Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

NPU-based image compositing in a distributed visualization system.

David Pugmire1, Laura Monroe, Carolyn Connor Davenport

  • 1Los Alamos National Laboratory, Los Alamos, NM 87545, USA. pugmire@lanl.gov

IEEE Transactions on Visualization and Computer Graphics
|May 15, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Carbon nitride monolayer nanosheets: astrochemical insights into the fate of interstellar hydrogen.

Physical chemistry chemical physics : PCCP·2026
Same author

MAGIC: Marching Cubes Isosurface Uncertainty Visualization for Gaussian Uncertain Data With Spatial Correlation.

IEEE transactions on visualization and computer graphics·2026
Same author

Photochemical Haze Formation on Titan and Uranus: A Comparative Review.

International journal of molecular sciences·2025
Same author

Implementation and evaluation of an integrated behavioral health curriculum within a family medicine clerkship.

Families, systems & health : the journal of collaborative family healthcare·2025
Same author

Parallelize Over Data Particle Advection: Participation, Ping Pong Particles, and Overhead.

IEEE transactions on visualization and computer graphics·2025
Same author

Fit for purpose testing and independent GMP validation of the monocyte activation test.

Current research in toxicology·2025
Same journal

MesoSplats: Texture Synthesis with Gaussian Splatting.

IEEE transactions on visualization and computer graphics·2026
Same journal

GLLA: A Unified Force-Directed Graph Layout Framework Supporting Local Adjustments.

IEEE transactions on visualization and computer graphics·2026
Same journal

Multi-Perception Crowd: Learning to combine entity and implicit perception for diverse crowd simulation.

IEEE transactions on visualization and computer graphics·2026
Same journal

Hiding in Plain Sight: Camouflaging Real-world Objects.

IEEE transactions on visualization and computer graphics·2026
Same journal

RTF2Mesh: Restricted Tangent Face Based Mesh Compression With Neural Displacement Fields.

IEEE transactions on visualization and computer graphics·2026
Same journal

Practical Occluder Generation for Mobile Games.

IEEE transactions on visualization and computer graphics·2026
See all related articles

This study introduces the first hardware-based image composition using a Network Processing Unit (NPU) in distributed rendering. This NPU approach significantly boosts performance, overcoming bottlenecks in clustered rendering systems.

Area of Science:

  • Computer Graphics
  • High-Performance Computing
  • Parallel Processing

Background:

  • Image composition is a critical bottleneck in distributed rendering systems.
  • Existing software and custom hardware solutions for image compositing have limitations in scalability and flexibility.
  • Image compositing algorithms often do not scale effectively with increasing data size and node count.

Purpose of the Study:

  • To investigate the use of a Network Processing Unit (NPU) for hardware-based image composition in distributed rendering.
  • To address the scalability and performance limitations of traditional software-based compositing methods.
  • To demonstrate a flexible, commercial off-the-shelf (COTS) solution for image composition.

Main Methods:

  • Utilized the heterogeneous multicore computation architecture of the Intel IXP28XX NPU for image composition.

Related Experiment Videos

  • Implemented a hardware-based image composition solution using programmable COTS technology.
  • Integrated the NPU-based compositor into a distributed rendering system.

    • Main Results:

    • Achieved a nearly four-times performance increase compared to traditional software-based compositing.
    • Sustained compositing rates of 22-28 frames per second (fps) for 1,024 x 1,024 images.
    • Demonstrated a scalable system with negligible frame rate penalty and high flexibility.

    Conclusions:

    • The NPU-based image composition offers a significant performance improvement for distributed rendering.
    • This modular NPU compositor is suitable for integration into existing distributed software visualization packages.
    • The use of COTS NPU technology provides a flexible and scalable solution for image composition challenges.