Debugging GPU-Accelerated Applications with NVIDIA Developer Tools, Nov 30, 2022

Introduction

This online webinar presented by Andrew Gontarek from Nvidia is part of the ALCF Developer Sessions, and is open to NERSC users.

Date and Time: 9 - 10 am (Pacific time), Wednesday, November 30, 2022

Abstract

As long as humans write software, there will be software bugs. And as many computational scientists today are orchestrating thousands of threads across massively parallel GPU systems, debugging and correctness tools are key pieces in the programmer’s toolchest. In this seminar, we’ll begin with an overview of runtime error-checking best practices and how to recover from CUDA errors using CUDA-GDB. Next we’ll  take a look at the CUDA Compute Sanitizer suite, which contains tools to detect race conditions and memory access errors. We’ll finish with a demonstration with CUDA-GDB on Polaris. 

Registration

Please find more information about the speaker and register on the event page of the ALCF Developer Sessions. 

Presentation Materials

• Slides
• Video