Abstract
The Notification Oriented Paradigm (NOP) introduced a new organization of software and hardware logic based on notifications among computational entities. This NOP new organization avoids processing redundancy and allows processing unit decoupling, therefore permitting proper processing performance and processing parallelism/distribution. Thus, the NOP provides means to make efficient use of the parallel execution capabilities of modern computing systems. However, as expected, the execution dynamics of NOP, based on notifications, is not efficiently performed by the hardware of most current computing systems. This paper presents a new solution called Notification-Oriented Computer Architecture (NOCA), which is suitable for the execution of software developed according to the NOP computing model. The NOCA was designed according to principles of generality and scalability, which allow it to execute NOP software of any size by fetching the application from memory. The proposed architecture is organized as a fine-grained multiprocessor that hierarchically executes instructions through sets of specialized processing cores. Preliminary experiments performed on prototypal FPGA implementation of the NOCA showed the expected behavior of executing NOP applications according to its theoretical computing model. This paper also presents experiments performed on a NOCA simulator extending the scale of parallelization of applications. Results show improvements in maximizing the speedups at higher scales of parallelization, as well as minimizing the effects of processor-to-memory communication bottlenecks by reducing the number of required memory accesses during execution.
Highlights
Computer architectures have lately evolved towards the design and construction of processors with multiple cores [1], [2]
WORK The proposal of the Notification-Oriented Computer Architecture (NOCA) is an alternative to conventional parallel computer architectures based on von Neumann or dataflow model since the NOCA was developed so as to totally adhere to the Notification Oriented Paradigm (NOP), whose execution model is based on notifications
This allows the NOCA to take advantage of the parallel execution characteristics coming from the structure of NOP applications
Summary
Computer architectures have lately evolved towards the design and construction of processors with multiple cores [1], [2]. Elixir), allowing the implementation of NOP software, for von Neumann architecture, using typical OOP abstractions such as classes and objects, but under notification approach of-course [16], [18]; prototype of a language and compiler called NOPL, for von Neumann architecture, that allow generating low-level language, namely C/C++, but under the NOP background [16]; circuit templates called NOP Digital Hardware (DH), afterward associated with new version of NOPL that allow the high-level implementation, in total conformance with NOP principles, of a determined application in reconfigurable hardware [13]; and a NOP co-processor (CoNOP), which is based on NOP-DH and can be reconfigured for a determined application, thereby allowing the hybrid execution of the NOP inference process in collaboration with a von Neumann core [17], [20] All these implementations have been absolutely important to demonstrate a set of NOP properties, such as declarative high-level implementation, implicit entity decoupling allowing parallelism and distribution, actual avoidance of entity redundancy allowing high performance in execution terms, and usefulness for both software and hardware. The NOCA is proposed in order to allow a NOP application to be loaded from memory to a set of processors and executed in a more scalable and flexible way
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
