In this video, Shane Moeykens from Ansys presents: Leveraging HPC and Optimizing the IT Environment for Engineering Simulation. The presentation was recorded at the HPC Advisory Council Stanford Conference 2013. Download the slides (PDF).
SC17 will feature a panel discussion entitled How Serious Are We About the Convergence Between HPC and Big Data? "The possible convergence between the third and fourth paradigms confronts the scientific community with both a daunting challenge and a unique opportunity. The challenge resides in the requirement to support both heterogeneous workloads with the same hardware architecture. The opportunity lies in creating a common software stack to accommodate the requirements of scientific simulations and big data applications productively while maximizing performance and throughput. [Read More...]
Using Remote Direct Memory Access based analytics and fast, scalable,external disk systems with massively parallel access to data, SAS analytics driven organizations can deliver timely and accurate execution for data intensive workflows such as risk management, while incorporating larger datasets than using traditional NAS.
Copyright © 2017
This presentation misses the most glaring issue with commercial software providers, such as ANSYS, namely that their licensing models are extremely out of touch with the pace of Moore’s law. Add into that mix the fact that they want to ala carte you to death for things like GPGPUs.
Rich – here is a great little side project for you. Track commercial software cost against hardware costs. With hardware, costs scale, with software it sadly misses the boat. You can spend $1.5M for something in the 100TF range for an fully depreciated life over 36 months. Commercial CAE software to run on that cluster (CFD, Crash, FEA, Chemistry) can hit you with that same number yearly.