Enhancing adaptive middleware for quantum chemistry applications with a database framework

Seshagiri, Lakshminarasimhan; Wu, Meng-Shiou; Sosonkina, Masha; Zhang, Zhao; Gordon, Mark S.; Schmidt, Michael W.

doi:10.1109/ipdpsw.2010.5470760

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The techniques are applied to routines in different fields like discrete Fourier transform [11], digital signal processing transforms [25], Fast Wavelet transform [4] or quantum chemistry [26]. In many scientific problems, the basic computational components are linear algebra routines, and so auto-tuning techniques are especially interesting in linear algebra, and there are numerous projects in this field: ATLAS [29] optimizes computational kernels for dense linear algebra, SPARSITY [13] works with sparse linear algebra kernels, ABCLib-DRSSED [17] with routines for obtaining eigenvalues, etc.…”

Section: Introductionmentioning

confidence: 99%

Empirical Installation of Linear Algebra Shared-Memory Subroutines for Auto-Tuning

Cámara

Cuenca

Giménez

et al. 2013

Int J Parallel Prog

View full text Add to dashboard Cite

The introduction of auto-tuning techniques in linear algebra shared-memory routines is analyzed. Information obtained in the installation of the routines is used at running time to take some decisions to reduce the total execution time. The study is carried out with routines at different levels (matrix multiplication, LU and Cholesky factorizations and linear systems symmetric or general routines) and with calls to routines in the LAPACK and PLASMA libraries with multithread implementations. Medium NUMA and large cc-NUMA systems are used in the experiments. This variety of routines, libraries and systems allows us to obtain general conclusions about the methodology to use for linear algebra shared-memory routines auto-tuning. Satisfactory execution times are obtained with the proposed methodology.

show abstract

Section: Introductionmentioning

confidence: 99%

Empirical Installation of Linear Algebra Shared-Memory Subroutines for Auto-Tuning

Cámara

Cuenca

Giménez

et al. 2013

Int J Parallel Prog

View full text Add to dashboard Cite

show abstract

“…The least intrusive and portable is to empower an application with a middleware that will provide a liaison between the application and system by monitoring the system resources dynamically, by making adaptation decisions based on the application performance, and then by invoking application adaptations, if needed. The NICAN middleware, proposed in [3], has been already used extensively as adaptation invocation tool in quantum chemistry applications, such as GAMESS [4], in which a runtime toggling of different Self-Consistent Field (SCF) method implementations constituted the nature of adaptations [5,6,7,8]. Joint execution protocols of GAMESS and NICAN have been carefully studied in [9] under the system I/O congestion conditions.…”

Section: Introductionmentioning

confidence: 99%

Fragment Molecular Orbital Method Adaptations for Heterogeneous Computing Platforms

Talamudupula

Sosonkina

Gaenko

et al. 2012

Procedia Computer Science

Self Cite

View full text Add to dashboard Cite

Modern electronic structure calculations are characterized by unprecedented complexity and accuracy. They demand the full power of high-performance computing and must be in tune with the given architecture for superior efficiency. Thus, it is desirable to enable their static and dynamic adaptations using some external software (middleware), which may monitor both system availability and application needs, rather than mix science with system-related calls inside the application.Building on the successful usage of the NICAN middleware with the computational chemistry package GAMESS, the work described in this paper links NICAN with the fragment molecular orbital (FMO) method to augment FMO with adaptive capabilities. Specifically, its fragment scheduling is performed, both statically and dynamically, based on current conditions within a heterogeneous computing environment. Significant execution time and throughput gains have been obtained with static adaptations, while the dynamic ones prevented FMO to abort calculations due to the insufficient memory available at the runtime.

show abstract

Adaptations in Electronic Structure Calculations in Heterogeneous Environments

Talamudupula

2011

View full text Add to dashboard Cite

Enhancing adaptive middleware for quantum chemistry applications with a database framework

Cited by 3 publications

References 16 publications

Empirical Installation of Linear Algebra Shared-Memory Subroutines for Auto-Tuning

Empirical Installation of Linear Algebra Shared-Memory Subroutines for Auto-Tuning

Fragment Molecular Orbital Method Adaptations for Heterogeneous Computing Platforms

Adaptations in Electronic Structure Calculations in Heterogeneous Environments

Contact Info

Product

Resources

About