ARMing GPUs for Impactful Science with the GH200 Superchip and True Exascale
Scalable Parallel Computing Lab, SPCL @ ETH Zurich via YouTube
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore NVIDIA's GH200 Superchip architecture through a comprehensive technical analysis that examines whether this ARM-based system represents a breakthrough for HPC workloads or merely serves as an expensive memory controller. Dive deep into the complex memory system architecture of the GH200, uncovering technical intricacies and hidden features while learning practical strategies for leveraging this powerful hardware for large-scale scientific computing applications. Discover how to harness the GH200's capabilities for revolutionary computational science projects that push the boundaries of exascale computing, with insights from the Scalable Parallel Computing Lab at ETH Zurich on optimizing performance for impactful scientific research.
Syllabus
ARMing GPUs for Impactful Science with the GH200 Superchip (and true Exascale)
Taught by
Scalable Parallel Computing Lab, SPCL @ ETH Zurich