High-performance GPU compressors have been developed and optimized primarily for NVIDIA GPUs, but many are not easily portable to other GPU architectures. This limits their applicability on heterogeneous platforms, including those used in U.S. exascale supercomputers. This project aims to design and implement architecture-agnostic GPU compression techniques that achieve performance portability across major GPU ecosystems (e.g., NVIDIA, AMD, and Intel), enabling broader adoption in large-scale scientific computing and AI workloads.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Part-time
Career Level
Intern
Education Level
No Education Listed