Modern supercomputers like CRAY X-MP and CRAY Y-MP achieve their high computing speed by using both vector and parallel hardware. This paper gives a short introduction into the CRAY Y-MP system architecture and describes the multitasking concepts which can be used on this machine. There are three different concepts which support parallelism on the programming language level: macrotasking, microtasking, and autotasking. The concepts and implementations are discussed, and measurements of the overhead as well as performance results for kernels and an application program are presented.Moreover, the overall system performance is of interest when multitasking concepts are used. Therefore, a programming system is developed, generating synthetic us...
The article describes various options for speeding up calculations on computer systems. These featur...
The standardized-maximalist approach to supercom-puter benchmarking consists in optimizing a standar...
Multiscalar processors use a new, aggressive implementation paradigm for extracting large quantities...
Modern supercomputers like the CRAY Y-MP achieve their high computing speed by using both vector and...
On the multiprocessor vector-supercomputer CRAY X-MP, parallelism—beyond vectorization—can be exploi...
KFA Jülich is one of the largest big-science research centers in Europe. At KFA, computational scien...
Today most of the multiprocessor supercomputer systems are still used within a multiprogramming envi...
Today, most of the Cray multiprocessor systems are still used within a multiprogramming environment....
At KFA - and in particular enforced by ZAM - supercomputing and parallel processing for computationa...
We present a new scheme for evaluating the performance of multithreaded computers and demonstrate it...
Quantum Chromodynamics, the theory of the nuclear forces, is simulated on a space-time lattice by me...
ABSTRACT: In this paper, we describe how to write efficient, parallel codes for the Cray XMTTM syste...
Today, most of the Cray multiprocessor systems are still used within a multiprogramming environment....
While the efficiency of autotasking with respect to speedup values already is proved for parallel pr...
The fast Fourier transform (FFT) kernel of the NAS benchmark program has been utilized to experiment...
The article describes various options for speeding up calculations on computer systems. These featur...
The standardized-maximalist approach to supercom-puter benchmarking consists in optimizing a standar...
Multiscalar processors use a new, aggressive implementation paradigm for extracting large quantities...
Modern supercomputers like the CRAY Y-MP achieve their high computing speed by using both vector and...
On the multiprocessor vector-supercomputer CRAY X-MP, parallelism—beyond vectorization—can be exploi...
KFA Jülich is one of the largest big-science research centers in Europe. At KFA, computational scien...
Today most of the multiprocessor supercomputer systems are still used within a multiprogramming envi...
Today, most of the Cray multiprocessor systems are still used within a multiprogramming environment....
At KFA - and in particular enforced by ZAM - supercomputing and parallel processing for computationa...
We present a new scheme for evaluating the performance of multithreaded computers and demonstrate it...
Quantum Chromodynamics, the theory of the nuclear forces, is simulated on a space-time lattice by me...
ABSTRACT: In this paper, we describe how to write efficient, parallel codes for the Cray XMTTM syste...
Today, most of the Cray multiprocessor systems are still used within a multiprogramming environment....
While the efficiency of autotasking with respect to speedup values already is proved for parallel pr...
The fast Fourier transform (FFT) kernel of the NAS benchmark program has been utilized to experiment...
The article describes various options for speeding up calculations on computer systems. These featur...
The standardized-maximalist approach to supercom-puter benchmarking consists in optimizing a standar...
Multiscalar processors use a new, aggressive implementation paradigm for extracting large quantities...