“Before (the Exascale Computing Project), both packages had very little support for GPUs. We could get some benefit from running on a single GPU, but without updating the code, even 10 GPUs wouldn’t make it run much faster. We had to redesign a lot of algorithms ….”
At SC22: An Update on the Altair-AMD Collaboration
At SC22 we caught up with Altair and AMD on their long-running partnership utilizing AMD data center server chips in support of Altair engineering software. We spoke with Eric Lequiniou, Vice President of RADIOSS Development and Altair Solver HPC, and with AMD’s Kevin Mayo, Director of HPC Engineering. The two spoke about AMD’s latest generation […]
Out of Core Solvers on a Cluster
One of the most used algorithms in numerical simulation is the solving of large, dense matrices. Thermal analysis, boundary element methods and electromagnetic wave calculations all depend on the ability to solve these large matrices as fast as possible. The ability to use a coprocessor such as the Intel Xeon Phi coprocessor will greatly speed up these calculations.