The nano-threads programming model was proposed to effectively integrate multiprogramming on shared-memory multiprocessors, with the exploitation of fine-grain parallelism from standard applications. A prerequisite fo...
详细信息
The Distributed Computer Network (DCN) is a resource-sharing computer network which includes a number of DEC PDP11 computers. The DCN supports a number of processes in a multiprogrammed virtual environment. Processes ...
详细信息
The memory access stream to the last level cache (LLC) is a filtered version from the upper level caches. There are a large number of cache blocks with long re-reference interval in the LLC. What's worse, zero reu...
详细信息
This paper presents a new model for use in scheduling processes for the sharing of a processor. The model may be used in various modes of operation, including multiprogramming, real time and time sharing. Because the ...
详细信息
A tree-structured multiprocessing system design is proposed in which process communication is the primary link between processors. A hardware cluster, called a Processing Module, is proposed as the basic structural co...
详细信息
A tree-structured multiprocessing system design is proposed in which process communication is the primary link between processors. A hardware cluster, called a Processing Module, is proposed as the basic structural component. These modules literally "plug together" tc form a system of arbitrary size. Each module has its own memory and runs its own hierarchically-structured operating system, the nucleus of which inplements P. B. Hansen's communications primitives along with process creation and removal. Workload scheduling and process location are performed recursively in the systec's tree structure. multiprogramming is implemented system-wide, allowing processes to migrate away from overloaded modules. It is argued that the resulting system would be truly general-purpose and is subject to no limit on its size and conseguent computing power.
This paper develops analytic techniques for achieving macro-level configurational optimization of computer systems. The computer is viewed as a network of queues with the processors, main memory, auxiliary memory and ...
详细信息
Barrier synchronizations can be very expensive on multiprogramming environment because no process can go past a barrier until all the processes have arrived. If a process participating at a barrier is swapped out by t...
详细信息
ISBN:
(纸本)9780897919982
Barrier synchronizations can be very expensive on multiprogramming environment because no process can go past a barrier until all the processes have arrived. If a process participating at a barrier is swapped out by the operating system, the rest of participating processes end up waiting for the swapped-out process. This paper presents a compile-time/run-time system that uses a dependence-driven execution to overlap the execution of computations separated by barriers so that the processes do not spend most of the time idling at the synchronization point.
NASA Technical Reports Server (Ntrs) 19870017088: the Predictive Information Obtained by Testing Multiple Software Versions by NASA Technical Reports Server (Ntrs); published by
NASA Technical Reports Server (Ntrs) 19870017088: the Predictive Information Obtained by Testing Multiple Software Versions by NASA Technical Reports Server (Ntrs); published by
暂无评论