MARCONI 100 (M100) is the new accelerated cluster acquired by CINECA, Italy, within PPI4HPC European initiative. MI100 is based on the IBM Power9 architecture with NVIDIA Volta GPUs and has a peak performance of 32 Pflops.
M100 became available in May 2020 to the European public and industrial researchers. In particular, the access to M100 is granted to users with approved projects for this platform (EUROfusion, PRACE, European HPC programs,…). EUROfusion community has 80 dedicated nodes of M100, which means a peak performance of 2.5 Pflops, to run fusion codes and boost the research in this field.
M100 opens the way to the pre-exascale Leonardo Supercomputer expected to be installed in 2021.
The EUROfusion High Level Support Team (HLST) will provide support to the fusion community to port their codes and take advantage of this new resource. One of the HLST member is Xavier Sáez from our Fusion Group. Lately, Xavier is attending EUROfusion webinars on GPUs to get ready for working with this new HPC system.
M100 Technical Information:
- Nodes: 980
- Processors: 2×16 cores IBM POWER9 AC922 at 3.1 GHz
- Accelerators: 4 x NVIDIA Volta V100 GPUs, Nvlink 2.0, 16GB
- Cores: 32 cores/node, Hyperthreading x4
- RAM: 256 GB/node (242 usable)
- Peak Performance: about 32 Pflop/s, 32 TFlops per node
- Internal Network: Mellanox IB EDR DragonFly++
- Disk Space: 8PB raw GPFS storage
Source: CINECA News