Interactive Visualization for Memory Reference Traces

Choudhury, Abhinav; Potter, Kristin; Parker, Steven G.

doi:10.1111/j.1467-8659.2008.01212.x

Cited by 11 publications

(7 citation statements)

References 12 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Of particular interest is the addition of a component that provides a so-called source code orientation [Brown and Sedgewick 1984;Choudhury et al 2008], wherein lines of code corresponding to current ray tracing operations are highlighted. Such a component may better orient a user within the overall ray tracing algorithm by combining the familiar environment of traditional software debuggers with the visual process enabled by rtVTK.…”

Section: Discussionmentioning

confidence: 99%

“…A large number of systems are designed to visualize various aspects of algorithms or programs, including general run-time behavior [Brown and Sedgewick 1984], advanced CPU state [Stolte et al 1999], memory system performance [Choudhury et al 2008;Aftandilian et al 2010;Choudhury and Rosen 2011], and parallel performance [Nagel et al 1996;Shende and Malony 2006], among others. However, the existing tools are either too low-level or too specific for our purposes-focusing on particular algorithms, data structures, or hardware components-and do not provide the flexibility we require for tasks in development, education, and analysis.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Ray tracing visualization toolkit

Gribble

Fisher

Eby

et al. 2012

Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games

View full text Add to dashboard Cite

Figure 1: Ray Tracing Visualization Toolkit. An extensible GUI, together with a ray state recording library and a collection of visualization components, integrate existing client renderers via a flexible plug-in architecture to support visual analysis of ray-based rendering algorithms. Here, rtVTK is used to visually debug an ill-behaved path tracer. The previously undiscovered bug is not obvious in either a low-quality image with relatively few samples per pixel (top left) or a high-quality image with many more samples per pixel (bottom left). However, when viewing the ray state directly with rtVTK (middle, right), the problem is immediately obvious: some shadow rays originating from diffuse surfaces (circled) are not directed toward any light source in the scene. Once identified, the correction was trivial; however, in its previous state, the renderer was incorrect, and likely would have remained so without the ability to visualize the ray tracing process itself. AbstractThe Ray Tracing Visualization Toolkit (rtVTK) is a collection of programming and visualization tools supporting visual analysis of ray-based rendering algorithms. rtVTK leverages layered visualization within the spatial domain of computation, enabling investigators to explore the computational elements of any ray-based renderer. Renderers utilize a library for recording and processing ray state, and a configurable pipeline of loosely coupled components allows run-time control of the resulting visualization. rtVTK enhances tasks in development, education, and analysis by enabling users to interact with a visual representation of ray tracing computations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Ray tracing visualization toolkit

Gribble

Fisher

Eby

et al. 2012

Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games

View full text Add to dashboard Cite

show abstract

“…Most of these profiling tools work at coarse granularity, limiting potential insights to large scale bottlenecks. The recent work of Choudhury et al [CPP08, CR11] has focused on individual memory transactions. While the approaches unlock new insights, they have yet to scale to large memory traces or parallel applications the way this work does.…”

Section: Introductionmentioning

confidence: 99%

A Visual Approach to Investigating Shared and Global Memory Behavior of CUDA Kernels

Rosen

2013

Computer Graphics Forum

View full text Add to dashboard Cite

“…YACO [22] is a cache optimization tool focusing on performance statistics, plotting cache misses in different ways, highlighting performance bottlenecks in lines of code and data structures. By contrast, the Memory Trace Visualizer [6] visualizes reference traces directly, highlighting access patterns and showing their effects in a simulated cache, while follow-on work [7] visualizes the detailed data motion between the levels of a simulated cache.…”

Section: Related Workmentioning

confidence: 99%

Topological analysis and visualization of cyclical behavior in memory reference traces

Choudhury

Wang

Rosen

et al. 2012

2012 IEEE Pacific Visualization Symposium

View full text Add to dashboard Cite

(a) (b) Figure 1: One circular parameterization of the memory behavior of bubble sort (box (a)) morphing into another (box (b)), highlighting both their similarities and differences, and giving two views of the recurrent nature of the program. ABSTRACTWe demonstrate the application of topological analysis techniques to the rather unexpected domain of software visualization. We collect a memory reference trace from a running program, recasting the linear flow of trace records as a high-dimensional point cloud in a metric space. We use topological persistence to automatically detect significant circular structures in the point cloud, which represent recurrent or cyclical runtime program behaviors. We visualize such recurrences using radial plots to display their time evolution, offering multi-scale visual insights, and detecting potential candidates for memory performance optimization. We then present several case studies to demonstrate some key insights obtained using our techniques.

show abstract

Interactive Visualization for Memory Reference Traces

Abstract: Abstract

Cited by 11 publications

References 12 publications

Ray tracing visualization toolkit

Ray tracing visualization toolkit

A Visual Approach to Investigating Shared and Global Memory Behavior of CUDA Kernels

Topological analysis and visualization of cyclical behavior in memory reference traces

Contact Info

Product

Resources

About