We have analyzed the parallel performance of some numerical libraries for the Cray CS 6400 parallel computer system of the computing center of the Earthquake Research Institute, Univ. of Tokyo. We used both the matrix multiplications and the solution of the linear system of equations for comparing the performance of LibSci, IMSL 90 Library, and IMSL 77 Library. The size of matrices was tested from 32 to 1024. As a result, it became clear that LibSci had good performance for this system, but IMSL 90 Library was not parallelized. We had modest parallel performance from IMSL 77 Library with the Cray CF 90 compiler.<論説
SuperLU_DIST is a distributed memory parallel solver for sparse linear systems. The solver makes sev...
Parallel computing on networks of workstations are intensively used in some application areas such a...
Mathematical software libraries (IMSL, NAG) supply subprograms for the solution of a broad class of ...
Today, most of the Cray multiprocessor systems are still used within a multiprogramming environment....
Today, most of the Cray multiprocessor systems are still used within a multiprogramming environment....
Parallel eigensolver operations are at the computational core of many large-scale scientific and eng...
AbstractMathematical software libraries represent collections of subprograms for the solution of fre...
Mathematical software libraries represent collections of subprograms for the solution of frequently ...
The paper investigates the effective performance attainable for a specific class of application pro...
Abstract—Partitioned Global Address Space (PGAS) languages offer programmers a shared memory view th...
This dissertation details contributions made by the author to the field of computer science while wo...
Massively parallel computing holds the promise of extreme performance. The utility of these systems ...
We carried out a series of benchmark tests to know the ability of automatic parallelization of four ...
MPP systems with a message-passing programming paradigm such as CRAY T3E still play an important rol...
Finite element method is one of the bases for numerical solutions to engineering problems. Complex e...
SuperLU_DIST is a distributed memory parallel solver for sparse linear systems. The solver makes sev...
Parallel computing on networks of workstations are intensively used in some application areas such a...
Mathematical software libraries (IMSL, NAG) supply subprograms for the solution of a broad class of ...
Today, most of the Cray multiprocessor systems are still used within a multiprogramming environment....
Today, most of the Cray multiprocessor systems are still used within a multiprogramming environment....
Parallel eigensolver operations are at the computational core of many large-scale scientific and eng...
AbstractMathematical software libraries represent collections of subprograms for the solution of fre...
Mathematical software libraries represent collections of subprograms for the solution of frequently ...
The paper investigates the effective performance attainable for a specific class of application pro...
Abstract—Partitioned Global Address Space (PGAS) languages offer programmers a shared memory view th...
This dissertation details contributions made by the author to the field of computer science while wo...
Massively parallel computing holds the promise of extreme performance. The utility of these systems ...
We carried out a series of benchmark tests to know the ability of automatic parallelization of four ...
MPP systems with a message-passing programming paradigm such as CRAY T3E still play an important rol...
Finite element method is one of the bases for numerical solutions to engineering problems. Complex e...
SuperLU_DIST is a distributed memory parallel solver for sparse linear systems. The solver makes sev...
Parallel computing on networks of workstations are intensively used in some application areas such a...
Mathematical software libraries (IMSL, NAG) supply subprograms for the solution of a broad class of ...