Overview of the JUMP-1, an MPP prototype for general-purpose parallel computations
نویسندگان
چکیده
Recent progress in semiconductor technology enables practical use of MPP systems in numerical intensive computations. However, current MPPs are still very ine cient for general-purpose computations. Our main goal is to construct a truly general-purpose massively parallel processor that covers application elds not only for vector super-computers but also for main-frames and workstations. Potential application elds for our MPP system include:
منابع مشابه
The Intelligent Cache Controller of a Massively Parallel Processor JUMP-1
This paper describes the intelligent cache controller of JUMP-1, a distributed shared memory type MPP. JUMP-1 adopts an off-the-shelf superscalar as the element processor to meet the requirement of peak performance, but such a processor lacks the ability to hide inter-processor communication latency, which may easily become too long on MPPs. Therefore JUMP-1 provides an intelligent memory syste...
متن کاملThe RDT network router chip
The RDT network Router chip is a versatile router for the massively parallel computer prototype JUMP-1, which is currently under development by collaboration between 7 Japanese universities[1]. The major goal of this project is to establish techniques for building an e cient distributed shared memory on a massively parallel processor. For this purpose, the reduced hierarchical bit-map directory...
متن کاملReview of Parallel Genetic Algorithm Based on Computing Paradigm and Diversity in Search Space
Genetic Algorithm (GA), a stochastic optimization technique, doesn’t ensure optimal solution every time. Nowadays there is a need to improve the performance of each and every application so that the time required for obtaining quality solution can be minimized. This paper gives a brief overview of theoretical advances and computing trends, particularly population diversity in PGA (Parallel GA) ...
متن کاملGeneric Program Representation and Evaluation of Systolic Computations on Multicomputers
An overview of the uniied model (proposed earlier by us) for compiling systolic computations for multicomputers is given. Subsequently, we consider the diagonal and farming implementationalobjects which represent two speciic cases of the implementational objects deened in the model. For these two objects, we give prototype codes in the Occam language and give performance models for multi-transp...
متن کاملA Distributed Computing Center Software for the Efficient Use of Parallel Computer Systems
Nowadays, Computing systems accessible to researchers with "Grand Challenge" problems consist of a hardware mixture ranging from clusters of workstations to parallel supercomputers. This hardware is available via geographically distributed networks with various communication capabilities. Within this paper the Computing Center Software (CCS) is introduced. This software package is implemented a...
متن کامل