R & D  
Appl. divisions »
Tech. divisions »
Master Thesis
ENACTS Roadmap «
    Status Report 1
    Status Report 2
    Status Report 3
    Status Report 4
    Status Report 5
    Status Report 6
    Status Report 7
    Status Report 8
    Status Report 9
    Status Report 10
    Status Report 11
    Roadmap Flyer
    Roadmap Report
    Final Report
    Seminars
 

How Shall We Program High Performance Computers?


Click here to start

Contents

How Shall We Program High Performance Computers?

Parallel programming is still hard

Languages: chickens or eggs?

Languages should drive architecture

Avoid message passing1

Shmem

Co-array Fortran and UPC

Automatic scheduling: HPF

An array-oriented language: ZPL

Bulk-synchrony: BSP

Nested parallelism: NESL and ADL

Avoid shared memory2

Producer-consumer variables

Single-assignment variables

Linear variables

Avoid functional programming3

A transactional example

Javaspaces

Transactions on the Cray MTA

Conclusions

Author: Dr. Burton Smith

Further information:
Seminar presented at NSC in Linköping, June 20, 2001

Best viewed with
StarOffice






Page last modified: 2002-12-11 13:56
For more information contact us at info@nsc.liu.se.