Motivated by observations about job runtimes on the CPlant system, we use a trace-driven microsimulator to be-gin characterizing the performance of different classes of allocation algorithms on jobs with different communication patterns in space-shared parallel systems with mesh topol-ogy. We show that relative performance varies considerably with communication pattern. The Paging strategy using the Hilbert space-filling curve and the Best Fit heuristic per-formed best across several communication patterns. 1
Two strategies are used for the allocation of jobs to processors connected by mesh topologies: conti...
scheduling In this paper, we utilize a bandwidth-centric job communication model that captures the i...
Abstract Communications overhead is one of the most important factors affecting per-fonnance in mess...
Motivated by observations about job runtimes on the CPlant system, we use a trace-driven microsimula...
Current processor allocation techniques for highly parallel systems are typically restricted to cont...
The performance of contiguous allocation strategies can be significantly affected by the distributio...
The Computational Plant, or Cplant is a commodity-based supercomputer under development at Sandia Na...
Abstract. The performance of contiguous allocation strategies can be significantly affected by the d...
Abstract. The performance of contiguous allocation strategies can be significantly affected by the d...
The performance of contiguous allocation strategies can be significantly affected by the type of the...
Abstract—this paper studies the influence that task placement may have on the performance of applica...
Developing efficient programs for distributed systems is difficult because computations must be effi...
The Computational Plant or Cplant is a commodity-based distributed-memory supercomputer under develo...
We conduct a detailed study of the performance effects of irregular communications patterns on the C...
When multiple jobs compete for processing resources on a parallel computer, the operating system ker...
Two strategies are used for the allocation of jobs to processors connected by mesh topologies: conti...
scheduling In this paper, we utilize a bandwidth-centric job communication model that captures the i...
Abstract Communications overhead is one of the most important factors affecting per-fonnance in mess...
Motivated by observations about job runtimes on the CPlant system, we use a trace-driven microsimula...
Current processor allocation techniques for highly parallel systems are typically restricted to cont...
The performance of contiguous allocation strategies can be significantly affected by the distributio...
The Computational Plant, or Cplant is a commodity-based supercomputer under development at Sandia Na...
Abstract. The performance of contiguous allocation strategies can be significantly affected by the d...
Abstract. The performance of contiguous allocation strategies can be significantly affected by the d...
The performance of contiguous allocation strategies can be significantly affected by the type of the...
Abstract—this paper studies the influence that task placement may have on the performance of applica...
Developing efficient programs for distributed systems is difficult because computations must be effi...
The Computational Plant or Cplant is a commodity-based distributed-memory supercomputer under develo...
We conduct a detailed study of the performance effects of irregular communications patterns on the C...
When multiple jobs compete for processing resources on a parallel computer, the operating system ker...
Two strategies are used for the allocation of jobs to processors connected by mesh topologies: conti...
scheduling In this paper, we utilize a bandwidth-centric job communication model that captures the i...
Abstract Communications overhead is one of the most important factors affecting per-fonnance in mess...