Daisen: A Framework for Visualizing Detailed GPU Execution

Simple item page
dc.contributor.authorSun, Yifanen_US
dc.contributor.authorZhang, Yixuanen_US
dc.contributor.authorMosallaei, Alien_US
dc.contributor.authorShah, Michael D.en_US
dc.contributor.authorDunne, Codyen_US
dc.contributor.authorKaeli, Daviden_US
dc.contributor.editorBorgo, Rita and Marai, G. Elisabeta and Landesberger, Tatiana vonen_US
dc.date.accessioned2021-06-12T11:01:39Z
dc.date.available2021-06-12T11:01:39Z
dc.date.issued2021
dc.description.abstractGraphics 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.en_US
dc.description.number3
dc.description.sectionheadersMedical Applications and GPUs
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume40
dc.identifier.doi10.1111/cgf.14303
dc.identifier.issn1467-8659
dc.identifier.pages239-250
dc.identifier.urihttps://doi.org/10.1111/cgf.14303
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14303
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputer systems organization
dc.subjectSingle instruction
dc.subjectmultiple data
dc.subjectHuman centered computing
dc.subjectInformation visualization
dc.titleDaisen: A Framework for Visualizing Detailed GPU Executionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v40i3pp239-250.pdf
Size:
3.94 MB
Format:
Adobe Portable Document Format
Download
Collections
40-Issue 3