Microgrids — The exploitation of massive on-chip concurrency
References (23)
International Technology Roadmap for Semiconductors
(2003)- et al.
The IMS T800 Transputer
IEEE Micro, October 1987
(1987) - et al.
Hitting the Memory Wall: Implications of the Obvious
Computer Architecture News
(1995) The multicluster architecture: reducing cycle time through partitioning
- et al.
Multiscaler processors
Register organization for media processing
Scaling to the end of silicon with EDGE architectures
IEEE Computer
(2004)Parallel processing: a smart compiler and a dumb machine
- et al.
Dynamic schedlung in RISC architectures
IEE Trans. E, Computers and Digital Techniques
(1996)
Implementing an efficient vector instruction set in a chip multiprocessor using microthreaded pipellines
Cited by (4)
Cache-based high-level simulation of microthreaded many-core architectures
2014, Journal of Systems ArchitectureCitation Excerpt :We present the future work of this research in Section 8 and conclude the paper in Section 9. The Microgrid [19,6,17] is a general-purpose, many-core architecture developed at the University of Amsterdam which implements hardware multi-threading using data flow scheduling and a concurrency management protocol in hardware to create and synchronize threads within and across the cores on chip. The suggested concurrent programming model for this chip is based on fork-join constructs, where each created thread can define further concurrency hierarchically.
One-IPC high-level simulation of microthreaded many-core architectures
2017, International Journal of High Performance Computing ApplicationsAnalytical-based high-level simulation of the microthreaded many-core architectures
2014, Proceedings - 2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2014Supporting microthread scheduling and synchronisation in CMPs
2006, International Journal of Parallel Programming
Copyright © 2005 Elsevier B.V. All rights reserved.