Supercomputers have massive parallelism and very high computational speed. Often they have specific hardware to handle large amounts of floating point operations or vector operations.
Disadvantages are usually cost related. They are large, expensive to maintain, and require a lot of electrical power.
They are fast and tend to renew by the minute
This paper presents a comprehensive characterization of a multi-cluster supercomputer 1 workload using twelvemonth scientific research traces. Metrics that we characterize include system utilization, job arrival rate and interarrival time, job cancellation rate, job size (degree of parallelism), job run time, memory usage, and user/group behavior. Correlations between metrics (job runtime and memory usage, requested and actual runtime, etc) are identified and extensively studied. Differences with previously reported workloads are recognized and statistical distributions are fitted for generating synthetic workloads with the same characteristics. This study provides a realistic basis for experiments in resource management and evaluations of different scheduling strategies in a multi-cluster research environment. 1.