Eecient Processor Allocation for 3d Tori

نویسنده

  • Wenjian Qiao
چکیده

EEcient allocation of distinct subsets of processors to diierent jobs (i.e., space sharing) is critical to the performance of parallel computers, especially large scale parallel computers. This paper presents an eecient and lookahead strategy for processor allocation in 3D torus-connected systems, such as the Cray T3D, where each job requests for an exclusive allocation of a 3D submesh. The proposed processor allocation scheme has the following features: complete recognition of all maximal free submeshes, compact representation of submeshes, fairness with FCFS scheduling discipline, higher system utilization with lookahead scheduling, no restriction on the submesh orientation, and low allocation and scheduling overhead. The performance of the proposed strategy is demonstrated through simulation.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Eecient Processor Allocation for 3d Tori Eecient Processor Allocation for 3d Tori

EEcient allocation of distinct subsets of processors to diierent jobs (i.e., space sharing) is critical to the performance of parallel computers, especially large scale parallel computers. This paper presents an eecient and lookahead strategy for processor allocation in 3D torus-connected systems, such as the Cray T3D, where each job requests for an exclusive allocation of a 3D submesh. The pro...

متن کامل

The E ects of Dispersal on Message-Passing Contention in Processor Allocation Strategies

Processor allocation is a key task in the drive to fully realize the performance potential of massively parallel processing (MPP) systems. With the advent of the class of non-contiguous processor allocation strategies , the allocation performance bottleneck shifted from fragmentation to message-passing contention. This paper presents a method to estimate and minimize contention incurred by non-...

متن کامل

Contiguous and Non - Contiguous Processorallocation Algorithms for K - Ary N - Cubes

EEcient utilization of processing resources in a large, multiuser parallel computer depends on processor allocation algorithms that minimize system fragmentation. We propose three processor allocation algorithms for the k-ary n-cube class of parallel architectures, which includes the hypercube and multidi-mensional torus. The k-ary Partner strategy is a conventional contiguous processor allocat...

متن کامل

Multimedia object modelling and storage allocation strategies for heterogeneous parallel access storage devices in real time multimedia computing systems

The improvements in disk speeds have not kept up with improvements in processor and memory speeds. Conventional storage techniques, in the face of multi-media data, are ineecient and/or inadequate. Here, an eecient multimedia object allocation strategy is presented. We describe a multimedia object model, the object and storage device characteristics, and the fragmentation strategy. A bipartite ...

متن کامل

Modeling and Storage Allocation Strategies for Homogeneous Parallel Access Storage Devices in Real Time Multimedia Information Processing

1 The improvements in disk speeds have not kept up with improvements in processor and memory speeds. Conventional storage techniques, in the face of multi-media data, are ineecient and/or inadequate. Here, an eecient multimedia object allocation strategy is presented. We describe a multimedia object model, the object and storage device characteristics, and the fragmentation strategy. A bipartit...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1994