , an open source software stack that enables building unmodified CUDA and HIP programs into binaries that rely solely on open cross-vendor compute standards OpenCL and SPIR-V. The relevant technical aspects of chipStar and the feature mismatches between the CUDA/HIP APIs and OpenCL are discussed along with a set of standard extension proposals to bridge the essential gaps in the future. The key benefit of the software stack is its portability, which is demonstrated by providing performance evaluations on a diversity of less common CPU/GPU platforms including RISC-V/PowerVR and ARM Mali. A comparison against the original AMD HIP platform provides a geometric mean of 0.75, a reasonable price to pay for the enhanced portability. chipStar is now considered mature enough for wider testing and even production use, which is demonstrated by successful porting and competitive performance of GAMESS-GPU-HF, a complex HPC application.

The International Journal of High Performance Computing Applications
Argonne National Laboratory (US), Oak Ridge National Laboratory (US), Georgia Institute of Technology (US), Red Hat (United States) (US), Intel (United States) (US), Lawrence Berkeley National Laboratory (US), Tampere University (FI), Purdue University West Lafayette (US), Nevada Space Grant Consortium (US), National Energy Research Scientific Computing Center (US)
Industry, innovation and infrastructure
Openalex Percentile: Top 70%
Parallel Computing and Optimization Techniques
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.