NVIDIA | Deep Learning Algorithm Engineer (Junior/New Grad) | Screen | Phone Screen

30 minute HM screen round. Below were the questions. 1. if you have a GPU at 100% util given a batch size and some throughput/latency numbers, how are these affected when you increase batch size further 2. How to identify when to increase batch size This led to general discussion about memory bound and compute bound and roofline model analysis and how hardware arithmetic intensity related to software. 3. Overview of...