Advanced Program

Tuesday, September 11:

9:30AM – 9:40AM: Opening Remarks, Hironori Kasahara and Keiji Kimura

9:40AM – 10:40AM: Keynote I
Arvind, Massachusetts Institute of Technology

10:40AM – 11:00AM: break

11:00AM – 11:45AM: Invited Talk I
David Padua, University of Illinois at Urbana-Champaign

11:45AM – 12:45PM: Session 1, Compiler Optimizations

AlphaZ: A System for Design Space Exploration in the Polyhedral Model
Tomofumi Yuki (Colorado State University), Gautam Gupta (CORESPEQ), DaeGon Kim (CORESPEQ), Tanveer Pathan (CORESPEQ), Sanjay Rajopadhye (Colorado State University)
Compiler Optimizations: Machine Learning versus O3
Yuriy Kashnikov (UVSQ – ECR), Jean Christophe Beyler (Intel France – ECR), William Jalby (UVSQ – ECR)

12:45PM – 13:45PM: lunch

13:45PM – 14:30PM: Invited talk II
Lawrence Rauchwerger, Texas A&M University

14:30PM – 16:00PM: Session 2, Tools and Libraries

The STAPL Parallel Graph Library
Harshvardhan (Texas A&M University), Adam Fidel (Texas A&M University), Nancy M. Amato (Texas A&M University), Lawrence Rauchwerger (Texas A&M University)
Set and Relation Manipulation for the Sparse Polyhedral Framework
Michelle Mills Strout (Colorado State University), Geri Georg (Colorado State University), Catherine Olschanowsky (Colorado State University)
Parallel Clustered Low-rank Approximation of Graphs and Its Application to Link Prediction
Xin Sui (University of Texas at Austin), Tsung-Hsien Lee (University of Texas at Austin), Joyce Jiyoung Whang (University of Texas at Austin), Berkant Savas (Linköpings universitet), Saral Jain (University of Texas at Austin), Keshav Pingali (University of Texas at Austin), Inderjit Dhillon (University of Texas at Austin)

16:00PM – 16:20PM: break

16:20PM – 17:20PM: Session 3, Heterogeneous Systems

OmpSs-OpenCL Programming Model for Heterogeneous Systems
Vinoth Krishnan Elangovan (Barcelona Supercomputing Center), Rosa. M. Badia (Barcelona Supercomputing Center), Eduard Ayguade Parra (Barcelona Supercomputing Center)
Compiler Optimizations for Industrial Unstructured Mesh CFD Applications on GPUs
Carlo Bertolli (Imperial College London), Adam Betts (Imperial College London), Nicolas Loriant (Imperial College London), Gihan R. Mudalige (Oxford e-Research Centre), David Radford (Rolls Royce Plc.), Michael B. Giles (University of Oxford), Paul H.J. Kelly (Imperial College London)

18:00PM – : Banquet


Wednesday, September 12:

9:00AM – 10:00AM: Keynote II
David Kuck, Intel, Professor Emeritus University of Illinois at Urbana-Champaign

10:00AM – 10:15AM: break

10:15AM – 11:00AM: Invited talk III
Alex Nicolau, University of California, Irvine

11:00AM – 12:00PM: Session 4, Finegraine Optimizations

UCIFF: Unified Cluster assignment Instruction scheduling and Fast Frequency selection for heterogeneous clustered VLIW cores
Vasileios Porpodas (University of Edinburgh), Marcelo Cintra (University of Edinburgh)
A Study On The Impact Of Optimization Phase Ordering On High-Level Synthesis
Jason Cong (University of California, Los Angeles), Bin Liu (University of California, Los Angeles), Raghu Prabhakar (University of California, Los Angeles), Peng Zhang (University of California, Los Angeles)

12:00PM – 13:00PM: lunch

13:00PM – 13:45PM: Invited talk IV
Monica Lam, Stanford University

13:45PM – 14:45PM: Session 5, Languages and Programming Models

FlowPools: A Lock-Free Deterministic Concurrent Dataflow Abstraction
Aleksandar Prokopec (École Polytechnique Fédérale de Lausanne), Heather Miller (École Polytechnique Fédérale de Lausanne), Tobias Schlatter (École Polytechnique Fédérale de Lausanne), Philipp Haller (Typesafe, Inc.), Martin Odersky (École Polytechnique Fédérale de Lausanne)
Task Parallelism and Data Distribution: An Overview of Explicit Parallel Programming Languages
Dounia Khaldi (CRI, Mathématiques et Systèmes, MINES ParisTech), Pierre Jouvelot (CRI, Mathématiques et Systèmes, MINES ParisTech), Corinne Ancourt (CRI, Mathématiques et Systèmes, MINES ParisTech), François Irigoin (CRI, Mathématiques et Systèmes, MINES ParisTech)

14:45PM – 15:00PM: break

15:00PM – 16:30PM: Poster

Finish Accumulators: an Efficient Reduction Construct for Dynamic Task Parallelism
Jun Shirako (Rice University), Vincent Cavé (Rice University), Jisheng Zhao (Rice University), Vivek Sarkar (Rice University)
FlashbackSTM: Improving STM performance by remembering the past
Hugo Rito (INESC-ID/Technical University of Lisbon), João Cachopo (INESC-ID/Technical University of Lisbon)
Parallel libraries generated by the tool Kaira
Stanislav Bohm (VSB – Technical University of Ostrava), Marek Behalek (VSB – Technical University of Ostrava), Ondrej Meca (VSB – Technical University of Ostrava)
Language and Architecture Independent Software Thread-Level Speculation
Zhen Cao (McGill University), Clark Verbrugge (McGill University)
Abstractions for Defining Semi-Regular Grids Orthogonally from Stencil Computations
Andrew Stone (Colorado State University), Michelle Mills Strout (Colorado State University)
Shrek: Comparative Garbage Collector Performance Analysis in the Cloud
Arun Kejariwal (Netflix inc.), Omkar Iyer (Netflix Inc.), Gopal Krishnan (Netflix Inc.)

17:00PM – : Bus tour (departing from green center)


Thursday, September 13:

9:00AM – 9:45AM: Keynote III
Yoichi Muraoka, Waseda University

9:45AM – 10:00AM: break

10:00AM – 10:45AM: Invited talk V
Rudolf Eigenmann, Purdue University

10:45AM – 11:45AM: Session 6, Runtime Analysis and Optimizations

A Fast Parallel Graph Partitioner for Shared-Memory Inspector/Executor Strategies
Christopher D. Krieger (Colorado State University), Michelle Mills Strout (Colorado State University)
A Software-based Method-Level Speculation Framework for the Java Platform
Ivo Anjo (INESC-ID/Technical University of Lisbon), João Cachopo (INESC-ID/Technical University of Lisbon)

11:45AM – 13:00PM: lunch

13:00PM – 13:40PM: Invited talk VI
Utpal Banerjee, University of California, Irvine

13:40PM – 15:10PM: Session 7, Program Analysis

Ant: A Debugging Framework for MPI Parallel Programs
Jae-Woo Lee (Purdue University), Leonardo R. Bachega (Purdue University), Samuel P. Midkiff (Purdue University), Y. C. Hu (Purdue University)
Compiler automatic discovery of OmpSs task dependencies
Sara Royuela (Barcelona Supercomputing Center), Alejandro Duran (Intel Corporation), Xavier Martorell (Barcelona Supercomputing Center)
Beyond do loops: data transfer generation with convex array regions
Serge Guelton (Telecom Bretagne, Brest, France), Mehdi Amini (Silkan, Meudon, France and MINES ParisTech/CRI, Fontainebleau), Béatrice Creusillet (Silkan, Meudon, France)

15:10: Closing Remarks