Communications of the ACM - Special section on computer architecture
MULTILISP: a language for concurrent symbolic computation
ACM Transactions on Programming Languages and Systems (TOPLAS)
M68000 8-/16-/32-BIT microprocessors user's manual
M68000 8-/16-/32-BIT microprocessors user's manual
ISCA '85 Proceedings of the 12th annual international symposium on Computer architecture
Improvements in multiprocessor system design
ISCA '85 Proceedings of the 12th annual international symposium on Computer architecture
ISCA '84 Proceedings of the 11th annual international symposium on Computer architecture
THE DESIGN OF A MULTIPROCESSOR DEVELOPMENT SYSTEM
THE DESIGN OF A MULTIPROCESSOR DEVELOPMENT SYSTEM
Performance evaluation of multiple processor systems.
Performance evaluation of multiple processor systems.
Overview of concert multilisp: a multiprocessor symbolic computing system
ACM SIGARCH Computer Architecture News
Parallel processors and systems for algebraic manipulation: current work
ACM SIGSAM Bulletin
Speculative computation in multilisp
LFP '90 Proceedings of the 1990 ACM conference on LISP and functional programming
Cache consistency in hierarchical-ring-based multiprocessors
Proceedings of the 1992 ACM/IEEE conference on Supercomputing
Symmetric Crossbar Arbiters for VLSI Communication Switches
IEEE Transactions on Parallel and Distributed Systems
A bibliography on multiprocessor Lisp systems and applications
ACM SIGPLAN Lisp Pointers
A study of LISP on a multiprocessor preliminary version
ACM SIGPLAN Lisp Pointers
Hi-index | 0.00 |
Concert is a shared-memory multiprocessor testbed intended to facilitate experimentation with parallel programs and programming languages. It consists of up to eight clusters, with 4-8 processors in each cluster. The processors in each cluster communicate using a shared bus, but each processor also has a private path to some memory. The novel feature of Concert is the RingBus, a segmented bus in the shape of a ring that permits communication between clusters at relatively low cost. Efficient arbitration among requests to use the RingBus is a major challenge, which is met by a novel hardware organization, the criss-cross arbiter. Simulation of the Concert RingBus and arbiter show their performance to lie between that of a crossbar switch and a simple shared intercluster bus.