Manager, CUDA HPC Math Libraries
Over the last decade, GPU accelerated computing has dramatically changed the HPC world, making exascale computing a reality. But these changes are not likely to slow down anytime soon. Thanks to newer GPU architectures and advances in AI related technologies, new computational methods are emerging that leverage hardware and software technologies from both AI and traditional HPC. In this talk, we will look at one of these recently emerging trends: low and mixed precision computing in numerical methods. In particular, we will look at one application of mixed-precision computing that accelerates a very commonly used dense linear algebra routine by almost a factor of four while still delivering the solution in double precision on the same computer hardware.
Harun received his PhD degree in Mechanical Engineering from UC Berkeley in 2003. After graduating, he joined Dassault Systemes Simulia Corporation (formerly Abaqus, Inc.) as a software engineer and developed high-performance parallel numerical methods for FEA and CFD solvers. In 2010, Harun joined the Albany Engineered Composites where he lead the Research and Technology efforts on advanced 3D woven composite materials using simulation. In 2017, he joined NVIDIA and is currently the manager of CUDA HPC Math Libraries.
Hosted by: Professor Panayiotis Papadopoulos, 6131 Etcheverry Hall, 510- 642-3358, firstname.lastname@example.org