A Test Program Generation for Scalable SIMD Parallel Computer
نویسندگان
چکیده
منابع مشابه
Computer Assisted Parallel Program Generation
Parallel computation is widely employed in scientific researches, engineering activities and product development. Parallel program writing itself is not always a simple task depending on problems solved. Large-‐scale scientific computing, huge data analyses and precise visualizations, for example, would require parallel computations, and the parallel computing needs the parallelization techniq...
متن کاملSIMD code generation in data-parallel programming
Today’s desktop PCs feature a variety of parallel processing units. Developing applications that exploit this parallelism is a demanding task, and a programmer has to obtain detailed knowledge about the hardware for efficient implementation. CGiS is a data-parallel programming language providing a unified abstraction for two parallel processing units: graphics processing units (GPUs) and the ve...
متن کاملEecient Sparse Cholesky Factorization on a Parallel Simd Computer
We investigate the eeect of load balancing when performing Cholesky factor-ization on a SIMD computer. In particular we describe a supernodal algorithm for performing sparse Cholesky factorization. The way the matrix is mapped onto the processors has signiicant eeect on its eeciency. We show that this assignment problem can be modeled as a graph coloring problem in a weighted graph. By a simple...
متن کاملEfficient Sparse Cholesky Factorization on a Massively Parallel SIMD Computer
We investigate the effect of load balancing when performing Cholesky factorization on a massively parallel SIMD computer. In particular we describe a supernodal algorithm for performing sparse Cholesky factorization. The way the matrix is mapped onto the processors has significant effect on its efficiency. We show that this assignment problem can be modeled as a graph coloring problem in a weig...
متن کاملOrdinary linear model estimation on a massively parallel SIMD computer
Efficient algorithms for estimating the coefficient parameters of the ordinary linear model on a massively parallel SIMD computer are presented. The numerical stability of the algorithms is ensured by using orthogonal transformations in the form of Householder reflections and Givens plane rotations to compute the complete orthogonal decomposition of the coefficient matrix. Algorithms for recons...
متن کاملذخیره 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: IEEJ Transactions on Electronics, Information and Systems
سال: 2001
ISSN: 0385-4221,1348-8155
DOI: 10.1541/ieejeiss1987.121.8_1334