CFDlang: High-level code generation for high-order methods in fluid dynamics - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année :

CFDlang: High-level code generation for high-order methods in fluid dynamics

(1) , (2, 3) , (1) , (1) , (3, 2)
1
2
3

Résumé

Numerical simulations continue to enable fast and enormous progress in science and engineering. Writing efficient numerical codes is a difficult challenge that encompasses a variety of tasks from designing the right algorithms to exploiting the full potential of a platform's architecture. Domain-specific languages (DSLs) can ease these tasks by offering the right abstractions for expressing numerical problems. With the aid of domain knowledge, efficient code can then be generated automatically from abstract expressions. In this work, we present the CFDlang DSL for expressing tensor operations that constitute the performance-critical code sections in a class of real numerical applications from fluid dynamics. We demonstrate that CFDlang can be used to generate code automatically that performs as well, if not better, than carefully hand-optimized code.
Fichier non déposé

Dates et versions

hal-01857925 , version 1 (17-08-2018)

Identifiants

Citer

Norman A Rink, Adilla Susungi, Jeronimo Castrillon, Jörg Stiller, Claude Tadonki. CFDlang: High-level code generation for high-order methods in fluid dynamics. the Real World Domain Specific Languages Workshop 2018, Feb 2018, Vienna, France. pp.79-92, ⟨10.1145/3183895.3183900⟩. ⟨hal-01857925⟩
339 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook Twitter LinkedIn More