Reducing Shading on GPUs Using Quad-Fragment Merging JAEHYUN CHO

Slides:



Advertisements
Similar presentations
Destruction Masking in Frostbite 2 using Volume Distance Fields
Advertisements

Point-based Graphics for Estimated Surfaces
Exploration of advanced lighting and shading techniques
CS123 | INTRODUCTION TO COMPUTER GRAPHICS Andries van Dam © 1/16 Deferred Lighting Deferred Lighting – 11/18/2014.
Photon Mapping on Programmable Graphics Hardware Timothy J. Purcell Mike Cammarano Pat Hanrahan Stanford University Craig Donner Henrik Wann Jensen University.
CS 352: Computer Graphics Chapter 7: The Rendering Pipeline.
Object Space EWA Surface Splatting: A Hardware Accelerated Approach to High Quality Point Rendering Liu Ren Hanspeter Pfister Matthias Zwicker CMU.
Optimized Stencil Shadow Volumes
RealityEngine Graphics Kurt Akeley Silicon Graphics Computer Systems.
Topology-Caching for Dynamic Particle Volume Raycasting Jens Orthmann, Maik Keller and Andreas Kolb, University of Siegen.
Real-Time Rendering TEXTURING Lecture 02 Marina Gavrilova.
GPUs and GPU Programming Bharadwaj Subramanian, Apollo Ellis Imagery taken from Nvidia Dawn Demo Slide on GPUs, CUDA and Programming Models by Apollo Ellis.
High-Quality Parallel Depth-of- Field Using Line Samples Stanley Tzeng, Anjul Patney, Andrew Davidson, Mohamed S. Ebeida, Scott A. Mitchell, John D. Owens.
GCAFE 28 Feb Real-time REYES Jeremy Sugerman.
MATHIEU GAUTHIER PIERRE POULIN LIGUM, DEPT. I.R.O. UNIVERSITÉ DE MONTRÉAL GRAPHICS INTERFACE 2009 Preserving Sharp Edges in Geometry Images.
I3D Fast Non-Linear Projections using Graphics Hardware Jean-Dominique Gascuel, Nicolas Holzschuch, Gabriel Fournier, Bernard Péroche I3D 2008.
Christian Lauterbach COMP 770, 2/11/2009
Chapter 6: Vertices to Fragments Part 2 E. Angel and D. Shreiner: Interactive Computer Graphics 6E © Addison-Wesley Mohan Sridharan Based on Slides.
Control Flow Virtualization for General-Purpose Computation on Graphics Hardware Ghulam Lashari Ondrej Lhotak University of Waterloo.
Practical and Robust Stenciled Shadow Volumes for Hardware-Accelerated Rendering Cass Everitt and Mark J. Kilgard Speaker: Alvin Date: 5/28/2003 NVIDIA.
Image Quilting for Texture Synthesis and Transfer Alexei A. Efros1,2 William T. Freeman2.
Shadow Silhouette Maps Pradeep Sen, Mike Cammarano, Pat Hanrahan Stanford University.
Shadow Silhouette Maps Pradeep Sen Mike Cammarano Pat Hanrahan Stanford University Speaker: Alvin Date: 8/24/2003 SIGGRAPH 2003.
Microtriangle thesis mid-status September 22th, 2010.
Perspective Shadow Maps Marc Stamminger and George Drettakis Speaker: Alvin Date: 5/28/2003 SIGGRAPH 2002.
GRAMPS: A Programming Model For Graphics Pipelines Jeremy Sugerman, Kayvon Fatahalian, Solomon Boulos, Kurt Akeley, Pat Hanrahan.
Many-Core Programming with GRAMPS Jeremy Sugerman Kayvon Fatahalian Solomon Boulos Kurt Akeley Pat Hanrahan.
Many-Core Programming with GRAMPS Jeremy Sugerman Stanford University September 12, 2008.
The Radiosity Method Donald Fong February 10, 2004.
GPU vs. CPU computations Árni Einarsson Jacek Kolodziej.
A Real-Time Procedural Shading System for Programmable Graphics Hardware Kekoa Proudfoot William R. Mark Svetoslav Tzvetkov Pat Hanrahan.
© 2004 Tomas Akenine-Möller1 Shadow Generation Hardware Vision day at DTU 2004 Tomas Akenine-Möller Lund University.
Painterly Rendering for Animation Barbara J. Meier Walt Disney Feature Animation SIGGRAPH 96.
1 Occlusion Culling ©Yiorgos Chrysanthou, , Anthony Steed, 2004.
Ray Tracing and Photon Mapping on GPUs Tim PurcellStanford / NVIDIA.
Prefiltered Anti-Aliasing on Parallel Hardware
May 8, 2007Farid Harhad and Alaa Shams CS7080 Over View of the GPU Architecture CS7080 Class Project Supervised by: Dr. Elias Khalaf By: Farid Harhad &
COMP 261 Lecture 16 3D Rendering. input: set of polygons viewing direction direction of light source(s) size of window. output: an image Actions rotate.
Marching Cubes: A High Resolution 3D Surface Construction Algorithm William E. Lorenson Harvey E. Cline General Electric Company Corporate Research and.
Week 2 - Friday.  What did we talk about last time?  Graphics rendering pipeline  Geometry Stage.
CS 450: COMPUTER GRAPHICS ANTIALIASING SPRING 2015 DR. MICHAEL J. REALE.
1 Shadows (2) ©Anthony Steed Overview n Shadows – Umbra Recap n Penumbra Analytical v. Sampling n Analytical Aspect graphs Discontinuity meshing.
Week 6 - Wednesday.  What did we talk about last time?  Light  Material  Sensors.
Real-time Shading with Filtered Importance Sampling Jaroslav Křivánek Czech Technical University in Prague Mark Colbert University of Central Florida.
Visualization of Industrial Structures with Implicit GPU Primitives Rodrigo de Toledo Bruno Levy.
Rendering Complexity in Computer-Generated Pen- and-Ink Illustrations Brett Wilson & Kwan-Liu Ma The University of California, Davis.
Hardware-accelerated Rendering of Antialiased Shadows With Shadow Maps Stefan Brabec and Hans-Peter Seidel Max-Planck-Institut für Informatik Saarbrücken,
3D Computer Graphics in a Nutshell Guillaume Caumon, January 2002.
- Laboratoire d'InfoRmatique en Image et Systèmes d'information
Fateme Hajikarami Spring  What is GPGPU ? ◦ General-Purpose computing on a Graphics Processing Unit ◦ Using graphic hardware for non-graphic computations.
Ray Tracing using Programmable Graphics Hardware
Edison Gao 主讲人:高原. GameFinal A Next-Gen 3D Game Engine Edison Gao.
Depth-of-Field Rendering with Multiview Synthesis SigGraph Asia 2009 Sungkil Lee, Elmar Eisemann, and Hans-Peter Seidel Sunyeong Kim Nov. 2 nd
Efficient Partitioning of Fragment Shaders for Multiple-Output Hardware Tim Foley Mike Houston Pat Hanrahan Computer Graphics Lab Stanford University.
Shuen-Huei Guan Seminar in CMLab, NTU
Siggraph 2009 RenderAnts: Interactive REYES Rendering on GPUs Kun Zhou Qiming Hou Zhong Ren Minmin Gong Xin Sun Baining Guo JAEHYUN CHO.
Week 2 - Friday CS361.
Chapter 10 Computer Graphics
Deferred Lighting.
CDA 6938 Final Project Triangulation from Point Cloud
Advanced Computer Graphics:
View-Dependent Textured Splatting for Rendering Live Scenes
Hybrid Ray Tracing of Massive Models
CSc4730/6730 Scientific Visualization
Modeling.
UMBC Graphics for Games
Introduction to Meshes
Boolean Operations for Free-form Models Represented in Geometry Images
Ray Tracing on Programmable Graphics Hardware
Introduction to Meshes
Presentation transcript:

Reducing Shading on GPUs Using Quad-Fragment Merging JAEHYUN CHO SIGGRAPH 2010 Reducing Shading on GPUs Using Quad-Fragment Merging Kayvon Fatahalian Solomon Boulos James Hegarty Kurt Akeley William R. Mark Henry Moreton Pat Hanrahan JAEHYUN CHO 1

Outline Motivation System Results Conclusion

Highly Detailed Surfaces

GPU Rendering Pipeline Quad-fragments Fragments in 2 x 2 pixel blocks Quad pipeline in current GPUs Generate quad-fragment per triangle

Quad-fragment Shading

Quad-fragment Shading How many shadings occur per pixel?

Pixels at triangle boundaries are shaded multiple times Over Shade

Pixels at triangle boundaries are shaded multiple times

Over-shade in GPU pipeline

Main Idea Goal Shade once per pixel Solution Merge quad-fragments

Quad-fragment Merging Pipeline Reduce # of quad-fragments

Merging Process

Anti-aliasing Effect Triangle Mesh Final Pixels Anti-aliasing

Aliasing Effect on Naive Merging Triangle Mesh Final Pixels Aliasing

Conditions for Merging Triangles should be connected via edges Triangles have the same sideness Either front or back-facing

Conditions for Merging

Visual Quality Merging No merging

Shading Computations Merging No merging 1/2 pixel size triangles Merging : 8.5x less shading

Merging vs No merging

Result Scene

Merging vs No merging

Conclusions Contribution Limitation Faster than No merge GPU rendering No radical changes to current pipeline Limitation Motion/focal blur

Q & A Thank You