This paper discusses the development of statically balanced spatial parallel platform mechanisms. A mechanism is statically balanced if its potential energy is constant for all possible con gurations. This property is very convenient for robotic manipulators with large constant payloads, since it means that the mechanism is statically stable for any con guration, i.e., zero actuator torques are required whenever the manipulator is at rest. Furthermore, only inertial forces and moments have to be sustained while the manipulator is moving. This makes it possible to create passive devices that can assist humans to manipulate a heavy load, and to create robotic manipulators that require smaller actuators and/or consume less energy. Furthermore, by retro tting existing machine tools, static de ection problems due to gravitational loads may be reduced.This paper (1) summarizes how static balancing can be implemented in a parallel manipulator with six degrees of freedom, (2) presents the design of a small-scale prototype, and (3) discusses general implementation issues.
No abstract
As multiprocessor sizes scale andcomputer architects tumto interconnection networks with non-uniform communication latencies, the lure of exploiting communication locality to increase performance becomes inevitable. Models that accurately quantify locality effects provide invaluable insight into the importance of exploiting locality as machine sizes and features change. This paper presents a framework for modeling the impact of communication locality on system performance. The framework provides a means for combining simple models of application, processor, and network behavior to obtain a combined model that accurately reflects feedback effects between processors and networks. Reintroduce a model that characterizes application behavior with three parameters that capture computation grain, sensitivity to communication latency, and amount of locality present at execution time. Thecombined model is validated with measurements taken from a detailed simulator for a complete multiprocessor system. Usingthe combined model, weshowthat exploiting communication locality provides gains which are at most linear in the factor by which average communication distance is reduced when thenumberof outstanding communication transactions per processors bounded. Thecombined model isalsoused toobtain rough upper bounds on the performance improvement from exploiting locality to minimize communication distance. 1 Introduction At the heart of any multiprocessor lies the interconnection network through which processing nodes communicate with one another. The simplest types of interconnection networks allow all distinct pairs of processors to communicate with the same latency, ignoring contention effects. The simplicity of the cost model provided by such uniform communication latency (UCL) interconnection networks affords simplicity in software systems (e.g. compilers, schedulers, operating systems) built upon architectures that use such networks. Unfortunately, mechanisms used to implement UCL networks are not scalable. Single-level shared-bus architectures are limited by bus bandwidth and are unable to support reasonable communication loads from more than a few dozen processors. Full crossbars might provide nearly uniform communication Iatencies, but excessive hardware requirements prevent them Permission to copy without fee all or part of this material IS granted provided that the copies are not made or distributed for direct commercial advantage, the ACM copyright notice and the title of the publication and Its date appear, and notice is g]ven that copying IS by perrmssion of the Association for Computing Machinery. To copy otherwise, or to republmh, requires a fee and/or specific pernmwon. from being scalable. Indirect, multistage networks that circumvent the bandwidth problems of buses and quadratic hardware requirements of full crossbars provide bandwidth which scales with machine size. But this increased bandwidth comes at a price: all communication latency increases with the number of processors in the system. 1 Because the const...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.