ARCHER2 Weekly Newsletter
By ARCHER2 Service on October 29, 2025
Tags: 
                  
                    
                    
- UKRI National Compute Resources (NCRs): Phase One and Phase Two
 - Autumn 2025 UKRI Access to HPC Call open (deadline 6 November 2025)
 - ARCHER2 Celebration of Science 2026
 - CONTINENTS webinar: Earth Embeddings: Learning Concept Maps in Neural Nets
 - ARCHER2 storage
 - GPU programming with kernels, Online, 29-30 October, 5-7 November 09:30 - 12:00
 - Efficient Parallel IO, Online, 25 November 2025 09:30 - 16:00
 - ARCHER2 Image and Video Competition 2025 results
 - Recently added known issues
 - Upcoming ARCHER2 training
 
UKRI National Compute Resources (NCRs): Phase One and Phase Two
This opportunity is seeking potential hosting entities for the first phase of UKRI investment in NCRs. Currently it is anticipated that up to £9.5 million will be available per NCR and at least two NCRs will be supported in this round. Further funds (up to £2 million p.a.) will be provided for each NCR from 2026-2031 to cover NCR service provision, power and other directly relevant costs necessary for user support. These services will support research across the whole UKRI remit.
This opportunity is open to potential host site providers and their support teams (‘hosting entities’ – hosting entities may be a single site or a partnership co-localised across sites) who have the experience and access to the necessary infrastructure (either through direct ownership or through suitable commercial arrangements) to host an NCR, can deliver the hardware components by March 2026 and can operate a full service for users commencing in the 2026/2027 financial year. The requirements for hosting entities are provided below. Deadline: 31 Oct 2025.
It is expected that the 2025/2026 UKRI investment in NCRs will fund:
- At least one CPU-based system and;
 - At least one heterogeneous or accelerated system.
 
Full details can be found on the UKRI website.
There is also an Expression of Interest (EoI) for future (Phase 2) phased investment in Financial Year 2026/2027 open. Applicants for the phase 1 NCR call are welcome to submit EoIs for phase 2. A second NCR hosting opportunity is expected to launch in early 2026. Deadline: 20 Nov 2025.
Autumn 2025 UKRI Access to HPC Call open
This opportunity provides an open and flexible route to computational support for high quality projects across the entire UK Research and Innovation (UKRI) remit.
We particularly encourage applications that:
- involve early career researchers
 - onboard and train new users
 - significantly push the boundaries in computational research using high performance computing (HPC) in your field
 
This application process is purely for compute resource for up to 12 months.
You must be based at a UK research organisation eligible for UKRI funding.
Deadline: 6 November 2025 4:00pm UK time
Full details available on the UKRI website
For all routes to access ARCHER2, see the ARCHER2 access page
ARCHER2 Celebration of Science 2026
We are pleased to announce that ARCHER2 Celebration of Science 2026 will take place on the 19th - 20th March 2026 in Edinburgh at South Hall, The University of Edinburgh.
Please register here to participate. The event is in-person and there is no registration fee.
What to expect at ARCHER2 Celebration of Science
ARCHER2 Celebration of Science is annual event that brings together the ARCHER2 user community to celebrate their scientific achievements on ARCHER2. You can explore the highlights of previous events here and view the science showcased in the previous years.
The two-day programme of ARCHER2 Celebration of Science 2026 will include:
- Invited talks: a variety of talks from the invited speakers highlighting their impactful research using ARCHER2.
 - Poster programme: a platform for the ARCHER2 community to present and discuss their successes delivered on ARCHER2 through the lightning talks and the poster session. A Best Poster Prize will be awarded. - Call for Posters is now open!
 - Keynote: the keynote will be given by Professor Mark Parsons, Director of EPCC.
 - Panel Session: focuses on key topics for the ARCHER2 and UK research community.
 - ARCHER2 User Forum: learn about the latest service updates and engage directly with the ARCHER2 team.
 - Diversity Session: an interactive session to discuss the equality, diversity and inclusion challenges related to the delivery of HPC services.
 
Registration, and Call for posters are open now. Full details here
CONTINENTS webinar: Earth Embeddings: Learning Concept Maps in Neural Nets
The International Collaboration Towards Net Zero Computational Modelling and Simulation (CONTINENTS), is hosting its next webinar on Wednesday the 12th of November at 15h30 UK time, and will be delivered by Marc Rußwurm from Wageningen University & Research, with the title: “Earth Embeddings: Learning Concept Maps in Neural Nets”
The abstract and calendar invite can be found on our website
There is no registration needed, please share this event with your contacts.
ARCHER2 storage
A reminder that there are four different file systems on ARCHER2 and each type of storage has different characteristics and policies, and is suitable for different types of use.
- Home file systems (/home)
 - Work file systems (/work)
 - Solid state (NVMe) file system (/scratch)
 - RDFaaS (RDF as a Service) file systems (/epsrc and /general)
 
It should be noted that all projects have the same, large quota of 250,000 GiB on the solid state file system to allow them to use it as a scratch file system. Remember, any files that have not been accessed in the last 28 days will be automatically deleted.
Further details can be found in the ARCHER2 documentation.
GPU programming with kernels
Online, 29-30 October, 5-7 November 09:30 - 12:00
This course, taking place over five morning sessions, will provide an introduction to GPU computing with HIP aimed at scientific application programmers wishing to develop their own software. The course will give a background on the difference between CPU and GPU architectures as a prelude to introductory exercises in HIP programming. The course will discuss the execution of kernels, memory management, among other topics.
The course will not discuss programming with compiler directives, but does provide a concrete basis of understanding of the underlying principles of the HIP model which is useful for programmers ultimately wishing to make use of OpenMP or OpenACC. The course will not consider graphics programming, nor will it consider machine learning packages.
Note that the course is also appropriate for those wishing to use NVIDIA GPUs via the CUDA API, although we will not specifically use CUDA. Pre-requisite Programming Languages:
Attendees must be able to program in C or C++. A familiarity with threaded programming models would be useful, but no previous knowledge of GPU programming is required.
Course attendees do not need GPU hardware, access to ARCHER2 will be provided.
Efficient Parallel IO
Online, 25 November 2025 09:30 - 16:00
One of the greatest challenges to running parallel applications on large numbers of processors is how to handle file IO. Standard Unix IO routines are not designed with parallelism in mind, and IO overheads can grow to dominate the overall runtime. Parallel file systems are optimised for large volumes of data, but performance can be far from optimal if every process opens its own file or if all IO is funnelled through a single controller process.
This hands-on course explores a range of issues related to parallel IO. It uses ARCHER2 and its parallel Lustre file system as a platform for the exercises; however, almost all the IO concepts and performance considerations are applicable to any parallel system.
We will give a general overview of the Lustre filesystem and how parallel IO is implemented in MPI-IO since these are the routines ultimately used by many higher-level libraries such as HDF5 and NetCDF. A good understanding of the performance characteristics of MPI-IO is therefore very useful in optimising the IO performance of most parallel applications.
The course does not teach the detailed syntax of the various parallel IO libraries, but the Fortran source code provided for the benchmarking application used in the practical sessions should be useful reference material. Prerequisites:
The course assumes an understanding of basic MPI programming in C, C++ or Fortran. Knowledge of MPI derived datatypes would be useful but not essential.
ARCHER2 Image and Video Competition 2025 results
We are very pleased to announce the results of the ARCHER2 Image and Video Competition 2025
Do visit the gallery of images and videos
Recently added known issues
The “Known Issues” page of the ARCHER2 Documentation https://docs.archer2.ac.uk/known-issues/ lists all current open known issues including a description of the issue, its symptoms and any work-arounds.
Following the ACF outage, most services have been returned to service successfully, however the ARCHER2 GPU nodes are still unavailable
Upcoming ARCHER2 Training
- Message-passing Programming with MPI, Online, Always open - self-service
 - Shared Memory Programming with OpenMP, Online, Always open - self-service
 - Hands-on Introduction to HPC, Online, Always open - self-service     
 - HPC Carpentry, Edinburgh, 23 and 30 October 2025 10:00 - 16:00
 - GPU programming with kernels, Online, 29-30 October, 5-7 November 09:30 - 12:00
 - Parallel Python, online webinar, Wednesday 19th November 2025 15:00 - 16:00
 - Efficient Parallel IO, Online, 25 November 2025 09:30 - 16:00
 
Further details of upcoming training
We always welcome researchers wishing to present their work in a webinar - please contact the Service Desk if you would be interested in presenting your work.