High Performance Computing
ACRC HPC systems
High Performance Computing
The University's HPC systems can be used to accelerate your computational research. High-performance computing (HPC) is the ability to process data and perform complex calculations at high speeds. Today, HPC is essential for many types of workloads, including AI/ML, physical simulations, and big data analysis.
BlueCrystal Phase 4
BlueCrystal Phase 4 (BC4) is available to all HPC users at the University of Bristol it is capable of up to 600 trillion calculations per second. BC4 is capable of supporting large parallel jobs and has a number of Nvidia P100 GPUs.
BluePebble is available to researchers across the University of Bristol, it is targeted for high throughput computing, and also has a number of GPUs and accelerators, large memory and other specialised requirements.
The ACRC team installed and maintains the BBSRC funded BlueCryo high-performance computing (HPC) cluster dedicated to image processing for the GW4 Cryo-EM facility which supports pioneering cryo-microsopy research at the University of Bristol.
National HPC Facilities
Isambard at GW4 is one of the EPSRC Tier-2 HPC facilities. Isambard provides multiple advanced architectures within the same system in order to enable evaluation and comparison across a diverse range of hardware platforms. Free access is available to academic researchers working in the EPSRC domain and from some UK universities; academic users from other domains and institutions can purchase access. Industry access is available. Isambard is an ARM based supercomputer. This is a Tier 2 site funded by EPSRC for the GW4 consortium, and Bristol academics have a share of the available capacity. ISAMBARD is led by Professor Simon Mcintosh-Smith from the University of Bristol. For more information about using Isambard please see the ISAMBARD documentation.
JADE is one of the EPSRC Tier-2 HPC facilities. The system design exploits the capabilities of NVIDIA's DGX-1 Deep Learning System which has eight of its newest Tesla P100 GPUs tightly coupled by its high-speed NVlink interconnect. The DGX-1 runs optimized versions of many standard machine learning software packages such as Caffe, TensorFlow, Theano and Torch. Free access is available to academic researchers working in the EPSRC domain and from some UK universities; academic users from other domains and institutions can purchase access. Industry access is available.
The ARCHER National supercomputer is primarily funded by EPSRC and NERC. If you wish to use Archer you will need to apply for resources on the ARCHER system. It is often useful to have performed test runs on BlueCrystal 4 to support your application.
2022 ACRC News
minimalmarkers: Accelerating a genotyping script from 10 days to 34 seconds to reduce its environmental impact. Read how this research acceleration was achieved with Research Software Enginneering support.