Privacy-Preserving Performance Profiling of In-The-Wild GPUs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: McDougall, Ian, Davies, Michael, Chatterjee, Rahul, Jha, Somesh, Sankaralingam, Karthikeyan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916970842030080
author McDougall, Ian
Davies, Michael
Chatterjee, Rahul
Jha, Somesh
Sankaralingam, Karthikeyan
author_facet McDougall, Ian
Davies, Michael
Chatterjee, Rahul
Jha, Somesh
Sankaralingam, Karthikeyan
contents GPUs are the dominant platform for many important applications today including deep learning, accelerated computing, and scientific simulation. However, as the complexity of both applications and hardware increases, GPU chip manufacturers face a significant challenge: how to gather comprehensive performance characteristics and value profiles from GPUs deployed in real-world scenarios. Such data, encompassing the types of kernels executed and the time spent in each, is crucial for optimizing chip design and enhancing application performance. Unfortunately, despite the availability of low-level tools like NSYS and NCU, current methodologies fall short, offering data collection capabilities only on an individual user basis rather than a broader, more informative fleet-wide scale. This paper takes on the problem of realizing a system that allows planet-scale real-time GPU performance profiling of low-level hardware characteristics. The three fundamental problems we solve are: i) user experience of achieving this with no slowdown; ii) preserving user privacy, so that no 3rd party is aware of what applications any user runs; iii) efficacy in showing we are able to collect data and assign it applications even when run on 1000s of GPUs. Our results simulate a 100,000 size GPU deployment, running applications from the Torchbench suite, showing our system addresses all 3 problems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Privacy-Preserving Performance Profiling of In-The-Wild GPUs
McDougall, Ian
Davies, Michael
Chatterjee, Rahul
Jha, Somesh
Sankaralingam, Karthikeyan
Hardware Architecture
GPUs are the dominant platform for many important applications today including deep learning, accelerated computing, and scientific simulation. However, as the complexity of both applications and hardware increases, GPU chip manufacturers face a significant challenge: how to gather comprehensive performance characteristics and value profiles from GPUs deployed in real-world scenarios. Such data, encompassing the types of kernels executed and the time spent in each, is crucial for optimizing chip design and enhancing application performance. Unfortunately, despite the availability of low-level tools like NSYS and NCU, current methodologies fall short, offering data collection capabilities only on an individual user basis rather than a broader, more informative fleet-wide scale. This paper takes on the problem of realizing a system that allows planet-scale real-time GPU performance profiling of low-level hardware characteristics. The three fundamental problems we solve are: i) user experience of achieving this with no slowdown; ii) preserving user privacy, so that no 3rd party is aware of what applications any user runs; iii) efficacy in showing we are able to collect data and assign it applications even when run on 1000s of GPUs. Our results simulate a 100,000 size GPU deployment, running applications from the Torchbench suite, showing our system addresses all 3 problems.
title Privacy-Preserving Performance Profiling of In-The-Wild GPUs
topic Hardware Architecture
url https://arxiv.org/abs/2509.21762