ARRAY Research Papers
Focus and Description
Array-oriented programming is a powerful abstraction for compactly implementing numerically intensive algorithms. Many modern languages now provide some support for collective array operations, which are used by an increasing number of programmers (and non-programmers) for data analysis and scientific computing.
The aim of this workshop is to foster the cross-pollination of concepts across projects and research communities and to explore new directions, such as:
- Expanding the scope of array programming to encompass a wider range of data types and computations.
- Transparently utilizing parallel hardware (multi-core, SIMD, GPU, FPGA) by leveraging the implicitly parallel semantics of array operations.
- Simplifying the embedding of array constructs within existing languages which weren’t designed for numerical computing.
- Connections between array abstractions and other models such as dataflow programming, stream programming, and data parallelism.
- High-level compilation and optimization techniques for array-oriented programs.
- Compilers, virtual machines and frameworks for array-oriented programming languages.
Please see the external website for the ARRAY’15 workshop for details.
Sat 13 JunDisplayed time zone: Tijuana, Baja California change
09:00 - 11:00
Invited Talk and Paper Session 1ARRAY at C122
Chair(s): Laurie Hendren McGill University
|INVITED TALK: Array Notation for Everybody|
David Padua University of Illinois at Urbana-Champaign
|Loo.py: From Fortran to performance via transformation and substitution rules|
Andreas Kloeckner University of Illinois at Urbana-Champaign
|Techniques for Efficient MATLAB-to-C Compilation|
João Bispo FEUP, Universidade do Porto, Luís Reis , João Cardoso
11:20 - 12:30
Paper Session 2ARRAY at C122
Chair(s): Mary Sheeran
|Compiling APL to Accelerate Through a Typed Array Intermediate Language|
|Velociraptor: A compiler toolkit for array-based languages targeting CPUs and GPUs|
Rahul Garg , Sameer Jagdale McGill University, Laurie Hendren McGill University
14:00 - 15:30
Paper Session 3ARRAY at C122
Chair(s): Hidehiko Masuhara Tokyo Institute of Technology
|Performance Search Engine Driven by Prior Knowledge of Optimization|
Youngsung Kim , Pavol Cerny University of Colorado Boulder
|High-Level Accelerated Array Programming in the Web Browser|
|Accelerating Information Experts through Compiler Design|
16:00 - 18:00
Paper Session 4ARRAY at C122
Chair(s): David Grove IBM Research
|Fusing Convolution Kernels through Tiling|
|Array programming in Pascal|
|Abstract Expressionism for Parallel Performance|
Papers and Invited Talks
Call for Papers
The call for papers can be found on the external ARRAY’15 website.