Sunday April 7th, 2013

15:00 to 17:00 Registration

17:00 to 19:00 Welcome Reception

Monday April 8th, 2013

8:00 to 8:45 Registration

8:45 to 9:00 Welcome and Introduction

9:00 to 10:00 SESSION 1: Keynote Talk

Chair: David W. Matula

High-Precision Computation: Applications and Challenges
David H. Bailey, Lawrence Berkeley National Laboratory, USA
[Abstract]    [Presentation]

10:00 to 10:30 Coffee break

10:30 to 12:00 SESSION 2: Arithmetic Units

Chair: Stuart Oberman

The Floating-Point Unit of the Jaguar x86 Core
Jeff Rupley, John King, Eric Quinnell, Frank Galloway, Ken Patton, Peter-Michael Seidel, James Dinh, Hai Bui and Anasua Bhowmik (AMD, USA & India)
[Abstract]

Split-path Fused Floating Point Multiply ACcumulate (FPMAC)
Suresh Srinivasan, Ketan Budhiya, Rajaraman Ramanarayanan, P. Sahit Babu, Tiju Jacob, Sanu k. Mathew, Ram Krishnamurty and Vasantha Errgauntla (Intel India & USA)
[Abstract]    [Presentation]

FPU Generator for Design Space Exploration
Sameh Galal, Ofer Shacham, John S. Brunhaver II, Jing Pu, Artem Vassiliev and Mark Horowitz (Stanford University, USA)
[Abstract]    [Presentation]

12:00 to 13:30 Lunch

13:30 to 15:00 SESSION 3: Special Session on Exascale Computing

Chair: Eric Schwarz

Managing Computation, Precision, Accuracy, and Performance on ExaScale Systems

ExaScale-level systems may be available in less than a decade. Computer architects are already thinking of, and planning ways to achieve such levels of performance in the near future. It can be expected that researchers and engineers will carry out scientific and engineering computations more complex than ever before, and will attempt breakthroughs not possible today. If the size of the problems solved on such machines scales accordingly, we may face new issues related to precision, accuracy, performance, and programmability.

The session consists of three talks:

Precision, Accuracy, Rounding, and Error Propagation
Marius Cornea, Intel Corporation, USA.
[Paper]

Managing the Dense Linear Algebra Software Stack
Robert A. van de Geijn, University of Texas at Austin, USA.
[Presentation]

Numerical Accuracy and Reproducibility at ExaScale
Hong Diep Nguyen and Jim Demmel, UC Berkeley, USA.
[Paper]    [Presentation]

15:00 to 15:30 Coffee break

15:30 to 17:30 SESSION 4: Domain Specific Designs

Chair: Paolo Montuschi

Improved Architectures for a Floating-Point Fused Dot Product Unit
Jongwook Sohn and Earl Swartzlander (UT Austin, USA)
[Abstract]    [Presentation]

Floating Point Architecture Extensions for Optimized Matrix Factorization
Ardavan Pedram, Robert van de Geijn and Andreas Gerstlauer (UT Austin, USA)
[Abstract]    [Presentation]

A Fast Circuit Topology for Finding the Maximum of n k-bit Numbers
Bilgiday Yuce, H. Fatih Ugurdag, Sezer Goren and Gunhan Dundar (Bogazici University, Ozyegin University & Yeditepe University, Turkey)
[Abstract]    [Presentation]

A Non-Linear/Linear Instruction Set Extension for Lightweight Ciphers
Susanne Engels, Elif Bilge Kavun, Hristina Mihajloska, Christof Paar and Tolga Yalcin (Ruhr-Univ. Bochum, Germany & Ss Cyril and Methodius Univ. Skopje, Macedonia)
[Abstract]    [Presentation]

17:30 "Birds of a Feather" Session on Arithmetic for Accelerators

Organizer: Stuart Oberman

Speakers:

• Stuart Oberman, NVIDIA, USA    [Presentation]
• Marius Cornea, Intel, USA    [Presentation]
• Frode Heggelund, ARM, Norway    [Presentation]
• Michael Schulte, AMD, USA
• Theo Drane, Imagination Technologies
• Liang-Kai Wang, Qualcomm, USA    [Presentation]

Tuesday April 9th, 2013

8:45 to 10:00 SESSION 5: Keynote Talk

Chair: Neil Burgess

The Antikythera Mechanism and the early history of mechanical computing
Professor M.G. Edmunds, Cardiff University, UK
[Abstract]

10:00 to 10:30 Coffee break

10:30 to 12:30 SESSION 6: Verification and Correctness Proofs

Chair: David Hough

On the componentwise accuracy of complex floating-point division with an FMA
Claude-Pierre Jeannerod, Nicolas Louvet and Jean-Michel Muller (INRIA Lyon, France)
[Abstract]    [Presentation]

How to Compute the Area of a Triangle: a Formal Revisit
Sylvie Boldo (Univ. Paris-Sud, France)
[Abstract]    [Presentation]

SIPE: Small Integer Plus Exponent
Vincent Lefèvre (INRIA, Lyon, France)
[Abstract]    [Presentation]

A Formally-Verified C Compiler Supporting Floating-Point Arithmetic
Sylvie Boldo, Jacques-Henri Jourdan, Xavier Leroy and Guillaume Melquiond (Univ. Paris-Sud & INRIA Paris, France)
[Abstract]    [Presentation]

12:30 to 14:00 Lunch

14:00 to 15:30 SESSION 7: Modular Arithmetic

Chair: Peter Kornerup

Fault Detection in RNS Montgomery Modular Multiplication
Julien Eynard, Filippo Gandino and Jean-Claude Bajard (UPMC Paris, France & Politecnico Torino, Italy)
[Abstract]    [Presentation]

The unary arithmetical algorithm in bimodular number systems
Petr Kurka (Charles Univ. Prague, Czech Rep.) and Martin Delacourt (Centro Modelamiento Matematico, Chile)
[Abstract]    [Presentation]

Parallel modular multiplication on multi-core processors
Pascal Giorgi, Laurent Imbert and Thomas Izard (LIRMM Montpellier, France)
[Abstract]    [Presentation]

15:30 to 16:00 Coffee break

16:00 to 16:30 Commemoration Luigi Ciminiera and Luigi Dadda

16:30 to 18:00 SESSION 8: Floating-Point Error Analysis

Chair: Sanu Mathew

Comparison between binary64 and decimal64 floating-point numbers
Nicolas Brisebarre, Christoph Lauter, Marc Mezzarobba and Jean-Michel Muller (ENS Lyon & UPMC Paris, France)
[Abstract]    [Presentation]

Accurate Parallel Floating-Point Accumulation
Edin Kadric, Paul Gurniak and Andre Dehon (Univ. of Pennsylvania, USA)
[Abstract]    [Presentation]

Fast Reproducible Floating-Point Summation
Hong Diep Nguyen and James Demmel (UC Berkeley, USA)
[Abstract]    [Presentation]

19:00 Conference Banquet

Sponsored by Last modified: Thursday May 16, 2013 at 10:32 (CET)