HPL-MxP Benchmark: Mixed-Precision Algorithms, Iterative Refinement, and Scalable Data Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915510786981888 |
|---|---|
| author | Dongarra, Jack Luszczek, Piotr |
| author_facet | Dongarra, Jack Luszczek, Piotr |
| contents | We present a mixed-precision benchmark called HPL-MxP that uses both a lower-precision LU factorization with a non-stationary iterative refinement based on GMRES. We evaluate the numerical stability of one of the methods of generating the input matrix in a scalable fashion and show how the diagonal scaling affects the solution quality in terms of the backward-error. Some of the performance results at large scale supercomputing installations produced Exascale-level compute throughput numbers thus proving the viability of the proposed benchmark for evaluating such machines. We also present the potential of the benchmark to continue increasing its use with proliferation of hardware accelerators for AI workloads whose reliable evaluation continues to pose a particular challenge for the users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19618 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HPL-MxP Benchmark: Mixed-Precision Algorithms, Iterative Refinement, and Scalable Data Generation Dongarra, Jack Luszczek, Piotr Numerical Analysis Performance We present a mixed-precision benchmark called HPL-MxP that uses both a lower-precision LU factorization with a non-stationary iterative refinement based on GMRES. We evaluate the numerical stability of one of the methods of generating the input matrix in a scalable fashion and show how the diagonal scaling affects the solution quality in terms of the backward-error. Some of the performance results at large scale supercomputing installations produced Exascale-level compute throughput numbers thus proving the viability of the proposed benchmark for evaluating such machines. We also present the potential of the benchmark to continue increasing its use with proliferation of hardware accelerators for AI workloads whose reliable evaluation continues to pose a particular challenge for the users. |
| title | HPL-MxP Benchmark: Mixed-Precision Algorithms, Iterative Refinement, and Scalable Data Generation |
| topic | Numerical Analysis Performance |
| url | https://arxiv.org/abs/2509.19618 |