Posted: 30 Mar 2016 | 17:46
Does array index order affect performance?
A couple of weeks ago I was teaching an ARCHER Modern Fortran course, and one of the things we discuss during the course is index ordering for multi-dimension arrays. This course is an introduction to modern Fortran (primarily F90/F95), so we don't go into lots of details about parallel or performance programming, but as attendees are likely to be using Fortran for computational simulation it is important they understand which array dimensions are contiguous in memory so that they don't accidentally write code that is much slower than it should be.
Figure 1: Performance using the GNU compiler
During one of the practical sessions on the course, one of the students wrote a little program to investigate the performance impact of iterating through array elements in a non-contiguous order. They also included some code to investigate if there is a performance impact when using allocatable array rather than static arrays (I'd mentioned it shouldn't impact performance but I obviously wasn't convincing enough...).
Posted: 14 Mar 2016 | 12:55
I love starting a new policy campaign. There’s this sweet spot of no responsibility between the time when you first raise an issue and the time when you’re first asked “Where’s the evidence?”. After that, life far more difficult.
Posted: 24 Feb 2016 | 16:41
Or why debugging is hard and parallel debugging doubly so
Debugging programs is hard. I give a lecture on debugging for the Programming Skills module of EPCC's MScs in HPC and HPC with Data Science where we try to point out common programming mistakes, programming strategies for making bugs less likely, and the skills and tools required for investigating, identifying, and fixing bugs.
Posted: 12 Feb 2016 | 12:11
The Collaborations Workshop (CW) is coming home to Edinburgh. It will be held on 21st-22nd March in the Royal College of Surgeons with an optional hack day on 23rd of March. The series of CWs were originally started under the now defunct Open Middleware Infrastructure Institute UK (OMII-UK) that held two workshops in Edinburgh in 2009 and 2010 in what was then the National e-Science Institute in Edinburgh. The aim of these workshops was to get researchers to come together, talk, avoid reinventing the wheel and to establish fruitful collaborations. It was, and has remained, a most excellent networking event.
Posted: 31 Jan 2016 | 23:07
Lancaster University, 7-8 April 2016
The programme for the HPC-CORE (High Performance Computing-based Computational fluid dynamics for Offshore Renewable Energy) workshop has now been published. This event brings together scientific specialists from Engineering, Atmospheric and Environmental Sciences, and HPC experts to discuss the state of the art for simulation software, and the leading-edge simulations being undertaken with such software.
Posted: 19 Nov 2015 | 11:11
One of the projects I'm currently leading at EPCC is ExTASY, which is building an 'Extensible Toolkit for Advanced Sampling and analYsis'. I've blogged in the past about the goals of the project, and the painful process leading up to our first public release. As the project is now well into its final year, we are turning our attention to community outreach - showing off what we have built to the biomolecular simulation community and getting their feedback.
Posted: 12 Nov 2015 | 13:49
A recent MSc project at EPCC has paved the way for improved diagnosis of eye-related conditions.
Posted: 5 Oct 2015 | 12:24
Since 2013, EPCC has hosted PRACE Summer of HPC (SoHPC) students for eight weeks from early July. I was involved with SoHPC for the first time this year as mentor of two Masters students, Jana Boltersdorf from FH Aachen University of Applied Sciences (Germany) and Ondřej Vysocký from Brno University of Technology (Czech Republic).
Posted: 23 Sep 2015 | 14:59
After a couple of years of measuring and trying to understand the power and energy consumption of (parallel) software and hardware, we have now released one of the key tools that we've been using as part of this research: the Adept Benchmark Suite!
While measuring performance (ie time to solution) is well understood, doing the same for power or energy is much less straightforward and often hardware dependent. The Adept Benchmark Suite relies on third party power measurement (such as instrumentation of the hardware) to be in place. However, to get users started with initial experiments, we provide a library to use RAPL (Running Average Power Limit) counters on Intel processors to measure the power of CPUs and memory, as well as some example code on how to use this library within the Adept Benchmarks.
Posted: 23 Sep 2015 | 09:33
They go by many names: “Hackathons”, “Hackdays, “Hackfests”, or my personal favourite “Code Dungeons”. Despite having heard most of these terms repeatedly over the years, I had no personal experience of them. To me, they sounded like competitive events to show off one’s skills. However, after attending Eurohack 2015 (yes, another alias) this past July, as well as a similar event organised earlier in the year by Intel, I was surprised to discover a whole new aspect of Hackathons: education and scientific advancement.