HIHE01-36: Evaluate how various topologies perform in the context of link failures [Slides]
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Study looks at the effect that failed links have on the throughput of HPC systems: What workloads are most effected? How many links need to be down before throughput of the machine is noticeably affected?
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC); USDOE National Nuclear Security Administration (NNSA)
- DOE Contract Number:
- NA0003525
- OSTI ID:
- 1842916
- Report Number(s):
- SAND2022-1084R; 703169
- Country of Publication:
- United States
- Language:
- English
Similar Records
Evaluating Trade-offs in Potential Exascale Interconnect Topologies
Evaluating the potential of disaggregated memory systems for HPC applications
Geomancy: Automated Performance Enhancement through Data Layout Optimization
Technical Report
·
Mon Aug 13 00:00:00 EDT 2018
·
OSTI ID:1468904
Evaluating the potential of disaggregated memory systems for HPC applications
Journal Article
·
Thu May 30 20:00:00 EDT 2024
· Concurrency and Computation. Practice and Experience
·
OSTI ID:2369149
Geomancy: Automated Performance Enhancement through Data Layout Optimization
Conference
·
Thu Oct 29 00:00:00 EDT 2020
·
OSTI ID:1657070