Third Workshop on

Programmability Issues for Multi-Core Computers
(MULTIPROG)



Held in conjunction with:
the 5th International Conference on
High-Performance and Embedded Architectures and Compilers (HiPEAC)

Pisa, Italy, January 24, 2010


Computer manufacturers have already embarked on the multi-core roadmap, promising to double the number of processors on a chip every other year, and many-cores are on the horizon. This shift to an increasing number of cores and heterogeneous architectures has placed new burdens on the programming community. Until now, software has been developed with a single processor in mind and it needs to be parallelized (and optimized for accelerators such as GPUs) to take advantage of the new breed of multi-/many-core computers. As a result, progress in how to easily harness the computing power of multi-core architectures is in great demand.

The third edition of the MULTIPROG workshop aimed to bring together, and cause fruitful interaction between, researchers interested in programming models and their implementation and in computer architecture with the common interest in advancing our knowledge how to simplify the task of parallelization of software for multi-core platforms. A wide spectrum of issues were central themes for this workshop such as what the future programming models should look like to accelerate software productivity and how it should be implemented at the runtime, the compiler, and the architecture level.

MULTIPROG is intended for quick publication of early results, work-in-progress, etc, and is not intended to prevent later publication of extended papers. We prioritized papers addressing cross-cutting issues and that provide thought-provoking insights into the main themes. All the paperswere published on the workshop informal proceedings. Some papers were selected for a special issue of Transactions on HiPEAC, after a new review process.

Topics of interest

Papers were sought on topics including, but not limited to:

Final program

PDF file with all papers included in the informal proceedings.

09:00-10:00Keynote session:
Making Sense of Transactional Memory
Tim Harris, Microsoft Research Cambridge.
10:00-10:30Best Paper
Noninvasive concurrency with Java STM
G. Korland (Tel Aviv U.) N. Shavit (Tel Aviv U.), P. Felber (U. of Neuchatel)
10:30-11:00Coffee break
11:00-12:30Session 1
Parallelizing Barnes-Hut Method on the Cell BE Architecture
B. Demioz (Bogazici U.), H. Topcuoglu (Marmara U.), M. Kandemir (Pennsylvania State U.), O. Tosun (Bogazici U.)
Expressing Inter-task Dependencies between Parallel Stencil Operations
P. Larsen, S. Karlsson, J. Madsen (Dept. of Informatics, Technical University of Denmark)
A Performance Comparison of some recent Task-based Parallel Programming Models
A. Podobas (KTH), M. Brorsson (KTH and Swedish Institute of Computer Science), K. Faxén (Swedish Institute of Computer Science)
12:30-14:00Lunch
14:00-15:30 Session2
Handling of shared memory in many-core processors without locks and transactional memory
A. Vajda (Ericsson)
J-DSE: Joint Software and Hardware Design Space Exploration for Application Specific Processors
M. Paolieri (BSC), I. Bonesana (SUPSI), R. Gioiosa (BSC), M. Valero (UPC / BSC)
Building a Java Map-Reduce Framework for Multi-core Architectures
G. Kovoor; J. Singer, M. Lujan (U. of Manchester)

Organizers

Eduard AyguadeUPC/Barcelona Supercomputing CenterSpaineduard[at]ac.upc.edu
Roberto GioiosaIBM Research - WatsonUSArgioios[at]us.ibm.com
Per StenstromChalmers University of TechnologySwedenpers[at]chalmers.se
Osman UnsalBSC-Microsoft Research CentreSpainosman.unsal[at]bsc.es

Program committee

Mohammad AnsariUniversity of ManchesterUK
Francois BodinCAPS EntrepriseFrance
Mats BrorssonKTHSweden
Magnus EkmanNVIDIAUSA
Pascal FelberUniversity of NeuchatelSwitzerland
Maria GarzaranUniversity of Illinois, Urbana-ChampaignUSA
Guang GaoUniversity of DelawareUSA
Roberto GiorgiUniversity of SienaItaly
Tim HarrisMicrosoft Research CambridgeUK
Stefanos KaxirasUniversity of PatrasGreece
Mikel LujanUniversity of ManchesterUK
Milo MartinUniversity of PennsylvaniaUSA
Ami MarowkaBar-Ilan UniversityIsrael
Avi MendelsonMicrosoftIsrael
Dimitris NikolopoulosFORTH-ICSGreece
Oscar PlataUniversity of MalagaSpain
Andre SeznecINRIA/IRISAFrance
Nir ShavitTel Aviv UniversityIsrael
Peng WuIBM Research WatsonUSA


Webmaster: eduard[at]ac.upc.edu