Sukru Burc Eryilmaz

S. Burc Eryilmaz is a senior architect in Compute Architecture at NVIDIA, where he works on improving the end-to-end performance of neural network training both at single-node scale and supercomputer scale. He received his PhD from Stanford University, and B.S from Bilkent University.

Posts by Sukru Burc Eryilmaz

Technical Walkthrough 0

Boosting NVIDIA MLPerf Training v1.1 Performance with Full Stack Optimization

In MLPerf training v1.1, we optimized across the entire stack including hardware, system software, libraries, and algorithms. 22 MIN READ
Data server room. Courtesy of Forschungszentrum Jülich/Sascha Kreklau.
Technical Walkthrough 3

MLPerf HPC v1.0: Deep Dive into Optimizations Leading to Record-Setting NVIDIA Performance

Learn about the optimizations and techniques used across the full stack in the NVIDIA AI platform that led to a record-setting performance in MLPerf HPC v1.0. 7 MIN READ
Technical Walkthrough 0

MLPerf v1.0 Training Benchmarks: Insights into a Record-Setting NVIDIA Performance

Learn about some of the major optimizations made to the NVIDIA platform that contributed to the nearly 7x increase in performance since the first MLPerf training benchmark. 31 MIN READ