scholarly journals Daisen: A Framework for Visualizing Detailed GPU Execution

2021 ◽  
Author(s):  
Yifan Sun ◽  
Yixuan Zhang ◽  
Ali Mosallaei ◽  
Michael D. Shah ◽  
Cody Dunne ◽  
...  
Keyword(s):  
Performance Analysis ◽  
Performance Improvement ◽  
Graphics Processing Units ◽  
Qualitative Evaluation ◽  
Evaluation Study ◽  
Survey Study ◽  
Performance Bottlenecks ◽  
Making Sense ◽  
Execution Traces ◽  
Physics Simulation

Graphics Processing Units~(GPUs) have been widely used to accelerate artificial intelligence, physics simulation, medical imaging, and information visualization applications. To improve GPU performance, GPU hardware designers need to identify performance issues by inspecting a huge amount of simulator-generated traces. Visualizing the execution traces can reduce the cognitive burden of users and facilitate making sense of behaviors of GPU hardware components. In this paper, we first formalize the process of GPU performance analysis and characterize the design requirements of visualizing execution traces based on a survey study and interviews with GPU hardware designers. We contribute data and task abstraction for GPU performance analysis. Based on our task analysis, we propose Daisen, a framework that supports data collection from GPU simulators and provides visualization of the simulator-generated GPU execution traces. Daisen features a data abstraction and trace format that can record simulator-generated GPU execution traces. Daisen also includes a web-based visualization tool that helps GPU hardware designers examine GPU execution traces, identify performance bottlenecks, and verify performance improvement. Our qualitative evaluation with GPU hardware designers demonstrates that the design of Daisen reflects the typical workflow of GPU hardware designers. Using Daisen, participants were able to effectively identify potential performance bottlenecks and opportunities for performance improvement. The open-sourced implementation of Daisen can be found at gitlab.com/akita/vis. Supplemental materials including a demo video, survey questions, evaluation study guide, and post-study evaluation survey are available at osf.io/j5ghq.

scholarly journals Emergent model for community engagement: Developing courses and programs

2020 ◽  
Vol 4 (1) ◽  
pp. 80-95
Author(s):  
Barbara S. Spector ◽  
Cyndy Leard
Keyword(s):  
Community Engagement ◽  
Qualitative Evaluation ◽  
Evaluation Study ◽  
Informal Science Education ◽  
South Florida ◽  
Target Audience ◽  
Informal Science ◽  
Engaged Scholarship ◽  
Stakeholder Groups ◽  
The University

This retrospective emergent design qualitative evaluation study documents the development of a unique model for community engagement and engaged scholarship in higher education. The primary novel aspect of the model is participatory involvement of both the target audience for the program and representatives of various stakeholder groups who initiated, conceptualized, tested, assessed, and evaluated the courses and program with the professor. Members of the target audience and stakeholder groups also recruited participants, contributed to refining the courses and program to meet the needs of the stakeholder groups, and contributed to redesigning courses for online learning. The model emerged while developing and evaluating the Informal Science Institutions Environmental Education Graduate Certificate Program (ISI Program) at the University of South Florida. Garnering the resources of a previously untapped audience, the informal science education (ISE) community, presented the university with a way to increase enrollment. Also reported are sample benefits accrued to learners in the program, to the ISI community, to the community at large, and additional benefits to the University.

Non-Intrusive Adaptation of System Execution Traces for Performance Analysis of Software Systems

2014 ◽  
pp. 473-493
Author(s):  
Manjula Peiris ◽  
James H. Hill
Keyword(s):  
Performance Analysis ◽  
System Performance ◽  
Source Code ◽  
Software Systems ◽  
Software System ◽  
Original Source ◽  
Performance Properties ◽  
Execution Traces ◽  
Execution Trace ◽  
Analysis Of Performance

This chapter discusses how to adapt system execution traces to support analysis of software system performance properties, such as end-to-end response time, throughput, and service time. This is important because system execution traces contain complete snapshots of a systems execution—making them useful artifacts for analyzing software system performance properties. Unfortunately, if system execution traces do not contain the required properties, then analysis of performance properties is hard. In this chapter, the authors discuss: (1) what properties are required to analysis performance properties in a system execution trace; (2) different approaches for injecting the required properties into a system execution trace to support performance analysis; and (3) show, by example, the solution for one approach that does not require modifying the original source code of the system that produced the system execution.

scholarly journals Haemophilia home care: A qualitative evaluation study of the Be Involved infusion program

Haemophilia ◽  
2019 ◽  
Vol 25 (5) ◽  
pp. 807-813
Author(s):  
Emma Rossnagel ◽  
John L. Oliffe ◽  
Yanina Jackson ◽  
Claude Bartholomew
Keyword(s):  
Home Care ◽  
Qualitative Evaluation ◽  
Evaluation Study

AUTOMATIC PERFORMANCE ANALYSIS AND DYNAMIC TUNING OF DISTRIBUTED APPLICATIONS

2003 ◽  
Vol 13 (02) ◽  
pp. 169-187 ◽  
Author(s):  
ANNA MORAJKO ◽  
OLEG MORAJKO ◽  
JOSEP JORBA ◽  
TOMÀS MARGALEF ◽  
EMILIO LUQUE
Keyword(s):  
Performance Analysis ◽  
Dynamic Behavior ◽  
Distributed Applications ◽  
Performance Expectations ◽  
Performance Bottlenecks ◽  
Dynamic Tuning ◽  
Dynamic Variations ◽  
Automatic Performance Analysis ◽  
Monitoring Information

The classical way of tuning parallel/distributed applications is based on the analysis of the monitoring information obtained from an execution of the application. However, this "measure and modify" approach is not feasible when the applications have a dynamic behavior. In this case, another approach is required to accomplish performance expectations. This paper presents a solution based on the dynamic tuning approach that addresses these issues. In this approach, an application is monitored, its performance bottlenecks are detected and the application is modified automatically during the execution, without stopping, recompiling or re-running it. The introduced modifications adapt the behavior of the application to dynamic variations.

The legal macroscope: Experimenting with visual legal analytics

2016 ◽  
Vol 16 (4) ◽  
pp. 332-345 ◽  
Author(s):  
Nicola Lettieri ◽  
Antonio Altamura ◽  
Delfina Malandrino
Keyword(s):  
User Satisfaction ◽  
Visual Analytics ◽  
Web Application ◽  
Evaluation Study ◽  
Legal Framework ◽  
Preliminary Evaluation ◽  
Legal Documents ◽  
Making Sense ◽  
Legal Literature ◽  
Different Sources

This work presents Knowlex, a web application designed for visualization, exploration, and analysis of legal documents coming from different sources. Understanding the legal framework relating to a given issue often requires the analysis of complex legal corpora. When a legal professional or a citizen tries to understand how a given phenomenon is disciplined, his attention cannot be limited to a single source of law but has to be directed on the bigger picture resulting from all the legal sources related to the theme under investigation. Knowlex exploits data visualization to support this activity by means of interactive maps making sense out of heterogeneous documents (norms, case law, legal literature, etc.). Starting from a legislative measure (what we define as Root) given as input by the user, the application implements two visual analytics functionalities aiming to offer new insights on the legal corpus under investigation. The first one is an interactive node graph depicting relations and properties of the documents. The second one is a zoomable treemap showing the topics, the evolution, and the dimension of the legal literature settled over the years around the norm of interest. The article gives an overview of the research so far conducted presenting the results of a preliminary evaluation study aiming at evaluating the effectiveness of visualization in supporting legal activities as well as the effectiveness of Knowlex, the usability of the proposed system, and the overall user satisfaction when interacting with its applications.

Sign in / Sign up

Export Citation Format

Share Document