Design of a parallel linear algebra library for verified computation
نویسنده
چکیده
O6cy~g.Ra~OTC~ npMHuHnr~ nocTpoeHHfl H peamf3au.Ha6opa JiHHe~Ho-a:lre6paHqecK}lx uolmporpaMM nepeHOCUMOfi 6HrJIHOTeKI4 ~Jl~l napannenba~x gOMnhloTepoB, rIoa~.epx<anaeTca nOBTOpHOe HCHOJU~3OBaHHe Ko;aa. rloanporpaMM~ MOryT ~erKo a/laUVMpOBaThC~ K HOB1AM napa~arMaM napa~eabHoro nporpaMMHpOBaH~l~l I4 CeTeBhIM KOH~FypauH.qM. l'loanporpaMMl, i npenHa3HaqeHH 2Lrl$1 HCnOJIb3OBaHI~.q B CaMOBepxOpHu.Hpyx)m~x aaropnTMaX, no3TOMy OHH ~alOT aOCTOBepHbm pe3y.~bTa'rta BhlCOKOI~I TOMHOCTI4.
منابع مشابه
Parallelism and Aldor: a Rst Report of It
We describe the implementation of , a library for parallel computations in Aldor. In the poster, both design and experimentations on linear algebra examples are presented.
متن کاملParallel Extensions to the Matrix Template Library
We present the preliminary design for a C++ template library to enable the compositional construction of matrix classes suitable for high performance numerical linear algebra computations. The library based on our interface definition — the Matrix Template Library (MTL) — is written in C++ and consists of a small number of template classes that can be composed to represent commonly used matrix ...
متن کاملNumerical Library Reuse in Parallel and Distributed Platforms
In the context of parallel and distributed computation, the currently existing numerical libraries do not allow code reuse. Besides, they are not able to exploit the multi-level parallelism offered by many numerical methods. A few linear algebra numerical libraries make use of object oriented approach allowing modularity and extensibility. Nevertheless, those which offer modularity together wit...
متن کاملDesign of a Parallel Object-Oriented Linear Algebra Library
Scientific programmers are eager to exploit the computational power offered by Distributed Memory Parallel Computers (DMPCs), but are generally reluctant to undertake the manual porting of their application programs onto such machines. A possible solution to this problem consists in using libraries that hide the details of parallel computations. We show how to go one step beyond, using the full...
متن کاملCrpc Research Into Linear Algebra Software for High Performance Computers
In this paper we look at a number of approaches being investigated in the Center for Research on Parallel Computation (CRPC) to develop linear algebra software for high-performance computers. These approaches are exempliied by the LAPACK, templates, and ARPACK projects. LAPACK is a software library for performing dense and banded linear algebra computations, and was designed to run eeciently on...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Reliable Computing
دوره 1 شماره
صفحات -
تاریخ انتشار 1995