Implementing the Data Diffusion Machine using Crossbar Routersy
نویسندگان
چکیده
The Data Diffusion Machine is a scalable virtual shared memory architecture. A hierarchical network is used to ensure that all data can be located in a time bounded by O(log p), where p is the number of processors. The DDM hierarchy requires a high degree of connectivity between clusters of nodes, which can be provided with point-topoint links. For large machines however the wiring will be complex. In this article we discuss the implementation of such networks, and develop three alternative implementations. The base level performance of each alternative has been measured on an emulator of the DDM. The final solution collapses the physical hierarchy, and we show that this does not affect the performance, while clearly simplifying the design. It demonstrates that with the use of crossbar routers we can make a cheap, scalable and high performance implementation of the DDM.
منابع مشابه
Implementing the Data Diffusion Machine Using Crossbar Routers
The Data Diffusion Machine is a scalable virtual shared memory architecture. A hierarchical network is used to ensure that all data can be located in a time bounded by O(log p), where p is the number of processors. The DDM hierarchy requires a high degree of connectivity between clusters of nodes, which can be provided with point-topoint links. For large machines however the wiring will be comp...
متن کاملPower efficient Spiking Neural Network Classifier based on memristive crossbar network for spike sorting application
In this paper authors have presented a power efficient scheme for implementing a spike sorting module. Spike sorting is an important application in the field of neural signal acquisition for implantable biomedical systems whose function is to map the Neural-spikes (N-spikes) correctly to the neurons from which it originates. The accurate classification is a pre-requisite for the succeeding syst...
متن کاملExplain the theoretical and practical model of automatic facade design intelligence in the process of implementing the rules and regulations of facade design and drawing
Artificial intelligence has been trying for decades to create systems with human capabilities, including human-like learning; Therefore, the purpose of this study is to discover how to use this field in the process of learning facade design, specifically learning the rules and standards and national regulations related to the design of facades of residential buildings by machine with a machine ...
متن کاملImplementing Snoop-Coherence Protocol for Future SMP Architectures
Maintaining the coherence is becoming one of the most serious problems faced when designing nowadays machines. Initially, this problem was relatively simple when the interconnection network of Symmetric MultiProcessors (SMP) reduced to an atomic bus which simplified the implementation of invalidation coherence protocols. However, atomic busses have been progressively replaced by split busses th...
متن کاملFpga Based Adaptive Resource Efficient Error Control Methodology for Network on Chip
This research work proposes resource efficient and secured network on chip router using error control schemes. The proposed method combines the Cipher block encryption based parallel crossbar methodologies of the NoC data link and network layers to efficiently gives error control strength in variable network topology conditions. The proposed method significantly minimizes hardware utilization w...
متن کامل