What is actually needed is to set mp_host_list parameter for abaqus, which needs to be set in an abaqus_v6.env file. However, on a SLURM managed job it is not possible to set this statically. 440 more words
Tags » HPC
In 2013 a new cluster with 6,336 CPU-cores and 73,728 CUDA-cores (GPU) will replace the current Titan system. The new system will have a maximum performance of 212 TFlops, almost 9 times the performance of the current system. 15 more words
What is a quantum computer?
While everyday life doesn’t show us much quantum effects, quantum physics rule every particle at the atomic level. Quantum physics and particularly the superposition principle, allow particles to be in different places at the same time until a signal interferes with them. 521 more words
In Parallel and Distributed Processing Symposium, 2014 IEEE 28th International
We propose a cluster scheduling technique for compute clusters with Xeon Phi coprocessors. Even though the Xeon Phi runs Linux which allows multiprocessing, cluster schedulers generally do not allow jobs to share coprocessors because sharing can cause oversubscription of coprocessor memory and thread resources. 242 more words
A supercomputing mind that powers smart cities has been my dream for a very long time. Instead of a corporate handling the services and computational resources of a sustainable city, my wish has been that skilled developers get involved in building a model for smarter cities, not necessarily without the help from corporate giants. 606 more words