Skip to content. | Skip to navigation

  Programming Language Approaches to Concurrency and Communication-cEntric Software

Sections
Personal tools
You are here: Home
Log in


Forgot your password?
 

PLACES'12

Programming Language Approaches to Concurrency and Communication-cEntric Software

31st March 2012, Tallinn, Estonia

Workshop affiliated with

ETAPS 2012

 etaps-logo

PLACES'11 was in Saarbrücken with ETAPS
PLACES'10 was in Paphos with ETAPS
PLACES'09 was in York with ETAPS
PLACES'08 was in Oslo with DisCoTec


Theme and Goals

Applications today are built using numerous interacting services; soon off-the-shelf CPUs will host thousands of cores, and sensor networks will be composed from a large number of processing units. Many applications need to make effective use of thousands of computing nodes. At some level of granularity, computation in such systems is inherently concurrent and communication-centred.

To exploit and harness the richness of this computing environment, designers and programmers will utilise a rich variety of programming paradigms, depending on the shape of the data and control flow. Plausible candidates for such paradigms include structured imperative concurrent programming, stream-based programming, concurrent functions with asynchronous message passing, higher-order types for events, and the use of types for communications and data structures (such as session types and linear types), to name but a few. Combinations of these abstractions will be used even in a single application, and the runtime environment needs to ensure seamless execution without relying on differences in available resources such as the number of cores.

The development of effective programming methodologies for the coming computing paradigm demands exploration and understanding of a wide variety of ideas and techniques. This workshop aims to offer a forum where researchers from different fields exchange new ideas on one of the central challenges for programming in the near future, the development of programming methodologies and infrastructures where concurrency and distribution are the norm rather than a marginal concern.

Post-proceedings

 Post-proceedings, EPTCS 109

Invited Talk

Can GPGPU programming be liberated from the data-parallel bottleneck? A style of braided parallelism and its programs

Benedict Gaster, AMD

 

Abstract

With the success of programming models such as Khronos' OpenCL and NVIDIA's Cuda, Heterogeneous computing is going mainstream. However, these systems are low-level, even when considering them as systems programming models. They are effectively extended subsets of C99, limited to the type unsafe procedural abstraction that C has provided for more than 30 years. Computer systems programming has for more than two decades been able to do a lot better. One successful case in point is the systems programming language C++, known for its strong(er) type system and template and object-oriented abstraction features. A further limitation of the OpenCL/Cuda programming models is that, while they are intended to support a selection of different devices, to date they have really reflected the GPU programming model of the previous decade, i.e. they have focused on fine grain data-parallel workloads. What about other work-loads, e.g. task-parallel workloads? In this talk we introduce a model of braided parallelism and an object-oriented (based on C++11) programming model for heterogeneous computing - liberating GPGPU programming from its data-parallel bottleneck, while at the same time adopting modern programming abstractions.

We are grateful to AMD for funding Benedict Gaster's trip to PLACES.

Program Committee

Alastair Beresford _ University of Cambridge, UK
Mario Bravetti _ University of Bologna, Italy
Marco Carbone _ IT University of Copenhagen, Denmark
Alastair Donaldson _ Imperial College London, UK
Stephen Fink _ IBM T. J. Watson Research Center, USA
Simon Gay (co-chair) _ University of Glasgow, UK
Kohei Honda _ Queen Mary, University of London, UK
Lee Howes _ AMD
Paul Kelly (co-chair) _ Imperial College London, UK
Anton Lokhmotov _ ARM
David Pearce _ Victoria University of Wellington, New Zealand
Franz Puntigam _ Technical University of Vienna, Austria
Nikhil Swamy _ Microsoft Research, USA
Ana Lucia Varbanescu _ Vrije Universiteit Amsterdam, The Netherlands
Jan Vitek _ Purdue University, USA

Organizing Committee

Alastair Beresford _ University of Cambridge, UK
Simon Gay _ University of Glasgow, UK
Kohei Honda _ Queen Mary, University of London, UK
Alan Mycroft _ University of Cambridge, UK
Vasco Vasconcelos _ University of Lisbon, Portugal
Nobuko Yoshida _ Imperial College London, UK

Document Actions
« Julho 2014 »
Julho
Do
123456
78910111213
14151617181920
21222324252627
28293031