Unparalleled Parallelism? CPU & GPU Architecture Trends and Their Implications for HPC Software
| dc.contributor.author | Morgenstern, Laura | |
| dc.contributor.author | Kabadshow, Ivo | |
| dc.contributor.author | Werner, Matthias | |
| dc.date.accessioned | 2021-03-11T10:45:36Z | |
| dc.date.available | 2021-03-11T10:45:36Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | The free lunch is over – again? In 2004, Herb Sutter observed the stagnation of clock frequencies and predicted hyperthreading and multicore capabilities as drivers for performance growth on CPUs. This prediction and the resulting advice to focus more on concurrency to achieve sustainable application performance, has become the daily reality of HPC software engineers. In this paper, we compare trends in the development of CPU and GPU architectures and examine their implications for the parallelization and portability of HPC software. The data analysis still reveals levelling clock frequencies but this time also for GPUs. Additionally, an increasing amount of hardware parallelism can be observed for both architectures. | en |
| dc.identifier.doi | 10.18420/fgbs2021f-02 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/35785 | |
| dc.language.iso | en | |
| dc.publisher | Gesellschaft für Informatik e.V. | |
| dc.relation.ispartof | Tagungsband des FG-BS Frühjahrstreffens 2021 | |
| dc.subject | CPU | |
| dc.subject | GPU | |
| dc.subject | multicore architectures | |
| dc.subject | GPGPU | |
| dc.title | Unparalleled Parallelism? CPU & GPU Architecture Trends and Their Implications for HPC Software | en |
| dc.type | Text | |
| gi.citation.publisherPlace | Bonn | |
| gi.conference.date | 11.-12. März 2021 | |
| gi.conference.location | Wiesbaden | |
| gi.document.quality | digidoc |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- Paper02.pdf
- Größe:
- 386.14 KB
- Format:
- Adobe Portable Document Format