Started in 1993, the TOP500 lists the fastest computers used today, ranked according to Linpack benchmark results. Published twice a year, the TOP500 list provides an important tool for tracking usage trends in high-performance computing. The 50th TOP500 List was released during the June Supercomputing’18 conference.
TOP500 50th List Highlights
Mellanox connects 43 percent of overall TOP500 platforms or 216 systems, including both InfiniBand and Ethernet, compared to 192 systems in Nov’17, representing 13% increase in six months. InfiniBand accelerates nearly 60 percent of the total HPC systems on the list and is the most used high-speed interconnect for the top 100, 200, 300 and 400 systems. InfiniBand is the interconnect of choice for HPC and AI infrastructures.
Highlights of InfiniBand and Mellanox usage on the June 2018 TOP500 list:
- Mellanox connects 43% of overall TOP500 systems or 216 systems (InfiniBand and Ethernet), compared to 192 systems in Nov’17, 13% increase
- InfiniBand accelerates the fastest HPC and AI supercomputer in the world – Oak Ridge National Laboratory ‘Summit’ system
- InfiniBand accelerates 4 of the top 5 supercomputers in the world - #1 (USA), #2 (China), #3 (USA), #5 (Japan); and overall 140 systems on the list
- InfiniBand connects nearly 60% of overall HPC systems on the TOP500 list
- InfiniBand is the most used high-speed interconnect for the top 100, 200, 300 and 400 systems
- Mellanox connects 76 Ethernet systems (all 25G and faster), or 31% of total Ethernet systems
- The TOP500 list has evolved to Include both HPC and Cloud / Hyperscale (non-HPC) platforms
- Nearly half of the platforms on the TOP500 list can be categorized as non-HPC application platforms (mostly Ethernet-based)
- InfiniBand is the interconnect of choice for HPC and AI infrastructures
- Mellanox Ethernet is the interconnect of choice for Cloud and Hyperscale platforms
Mellanox ConnectX-5 EDR 100Gb/s InfiniBand adapters, Switch-IB2 based switch systems and LinkX fiber and copper cables optimize server and storage performance and provide the scalable, low-latency, and power-efficient interconnect for the world’s fastest supercomputers.