In this paper, we show how application scheduling can be used to reduce the turn-around time of supercomputer jobs. Our approach focuses on the use of SA, an AppLeS application scheduler, to adaptively craft the request to be submitted to the supercomputer based on the current state of the system. We demonstrate that SA significantly improves a job’s turn-around time in a variety of scenarios. ...

Tits paper describes the collection and analysis of supercomputer I/O traces and their use in a collection of buffering and caching simulations. TJ,As serves two purposes. First, it gives a model of how individual applications running on supercomputers request f'fl¢ system I/0, allowing system designers to optimize I/0 hardware and file system algorithms to that model. Second, the buffering sim...

We discuss some of the engineering challenges in implementing a constraint programming based scheduling engine to scale well on massively parallel computer hardware. In particular, we have been targeting our solvers to work in high performance computer environments such as the IBM BlueGene/P supercomputer. On such hardware parallelism is enabled at the software level using message passing, base...

Supercomputer components are inherently stateful and interdependent, so accurate assessment of an event on one component often requires knowledge of previous events on that component or others. Administrators who daily monitor and interact with the system generally possess sufficient operational context to accurately interpret events, but researchers with only historical logs are at risk for in...

Re-hosting legacy codes optimized for a platform such as a vector supercomputer often requires a complete re-write of the original code. This work provides a framework and approach to use configurable computing resources in place of a vector supercomputer towards the implementation of a legacy code without a long and expensive re-hosting effort. The approach automatically tailors a parameterize...

In this paper, we examine the performance of two components of the NCAR Community Climate System Model (CCSM) executing on clusters with a variety of microprocessor architectures and interconnects. Specifically, we examine the execution time and scalability of the Community Atmospheric Model (CAM) and the Parallel Ocean Program (POP) on Linux clusters with Intel Xeon and AMD Opteron processors,...

In the world of supercomputers, the large number of processors requires to minimize the inefficiencies of parallelization, which appear as a sequential part of the program from the point of view of Amdahl’s law. The recently suggested new figure of merit is applied to the recently presented supercomputer, and the timeline of ”Top 500” supercomputers is scrutinized using the metric. It is demons...

The use of " event-based " algorithms for particle transport Monte Carlo methods has allowed the successful adaptation of these methods to vector supercomputers. An alternative algorithm for the specific application of photon transport in an axisymmetric inertially confined fusion plasma has been developed and implemented on a vector supercomputer. The new algorithm is described; its unique fea...

As part of a parallel computing course where undergraduate students learned parallel computing techniques and got to run their programs on a supercomputer, one student designed and implemented a sequential algorithm and two versions of a parallel algorithm to solve the knapsack problem. Performance tests of the programs were conducted on the Ranger supercomputer. The performance of the sequenti...

At the Electronics Lab of the Swiss Federal Institute of Techology (ETH) in Zurich, the high performance Parallel Supercomputer MUSIC (MUlti processor System with Intelligent Communication) has beed developed. As applications in neural network simulation and molecular dynamics show, the Electronics Lab Supercomputer is absolutely on a par with those of conventional supercomputers, but electric ...