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.
Avatar photo

Posts by Sukru Burc Eryilmaz

Technical Walkthrough 4 Nov 09, 2022

Tuning AI Infrastructure Performance with MLPerf HPC v2.0 Benchmarks

As the fusion of AI and simulation accelerates scientific discovery, the need has arisen for a means to measure and rank the speed and throughput for building... 14 MIN READ
Technical Walkthrough 5 Nov 09, 2022

Leading MLPerf Training 2.1 with Full Stack Optimizations for AI

MLPerf benchmarks, developed by MLCommons, are critical evaluation tools for organizations to measure the performance of their machine learning models' training... 14 MIN READ
Technical Walkthrough 1 Jun 30, 2022

The Full Stack Optimization Powering NVIDIA MLPerf Training v2.0 Performance

MLPerf benchmarks are developed by a consortium of AI leaders across industry, academia, and research labs, with the aim of providing standardized, fair, and... 14 MIN READ
Technical Walkthrough 2 Dec 01, 2021

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

Five months have passed since v1.0, so it is time for another round of the MLPerf training benchmark. In this v1.1 edition, optimization over the entire... 22 MIN READ
Data server room. Courtesy of Forschungszentrum Jülich/Sascha Kreklau.
Technical Walkthrough 4 Nov 17, 2021

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

In MLPerf HPC v1.0, NVIDIA-powered systems won four of five new industry metrics focused on AI performance in HPC. As an industry-wide AI... 7 MIN READ
Technical Walkthrough 1 Jun 30, 2021

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

MLPerf is an industry-wide AI consortium tasked with developing a suite of performance benchmarks that cover a range of leading AI workloads widely in use. The... 31 MIN READ