Graph 500 | large-scale benchmarks (original) (raw)
Submission deadline for next BFS & SSSP is November 1st 2024!
Top Ten from June 2024 BFS
| Rank | Machine | Vendor | Installation Site | Location | Country | Year | Number of nodes | Number of cores | Scale | GTEPS |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Supercomputer Fugaku | Fujitsu | RIKEN Center for Computational Science (R-CCS) | Kobe Hyogo | Japan | 2020 | 152064 | 7299072 | 42 | 166029 |
| 2 | Wuhan Supercomputer | HUST | Wuhan Supercomputing Center | Wuhan | China | 2023 | 252 | 6999552 | 41 | 115357.6 |
| 3 | Frontier | HPE | DOE/SC/Oak Ridge National Laboratory | Oak Ridge TN | United States | 2021 | 9248 | 8730112 | 40 | 29654.6 |
| 4 | Pengcheng Cloudbrain-II | HUST-Pengcheng Lab-HUAWEI | Pengcheng Lab | ShenZhen | China | 2022 | 488 | 93696 | 40 | 28463.1 |
| 5 | Aurora | Intel/HPE | DOE/SC/Argonne National Laboratory | Argonne IL | United States | 2023 | 4096 | 25591808 | 40 | 24250.2 |
| 6 | Sunway TaihuLight | NRCPC | National Supercomputing Center in Wuxi | Wuxi | China | 2015 | 40768 | 10599680 | 40 | 23755.7 |
| 7 | Wisteria/BDEC-01 (Odyssey) | Fujitsu | Information Technology Center The University of Tokyo | Kashiwa Chiba | Japan | 2021 | 7680 | 368640 | 37 | 16118 |
| 8 | MareNostrum 5 ACC | Eviden | Barcelona Supercomputing Center | Barcelona | Spain | 2024 | 1120 | 680960 | 35 | 15737.43 |
| 9 | TOKI-SORA | Fujitsu | Japan Aerospace eXploration Agency (JAXA) | Tokyo | Japan | 2020 | 5760 | 276480 | 36 | 10813 |
| 10 | NAPS-FX1000 | Fujitsu | Japan Meteorological Agency | Tokyo | Japan | 2022 | 4608 | 221184 | 36 | 10158 |
Top Ten from June 2024 SSSP
| Rank | Machine | Vendor | Installation Site | Location | Country | Year | Number of nodes | Number of cores | Scale | GTEPS |
|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Wuhan Supercomputer | HUST | Wuhan Supercomputing Center | Wuhan | China | 2023 | 252 | 6999552 | 41 | 15335.9 |
| 2 | Pengcheng Cloudbrain-II | HUST-Pengcheng Lab-HUAWEI | Pengcheng Lab | ShenZhen | China | 2022 | 488 | 93696 | 40 | 11529.7 |
| 3 | Supercomputer Fugaku | Fujitsu | RIKEN Center for Computational Science (R-CCS) | Kobe Hyogo | Japan | 2020 | 82944 | 3981312 | 39 | 2126.45 |
| 4 | Tianhe Exascale Prototype Upgrade System | National University of Defense Technology | National Supercomputer Center in Tianjin | Tianjin | China | 2021 | 2048 | 131072 | 34 | 2054.35 |
| 5 | SuperMUC-NG | Lenovo | Leibniz Rechenzentrum | Garching | Germany | 2018 | 4096 | 196608 | 37 | 1053.93 |
| 6 | NERSC Cori - 1024 haswell partition | Cray | NERSC/LBNL | DOE/SC/LBNL/NERSC | United States | 2017 | 1024 | 32768 | 36 | 558.833 |
| 7 | Nurion | Cray | Korea Institute of Science and Technology Information | Daejeon | Korea Republic Of | 2018 | 1024 | 65536 | 36 | 337.239 |
| 8 | NERSC Cori - 512 KNL partition | Cray | NERSC/LBNL | DOE/SC/LBNL/NERSC | United States | 2017 | 512 | 32768 | 35 | 229.188 |
| 9 | Lise | Atos | Zuse Institute Berlin (ZIB) | Berlin | Germany | 2019 | 1270 | 121920 | 38 | 197.7 |
| 10 | Undisclosed Cray XE6 | Cray | National Computing Facility | University | United States | 2013 | 512 | 16384 | 34 | 134.173 |
The Graph 500 List
About Us
Brief Introduction
Data intensive supercomputer applications are increasingly important for HPC workloads, but are ill-suited for platforms designed for 3D physics simulations. Current benchmarks and performance metrics do not provide useful information on the suitability of supercomputing systems for data intensive applications. A new set of benchmarks is needed in order to guide the design of hardware architectures and software systems intended to support such applications and to help procurement. Graph algorithms are a core part of many analytic workloads.
Backed by a steering committee of over 50 international HPC experts from academia, industry, and national laboratories, Graph 500 will establish a set of large-scale benchmarks for these applications. The Graph 500 steering committee is in the process of developing comprehensive benchmarks to address three application kernels: concurrent search, optimization (single source shortest path), and edge-oriented (maximal independent set). Further, we are in the process of addressing five graph-related business areas: Cybersecurity, Medical Informatics, Data Enrichment, Social Networks, and Symbolic Networks.
This is the first serious approach to complement the Top 500 with data intensive applications. Additionally, we are working with the SPEC committee to include our benchmark in their CPU benchmark suite. We also maintain a list of the most energy efficient systems for data intensive computing. The Green Graph 500 will be released together with the Graph500 list. We anticipate the list will rotate between ISC and SC in future years.
The Graph 500 was announced at ISC2010 and the first list appeared at SC2010.