PUMMA: Parallel Universal Matrix Multiplication Algorithms on distributed memory concurrent computers
- Oak Ridge National Lab., TN (US)
This paper describes the Parallel Universal Matrix Multiplication Algorithms (PUMMA) on distributed memory concurrent computers. The PUMMA package includes not only the non-transposed matrix multiplication routine C = A{center_dot}B, but also transposed multiplication routines C = A{sup T}{center_dot}B, C = A{center_dot}B{sup T}, and C = A{sup T}{center_dot}B{sup T}, for a block scattered data distribution. The routines perform efficiently for a wide range of processor configurations and block sizes. The PUMMA together provide the same functionality as the Level 3 BLAS routine xGEMM. Details of the parallel implementation of the routines are given, and results are presented for runs on the Intel Touchstone Delta computer.
- Research Organization:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States); Department of Defense, Washington, DC (United States)
- DOE Contract Number:
- AC05-84OR21400
- OSTI ID:
- 10180105
- Report Number(s):
- ORNL/TM-12252; ON: DE93019163; CNN: Contract DAAL03-91-C-0047; TRN: 93:003127
- Resource Relation:
- Other Information: PBD: Aug 1993
- Country of Publication:
- United States
- Language:
- English
Similar Records
Parallel matrix transpose algorithms on distributed memory concurrent computers
The spectral decomposition of nonsymmetric matrices on distributed memory parallel computers