Publications associées à Auto-vectorisation

An Optimizing Multi-platform Source-to-source Compiler Framework for the NEURON MODeling Language

Felix Schürmann, James Gonzalo King, Michael Lee Hines, Pramod Shivaji Kumbhar, Omar Awile, Jorge Blanco Alonso, Liam Roger George Keegan

Domain-specific languages (DSLs) play an increasingly important role in the generation of high performing software. They allow the user to exploit domain knowledge for the generation of more efficient code on target architectures. Here, we describe a new c ...

Springer2020

Exploiting Flow Graph of System of ODEs to Accelerate the Simulation of Biologically-Detailed Neural Networks

Felix Schürmann, Michael Lee Hines, Bruno Ricardo Da Cunha Magalhães

Exposing parallelism in scientific applications has become a core requirement for efficiently running on modern distributed multicore SIMD compute architectures. The granularity of parallelism that can be attained is a key determinant for the achievable ac ...

IEEE2019

Porting an MPEG-HEVC decoder to a low-power many-core platform

Marco Mattavelli, Simone Casale Brunet, Claudio Paolo Alberti, Damien Jack De Saint Jorre

After several generations of video coding standards, MPEG High Efficient Video Coding (HEVC) is likely to emerge as the video coding standards for HD and Ultra-HD TV. HEVC decoding is expected to be less computationally demanding and to provide a higher le ...

2013

Self-Similar Vector Fields

Pouya Dehghani Tafti

We propose statistically self-similar and rotation-invariant models for vector fields, study some of the more significant properties of these models, and suggest algorithms and methods for reconstructing vector fields from numerical observations, using the ...

EPFL2011

Scalable instruction set simulator for thousand-core architectures running on GPGPUs

David Atienza Alonso, Luca Benini, Martino Ruggiero, Shivani Raghav

Simulators are still the primary tools for development and performance evaluation of applications running on massively parallel architectures. However, current virtual platforms are not able to tackle the complexity issues introduced by 1000-core future sc ...

IEEE Press2010