The Rephrase project showcases its ParaFormance technology in the latest HiPEAC magazine. For more information about ParaFormance visit www.paraformance.com or contact firstname.lastname@example.org.
Evgueni Kolossov, of PRQA, UK, gave an interview at the latest Embeded World Trade Fair in Nuremberg, Germany, in March 2017.
The intervew is published, and available here:
Our second year project workshop, HLPGPU 2017, was a huge success at HiPEAC in Stockholm yesterday. We had 9 high-quality research talks, including a keynote by Alistair Murray, a senior compiler engineer from CodePlay in Edinburgh.
We are looking forward to hosting many more successful HLPGPU events in the future.
We are now in the process of preparing a high-quality proceedings of the papers appearing in a special issue of a prestigious journal. We will also make the slides available from the workshop online in due course.
The programme for the 2017 HLPGPU workshop is now live! Join us at HiPEAC in Stockholm for a day packed full of high-quality talks. We are also very pleased and excited to have Alastair Murray from Codeplay, Edinburgh giving us an invited keynote.
10:00 – 10:10 Introduction
10:10 – 11:00 Keynote. Alastair Murray, CodePlay.
11:00 – 11:30 Coffee Break
11:30 – 12:00 The RePhrase Extended Pattern Set for Data Intensive Parallel Computing
Marco Danelutto, Massimo Torquati, Peter Kilpatrick, Gabriele Mencagli, Daniele De Sensi, Tiziano De Matteis and Marco Aldinucci
12:00 – 12:30 Obliterating Obstructions: Discovering Potential Parallelism by Slicing for Dependencies in Recursive Functions
Adam Barwell and Kevin Hammond
12:30 – 13:00 Automatically Deriving Cost Models for Structured Parallel Processes Using Hylomorphisms
David Castro, Kevin Hammond, Susmit Sarkar and Yasir Alguwaifli
13:00 – 14:00 Lunch Break
14:00 – 14:30 Verifying Parallel Code after Refactoring using Equivalence Checking
Moria Abadi, Sharon Keidar-Barner, Dmitry Pidan and Tatyana Veksler
14:30 – 15:00 Correct-by-Construction Program Transformations and Cost Modelling for Optimising Streaming Programs on FPGAs
Wim Vanderbauwhede and Waqar Nabi
15:30 – 16:00 Efficient Dynamic Pinning of Parallelized Applications by Distributed Reinforcement Learning
Georgios Chasparis and Michael Rossbory
15:30 – 16:00 Coffee Break
16:00 – 16:30 Multi-Device Controllers: A Library to Simplify the Parallel Heterogeneous Programming
Ana Moreton-Fernandez, Arturo Gonzalez-Escribano and Diego R. Llanos
16:30 – 17:00 Compiler Optimization of Accelerator Data Transfers
Matthew Ashcraft, Alexander Lemon, David Penry and Quinn Snell
17:00 – 17:30 Mobile Cloud for Parallel and Distributed Green Computing
Leszek Siwik, Dawid Kala, Mateusz Godzik, Wojciech Turek, Aleksander Byrski and Marek Kisiel-Dorohinicki
The RePhrase C++ Coding Standard project aims to make use of the functionality for mutli-threading and parallel programming including the use of patterns. These patterns may also have common pitfalls which appropriate can help mitigate against.
This standard adopts the view that restrictions should be placed on the use of the ISO C++ language without sacrificing its core flexibility. This approach allows for the creation of robust and easy to maintain programs while minimizing problems created either by compiler, diversity, different programming styles, or dangerous/confusing aspects of the language.
Please complete the form to participate in reviewing the standard.
Have a look around our new website! We've worked hard on making sure the content and style of the new site is just right for you. We have moved the focus to the activities of our project partners; created a new tools page that brings the latest and greatest information to you on the cutting edge tools produced on our project; a new news and events blog page to make sure you are kept up to date with all of our news; a contact page so you can directly in touch with us; finally, all of our deliverables and publications are available directly through the website. Take a look around and get in touch if you like it!
In the last decade processors clock frequency has not seen any major improvements while at the same time energy consumption has become a concern. As a consequence there has been a paradigm shift in many domains from sequential computing towards parallel processing with a transition to parallel heterogeneous computers. However the use of multiple divergent architectures with different programming models has made programming increasingly difficult and costly. To overcome this difficulties software reegineering may help to simplify the development process. In this talk I will explore what are the some of the challenges and provide some examples to overcome them. During the talk I will focus in examples using latest version of the C++ programming language, paying attention to its current status and evolution roadmap.
Jose Daniel Garcia from Madrid gives a series at the Compilers For Parallel Computing Workshop. preliminary program .
Jose Daniel from Madrid gave a talk at the ACCU conference in Bristol, UK. You can go here for the youtube video, and here for the slides.
Marco Aldinucci is organising a FastData event at the Computer Science department of the University of Torino. It is a one day workshop for researchers, students and industry to discuss data analytics and HPC.