The Counterflow Pipeline Processor Architecture
IEEE Design & Test
MOUSETRAP: Ultra-High-Speed Transition-Signaling Asynchronous Pipelines
ICCD '01 Proceedings of the International Conference on Computer Design: VLSI in Computers & Processors
An Area- and Energy-Efficient Asynchronous Booth Multiplier for Mobile Devices
ICCD '04 Proceedings of the IEEE International Conference on Computer Design
A Scalable Counterflow-Pipelined Asynchronous Radix-4 Booth Multiplier
ASYNC '05 Proceedings of the 11th IEEE International Symposium on Asynchronous Circuits and Systems
Synchronous elastic circuits with early evaluation and token counterflow
Proceedings of the 44th annual Design Automation Conference
Using functional independence conditions to optimize the performance of latency-insensitive systems
Proceedings of the 2007 IEEE/ACM international conference on Computer-aided design
Accelerating Speculative Execution in High-Level Synthesis with Cancel Tokens
ARC '08 Proceedings of the 4th international workshop on Reconfigurable Computing: Architectures, Tools and Applications
Analysis of Static Data Flow Structures
Fundamenta Informaticae - Application of Concurrency to System Design, the Sixth Special Issue
Correct-by-construction microarchitectural pipelining
Proceedings of the 2008 IEEE/ACM International Conference on Computer-Aided Design
Workcraft --- A Framework for Interpreted Graph Models
PETRI NETS '09 Proceedings of the 30th International Conference on Applications and Theory of Petri Nets
Retiming and recycling for elastic systems with early evaluation
Proceedings of the 46th Annual Design Automation Conference
Speculation in elastic systems
Proceedings of the 46th Annual Design Automation Conference
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Workcraft: a static data flow structure editing, visualisation and analysis tool
ICATPN'07 Proceedings of the 28th international conference on Applications and theory of Petri nets and other models of concurrency
Analysis of Static Data Flow Structures
Fundamenta Informaticae - Application of Concurrency to System Design, the Sixth Special Issue
Hi-index | 0.00 |
This paper introduces a novel approach to efficiently implement several useful architectural features in asynchronous application-specific ICs (ASICs). These features include speculation, preemption, and eager evaluation, which have so far only been available on CPUs, and have not been adequately investigated for custom ASICs. For the efficient implementation of the new architectural features, a radically new approach inspired by Sproull's counterflow pipelines [7] is proposed. The key idea is to allow special commands, called anti-tokens, to be propagated in a direction opposite to that of data, allowing certain computations to be killed before they are completed, if their results are no longer required. The net impact is a significant improvement in the throughput of a certain class of systems---e.g., those involving conditional computation---where a bottleneck pipeline stage can often be preempted if its result is determined to be no longer needed. Experimental results indicate that our approach can improve the system throughput by a factor of up to 2.2x, along with an energy savings of up to 27%.