This session will explore the objectives for building the DGX-2, along with the inspired, innovative technology and architecture used to eliminate traditional bottlenecks and to enable multi-GPU training at unprecedented scale. This talk led by the DGX product team will present on the following topics:
- the need for GPU-Ready Infrastructure from cooling, storage, compute, and networking
- the innovation and architecture found in NVSwitch, which enables the AI network fabric for the DGX-2 platform
- the design challenges and hardware architecture employed to enable 16 V100's to operate as one
- feature by feature walkthrough highlighting the most important innovations that accelerate deep learning workflow and training performance
- use cases that were previously unaddressable on a GPU platform, now solved with DGX-2.
- DGX systems reference architecture with storage partners
ABOUT THE SPEAKER: Renee Yao is a senior product marketing manager at NVIDIA, focusing on AI Systems. She graduated from Haas School of Business at the University of California, Berkeley and was named the top 50 B2B product marketers to watch by Kapost. When she has free time, she enjoys competitive Latin dancing, horseback riding, golfing, sculpturing.