AP1000+
- 1 November 1994
- proceedings article
- Published by Association for Computing Machinery (ACM)
- Vol. 28 (5) , 196-207
- https://doi.org/10.1145/195473.195538
Abstract
The scalability of distributed-memory parallel computersmakes them attractive candidates for solving largescaleproblems. New languages, such as HPF, FortranD,and VPP Fortran, have been developed to enable existingsoftware to be easily ported to such machines. Manydistributed-memory parallel computers have been built,but none of them support the mechanisms required bysuch languages. We studied the mechanisms required byparallelizing compilers and proposed a new architectureto support...Keywords
This publication has 11 references indexed in Scilit:
- VPP Fortran for Distributed Memory Parallel ComputersPublished by Springer Nature ,1995
- Anatomy of a message in the Alewife multiprocessorPublished by Association for Computing Machinery (ACM) ,1993
- Improving AP1000 parallel computer performance with message communicationPublished by Association for Computing Machinery (ACM) ,1993
- Parallel programming in Split-CPublished by Association for Computing Machinery (ACM) ,1993
- Integrating message-passing and shared-memoryPublished by Association for Computing Machinery (ACM) ,1993
- Low-latency message communication support for the AP1000Published by Association for Computing Machinery (ACM) ,1992
- Active messagesPublished by Association for Computing Machinery (ACM) ,1992
- Compiler optimizations for Fortran D on MIMD distributed-memory machinesPublished by Association for Computing Machinery (ACM) ,1991
- Compiling global name-space parallel loops for distributed executionIEEE Transactions on Parallel and Distributed Systems, 1991
- Parallelization of FORTRAN code on distributed-memory parallel processorsPublished by Association for Computing Machinery (ACM) ,1990