High-performance computer architecture
High-performance computer architecture
Distributing Hot-Spot Addressing in Large-Scale Multiprocessors
IEEE Transactions on Computers
Reconfigurable Tree Architectures Using Subtree Oriented Fault Tolerance
IEEE Transactions on Computers
A fetch-and-op implementation for parallel computers
ISCA '88 Proceedings of the 15th Annual International Symposium on Computer architecture
On hot-spot contention in interconnection networks
SIGMETRICS '88 Proceedings of the 1988 ACM SIGMETRICS conference on Measurement and modeling of computer systems
A Performance Bound of Multistage Combining Networks
IEEE Transactions on Computers
Solution of a problem in concurrent programming control
Communications of the ACM
ACM SIGARCH Computer Architecture News
X-Tree: A tree structured multi-processor computer architecture
ISCA '78 Proceedings of the 5th annual symposium on Computer architecture
A Large Scale, Homogenous, Fully Distributed Parallel Machine, II
ISCA '77 Proceedings of the 4th annual symposium on Computer architecture
Analysis of Finite Buffered Multistage Combining Networks
IEEE Transactions on Parallel and Distributed Systems
A Circular List-Based Mutual Exclusion Scheme for Large Shared-Memory Multiprocessors
IEEE Transactions on Parallel and Distributed Systems
| Hi-index | 14.98 |
A cost-effective combining structure to alleviate hot-spot contention is proposed. The key idea is that the combining function is separated from the routing function, so that a binary tree-based combining configuration becomes feasible. The combining element for realizing the new structure has only one wait buffer and one combining logic, involving less hardware than the element used in earlier combining networks. More importantly, the number of constituent combining elements in such a structure with size N is reduced to O(1/log/sub 2/ N) of that required in the previous design. The proposed combining structure in conjunction with a regular multistage interconnection network can remove hot-spot contention effectively in any sized system at a considerably lower cost, and appears readily suitable for use in some applications.