Scalable Many-Core Algorithms for Tridiagonal Solvers

نویسندگان

چکیده

In this article, we present a novel distributed memory tridiagonal solver library, targeting large-scale systems based on modern multicore and many-core processor architectures. The library uses methods both approximate exact algorithms. Performance comparisons with the state of art, using large Cray EX system GPU cluster show algorithmic tradeoffs required at increasing machine scale to achieve good performance, particularly considering advent exascale systems.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Parallel Solvers for Almost-Tridiagonal Linear Systems

The problem of solving tridiagonal systems on parallel machines has been studied extensively. This paper examines an existing parallel solvers for tridiagonal systems and extends this divide-and-conquer algorithm to solving almost-tridiagonal systems, systems consisting of a tridiagonal matrix with non-zeros elements in the upper right and lower left corners. In addition to a sketch of a solver...

متن کامل

Many-core algorithms for statistical phylogenetics

MOTIVATION Statistical phylogenetics is computationally intensive, resulting in considerable attention meted on techniques for parallelization. Codon-based models allow for independent rates of synonymous and replacement substitutions and have the potential to more adequately model the process of protein-coding sequence evolution with a resulting increase in phylogenetic accuracy. Unfortunately...

متن کامل

Scalable and Distributed Resource Management for Many-Core Systems

German Version) Many-Core Systeme stellen die Forschung vor vielfältige neue Herausforderungen, darunter die Handhabung von sehr dynamischer und kaum voraussagbarer Rechenlast. Optimale Ressourcenverwaltung von Many-Core Systemen ist ein NP-vollständiges Problem. Die große Anzahl der zu verwaltenden Anwendungen und Kernen führt bei zentral agierenden Heuristiken, welche stets einen globalen Bli...

متن کامل

Design Challenges of Scalable Operating Systems for Many-Core Architectures

Computers will move from the multi-core reality of today to manycore. Instead of only a few cores on a chip, we will have thousands of cores available for use. This new architecture will force engineers to rethink OS design. It is the only way for operating systems to remain scalable even as the number of cores increases. Presented here are three design challenges of operating systems for many-...

متن کامل

A novel and scalable Multigrid algorithm for many-core architectures

Multigrid algorithms are among the fastest iterative methods known today for solving large linear and some non-linear systems of equations. Greatly optimized for serial operation, they still have a great potential for parallelism not fully realized. In this work, we present a novel multigrid algorithm designed to work entirely inside many-core architectures like the graphics processing units (G...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Computing in Science and Engineering

سال: 2022

ISSN: ['1558-366X', '1521-9615']

DOI: https://doi.org/10.1109/mcse.2021.3130544