Please use this identifier to cite or link to this item:
http://10.1.7.192:80/jspui/handle/123456789/12389
Title: | GPU Debugging Tool - GPU SnapShot |
Authors: | Parmar, Aniruddhsinh |
Keywords: | EC 2022 Project Report Project Report 2022 EC Project Report EC (ES) Embedded Systems Embedded Systems 2022 22MEC 22MECE 22MECE04 |
Issue Date: | 1-Jun-2024 |
Publisher: | Institute of Technology |
Series/Report no.: | 22MECE04; |
Abstract: | GPU snapshot debugging tool, a sophisticated utility meticulously crafted to capture a comprehensive array of GPU-related data vital for troubleshooting. It adeptly collects diverse information including ring buffers, registers, data structures, instruction buffers (PM4 packets), and page tables. Functioning seamlessly within a sysfs node, the tool orchestrates the creation of a binary file housing the gathered data. To render this information accessible and understandable, a Python script is enlisted to process the binary file, transforming it into a human-readable format. This streamlined process empowers developers to efficiently debug issues, thereby enhancing the robustness and stability of GPU-dependent systems. |
URI: | http://10.1.7.192:80/jspui/handle/123456789/12389 |
Appears in Collections: | Dissertation, EC (ES) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
22MECE04.pdf | 22MECE04 | 616.87 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.