Guest Lectures 2013-2014

Lecture abstracts

Note: lecture materials are all publicly available but require a password due to the configuration of the University's file-hosting service​. When prompted, enter "EPCCguestlectures" .

High Performance Computing: Driving innovation and capability (February 2014)
Iain Wardrope, Intel UK 

Iain will provide an insight into future HPC technology development looking at hardware trends, ecosystem support and the challenges around Exascale computing.
The talk will also touch upon the convergence of High Performance Computing and High Performance Data Analytics, examining where the effective use of this rapidly maturing capability can provide industry and academia with a competitive advantage.

Downloads: Podcast (MP3) Slides (PDF)

Solar analysis: the journey from two weeks to one hour with HPC (March 2014)
Steven Turner, Integrated Environmental Solutions 

Performing complex solar shading analysis to take into account the sun's path and solar penetration on large buildings has historically consumed very many CPU cycles for IES "Virtual Environment" (3D building physics) simulation users. One particularly complex model took almost 2 weeks to process.
A description of the collaboration between IES and EPCC to apply HPC practices to the solar analysis algorithm and benchmark results will be presented. Additionally we will cover the pitfalls found when integrating the MPI solution in a commercial environment and how we addressed these.
The presentation will conclude with a brief description of in-progress and potential future developments with EPCC.
Downloads: Podcast (MP3) Slides (PDF)

Adventures in the Biology trade: Bioinformatics in the Petabyte era (March 2014)
Dr Hugh Shanahan, Royal Holloway University of London 

Bioinformatics and more widely Computational Biology is a largely data-driven science. The array of high-throughput technology platforms in the last 10 years mean that the amount of data being generated in this field is likely to enter into Exabytes by 2020. The challenges associated with this are quite different from the data sets generated by High Energy Physics or Astrophysics in that they tend to gathered from a wide variety of different providers. Meta-analyses of these data sets can give startling new insights but come with many caveats - in particular that the quality of the data from each provider can be highly variable. I will spend some time talking about one set of experiences I have dealing with one specific technology platform and in particular how it is clear that the detection of bias in data sets is a key element of any high-throughput analysis. 
Downloads: Podcast (MP3) Slides (PDF)

C++ for Heterogeneous Parallelism (March 2014)
Paul Keir, Codeplay

Codeplay are internationally recognized experts in advanced optimizing technologies, compilers and programmable graphics. We have been providing acceleration solutions that optimize performance for graphics semiconductor designers and AAA game developers since 1999.
In the semiconductor sector, Codeplay partners with leading chip manufacturers, such as Qualcomm and Movidius; helping them to exploit the full potential of their chipsets, and accelerate time-to-market. Codeplay are also a leading participant in a number of European FP7 research projects including Peppher, LPGPU, and CARP. Meanwhile, as a highly active member of the Khronos Group, Codeplay work towards the design of the next generation of the OpenCL standard.
In this talk I will give an overview of Codeplay's motivations and contributions towards the use of C++ for heterogeneous concurrent and parallel processing. This has included extensions to the semantics, control structures, and type system of the C++ language. Details of an exciting new C++ parallel language technology will also be introduced.
Downloads: Slides (PDF)

Contact us

Mr Ben Morse
+44 (0) 131 651 3398
msc@epcc.ed.ac.uk

Connect with the MSc programmes via Facebook.