You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
openpower.foundation/content/blog/tau-performance-system-open...

21 lines
1.6 KiB
Markdown

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

---
title: "TAU Performance System Showcased at OpenPOWER Summit Europe 2018"
date: "2018-10-24"
categories:
- "blogs"
tags:
- "featured"
---
By: Sameer Shende, director, Performance Research Laboratory, University of Oregon
At the University of Oregon, weve been looking at the problem of performance engineering of complex PowerAI applications. The [TAU Performance System](http://tau.uoregon.edu)® is a performance profiling and tracing toolkit that we developed, and it has been successfully applied to evaluate the performance of PowerAI components.
I recently had the chance to share early results in my session “TAU for Accelerating AI Applications” at the [OpenPOWER Summit Europe 2018](https://openpowerfoundation.org/summit-2018-10-eu/).
<iframe style="border: 1px solid #CCC; border-width: 1px; margin-bottom: 5px; max-width: 100%;" src="//www.slideshare.net/slideshow/embed_code/key/2k282L9ATrumrV" width="595" height="485" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" allowfullscreen="allowfullscreen"></iframe>
**[TAU for Accelerating AI Applications at OpenPOWER Summit Europe](//www.slideshare.net/OpenPOWERorg/tau-for-accelerating-ai-applications-at-openpower-summit-europe "TAU for Accelerating AI Applications at OpenPOWER Summit Europe ")** from **[OpenPOWERorg](https://www.slideshare.net/OpenPOWERorg)**
At OpenPOWER Summit Europe, researchers presented state-of-the-art approaches to running AI workloads on OpenPOWER systems. PowerAI is a powerful software stack. And, running larger datasets on it with TAU will enhance our understanding of the complex inner workings of the interplay between Power9 CPUs and NVIDIA GPUs.