2021
DOI: 10.48550/arxiv.2103.10116
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Porting a sparse linear algebra math library to Intel GPUs

Yuhsiang M. Tsai,
Terry Cojean,
Hartwig Anzt

Abstract: With the announcement that the Aurora Supercomputer will be composed of general purpose Intel CPUs complemented by discrete high performance Intel GPUs, and the deployment of the oneAPI ecosystem, Intel has committed to enter the arena of discrete high performance GPUs. A central requirement for the scientific computing community is the availability of production-ready software stacks and a glimpse of the performance they can expect to see on Intel high performance GPUs. In this paper, we present the first pla… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 10 publications
0
1
0
Order By: Relevance
“…Sometimes, it is desirable to have explicit control over where the data is rather than delegating the management of memory to the SYCL runtime. In [36], the authors describe their customized porting flow for their platform-portable math library. They present a hierarchical view of CUDA and SYCL kernel calls and parameters for a clear understanding of the differences of the two programming models.…”
Section: Related Workmentioning
confidence: 99%
“…Sometimes, it is desirable to have explicit control over where the data is rather than delegating the management of memory to the SYCL runtime. In [36], the authors describe their customized porting flow for their platform-portable math library. They present a hierarchical view of CUDA and SYCL kernel calls and parameters for a clear understanding of the differences of the two programming models.…”
Section: Related Workmentioning
confidence: 99%