Sat 13 Jun 2015 10:30 - 11:00 at C122 - Invited Talk and Paper Session 1 Chair(s): Laurie Hendren

The translation of MATLAB to C is an important step to raise the overall abstraction level when mapping computations to embedded systems, and thus to increase productivity and to achieve a full-automated model-driven design-flow. This paper describes recent work developed in MATISSE, a MATLAB to C compiler targeting embedded systems. We introduce several techniques to allow the efficient implementation of C code, such as weak types, primitives and pointer views. We evaluate the compiler with a set of 9 publicly available benchmarks, targeting both embedded systems and a desktop system. We compare the execution time of the generated C code with the original code running on MATLAB, achieving a geometric mean speedup of 8.1×, and qualitatively compare with the performance of related work.

Sat 13 Jun

Displayed time zone: Tijuana, Baja California change

09:00 - 11:00
Invited Talk and Paper Session 1ARRAY at C122
Chair(s): Laurie Hendren McGill University
09:00
60m
Talk
INVITED TALK: Array Notation for Everybody
ARRAY
David Padua University of Illinois at Urbana-Champaign
10:00
30m
Talk
Loo.py: From Fortran to performance via transformation and substitution rules
ARRAY
Andreas Kloeckner University of Illinois at Urbana-Champaign
10:30
30m
Talk
Techniques for Efficient MATLAB-to-C Compilation
ARRAY
João Bispo FEUP, Universidade do Porto, Luís Reis , João Cardoso