A new way of constructing N-way arbiters is proposed. The main idea is to perform arbitrations between all pairs of requests, and then make decision on what grant to issue based on their outcomes. Crucially, all the mutual exclusion elements in such an arbiter work in parallel. This ‘flat’ arbitration is prone to new threats such as formation of cycles (leading to deadlocks), but at the same time opens up new opportunities for designing arbitration structures with different decision policies due to the availability of the global order relation between requests. To facilitate resolution of such cycles and further developments in the context of flat arbitration, the paper presents new theoretical results, including a proof of correctness of a generic structure for the N-way arbiter decision logic. In particular, in some situations a request that lost some pairwise arbitrations has to be granted to avoid a deadlock.
2
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
This paper introduces enhancements to the synthesis of circuits that involve write-afterread (WAR) operations and use the four-phase handshake protocol. The paper demonstrates that the use of edge-triggering makes possible many useful trade-offs among speed, area and powerdelay product. Significant increases in speed are possible as a result of increased concurrency in the circuit's operation, which compensates for much of the penalty associated with the down phase of the four-phase protocol. It is also shown that concurrency can be increased by the judicious insertion of T-elements in the system's control structure. Simulation results for a 16-bit accumulator showed a speed increase of 50% and a reduction of 23% in the power-delay product. The speed of a radix-4 Booth multiplier increased by over 27% and its area and energy consumption were reduced by 5%. These results were derived using test circuits synthesized by Balsa and implemented in Synopsys using 180-nm technology.
3
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
Signal Transition Graphs (STG) are a formalism for the description of asynchronous circuit behaviour. In this paper we propose (and justify) a formal semantics of non-deterministic STGs with dummies and OR-causality. For this, we introduce the concept of output-determinacy, which is a relaxation of determinism, and argue that it is reasonable and useful in the speed-independent context. We apply the developed theory to improve an STG decomposition algorithm used to tackle the state explosion problem during circuit synthesis, and present some experimental data for this improved algorithm and some benchmark examples.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.