Program

Note: as CPC is a workshop whose proceedings are available only to participants, publication of papers and slides do not prevent a more formal copyrighted publication in another conference. However, some authors accepted to share their files (papers and/or slides) more openly, as provided in the program below.

Day 1: July 3, 2013 (Wednesday)

Time Event Files
08:45 Registration
09:15 Welcome address
Session 1. Runtime organizations of computations
Chair: Markus Püschel
09:30 Compiler Optimization of an Application-specific Runtime
Kathleen Knobe (Intel Corporation), Zoran Budimlić (Rice University)
10:00 Sparse Tiling for Unstructured Mesh Computations in the OP2 Framework
Fabio Luporini, Paul H. J. Kelly (Imperial College London), Carlo Bertolli (IBM Watson)
10:30 Coffee break
Session 2. Code analysis and optimizations
Chair: J. Nelson Amaral
11:00 Model-Driven Search-Based Loop Fusion Optimization for Handwritten Code
Ajay Panyala (Louisiana State University), Pamela Bhattacharya (UC Riverside), Gerald Baumgartner, J. Ramanujam (Louisiana State University)
11:30 Pointer-Based Divergence Analysis in the SSA Form
Shao-Chung Wang, Ming-Yu Hung, Jenq-Kuen Lee (Tsing-Hua University), Yuan-Shin Hwang (National Taiwan University of Science & Technology), Roy Dz-Ching Ju (Advanced Micro Devices)
12:00 Parallelizing Irregular Reductions Using Transactions
Miguel A. Gonzalez-Mesa, Eladio Gutierrez, Oscar Plata (University of Malaga)
12:30 Lunch break
Session 3. Polyhedral and tuple-based code representations
Chair: François Irigoin
14:00 Compilation of Structured Polyhedral Equations
Yun Zou, Guillaume Iooss, Sanjay Rajopadhye (Colorado State University)
14:30 Oil and Water can mix! Experiences with integrating Polyhedral and AST-based Transformations
Jun Shirako, Vivek Sarkar (Rice University)
15:00 Forelem: A Versatile Optimization Framework For Tuple-Based Computations
K. F. D. Rietveld, H. A. G. Wijshoff (LIACS Leiden)
15:30 Coffee break
Session 4. Parallel languages, X10
Chair: Henk Sips
16:00 Locality-Aware Load-Balancing Strategy Applied to PGAS Languages
Jeeva Paudel, J. Nelson Amaral (University of Alberta), Olivier Tardieu (IBM Watson)
16:30 SPIRE: A Methodology for Sequential to Parallel Intermediate Representation Extension
Dounia Khaldi, Pierre Jouvelot, François Irigoin, Corinne Ancourt (Mines ParisTech)
16:55 Determinacy Analysis of Polyhedral X10 Programs
Alain Ketterlin, Eric Violard (Camus, Strasbourg University), Paul Feautrier (Compsys, ENS-Lyon), Tomofumi Yuki, Sanjay V. Rajopadhye (Colorado State University), Vijay Saraswat (IBM Watson)
17:30 End of first day

Day 2: July 4, 2013 (Thursday)

Time Event Files
Session 5. Metrics and performances
Chair: Basilio B. Fraguela
09:00 Workload Partition for Heterogeneous Platforms
Jie Shen, Henk Sips (Delft University), Ana Lucia Varbanescu (University of Amsterdam)
09:30 Effectiveness of Program Transformations and Compilers for Directive-based Programming Models for GPGPUs
Swapnil Ghike, María J. Garzaran, David Padua (University of Illinois at Urbana-Champaign), Rubén Gran (Universidad de Zaragoza)
10:00 Applying the Roofline Model
Georg Ofenbeck, Ruedi Steinmann, Victoria Caparrós Cabezas, Daniele G. Spampinato, Markus Püschel (ETH Zürich)
10:30 Coffee break
Session 6. Metrics (cont’d) + parallelizing compilers
Chair: Michael O’Boyle
11:00 Progressive Compilation: New Metrics and Usages
Victor Lomüller, Henri-Pierre Charles (CEA-List Grenoble)
11:20 Parallelizing Equation-Based Models for Simulation on Multi-Core Platforms by Utilizing Model Structure
Martin Sjölund, Mahder Gebremedhin, Peter Fritzson (Linköping University)
11:45 OSCAR API v2.1: Extensions for an Advanced Accelerator Control Scheme to a Low-Power Multicore API
Keiji Kimura, Cecilia Gonzáles-Álvarez, Akihiro Hayashi, Hiroki Mikami, Mamoru Shimaoka, Jun Shirako, Hironori Kasahara (Waseda University)
12:10 Automatic Parallelization of Hand Written Automotive Engine Control Codes Using OSCAR Compiler
Dan Umeda, Yohei Kanehagi, Hiroki Mikami, Akihiro Hayashi, Keiji Kimura, Hironori Kasahara (Waseda University)
12:30 Lunch break
Social events

Day 3: July 5, 2013 (Friday)

Time Event Files
Session 7. Streams
Chair: Kathleen Knobe
09:00 Bringing Together FIFO Queues and Dynamic Scheduling for the Correct and Efficient Execution of Dynamic, Task-Parallel, Data-Flow Programs
Albert Cohen, Adrien Guatto, Nhat Minh Lê, Antoniu Pop (Parkas, ENS Paris)
09:30 A Framework to Schedule Parametric Dataflow Applications on Many-Core Platforms
Vagelis Bebelis, Pascal Fradet, Alain Girault (Inria Rhône-Alpes), Bruno Lavigueur (STMicroelectronics)
10:00 Dynamic Compilation of Parallel Audio Applications
Stéphane Letz, Yann Orlarey, Dominique Fober (GRAME Lyon)
10:30 Coffee break
Session 8. Portability and heterogeneous platforms
Chair: J. Ramanujam
11:00 Towards Global Composition of Performance-aware Components for GPU-based Systems
Usman Dastgeer, Christoph W. Kessler (Linköping University)
11:30 Identifying the Key Features of Intel Xeon Phi
Jianbin Fang, Ana Lucia Varbanescu, Henk Sips (Delft University)
12:00 Towards Automatic Cross-Platform Portable OpenCL Performance
Alberto Magni, Christophe Dubach, Michael O’Boyle (Edinburgh University)
12:30 Lunch break
Session 9. Portability (cont’d) + domain-specific languages (DSL)
Chair: Paul H. J. Kelly
14:00 Heterogeneous Programming Library: A Framework for Facilitating the Exploitation of Heterogeneous Systems
Moisés Vinãs, Basilio B. Fraguela (University of A Coruña), Zeki Bozkus (Khadir Has University)
14:30 A Domain-Specific Language and Compiler for Stencil Computations on Short-Vector SIMD and GPU Architectures
Tom Henretty, Justin Holewinski, P. Sadayappan, Atanas Rountev (Ohio State), Richard Veras, Franz Franchetti (Carnegie Mellon), Louis-Noël Pouchet (UCLA), J. Ramanujam (Louisiana State)
15:00 Persistent Asynchronous Adaptive Specialisation for Data-Parallel Array Processing in SAC
Clemens Grelck, Heinz Wiesinger (University of Amsterdam)
15:30 Coffee break
Session 10. Domain-specific languages (cont’d)
Chair: Albert Cohen
16:00 LARA-based Strategies for Targeting Multicore Architectures
Ricardo Nobre, Pedro Pinto, Tiago Carvalho, João M. P. Cardoso (University of Porto), Pedro C. Diniz (INESC-ID Lisbon)
16:30 Performance-Portable Finite-element Computations from High-level Specifications with FFC and PyOP2
Florian Rathgeber, Graham R. Markall, Nicolas Loriant, David A. Ham, Paul H. J. Kelly (Imperial College London), Lawrence Mitchell (University of Edinburgh), Carlo Bertolli (IBM Watson)
17:00 End of CPC’13