A domain-specific compiler for a parallel multiresolution adaptive numerical simulation environment

Abstract : This paper describes the design and implementation of a layered domain-specific compiler to support MADNESS---Multiresolution ADaptive Numerical Environment for Scientific Simulation. MADNESS is a high-level software environment for the solution of integral and differential equations in many dimensions, using adaptive and fast harmonic analysis methods with guaranteed precision. MADNESS uses k-d treesto represent spatial functions and implements operators like addition, multiplication, differentiation, and integration on the numerical representation of functions. The MADNESS runtime system provides global namespace support and a task-based execution model including futures. MADNESS is currently deployed on massively parallel supercomputers and has enabled many science advances. Due to the highly irregular and statically unpredictable structure of the k-d trees representing the spatial functions encountered in MADNESS applications, only purely runtime approaches to optimization have previously been implemented in the MADNESS framework. This paper describes a layered domain-specific compiler developed to address some performance bottlenecks in MADNESS. The newly developed static compile-time optimizations, in conjunction with the MADNESS runtime support, enable significant performance improvement for the MADNESS framework.
Complete list of metadatas

https://hal.inria.fr/hal-01412903
Contributor : Fabrice Rastello <>
Submitted on : Friday, December 9, 2016 - 8:50:58 AM
Last modification on : Friday, October 12, 2018 - 1:18:06 AM

Identifiers

  • HAL Id : hal-01412903, version 1

Collections

Citation

Rajbhandari Samyam, Kim Jinsung, Krishnamachari Sriram, Fabrice Rastello, Louis-Noël Pouchet, et al.. A domain-specific compiler for a parallel multiresolution adaptive numerical simulation environment. SC 2016 - International Conference for High Performance Computing, Networking, Storage and Analysis, Nov 2016, Salt-Lake City, United States. ⟨hal-01412903⟩

Share

Metrics

Record views

253