TU Darmstadt / ULB / TUbiblio

Profiling and Visualizing GPU Memory Access and Cache Behavior of Ray Tracers

Buelow, Max von ; Riemann, Kai ; Guthe, Stefan ; Fellner, Dieter W. (2022)
Profiling and Visualizing GPU Memory Access and Cache Behavior of Ray Tracers.
22nd Eurographics Symposium on Parallel Graphics and Visualization. Rome, Italy (13.06.2022)
doi: 10.2312/pgv.20221061
Conference or Workshop Item, Bibliographie

Abstract

Graphical processing units (GPUs) have gained popularity in recent years due to their efficiency in running massively parallel applications. Recent developments have also adapted ray-tracing algorithms to the GPU, where the bottleneck in the overall performance is usually given by the memory bandwidth. In this paper, we present an interactive, web-based visualization tool for GPU memory traces that provides visual insight into the memory and cache behavior of our reference ray tracer, by mapping internal GPU state back onto 3D objects. In order to visualize cache behavior, we use reuse distances on both GPU cache layers that are calculated on the basis of memory traces extracted from a real GPU using binary instrumentation. An advantage of our system is that it runs independently of the ray-tracing program. We further show visualizations of our GPU ray tracer and compare the visualizations of several ray-tracing approaches. We find our work to act as a convenient toolset to gather insights on which data structures and mesh regions can be cached efficiently, and how ray-tracing acceleration structures behave on various input meshes, bounding volume hierarchies, memory layouts, frame buffer resolutions, and work distribution techniques.

Item Type: Conference or Workshop Item
Erschienen: 2022
Creators: Buelow, Max von ; Riemann, Kai ; Guthe, Stefan ; Fellner, Dieter W.
Type of entry: Bibliographie
Title: Profiling and Visualizing GPU Memory Access and Cache Behavior of Ray Tracers
Language: English
Date: 2022
Publisher: Eurographics Association
Book Title: EGPGV22: Eurographics Symposium on Parallel Graphics and Visualization
Series: EGPGV: Eurographics Workshop on Parallel Graphics and Visualization
Event Title: 22nd Eurographics Symposium on Parallel Graphics and Visualization
Event Location: Rome, Italy
Event Dates: 13.06.2022
DOI: 10.2312/pgv.20221061
URL / URN: https://diglib.eg.org:443/handle/10.2312/pgv20221061
Abstract:

Graphical processing units (GPUs) have gained popularity in recent years due to their efficiency in running massively parallel applications. Recent developments have also adapted ray-tracing algorithms to the GPU, where the bottleneck in the overall performance is usually given by the memory bandwidth. In this paper, we present an interactive, web-based visualization tool for GPU memory traces that provides visual insight into the memory and cache behavior of our reference ray tracer, by mapping internal GPU state back onto 3D objects. In order to visualize cache behavior, we use reuse distances on both GPU cache layers that are calculated on the basis of memory traces extracted from a real GPU using binary instrumentation. An advantage of our system is that it runs independently of the ray-tracing program. We further show visualizations of our GPU ray tracer and compare the visualizations of several ray-tracing approaches. We find our work to act as a convenient toolset to gather insights on which data structures and mesh regions can be cached efficiently, and how ray-tracing acceleration structures behave on various input meshes, bounding volume hierarchies, memory layouts, frame buffer resolutions, and work distribution techniques.

Uncontrolled Keywords: Visual analytics, Graphics processors
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Date Deposited: 03 Jan 2023 09:47
Last Modified: 11 Jan 2023 09:24
PPN: 503548324
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details