Compass: Eecient Communication Services for Scalable Architectures
نویسندگان
چکیده
In massively parallel computers (MPCs), eecient communication among processors is critical to performance. This paper describes the initial implementation of the ComPaSS communication library to support scalable software development in MPCs. ComPaSS provides high-level global communication operations for both data manipulation and process control, many of which are based upon a small set of low-level communication primitives. The ComPaSS library is unique in that these low-level operations are prov-ably optimal for a class of architectures representative of many commercial scalable systems, in particular, those using wormhole routing and n-dimensional mesh network topologies. This paper concentrates on the multicast component of the ComPaSS library, which is useful in several data parallel operations. The design of the multicast primitive is described, and an example of its use in a data parallel application is given. Improvements in performance resulting from use of the library on a 64-node nCUBE-2 are presented.
منابع مشابه
Design of a novel congestion-aware communication mechanism for wireless NoC architecture in multicore systems
Hybrid Wireless Network-on-Chip (WNoC) architecture is emerged as a scalable communication structure to mitigate the deficits of traditional NOC architecture for the future Multi-core systems. The hybrid WNoC architecture provides energy efficient, high data rate and flexible communications for NoC architectures. In these architectures, each wireless router is shared by a set of processing core...
متن کاملPricing in Integrated Service Networks
The service discipline implemented by the network and the ooered load are important variables determining network performance. An integrated service network is one which implements a single, uniied architecture suitable for supporting a wide range of traac types like guaranteed performance services, bounded delay services and best eeort traac. Such a network implements eecient scheduling and st...
متن کاملScalable Parallel Sparse Factorization with Left-right Looking Strategy on Shared Memory Multiprocessors 1 Scalable Parallel Sparse Factorization with Left-right Looking Strategy on Shared Memory Multiprocessors
An eecient sparse LU factorization algorithm on popular shared memory mul-tiprocessors is presented. Interprocess communication is critically important on these architectures-the algorithm introduces O(n) synchronization events only. No global barrier is used and a completely asynchronous scheduling scheme is one central point of the implementation. The algorithm aims at optimizing the single n...
متن کاملEecient Barriers for Distributed Shared Memory Computers University of Colorado at Boulder Eecient Barriers for Distributed Shared Memory Computers
Barrier algorithms are central to the performance of numerous algorithms on scalable, high-performance architectures. Numerous barrier algorithms have been suggested and studied for Non-Uniform Memory Access (NUMA) architectures, but less work has been done for Cache Only Memory Access (COMA) or attraction memory 2] architectures such as the KSR-1. In this paper, we present two new barrier algo...
متن کاملCommunication Primitives for Unstructured Finite Element Simulations on Data Parallel Architectures Communication Primitives for Unstructured Finite Element Simulations on Data Parallel Architectures
EEcient data motion is critical for high performance computing on distributed memory architectures. The value of some techniques for eecient data motion is illustrated by identifying generic communication primitives. Further, the eeciency of these primitives is demonstrated on three diier-ent applications using the nite element method for unstructured grids and sparse solvers with diierent comm...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1992