Implementation Indices (1975-1979). Volume 1.
Abstract
General purpose multiprocessors have largely failed to meet expectations for programmability and performance. We blame the lack of usable parallel programming languages and systems on the underlying processor architecture. Machines built out of conventional sequential processors simply do not support the synchronization demands of parallel execution, so the programmer focuses upon the dangerous and arduous task of discovering a minimum set of synchronization points without introducing nondeterminism. We argue that processors must be fundamentally changed to execute a parallel machine language, in which parallel activities are coordinated as efficiently as instructions are scheduled. Tagged token dataflow, Dataflow graphs, Multiprocessor computer architecture, Pipelined processor, Associative memory. (jes)
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 1988
- Accession Number
- ADA207609
Entities
People
- Gregory M. Papadopoulos
Organizations
- Massachusetts Institute of Technology