Posted: 28 Sep 2016 | 15:06
September seems to have passed by in a bit of a blur, and it's already a whole month since the CP2K Summer School, which we ran at King's College London (23-26th August), so I thought it would be a good time to give an update on the recent activities of the CP2K-UK project.
Posted: 4 Mar 2016 | 12:42
Last week we held the 3rd annual CP2K users group meeting down at Kings College London. Amazingly, we are already half-way through the 5-year 'CP2K-UK' project - the EPSRC-funded community support effort that I'm leading - how time flies! It was great to see these meetings continue to go from strength to strength. This year we had over 50 people there on the day from around the UK but also a significant proportion from overseas too! While the primary aim of our activities is to support the UK research community, if we have a wider impact that's of course a bonus.
Posted: 21 Jun 2015 | 20:02
The final analysis and future plans
A week ago we finished our 5 days of intensive work optimising CP2K (and to a lesser extent GS2) for Xeon Phi processors. As discussed in previous blog posts (Day4, Day3, Day2, Day1), this was done in conjunction with research engineers from Colfax, and built on the previous year's work on these codes by EPCC staff through the Intel-funded IPCC project.
Posted: 12 Jun 2015 | 15:41
MPI and vectorisation: Two ends of the optimisation spectrum
Day four of this week of intensive work optimising codes for Xeon Phi saw a range of work. The majority of the effort focussed on the vectorisation performance of CP2K and GS2; looking at the low level details of the computationally-intensive parts of these codes and seeing whether the compiler is producing vectorised codes, and if not is there anything that can be done to make the code vectorise.
Posted: 11 Jun 2015 | 16:01
Moving from OpenMP to vectorisation and MPI
Reality hit home a bit on the third day of our intensive week working with Colfax to optimise codes for the Xeon Phi.
After further implementation and analysis work it appears that the removal of the allocation and deallocation calls from some of the low level routines in CP2K will improve the OpenMP performance on Xeon and Xeon Phi, but only because there is an issue with the Intel compiler that is causing poor performance. The optimisation can see a reduction in runtime of around 20-30% for the OpenMP code, but only with versions 15 and 16 of the Intel compiler, on v14 there is a much smaller performance improvement.
Posted: 10 Jun 2015 | 00:08
Day 2: profiling and the start of optimising
After a first day spent getting codes set up and systems running, we got into the profiling of CP2K in anger today and have made some good progress.
Posted: 8 Jun 2015 | 17:48
Intel Parallel Computing Center collaboration with Colfax
We're just kicking off a week's collaboration with Colfax, a US technology company that collaborates heavily with Intel on Xeon Phi optimisation and training for the Xeon Phi.
Posted: 5 Mar 2015 | 09:36
Earlier this month we held the second annual CP2K User Group Meeting at King's College London, in the shadow of London's iconic 'Shard'. The meeting was even more popular than last year's, with around 60 people coming along to learn about the latest new features available in CP2K, and to hear from a wide range of existing users what they are doing with the code.
Posted: 21 Nov 2014 | 10:29
EPCC's Grand Challenges Optimisation Centre, an Intel Parallel Computing Centre which we announced earlier in the year, has made significant progress over recent months.
The collaboration was created to optimise codes for Intel processors, particularly to port and optimise scientific simulation codes for Intel Xeon Phi co-processors. As EPCC also runs the ARCHER supercomputer, which contains a large number of Intel Xeon processors (although no accelerators or co-processors), for EPSRC and other UK research funding councils, we also have a strong focus on ensuring that scientific simulation codes are highly optimised for these processors. Therefore, the IPCC work at EPCC has been concentrating on improving the performance of a range of codes that are heavily used for computational simulation in the UK on both Intel Xeon and Intel Xeon Phi processors.
Posted: 5 Sep 2014 | 19:50
I spent a couple of days last week at Imperial College's Department of Chemistry running a 2-day training course on CP2K. The course was hosted by NSCCS - the National Service for Computational Chemistry Software, and ARCHER - the National HPC Service we manage here in Edinburgh.
I've blogged before about the CP2K-UK project, a direct result of EPSRC's recognition of the growing community of CP2K users in the UK. Currently around £25,000 worth of CPU time is used per month on ARCHER for CP2K calculations, so it is important that users have access to the latest information on how to make the best use of the code.