Multi-grained parallel computers can be very eective on computationally intensive problems that have important serial and parallel components. We examine the Mesh Su-perHet, a model of this type consisting of the close coupling of a d-dimensional toroidal mesh of coarse-grained processors to a serial machine containing memory modules con-nected via a low-diameter network to a fast serial processor. We exhibit problems for which the Mesh SuperHet is superior to its serial or parallel components alone and develop tight performance bounds for sorting, the fast Fourier transform, and matrix multiplication. As multi-grained machines become more common, studies such as this will both reveal the fundamental limitations on such architectures and se...
175 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2009.High performance, massively-p...
As polygonal models rapidly grow to sizes orders of magnitudes bigger than the memory of commodity w...
Abstract: Making multigrid algorithms run efficiently on large parallel computers is a challenge. Wi...
We studyscalable parallel computational geometry algorithms for the coarse grained multicomputer mod...
Given the proliferation of layered, multicore- and SMT-based architectures, it is imperative to depl...
In this work an efficient model for parallel computing, called Shuffled Mesh (SM), is in-troduced. T...
We study the potential performance of multigrid algorithms running on massively parallel computers w...
We present parallel algorithms for geometric problems on coarse grained multicomputers. More specifi...
We consider the problem of subsystem allocation in the mesh, torus, and hypercube multicomputers. Al...
We propose an architecture-independent parallel model, the C³-model. The C³-model evaluates, for a g...
The new generation of microprocessors incorporates a huge number of cores on the same chip. Graphics...
A number of parallel formulations of dense matrix multiplication algorithm have been developed. For ...
The majority of finite element models in structural engineering are composed of unstructured meshes....
This paper demonstrates that scalability and competitive efficiency can be achieved for unstructured...
This paper describes several parallel algorithms that solve geometric problems. The algorithms are...
175 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2009.High performance, massively-p...
As polygonal models rapidly grow to sizes orders of magnitudes bigger than the memory of commodity w...
Abstract: Making multigrid algorithms run efficiently on large parallel computers is a challenge. Wi...
We studyscalable parallel computational geometry algorithms for the coarse grained multicomputer mod...
Given the proliferation of layered, multicore- and SMT-based architectures, it is imperative to depl...
In this work an efficient model for parallel computing, called Shuffled Mesh (SM), is in-troduced. T...
We study the potential performance of multigrid algorithms running on massively parallel computers w...
We present parallel algorithms for geometric problems on coarse grained multicomputers. More specifi...
We consider the problem of subsystem allocation in the mesh, torus, and hypercube multicomputers. Al...
We propose an architecture-independent parallel model, the C³-model. The C³-model evaluates, for a g...
The new generation of microprocessors incorporates a huge number of cores on the same chip. Graphics...
A number of parallel formulations of dense matrix multiplication algorithm have been developed. For ...
The majority of finite element models in structural engineering are composed of unstructured meshes....
This paper demonstrates that scalability and competitive efficiency can be achieved for unstructured...
This paper describes several parallel algorithms that solve geometric problems. The algorithms are...
175 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2009.High performance, massively-p...
As polygonal models rapidly grow to sizes orders of magnitudes bigger than the memory of commodity w...
Abstract: Making multigrid algorithms run efficiently on large parallel computers is a challenge. Wi...