Results 191 to 200 of about 1,131,680 (246)
Some of the next articles are maybe not open access.
Shared memory vs. message passing in shared-memory multiprocessors
[1992] Proceedings of the Fourth IEEE Symposium on Parallel and Distributed Processing, 2003It is argued that the choice between the shared-memory and message-passing models depends on two factors: the relative cost of communication and computation as implemented by the hardware, and the degree of load imbalance inherent in the application. Two representative applications are used to illustrate the performance advantages of each programming ...
T.J. LeBlanc, E.P. Markatos
openaire +1 more source
UNAMBIGUOUS SHARED-MEMORY SYSTEMS
International Journal of Foundations of Computer Science, 2010Shared-memory systems appear as a generalization of asynchronous cellular automata. In this paper we relate the partial-order semantics of shared-memory systems to Mazurkiewicz trace languages by means of a new refinement construction. We show that a set of labeled partial orders is recognized by some unambiguous shared-memory system if and only if it
openaire +1 more source
Scalable Shared Memory and Shared Memory Clustering
1998Users want tightly coupled, shared everything systems that are highly available, scalable, have a single system image, and are cheap. Unfortunately for computer customers (and fortunately for computer engineering research), these goals conflict. The talk will discuss possible design points and trade-offs that can be pursued in an attempt to reconcile ...
openaire +1 more source
Shared memory and distributed shared memory systems: A survey
2000Publisher Summary This chapter illustrates distributed shared memory (DSM) systems that are intended to combine the ease of programming of the shared-memory model with the scalability of the distributed-memory system. DSM systems aim to unify parallel processing systems that rely on message passing with the shared-memory systems. The chapter explores
Krishna Kavi +3 more
openaire +1 more source
Proceedings of the 3rd ACM/IEEE Symposium on Architecture for networking and communications systems, 2007
Network processors provide an economical programmable platform to handle the high throughput and frame rates of modern and next-generation communication systems. However, these platforms have exchanged general-purpose capabilities for performance.This paper presents an alternative; a software network processor (Soft-NP) framework using commodity ...
John Giacomoni +5 more
openaire +1 more source
Network processors provide an economical programmable platform to handle the high throughput and frame rates of modern and next-generation communication systems. However, these platforms have exchanged general-purpose capabilities for performance.This paper presents an alternative; a software network processor (Soft-NP) framework using commodity ...
John Giacomoni +5 more
openaire +1 more source
Proceedings of the fifth international conference on Architectural support for programming languages and operating systems, 1992
We believe the absence of massively-parallel, shared-memory machines follows from the lack of a shared-memory programming performance model that can inform programmers of the cost of operations (so they can avoid expensive ones) and can tell hardware designers which cases are common (so they can build simple hardware to optimize them).
Mark D. Hill +3 more
openaire +1 more source
We believe the absence of massively-parallel, shared-memory machines follows from the lack of a shared-memory programming performance model that can inform programmers of the cost of operations (so they can avoid expensive ones) and can tell hardware designers which cases are common (so they can build simple hardware to optimize them).
Mark D. Hill +3 more
openaire +1 more source
Proceedings of the 21st international conference on Parallel architectures and compilation techniques, 2012
On-chip shared memory (a.k.a. local data share) is a critical resource to many GPGPU applications. In current GPUs, the shared memory is allocated when a thread block (also called a workgroup) is dispatched to a streaming multiprocessor (SM) and is released when the thread block is completed. As a result, the limited capacity of shared memory becomes a
Yi Yang +4 more
openaire +1 more source
On-chip shared memory (a.k.a. local data share) is a critical resource to many GPGPU applications. In current GPUs, the shared memory is allocated when a thread block (also called a workgroup) is dispatched to a streaming multiprocessor (SM) and is released when the thread block is completed. As a result, the limited capacity of shared memory becomes a
Yi Yang +4 more
openaire +1 more source
2004
Shared memory machines typically have relatively few processors, say 2–128. An intrinsic characteristic of these machines is a strategy for memory coherence and a fast tightly coupled network for distributing data from a commonly accessible memory system.
Wesley Petersen, Peter Arbenz
openaire +1 more source
Shared memory machines typically have relatively few processors, say 2–128. An intrinsic characteristic of these machines is a strategy for memory coherence and a fast tightly coupled network for distributing data from a commonly accessible memory system.
Wesley Petersen, Peter Arbenz
openaire +1 more source
1989
Abstract : The objectives of this effort was to investigate and evaluate OPTIMUL, an Optical Interconnect for Multiprocessor Systems, which could be used to interconnect a range of granularity of processors and memories for access to very large/knowledge bases (10**12-10**16 bytes).
M. Loving +4 more
openaire +1 more source
Abstract : The objectives of this effort was to investigate and evaluate OPTIMUL, an Optical Interconnect for Multiprocessor Systems, which could be used to interconnect a range of granularity of processors and memories for access to very large/knowledge bases (10**12-10**16 bytes).
M. Loving +4 more
openaire +1 more source
Proceedings of the 5th workshop on ACM SIGOPS European workshop Models and paradigms for distributed systems structuring - EW 5, 1992
Distributed shared memory (DSM) is the provision in software of a shared memory programming model on a distributed memory machine [6]. We are exploring the use of DSM in a cluster-based computing environment of workstations and servers connected by a local internetwork.We have concentrated so far on using DSM to program compute-intensive tasks on ...
J. K. Bennett +6 more
openaire +1 more source
Distributed shared memory (DSM) is the provision in software of a shared memory programming model on a distributed memory machine [6]. We are exploring the use of DSM in a cluster-based computing environment of workstations and servers connected by a local internetwork.We have concentrated so far on using DSM to program compute-intensive tasks on ...
J. K. Bennett +6 more
openaire +1 more source