Wednesday, December 2nd, 2020
Bede, The N8’s new high performance GPU computing platform, is now open for users. Bede is the N8’s IBM Power9 + Nvidia GPU-based high-performance computing (HPC) platform. Unlike traditional x86 platforms, Bede is GPU-based and makes use of NVIDIA’s NV Link high-bandwidth interconnects to move tensor outputs between the GPU and system memory. This unique architecture is ideally suited to artificial intelligence (AI) and machine learning (ML) applications. Bede will also be able to work.. Read more »
Categories: CUDA, GPU, hardware, HPC, N8CIR, nvidia, Power9 | Comments Off on N8-CIR GPU Cluster (bede) now open
Wednesday, March 20th, 2019
Last year we asked for your input — how should we spend RLP funds to develop our computational resources on a year-by-year basis? On those recommendations we are procuring: more GPUs some very high memory (RAM) compute nodes more capacity for the CSF and more Cloud-based resources We are starting the work for next year’s RLP investment early! What do you believe we should procure, to enable your research? Please come along to one of.. Read more »
Categories: CSF, hardware, HPC, Uncategorized | Comments Off on More University investment in compute resources — your input required!
Wednesday, March 20th, 2019
A new computational resource is now available at The University of Manchester! It comprises 4096 cores of Intel Skylake all with low-latency, high-bandwidth, Infiniband interconnect. This new resource is intended to replace Polaris (the N8-HPC cluster) which was decommissioned last July. Our share of Polaris was about 750 cores, so this is a big compute capacity increase! Initially the HPC Pool will support jobs of up to 1024 cores. These resources are suitable for true.. Read more »
Categories: hardware, HPC, Uncategorized | Comments Off on New HPC Pool of computational resources
Wednesday, August 29th, 2018
We are pleased to announce that there has recently been a significant investment in The Central Shared Facility, The CSF, with over 1000 CPU cores and 16 Nvidia V100 GPUs coming online in the next few weeks — and further investment coming in the next few months! We realise that for some UoM researchers this still won’t meet their requirements and they will have out-grown the on-site platforms, such as the CSF. Also some researchers.. Read more »
Categories: HPC | Comments Off on National HPC (Tier-1) and Tier-2 Support