Mark Kilgard, profile picture
Uploaded byMark Kilgard
PPT, PDF2,863 views

SIGGRAPH 2012: GPU-Accelerated 2D and Web Rendering

Mark Kilgard's talk focuses on advancements in GPU-accelerated 2D graphics and web rendering, highlighting NVIDIA's approach to optimizing path rendering using a 'stencil, then cover' method for improved efficiency and quality. The presentation covers various applications, rendering standards, and the benefits of integrating resolution-independent graphics into web content. It aims to demonstrate how modern GPUs can significantly enhance rendering processes for both 3D and 2D content, making them essential for interactive visual computing.

Embed presentation

Downloaded 67 times
GPU-Accelerated 2D and Web Rendering Mark Kilgard
Talk Details Location: West Hall Meeting Room 503, Los Angeles Convention Center Date: Wednesday, August 8, 2012 Time: 2:40 PM – 3:40 PM Mark Kilgard (Principal Software Engineer, NVIDIA) Abstract: The future of GPU-based visual computing integrates the web, resolution-independent 2D graphics, and 3D to maximize interactivity and quality while minimizing consumed power. See what NVIDIA is doing today to accelerate resolution-independent 2D graphics for web content. This presentation explains NVIDIA's unique "stencil, then cover" approach to accelerating path rendering with OpenGL and demonstrates the wide variety of web content that can be accelerated with this approach. Topic Areas: GPU Accelerated Internet; Digital Content Creation & Film; Visualization Level: Intermediate Watch video replay: http://nvidia.fullviewmedia.com/siggraph2012/ondemand/SS106.html
Mark Kilgard Principal System Software Engineer OpenGL driver and API evolution Cg (“C for graphics”) shading language GPU-accelerated path rendering OpenGL Utility Toolkit (GLUT) implementer Author of OpenGL for the X Window System Co-author of Cg Tutorial
GPUs are good at a lot of stuff
Games Battlefield 3, EA
Data visualization
Product design Catia
Physics simulation CUDA N-Body
Interactive ray tracing OptiX
Training
Molecular modeling NCSA
Impressive stuff
What about advancing 2D graphics?
Can GPUs render & improve the immersive web?
What is path rendering? A rendering approach Resolution-independent two-dimensional graphics Occlusion & transparency depend on rendering order So called “Painter’s Algorithm” Basic primitive is a path to be filled or stroked Path is a sequence of path commands Commands are – moveto, lineto, curveto, arcto, closepath, etc. Standards Content: PostScript, PDF, TrueType fonts, Flash, Scalable Vector Graphics (SVG), HTML5 Canvas, Silverlight, Office drawings APIs: Apple Quartz 2D, Khronos OpenVG, Microsoft Direct2D, Cairo, Skia, Qt::QPainter, Anti-grain Graphics
Seminal Path Rendering Paper John Warnock & Douglas Wyatt, Xerox PARC Presented SIGGRAPH 1982 Warnock founded Adobe months later John Warnock Adobe founder
Path Rendering Standards Document Resolution- Immersive 2D Graphics Office Printing and Independent Web Programming Productivity Exchange Fonts Experience Interfaces Applications Java 2D API OpenType Flash QtGui API TrueType Scalable Mac OS X Vector 2D API Adobe Illustrator Graphics Open XML Paper (XPS) Inkscape HTML 5 Khronos API Open Source
Live Demo Classic PostScript content Complex text rendering Yesterday’s New York Times rendered from Flash content its resolution-independent form
Last Year’s SIGGRAPH Results in Real-time Ron Maharik, Mikhail Bessmeltsev, Alla Sheffer, Ariel Shamir and Nathan Carr SIGGRAPH 2011, July 2011 “Girl with Words in Her Hair” scene 591 paths 338,507 commands 1,244,474 coordinates
3D Rendering vs. Path Rendering Characteristic GPU 3D rendering Path rendering Dimensionality Projective 3D 2D, typically affine Pixel mapping Resolution independent Resolution independent Occlusion Depth buffering Painter’s algorithm Rendering primitives Points, lines, triangles Paths Primitive constituents Vertices Control points Constituents per primitive 1, 2, or 3 respectively Unbounded Topology of filled primitives Always convex Can be concave, self-intersecting, and have holes Degree of primitives 1st order (linear) Up to 3rd order (cubic) Rendering modes Filled, wire-frame Filling, stroking Line properties Width, stipple pattern Width, dash pattern, capping, join style Color processing Programmable shading Painting + filter effects Text rendering No direct support (2nd class support) Omni-present (1st class support) Raster operations Blending Brushes, blend modes, compositing Color model RGB or sRGB RGB, sRGB, CYMK, or grayscale Clipping operations Clip planes, scissoring, stenciling Clipping to an arbitrary clip path Coverage determination Per-color sample Sub-color sample
CPU vs. GPU Limited at Rendering Tasks over Time 100% 100% 90% 90% 80% 80% 70% 70% 60% 60% 50% GPU 50% GPU CPU CPU 40% 40% 30% 30% 20% 20% 10% 10% 0% 0% 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 Pipelined 3D Interactive Rendering Path Rendering Goal of NV_path_rendering is to make path rendering a GPU-limited task Render all interactive pixels, whether 3D or 2D or web content with the GPU
What is NV_path_rendering? OpenGL extension to GPU-accelerate path rendering Uses “stencil, then cover” (StC) approach Create a path object Step 1: “Stencil” the path object into the stencil buffer GPU provides fast stenciling of filled or stroked paths Step 2: “Cover” the path object and stencil test against its coverage stenciled by the prior step Application can configure arbitrary shading during the step More details later Supports the union of functionality of all major path rendering standards Includes all stroking embellishments Includes first-class text and font support Allows functionality to mix with traditional 3D and programmable shading
Configuration GPU: GeForce 480 GTX (GF100) CPU: Core i7 950 @ 3.07 GHz NV_path_rendering Compared to Alternatives Alternative approaches are all much slower
Configuration GPU: GeForce 480 GTX (GF100) CPU: Core i7 950 @ 3.07 GHz Detail on Alternatives Fast, but unacceptable quality
Across an range of scenes… Release 300 GeForce GTX 480 Speedups over Alternatives Y axis is logarithmic—shows how many TIMES faster NV_path_rendering is that competitor
GeForce 650 (Kepler) Results
Tiger Scene on GeForce 650 Absolute Frames/Second on GeForce 650 500.0 450.0 NVpr “peaks” at 1,800 FPS at 100x100 400.0 NV_path_rendering (16x) Cairo 350.0 Qt Frames per second Skia Bitmap 300.0 Skia Ganesh FBO Skia Ganesh 1x (aliased) 250.0 Direct2D GPU Direct2D WARP 200.0 poor quality 150.0 100.0 50.0 0.0 100x100 200x200 300x300 400x400 500x500 600x600 700x700 800x800 900x900 1000x1000 1100x1100 Window resolution
NV_path_rendering is more than just matching CPU vector graphics 3D and vector graphics mix Superior quality   CPU GPU Competitors Arbitrary programmable shader on paths— 2D in perspective is free bump mapping
Partial Solutions Not Enough Path rendering has 30 years of heritage and history Can’t do a 90% solution and Software to change Trying to “mix” CPU and GPU methods doesn’t work Expensive to move software—needs to be an unambiguous win Must surpass CPU approaches on all fronts Performance Quality Functionality Conformance to standards More power efficient Enable new applications
Path Filling and Stroking just filling just stroking filling + stroke = intended content
Dashing Content Examples Artist made windows with dashed line Same cake segment missing dashed stroking details Technical diagrams and charts often employ Frosting on cake is dashed dashing elliptical arcs with round end caps for “beaded” look; flowers are also dashing All content shown is fully GPU rendered Dashing character outlines for quilted look
Excellent Geometric Fidelity for Stroking Correct stroking is hard Lots of CPU implementations approximate stroking GPU-accelerated OpenVG reference GPU-accelerated stroking avoids such short-cuts   GPU has FLOPS to compute true stroke point containment Cairo Qt   Stroking with tight end-point curve
The Approach Step 1 Step 2: Stencil Cover repeat “Stencil, then Cover” (StC) Map the path rendering task from a sequential algorithm… …to a pipelined and massively parallel task Break path rendering into two steps First, “stencil” the path’s coverage into stencil buffer Second, conservatively “cover” path Test against path coverage determined in the 1st step Shade the path And reset the stencil value to render next path
Pixel pipeline Vertex pipeline Path pipeline Application Path specification Pixel assembly Vertex assembly Transform path (unpack) Vertex operations transform feedback Primitive assembly Pixel operations Primitive operations Fill/Stroke Covering Pixel pack Rasterization read Texture Fragment operations back memory Fill/Stroke Application Raster operations Stenciling Framebuffer Display
Key Operations for Rendering Path Objects Stencil operation only updates stencil buffer glStencilFillPathNV, glStencilStrokePathNV Cover operation glCoverFillPathNV, glCoverStrokePathNV renders hull polygons guaranteed to “cover” region updated by corresponding stencil Two-step rendering paradigm stencil, then cover (StC) Application controls cover stenciling and shading operations Gives application considerable control No vertex, tessellation, or geometry shaders active during steps Why? Paths have control points & rasterized regions, not vertices, triangles
Path Rendering Example (1 of 3) Let’s draw a green concave 5-point star even-odd fill style non-zero fill style Path specification by string of a star GLuint pathObj = 42; const char *pathString ="M100,180 L40,10 L190,120 L10,120 L160,10 z"; glPathStringNV(pathObj,GL_PATH_FORMAT_SVG_NV, strlen(pathString),pathString); Alternative: path specification by data static const GLubyte pathCommands[5] = { GL_MOVE_TO_NV, GL_LINE_TO_NV, GL_LINE_TO_NV, GL_LINE_TO_NV, GL_LINE_TO_NV, GL_CLOSE_PATH_NV }; static const GLshort pathVertices[5][2] = { {100,180}, {40,10}, {190,120}, {10,120}, {160,10} }; glPathCommandsNV(pathObj, 6, pathCommands, GL_SHORT, 10, pathVertices);
Path Rendering Example (2 of 3) Initialization Clear the stencil buffer to zero and the color buffer to black glClearStencil(0); glClearColor(0,0,0,0); glStencilMask(~0); glClear(GL_COLOR_BUFFER_BIT | GL_STENCIL_BUFFER_BIT); Specify the Path's Transform glMatrixIdentityEXT(GL_PROJECTION); glMatrixOrthoEXT(GL_MODELVIEW, 0,200, 0,200, -1,1); // uses DSA! Nothing really specific to path rendering here DSA = OpenGL’s Direct State Access extension (EXT_direct_state_access)
Path Rendering Example (3 of 3) Render star with non-zero fill style Stencil path glStencilFillPathNV(pathObj, GL_COUNT_UP_NV, 0x1F); non-zero fill style Cover path glEnable(GL_STENCIL_TEST); glStencilFunc(GL_NOTEQUAL, 0, 0x1F); glStencilOp(GL_KEEP, GL_KEEP, GL_ZERO); glColor3f(0,1,0); // green glCoverFillPathNV(pathObj, GL_BOUNDING_BOX_NV); Alternative: for even-odd fill style even-odd fill style Just program glStencilFunc differently glStencilFunc(GL_NOTEQUAL, 0, 0x1); // alternative mask
“Stencil, then Cover” stencil fill path command path front-end Path Fill Stenciling path projective object Specify a path per-path transform fill region Specify arbitrary path transformation operations Projective (4x4) allowed clipping & Depth values can be generated for scissoring sample depth testing accessibility Sample accessibility determined window, depth Accessibility can be limited by any & stencil tests or all of Scissor test, depth test, stencil test, view frustum, user-defined clip path winding planes, sample mask, stipple number pattern, and window ownership per-sample computation Winding number w.r.t. the operations transformed path is computed Added to stencil value of accessible stencil samples Fill stencil update: stenciling buffer +, -, or invert specific
“Stencil, then Cover” cover fill path command path front-end Path Fill Covering path projective object Specify a path per-path transform Specify arbitrary path fill region transformation operations clipping & Projective (4x4) allowed scissoring Depth values can be generated for sample depth testing accessibility window, depth Sample accessibility determined per-sample & stencil tests Accessibility can be limited by any operations or all of Scissor test, depth test, stencil stencil test, view frustum, user-defined per-fragment or update clip planes, sample mask, stipple per-sample pattern, and window ownership typically zero shading Conservative covering geometry uses stencil to “cover” filled path programmable Determined by prior stencil step color stencil path buffer shading buffer
Adding Stroking to the Star After the filling, add a stroked “rim” to the star like this… Set some stroking parameters (one-time): glPathParameterfNV(pathObj, GL_STROKE_WIDTH_NV, 10.5); glPathParameteriNV(pathObj, GL_JOIN_STYLE_NV, GL_ROUND_NV); non-zero fill style Stroke the star Stencil path glStencilStrokePathNV(pathObj, 0x3, 0xF); // stroked samples marked “3” Cover path glEnable(GL_STENCIL_TEST); glStencilFunc(GL_EQUAL, 3, 0xF); // update if sample marked “3” glStencilOp(GL_KEEP, GL_KEEP, GL_ZERO); glColor3f(1,1,0); // yellow glCoverStrokePathNV(pathObj, GL_BOUNDING_BOX_NV); even-odd fill style
stencil stroke “Stencil, then Cover” path command path front-end Path Stroke Stenciling path projective object Specify a path per-path transform Specify arbitrary path transformation fill region Projective (4x4) allowed operations clipping & Depth values can be generated for depth testing scissoring sample Sample accessibility determined accessibility Accessibility can be limited by any window, depth or all of & stencil tests Scissor test, depth test, stencil test, view frustum, user-defined clip planes, sample mask, stipple pattern, and window ownership stroke per-sample point Point containment w.r.t. the stroked path is determined operations containment Replace stencil value of contained samples Stroke stencil stencil stenciling update: buffer specific replace
cover stroke “Stencil, then Cover” path command path front-end Path Stroke Covering path projective object Specify a path per-path transform Specify arbitrary path fill region transformation operations clipping & Projective (4x4) allowed scissoring sample Depth values can be generated for depth testing accessibility Sample accessibility determined per-sample window, depth Accessibility can be limited by any & stencil tests operations or all of Scissor test, depth test, stencil test, view frustum, stencil user-defined clip planes, per-fragment or update sample mask, stipple pattern, per-sample typically zero and window ownership shading Conservative covering geometry uses stencil to “cover” stroked path programmable Determined by prior stencil step color stencil path buffer shading buffer
First-class, Resolution-independent Font Support Fonts are a standard, first-class part of all path rendering systems Foreign to 3D graphics systems such as OpenGL and Direct3D, but natural for path rendering Because letter forms in fonts have outlines defined with paths TrueType, PostScript, and OpenType fonts all use outlines to specify glyphs NV_path_rendering makes font support easy Can specify a range of path objects with A specified font Sequence or range of Unicode character points No requirement for applications use font API to load glyphs You can also load glyphs “manually” from your own glyph outlines Functionality provides OS portability and meets needs of applications with mundane font requirements
Handling Common Path Rendering Functionality: Filtering GPUs are highly efficient at image filtering Fast texture mapping  Qt Mipmapping Anisotropic filtering Wrap modes Moiré CPUs aren't really artifacts  GPU  Cairo
Handling Uncommon Path Rendering Functionality: Projection Projection “just works” Because GPU does everything with perspective-correct interpolation
Projective Path Rendering Support Compared  GPU  Skia  Cairo  Qt flawless yes, but bugs unsupported unsupported correct correct unsupported unsupported correct wrong unsupported unsupported
Path Geometric Queries glIsPointInFillPathNV determine if object-space (x,y) position is inside or outside path, given a winding number mask glIsPointInStrokePathNV determine if object-space (x,y) position is inside the stroke of a path accounts for dash pattern, joins, and caps glGetPathLengthNV returns approximation of geometric length of a given sub-range of path segments glPointAlongPathNV returns the object-space (x,y) position and 2D tangent vector a given offset into a specified path object Useful for “text follows a path” Queries are modeled after OpenVG queries
Accessible Samples of a Transformed Path When stenciled or covered, a path is transformed by OpenGL’s current modelview-projection matrix Allows for arbitrary 4x4 projective transform Means (x,y,0,1) object-space coordinate can be transformed to have depth Fill or stroke stenciling affects “accessible” samples A samples is not accessible if any of these apply to the sample clipped by user-defined or view frustum clip planes discarded by the polygon stipple, if enabled discarded by the pixel ownership test discarded by the scissor test, if enabled discarded by the depth test, if enabled displaced by the polygon offset from glPathStencilDepthOffsetNV discarded by the depth test, if enabled discarded by the (implicitly enabled) stencil test specified by glPathStencilFuncNV where the read mask is the bitwise AND of the glPathStencilFuncNV read mask and the bit-inversion of the effective mask parameter of the stenciling operation
Mixing Depth Buffering and Path Rendering PostScript tigers surrounding Utah teapot Plus overlaid TrueType font rendering No textures involved, no multi-pass
Demo
3D Path Rendering Details Stencil step uses GLfloat slope = -0.05; GLint bias = -1; glPathStencilDepthOffsetNV(slope, bias); glDepthFunc(GL_LESS); glEnable(GL_DEPTH_TEST); Stenciling step uses glPathCoverDepthFuncNV(GL_ALWAYS); Observation Stencil step is testing—but not writing—depth Stencil won’t be updated if stencil step fails depth test at a sample Cover step is writing—but not testing—depth Cover step doesn’t need depth test because stencil test would only pass if prior stencil step’s depth test passed Tricky, but neat because minimal mode changes involved
Without glPathStencilDepthOffset Bad Things Happen Each tiger is layered 240 paths Without the depth offset during the stencil step, all the—essentially co-planar—layers would Z-fight as shown below terrible z-fighting artifacts
Path Transformation Process Path object-space coordinates object (x,y,0,1) Modelview eye-space coordinates color/fog/tex coordinates matrix (xe,ye,ze,we) + attributes color/fog/tex coords. User-defined Object-space clip planes color/fog/tex Eye-space generation color/fog/tex generation clipped eye-space coordinates (xe,ye,ze,we) + attributes clipped clip-space Projection clip-space coordinates View-frustum coordinates to path matrix (xc,yc,zc,wc) + attributes clip planes (xc,yc,zc,wc) + attributes stenciling or covering
Clip Planes Work with Path Rendering Scene showing a Welsh dragon clipped to all 64 combinations of 6 clip planes enabled & disabled
Path Rendering Works with Scissoring and Stippling too Scene showing a tiger scissoring into 9 regions Tiger with two different polygon stipple patterns
Rendering Paths Clipped to Some Other Arbitrary Path Example clipping the PostScript tiger to a heart constructed from two cubic Bezier curves unclipped tiger tiger with pink background clipped to heart
Complex Clipping Example tiger is 240 paths cowboy clip is the union of 1,366 paths result of clipping tiger to the union of all the cowboy paths
Arbitrary Programmable GPU Shading with Path Rendering During the “cover” step, you can do arbitrary fragment processing Could be Fixed-function fragment processing OpenGL assembly programs Cg shaders compiled to assembly with Cg runtime OpenGL Shading Language (GLSL) shaders Your pick—they all work! Remember: Your vertex, geometry, & tessellation shaders ignored during cover step (Even your fragment shader is ignored during the “stencil” step)
Example of Bump Mapping on Path Rendered Text Phrase “Brick wall!” is path rendered and bump mapped with a Cg fragment shader light source position
Anti-aliasing Discussion Good anti-aliasing is a big deal for path rendering Particularly true for font rendering of small point sizes Features of glyphs are often on the scale of a pixel or less NV_path_rendering uses multiple stencil samples per pixel for reasonable antialiasing Otherwise, image quality is poor 4 samples/pixel bare minimum 8 or 16 samples/pixel is pretty sufficient But 16 requires expensive 2x2 supersampling of 4x multisampling 16x is extremely memory intensive Alternative: quality vs. performance tradeoff Fast enough to render multiple passes to improve quality Approaches Accumulation buffer Alpha accumulation
Anti-aliasing Strategy Benefits Benefits from GPU’s existing hardware AA strategies GPU Multiple color-stencil-depth rendered samples per pixel coverage NOT 4, 8, or 16 samples per pixel conflated with Rotated grid sub-positions opacity Fast downsampling by GPU Avoids conflating coverage & opacity Cairo, Qt, Skia, Maintains distinct color sample and Direct2D per sample location rendered Centroid sampling shows dark Fast enough for temporal cracks artifacts due to conflating schemes artifacts coverage with >>60 fps means multi-pass opacity, notice improves quality background bleeding
Real Flash Scene same scene, GPU-rendered without conflation conflation artifacts abound, rendered by Skia conflation is aliasing & edge coverage percents are un-predicable in general; means conflated pixels flicker when animated slowly
GPU Advantages Fast, quality filtering Mipmapping of gradient color ramps essentially free Includes anisotropic filtering (up to 16x) Filtering is post-conversion from sRGB Full access to programmable shading No fixed palette of solid color / gradient / pattern brushes Bump mapping, shadow mapping, etc.—it’s all available to you Blending Supports native blending in sRGB color space Both colors converted to linear RGB Then result is converted stored as sRGB Freely mix 3D and path rendering in same framebuffer Path rendering buffer can be depth tested against 3D So can 3D rendering be stenciled against path rendering Obviously performance is MUCH better than CPUs
Improved Color Space: sRGB Path Rendering Radial color gradient example Modern GPUs have native support for moving from saturated red to blue perceptually-correct for sRGB framebuffer blending sRGB texture filtering No reason to tolerate uncorrected linear RGB color artifacts! More intuitive for artists to control  linear RGB Negligible expense for GPU to perform transition between saturated red and saturated blue has sRGB-correct rendering dark purple region However quite expensive for software path renderers to perform sRGB rendering Not done in practice  sRGB perceptually smooth transition from saturated red to saturated blue
Trying Out NV_path_rendering Operating system support 2000, XP, Vista, Windows 7, Linux, FreeBSD, and Solaris Unfortunately no Mac support GPU support GeForce 8 and up (Tesla and beyond) Most efficient on Fermi and Kepler GPUs Current performance can be expected to improve Shipping since NVIDIA’s Release 275 drivers Available since summer 2011 New Release 300 drivers have remarkable NV_path_rendering performance Try it, you’ll like it
Learning NV_path_rendering White paper + source code available “Getting Started with NV_path_rendering” Explains Path specification “Stencil, then Cover” API usage Instanced rendering for text and glyphs
NV_path_rendering SDK Examples A set of NV_path_rendering examples of varying levels of complexity Most involved example is an accelerated SVG viewer Not a complete SVG implementation Compiles on Windows and Linux Standard makefiles for Linux Use Visual Studio 2008 for Windows
Whitepapers “Getting Started with NV_path_rendering”
Whitepapers “Mixing 3D and Path Rendering”
SDK Example Walkthrough (1) pr_basic—simplest example pr_hello_world—kerned, underlined, of path filling & stroking stroked, and linear gradient filled text pr_welsh_dragon—filled layers pr_gradient—path with holes with texture applied
SDK Example Walkthrough (2) pr_font_file—loading glyphs from a font file pr_korean—rendering UTF-8 string of Korea with the GL_FONT_FILE_NV target characters pr_shaders—use Cg shaders to bump map text with brick-wall texture
SDK Example Walkthrough (3) pr_text_wheel—render projected gradient pr_tiger—classic PostScript tiger rendered text as spokes of a wheel as filled & stroked path layers pr_warp_tiger—warp the tiger with a free projective transform click & drag the bounding rectangle corners to change the projection
SDK Example Walkthrough (4) pr_tiger3d—multiple projected and depth tested pr_svg—GPU-accelerated SVG viewer tigers + 3D teapot + overlaid text pr_pick—test points to determine if they are in the filled and/or stroked region of a complex path
Conclusions GPU-acceleration of 2D resolution-independent graphics is coming HTML 5 and low-power requirements are demanding it “Stencil, then Cover” approach Very fast Quality, functionality, and features Available today through NV_path_rendering Shipping today NV_path_rendering resources available
Questions?
More Information Best current driver: use OpenGL 4.3 beta driver http://www.nvidia.com/content/devzone/opengl-driver-4.3.html Or try www.nvidia.com/drivers Grab the latest Beta drivers for your OS & GPU Latest drivers greatly improve instanced stencil step performance! Developer resources http://developer.nvidia.com/nv-path-rendering Whitepapers, FAQ, specification NVprSDK—software development kit NVprDEMOs—pre-compiled Windows demos OpenGL Extension Wrangler (GLEW) has API support Email: nvpr-support@nvidia.com
Don’t Forget the 20th Anniversary Party Date: August 8th 2012 ( today! ) Location: JW Marriott Los Angeles at LA Live Venue: Gold Ballroom – Salon 1
Other OpenGL-related NVIDIA Sessions at SIGGRAPH GPU Ray Tracing and OptiX Wednesday in West Hall 503, 3:50 PM - 4:50 PM David McAllister, OptiX Manager, NVIDIA Phillip Miller, Director, Workstation Software Product Management, NVIDIA Voxel Cone Tracing & Sparse Voxel Octree for Real-time Global Illumination Wednesday in NVIDIA Booth, 3:50 PM - 4:50 PM Cyril Crassin, Postdoctoral Research Scientist, NVIDIA Research OpenSubdiv: High Performance GPU Subdivision Surface Drawing Thursday in NVIDIA Booth, 10:00 AM - 10:30 AM Pixar Animation Studios GPU Team, Pixar nvFX : A New Scene & Material Effect Framework for OpenGL and DirectX Thursday in NVIDIA Booth, 2:00 PM - 2:30 PM Tristan Lorach, Developer Relations Senior Engineer, NVIDIA

More Related Content

PPT
SIGGRAPH Asia 2012: GPU-accelerated Path Rendering
byMark Kilgard
 
PPT
GTC 2012: GPU-Accelerated Path Rendering
byMark Kilgard
 
PPT
SIGGRAPH 2012: NVIDIA OpenGL for 2012
byMark Kilgard
 
PDF
GPU-accelerated Path Rendering
byMark Kilgard
 
PPT
SIGGRAPH Asia 2012 Exhibitor Talk: OpenGL 4.3 and Beyond
byMark Kilgard
 
PPTX
Migrating from OpenGL to Vulkan
byMark Kilgard
 
PPT
GPU accelerated path rendering fastforward
byMark Kilgard
 
PPT
Slides: Accelerating Vector Graphics Rendering using the Graphics Hardware Pi...
byMark Kilgard
 
SIGGRAPH Asia 2012: GPU-accelerated Path Rendering
byMark Kilgard
 
GTC 2012: GPU-Accelerated Path Rendering
byMark Kilgard
 
SIGGRAPH 2012: NVIDIA OpenGL for 2012
byMark Kilgard
 
GPU-accelerated Path Rendering
byMark Kilgard
 
SIGGRAPH Asia 2012 Exhibitor Talk: OpenGL 4.3 and Beyond
byMark Kilgard
 
Migrating from OpenGL to Vulkan
byMark Kilgard
 
GPU accelerated path rendering fastforward
byMark Kilgard
 
Slides: Accelerating Vector Graphics Rendering using the Graphics Hardware Pi...
byMark Kilgard
 

What's hot

PPT
CS 354 Vector Graphics & Path Rendering
byMark Kilgard
 
PPT
An Introduction to NV_path_rendering
byMark Kilgard
 
PPT
NVIDIA OpenGL in 2016
byMark Kilgard
 
PPTX
OpenGL Shading Language
byJungsoo Nam
 
PPT
NVIDIA's OpenGL Functionality
byMark Kilgard
 
PPT
OpenGL 3.2 and More
byMark Kilgard
 
PPT
OpenGL 4 for 2010
byMark Kilgard
 
PPT
CS 354 GPU Architecture
byMark Kilgard
 
PPT
CS 354 Introduction
byMark Kilgard
 
PPT
OpenGL for 2015
byMark Kilgard
 
PDF
NV_path_rendering Frequently Asked Questions
byMark Kilgard
 
PPT
CS 354 Viewing Stuff
byMark Kilgard
 
PDF
Accelerating Vector Graphics Rendering using the Graphics Hardware Pipeline
byMark Kilgard
 
PPT
GTC 2012: NVIDIA OpenGL in 2012
byMark Kilgard
 
PDF
Realizing OpenGL
byMark Kilgard
 
PPT
Virtual Reality Features of NVIDIA GPUs
byMark Kilgard
 
PDF
Programming with NV_path_rendering: An Annex to the SIGGRAPH Asia 2012 paper...
byMark Kilgard
 
PDF
Modern OpenGL Usage: Using Vertex Buffer Objects Well
byMark Kilgard
 
PDF
Mixing Path Rendering and 3D
byMark Kilgard
 
PDF
Avoiding 19 Common OpenGL Pitfalls
byMark Kilgard
 
CS 354 Vector Graphics & Path Rendering
byMark Kilgard
 
An Introduction to NV_path_rendering
byMark Kilgard
 
NVIDIA OpenGL in 2016
byMark Kilgard
 
OpenGL Shading Language
byJungsoo Nam
 
NVIDIA's OpenGL Functionality
byMark Kilgard
 
OpenGL 3.2 and More
byMark Kilgard
 
OpenGL 4 for 2010
byMark Kilgard
 
CS 354 GPU Architecture
byMark Kilgard
 
CS 354 Introduction
byMark Kilgard
 
OpenGL for 2015
byMark Kilgard
 
NV_path_rendering Frequently Asked Questions
byMark Kilgard
 
CS 354 Viewing Stuff
byMark Kilgard
 
Accelerating Vector Graphics Rendering using the Graphics Hardware Pipeline
byMark Kilgard
 
GTC 2012: NVIDIA OpenGL in 2012
byMark Kilgard
 
Realizing OpenGL
byMark Kilgard
 
Virtual Reality Features of NVIDIA GPUs
byMark Kilgard
 
Programming with NV_path_rendering: An Annex to the SIGGRAPH Asia 2012 paper...
byMark Kilgard
 
Modern OpenGL Usage: Using Vertex Buffer Objects Well
byMark Kilgard
 
Mixing Path Rendering and 3D
byMark Kilgard
 
Avoiding 19 Common OpenGL Pitfalls
byMark Kilgard
 

Viewers also liked

PDF
Heterogeneous System Architecture Overview
byinside-BigData.com
 
PDF
PG-Strom - GPGPU meets PostgreSQL, PGcon2015
byKohei KaiGai
 
PPTX
Deep Learning on Hadoop
byDataWorks Summit
 
PDF
Spark Summit EU talk by Tim Hunter
bySpark Summit
 
PPTX
The Potential of GPU-driven High Performance Data Analytics in Spark
bySpark Summit
 
PDF
GPUs in Big Data - StampedeCon 2014
byStampedeCon
 
PPTX
GPU Support in Spark and GPU/CPU Mixed Resource Scheduling at Production Scale
bysparktc
 
PDF
GPU Ecosystem
byOfer Rosenberg
 
PDF
PG-Strom - GPU Accelerated Asyncr
byKohei KaiGai
 
PDF
How to Solve Real-Time Data Problems
byIBM Power Systems
 
PDF
Hadoop + GPU
byVladimir Starostenkov
 
PDF
Tallinn Estonia Advanced Java Meetup Spark + TensorFlow = TensorFrames Oct 24...
byChris Fregly
 
PDF
Computational Techniques for the Statistical Analysis of Big Data in R
byherbps10
 
PDF
Deep learning on spark
bySatyendra Rana
 
PPTX
Containerizing GPU Applications with Docker for Scaling to the Cloud
bySubbu Rama
 
PDF
PyData Amsterdam - Name Matching at Scale
byGoDataDriven
 
PDF
Accelerating Machine Learning Applications on Spark Using GPUs
byIBM
 
PDF
DeepLearning4J and Spark: Successes and Challenges - François Garillot
bysparktc
 
PPTX
From Machine Learning to Learning Machines: Creating an End-to-End Cognitive ...
bySpark Summit
 
PPT
Enabling Graph Analytics at Scale: The Opportunity for GPU-Acceleration of D...
byodsc
 
Heterogeneous System Architecture Overview
byinside-BigData.com
 
PG-Strom - GPGPU meets PostgreSQL, PGcon2015
byKohei KaiGai
 
Deep Learning on Hadoop
byDataWorks Summit
 
Spark Summit EU talk by Tim Hunter
bySpark Summit
 
The Potential of GPU-driven High Performance Data Analytics in Spark
bySpark Summit
 
GPUs in Big Data - StampedeCon 2014
byStampedeCon
 
GPU Support in Spark and GPU/CPU Mixed Resource Scheduling at Production Scale
bysparktc
 
GPU Ecosystem
byOfer Rosenberg
 
PG-Strom - GPU Accelerated Asyncr
byKohei KaiGai
 
How to Solve Real-Time Data Problems
byIBM Power Systems
 
Hadoop + GPU
byVladimir Starostenkov
 
Tallinn Estonia Advanced Java Meetup Spark + TensorFlow = TensorFrames Oct 24...
byChris Fregly
 
Computational Techniques for the Statistical Analysis of Big Data in R
byherbps10
 
Deep learning on spark
bySatyendra Rana
 
Containerizing GPU Applications with Docker for Scaling to the Cloud
bySubbu Rama
 
PyData Amsterdam - Name Matching at Scale
byGoDataDriven
 
Accelerating Machine Learning Applications on Spark Using GPUs
byIBM
 
DeepLearning4J and Spark: Successes and Challenges - François Garillot
bysparktc
 
From Machine Learning to Learning Machines: Creating an End-to-End Cognitive ...
bySpark Summit
 
Enabling Graph Analytics at Scale: The Opportunity for GPU-Acceleration of D...
byodsc
 

Similar to SIGGRAPH 2012: GPU-Accelerated 2D and Web Rendering

PDF
Hardware Accelerated 2D Rendering for Android
byNational Cheng Kung University
 
PPTX
The Rendering Pipeline - Challenges & Next Steps
byrepii
 
PPTX
Graphics pipelining
byAreena Javed
 
PPT
NVIDIA Graphics, Cg, and Transparency
byMark Kilgard
 
PDF
GPU Virtualization on VMware's Hosted I/O Architecture
byguestb3fc97
 
PDF
Modern Graphics Pipeline Overview
byslantsixgames
 
PDF
CPU is in Focus Again! Implementing DOF on CPU.
byEvgeny Gorodetsky
 
PPT
Computer Graphics Introduction
byGhaffar Khan
 
PDF
Keynote (Johan Andersson) - Mantle for Developers - by Johan Andersson, Techn...
byAMD Developer Central
 
PDF
GeForce 8800 OpenGL Extensions
byicastano
 
PPTX
GPU Computing: A brief overview
byRajiv Kumar
 
PPT
1 COMPUTER GRAPHICS.ppt
byARULKUMAR MUNIYAPPAN
 
PDF
Getting Started with NV_path_rendering
byMark Kilgard
 
PDF
NV_path_rendering
byNigel Stewart
 
PDF
Understanding hardware acceleration on mobile browsers presentation
byJustin Dorfman
 
PDF
3 d to _hpc
byObsidian Software
 
PDF
[03 1][gpu용 개발자 도구 - parallel nsight 및 axe] miller axe
bylaparuma
 
PDF
2D Games to HPC
byDVClub
 
PDF
3 d to_hpc
byObsidian Software
 
PPTX
Penn graphics
byfloored
 
Hardware Accelerated 2D Rendering for Android
byNational Cheng Kung University
 
The Rendering Pipeline - Challenges & Next Steps
byrepii
 
Graphics pipelining
byAreena Javed
 
NVIDIA Graphics, Cg, and Transparency
byMark Kilgard
 
GPU Virtualization on VMware's Hosted I/O Architecture
byguestb3fc97
 
Modern Graphics Pipeline Overview
byslantsixgames
 
CPU is in Focus Again! Implementing DOF on CPU.
byEvgeny Gorodetsky
 
Computer Graphics Introduction
byGhaffar Khan
 
Keynote (Johan Andersson) - Mantle for Developers - by Johan Andersson, Techn...
byAMD Developer Central
 
GeForce 8800 OpenGL Extensions
byicastano
 
GPU Computing: A brief overview
byRajiv Kumar
 
1 COMPUTER GRAPHICS.ppt
byARULKUMAR MUNIYAPPAN
 
Getting Started with NV_path_rendering
byMark Kilgard
 
NV_path_rendering
byNigel Stewart
 
Understanding hardware acceleration on mobile browsers presentation
byJustin Dorfman
 
3 d to _hpc
byObsidian Software
 
[03 1][gpu용 개발자 도구 - parallel nsight 및 axe] miller axe
bylaparuma
 
2D Games to HPC
byDVClub
 
3 d to_hpc
byObsidian Software
 
Penn graphics
byfloored
 

More from Mark Kilgard

PPT
NVIDIA OpenGL 4.6 in 2017
byMark Kilgard
 
PPT
CS 354 Ray Casting & Tracing
byMark Kilgard
 
PPT
NVIDIA OpenGL and Vulkan Support for 2017
byMark Kilgard
 
PPTX
OpenGL 4.5 Update for NVIDIA GPUs
byMark Kilgard
 
PPT
NV_path rendering Functional Improvements
byMark Kilgard
 
PPT
Computers, Graphics, Engineering, Math, and Video Games for High School Students
byMark Kilgard
 
PPT
CS 354 Acceleration Structures
byMark Kilgard
 
PPT
CS 354 Final Exam Review
byMark Kilgard
 
PPT
CS 354 Surfaces, Programmable Tessellation, and NPR Graphics
byMark Kilgard
 
PPT
CS 354 Typography
byMark Kilgard
 
PPT
CS 354 Bezier Curves
byMark Kilgard
 
PDF
D11: a high-performance, protocol-optional, transport-optional, window system...
byMark Kilgard
 
PPT
CS 354 Global Illumination
byMark Kilgard
 
PPT
EXT_window_rectangles
byMark Kilgard
 
PPT
CS 354 Performance Analysis
byMark Kilgard
 
NVIDIA OpenGL 4.6 in 2017
byMark Kilgard
 
CS 354 Ray Casting & Tracing
byMark Kilgard
 
NVIDIA OpenGL and Vulkan Support for 2017
byMark Kilgard
 
OpenGL 4.5 Update for NVIDIA GPUs
byMark Kilgard
 
NV_path rendering Functional Improvements
byMark Kilgard
 
Computers, Graphics, Engineering, Math, and Video Games for High School Students
byMark Kilgard
 
CS 354 Acceleration Structures
byMark Kilgard
 
CS 354 Final Exam Review
byMark Kilgard
 
CS 354 Surfaces, Programmable Tessellation, and NPR Graphics
byMark Kilgard
 
CS 354 Typography
byMark Kilgard
 
CS 354 Bezier Curves
byMark Kilgard
 
D11: a high-performance, protocol-optional, transport-optional, window system...
byMark Kilgard
 
CS 354 Global Illumination
byMark Kilgard
 
EXT_window_rectangles
byMark Kilgard
 
CS 354 Performance Analysis
byMark Kilgard
 

Recently uploaded

PDF
Making Sense of Raster: From Bit Depth to Better Workflows
bySafe Software
 
PDF
Digit Expo 2025 - EICC Edinburgh 27th November
byRay Bugg
 
DOCX
Introduction to the World of Computers (Hardware & Software)
byALIABBAS ABASOV
 
PDF
Vibe Coding vs. Spec-Driven Development [Free Meetup]
byHaim Michael
 
PDF
Guided Substation Engineering with CoMPAS: Simplifying IEC 61850
byDanBrown980551
 
PDF
Taming the Chaos: How to Turn Unstructured Data into Decisions
bySafe Software
 
PDF
Igniting the Future: Copilot trends, agentic transformation and product roadm...
byUni Systems S.M.S.A.
 
PPTX
Basics of Identity Access Management In mordern Infrastructure
byPrinceXavier18
 
PDF
Decoding the DNA: The Digital Networks Act, the Open Internet, and IP interco...
byCSUC - Consorci de Serveis Universitaris de Catalunya
 
PDF
Safeguarding AI-Based Financial Infrastructure
bysleepandremedies
 
PPTX
The Landscape of Computer Software Development Companies
byYash Singh
 
PDF
The Future of Search: Why LLM Optimization Matters for Every Website
byav0763436
 
PPTX
Combining Induction and Transduction for Abstract Reasoning.pptx
byallen578468
 
PPTX
The Future of IT Service Management AI Automation & Beyond.pptx
byChetu
 
PDF
Tracing the Thread: Decoding the Decision-Making Process with GraphRAG
byEnterprise Knowledge
 
PDF
Accelerating Responsible AI Adoption in Public Sector and Private Organizations.
bysleepandremedies
 
PDF
Innovative AI Solutions for Business Growth.pdf
byVox Works
 
PPTX
RISE with SAP for Automotive - S4 HANA Value.pptx
byAmira Jemi
 
PDF
Greetings All Students Update 3 by Mia Corp
by©LDMMIA, ©Reiki Yoga
 
PDF
Cybersecurity Prevention and Detection Specialization
byVICTOR MAESTRE RAMIREZ
 
Making Sense of Raster: From Bit Depth to Better Workflows
bySafe Software
 
Digit Expo 2025 - EICC Edinburgh 27th November
byRay Bugg
 
Introduction to the World of Computers (Hardware & Software)
byALIABBAS ABASOV
 
Vibe Coding vs. Spec-Driven Development [Free Meetup]
byHaim Michael
 
Guided Substation Engineering with CoMPAS: Simplifying IEC 61850
byDanBrown980551
 
Taming the Chaos: How to Turn Unstructured Data into Decisions
bySafe Software
 
Igniting the Future: Copilot trends, agentic transformation and product roadm...
byUni Systems S.M.S.A.
 
Basics of Identity Access Management In mordern Infrastructure
byPrinceXavier18
 
Decoding the DNA: The Digital Networks Act, the Open Internet, and IP interco...
byCSUC - Consorci de Serveis Universitaris de Catalunya
 
Safeguarding AI-Based Financial Infrastructure
bysleepandremedies
 
The Landscape of Computer Software Development Companies
byYash Singh
 
The Future of Search: Why LLM Optimization Matters for Every Website
byav0763436
 
Combining Induction and Transduction for Abstract Reasoning.pptx
byallen578468
 
The Future of IT Service Management AI Automation & Beyond.pptx
byChetu
 
Tracing the Thread: Decoding the Decision-Making Process with GraphRAG
byEnterprise Knowledge
 
Accelerating Responsible AI Adoption in Public Sector and Private Organizations.
bysleepandremedies
 
Innovative AI Solutions for Business Growth.pdf
byVox Works
 
RISE with SAP for Automotive - S4 HANA Value.pptx
byAmira Jemi
 
Greetings All Students Update 3 by Mia Corp
by©LDMMIA, ©Reiki Yoga
 
Cybersecurity Prevention and Detection Specialization
byVICTOR MAESTRE RAMIREZ
 

SIGGRAPH 2012: GPU-Accelerated 2D and Web Rendering

  • 1.
    GPU-Accelerated 2D and Web Rendering Mark Kilgard
  • 2.
    Talk Details Location: WestHall Meeting Room 503, Los Angeles Convention Center Date: Wednesday, August 8, 2012 Time: 2:40 PM – 3:40 PM Mark Kilgard (Principal Software Engineer, NVIDIA) Abstract: The future of GPU-based visual computing integrates the web, resolution-independent 2D graphics, and 3D to maximize interactivity and quality while minimizing consumed power. See what NVIDIA is doing today to accelerate resolution-independent 2D graphics for web content. This presentation explains NVIDIA's unique "stencil, then cover" approach to accelerating path rendering with OpenGL and demonstrates the wide variety of web content that can be accelerated with this approach. Topic Areas: GPU Accelerated Internet; Digital Content Creation & Film; Visualization Level: Intermediate Watch video replay: http://nvidia.fullviewmedia.com/siggraph2012/ondemand/SS106.html
  • 3.
    Mark Kilgard PrincipalSystem Software Engineer OpenGL driver and API evolution Cg (“C for graphics”) shading language GPU-accelerated path rendering OpenGL Utility Toolkit (GLUT) implementer Author of OpenGL for the X Window System Co-author of Cg Tutorial
  • 4.
    GPUs are goodat a lot of stuff
  • 5.
  • 6.
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13.
  • 14.
    Can GPUs render& improve the immersive web?
  • 15.
    What is pathrendering? A rendering approach Resolution-independent two-dimensional graphics Occlusion & transparency depend on rendering order So called “Painter’s Algorithm” Basic primitive is a path to be filled or stroked Path is a sequence of path commands Commands are – moveto, lineto, curveto, arcto, closepath, etc. Standards Content: PostScript, PDF, TrueType fonts, Flash, Scalable Vector Graphics (SVG), HTML5 Canvas, Silverlight, Office drawings APIs: Apple Quartz 2D, Khronos OpenVG, Microsoft Direct2D, Cairo, Skia, Qt::QPainter, Anti-grain Graphics
  • 16.
    Seminal Path RenderingPaper John Warnock & Douglas Wyatt, Xerox PARC Presented SIGGRAPH 1982 Warnock founded Adobe months later John Warnock Adobe founder
  • 17.
    Path Rendering Standards Document Resolution- Immersive 2D Graphics Office Printing and Independent Web Programming Productivity Exchange Fonts Experience Interfaces Applications Java 2D API OpenType Flash QtGui API TrueType Scalable Mac OS X Vector 2D API Adobe Illustrator Graphics Open XML Paper (XPS) Inkscape HTML 5 Khronos API Open Source
  • 18.
    Live Demo Classic PostScript content Complex text rendering Yesterday’s New York Times rendered from Flash content its resolution-independent form
  • 19.
    Last Year’s SIGGRAPHResults in Real-time Ron Maharik, Mikhail Bessmeltsev, Alla Sheffer, Ariel Shamir and Nathan Carr SIGGRAPH 2011, July 2011 “Girl with Words in Her Hair” scene 591 paths 338,507 commands 1,244,474 coordinates
  • 20.
    3D Rendering vs.Path Rendering Characteristic GPU 3D rendering Path rendering Dimensionality Projective 3D 2D, typically affine Pixel mapping Resolution independent Resolution independent Occlusion Depth buffering Painter’s algorithm Rendering primitives Points, lines, triangles Paths Primitive constituents Vertices Control points Constituents per primitive 1, 2, or 3 respectively Unbounded Topology of filled primitives Always convex Can be concave, self-intersecting, and have holes Degree of primitives 1st order (linear) Up to 3rd order (cubic) Rendering modes Filled, wire-frame Filling, stroking Line properties Width, stipple pattern Width, dash pattern, capping, join style Color processing Programmable shading Painting + filter effects Text rendering No direct support (2nd class support) Omni-present (1st class support) Raster operations Blending Brushes, blend modes, compositing Color model RGB or sRGB RGB, sRGB, CYMK, or grayscale Clipping operations Clip planes, scissoring, stenciling Clipping to an arbitrary clip path Coverage determination Per-color sample Sub-color sample
  • 21.
    CPU vs. GPULimited at Rendering Tasks over Time 100% 100% 90% 90% 80% 80% 70% 70% 60% 60% 50% GPU 50% GPU CPU CPU 40% 40% 30% 30% 20% 20% 10% 10% 0% 0% 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 Pipelined 3D Interactive Rendering Path Rendering Goal of NV_path_rendering is to make path rendering a GPU-limited task Render all interactive pixels, whether 3D or 2D or web content with the GPU
  • 22.
    What is NV_path_rendering? OpenGL extension to GPU-accelerate path rendering Uses “stencil, then cover” (StC) approach Create a path object Step 1: “Stencil” the path object into the stencil buffer GPU provides fast stenciling of filled or stroked paths Step 2: “Cover” the path object and stencil test against its coverage stenciled by the prior step Application can configure arbitrary shading during the step More details later Supports the union of functionality of all major path rendering standards Includes all stroking embellishments Includes first-class text and font support Allows functionality to mix with traditional 3D and programmable shading
  • 23.
    Configuration GPU: GeForce 480GTX (GF100) CPU: Core i7 950 @ 3.07 GHz NV_path_rendering Compared to Alternatives Alternative approaches are all much slower
  • 24.
    Configuration GPU: GeForce 480GTX (GF100) CPU: Core i7 950 @ 3.07 GHz Detail on Alternatives Fast, but unacceptable quality
  • 25.
    Across an rangeof scenes… Release 300 GeForce GTX 480 Speedups over Alternatives Y axis is logarithmic—shows how many TIMES faster NV_path_rendering is that competitor
  • 26.
  • 27.
    Tiger Scene onGeForce 650 Absolute Frames/Second on GeForce 650 500.0 450.0 NVpr “peaks” at 1,800 FPS at 100x100 400.0 NV_path_rendering (16x) Cairo 350.0 Qt Frames per second Skia Bitmap 300.0 Skia Ganesh FBO Skia Ganesh 1x (aliased) 250.0 Direct2D GPU Direct2D WARP 200.0 poor quality 150.0 100.0 50.0 0.0 100x100 200x200 300x300 400x400 500x500 600x600 700x700 800x800 900x900 1000x1000 1100x1100 Window resolution
  • 28.
    NV_path_rendering is morethan just matching CPU vector graphics 3D and vector graphics mix Superior quality   CPU GPU Competitors Arbitrary programmable shader on paths— 2D in perspective is free bump mapping
  • 29.
    Partial Solutions NotEnough Path rendering has 30 years of heritage and history Can’t do a 90% solution and Software to change Trying to “mix” CPU and GPU methods doesn’t work Expensive to move software—needs to be an unambiguous win Must surpass CPU approaches on all fronts Performance Quality Functionality Conformance to standards More power efficient Enable new applications
  • 30.
    Path Filling andStroking just filling just stroking filling + stroke = intended content
  • 31.
    Dashing Content Examples Artist made windows with dashed line Same cake segment missing dashed stroking details Technical diagrams and charts often employ Frosting on cake is dashed dashing elliptical arcs with round end caps for “beaded” look; flowers are also dashing All content shown is fully GPU rendered Dashing character outlines for quilted look
  • 32.
    Excellent Geometric Fidelityfor Stroking Correct stroking is hard Lots of CPU implementations approximate stroking GPU-accelerated OpenVG reference GPU-accelerated stroking avoids such short-cuts   GPU has FLOPS to compute true stroke point containment Cairo Qt   Stroking with tight end-point curve
  • 33.
    The Approach Step 1 Step 2: Stencil Cover repeat “Stencil, then Cover” (StC) Map the path rendering task from a sequential algorithm… …to a pipelined and massively parallel task Break path rendering into two steps First, “stencil” the path’s coverage into stencil buffer Second, conservatively “cover” path Test against path coverage determined in the 1st step Shade the path And reset the stencil value to render next path
  • 34.
    Pixel pipeline Vertex pipeline Path pipeline Application Path specification Pixel assembly Vertex assembly Transform path (unpack) Vertex operations transform feedback Primitive assembly Pixel operations Primitive operations Fill/Stroke Covering Pixel pack Rasterization read Texture Fragment operations back memory Fill/Stroke Application Raster operations Stenciling Framebuffer Display
  • 35.
    Key Operations forRendering Path Objects Stencil operation only updates stencil buffer glStencilFillPathNV, glStencilStrokePathNV Cover operation glCoverFillPathNV, glCoverStrokePathNV renders hull polygons guaranteed to “cover” region updated by corresponding stencil Two-step rendering paradigm stencil, then cover (StC) Application controls cover stenciling and shading operations Gives application considerable control No vertex, tessellation, or geometry shaders active during steps Why? Paths have control points & rasterized regions, not vertices, triangles
  • 36.
    Path Rendering Example(1 of 3) Let’s draw a green concave 5-point star even-odd fill style non-zero fill style Path specification by string of a star GLuint pathObj = 42; const char *pathString ="M100,180 L40,10 L190,120 L10,120 L160,10 z"; glPathStringNV(pathObj,GL_PATH_FORMAT_SVG_NV, strlen(pathString),pathString); Alternative: path specification by data static const GLubyte pathCommands[5] = { GL_MOVE_TO_NV, GL_LINE_TO_NV, GL_LINE_TO_NV, GL_LINE_TO_NV, GL_LINE_TO_NV, GL_CLOSE_PATH_NV }; static const GLshort pathVertices[5][2] = { {100,180}, {40,10}, {190,120}, {10,120}, {160,10} }; glPathCommandsNV(pathObj, 6, pathCommands, GL_SHORT, 10, pathVertices);
  • 37.
    Path Rendering Example(2 of 3) Initialization Clear the stencil buffer to zero and the color buffer to black glClearStencil(0); glClearColor(0,0,0,0); glStencilMask(~0); glClear(GL_COLOR_BUFFER_BIT | GL_STENCIL_BUFFER_BIT); Specify the Path's Transform glMatrixIdentityEXT(GL_PROJECTION); glMatrixOrthoEXT(GL_MODELVIEW, 0,200, 0,200, -1,1); // uses DSA! Nothing really specific to path rendering here DSA = OpenGL’s Direct State Access extension (EXT_direct_state_access)
  • 38.
    Path Rendering Example(3 of 3) Render star with non-zero fill style Stencil path glStencilFillPathNV(pathObj, GL_COUNT_UP_NV, 0x1F); non-zero fill style Cover path glEnable(GL_STENCIL_TEST); glStencilFunc(GL_NOTEQUAL, 0, 0x1F); glStencilOp(GL_KEEP, GL_KEEP, GL_ZERO); glColor3f(0,1,0); // green glCoverFillPathNV(pathObj, GL_BOUNDING_BOX_NV); Alternative: for even-odd fill style even-odd fill style Just program glStencilFunc differently glStencilFunc(GL_NOTEQUAL, 0, 0x1); // alternative mask
  • 39.
    “Stencil, then Cover” stencil fill path command path front-end Path Fill Stenciling path projective object Specify a path per-path transform fill region Specify arbitrary path transformation operations Projective (4x4) allowed clipping & Depth values can be generated for scissoring sample depth testing accessibility Sample accessibility determined window, depth Accessibility can be limited by any & stencil tests or all of Scissor test, depth test, stencil test, view frustum, user-defined clip path winding planes, sample mask, stipple number pattern, and window ownership per-sample computation Winding number w.r.t. the operations transformed path is computed Added to stencil value of accessible stencil samples Fill stencil update: stenciling buffer +, -, or invert specific
  • 40.
    “Stencil, then Cover” cover fill path command path front-end Path Fill Covering path projective object Specify a path per-path transform Specify arbitrary path fill region transformation operations clipping & Projective (4x4) allowed scissoring Depth values can be generated for sample depth testing accessibility window, depth Sample accessibility determined per-sample & stencil tests Accessibility can be limited by any operations or all of Scissor test, depth test, stencil stencil test, view frustum, user-defined per-fragment or update clip planes, sample mask, stipple per-sample pattern, and window ownership typically zero shading Conservative covering geometry uses stencil to “cover” filled path programmable Determined by prior stencil step color stencil path buffer shading buffer
  • 41.
    Adding Stroking tothe Star After the filling, add a stroked “rim” to the star like this… Set some stroking parameters (one-time): glPathParameterfNV(pathObj, GL_STROKE_WIDTH_NV, 10.5); glPathParameteriNV(pathObj, GL_JOIN_STYLE_NV, GL_ROUND_NV); non-zero fill style Stroke the star Stencil path glStencilStrokePathNV(pathObj, 0x3, 0xF); // stroked samples marked “3” Cover path glEnable(GL_STENCIL_TEST); glStencilFunc(GL_EQUAL, 3, 0xF); // update if sample marked “3” glStencilOp(GL_KEEP, GL_KEEP, GL_ZERO); glColor3f(1,1,0); // yellow glCoverStrokePathNV(pathObj, GL_BOUNDING_BOX_NV); even-odd fill style
  • 42.
    stencil stroke “Stencil, thenCover” path command path front-end Path Stroke Stenciling path projective object Specify a path per-path transform Specify arbitrary path transformation fill region Projective (4x4) allowed operations clipping & Depth values can be generated for depth testing scissoring sample Sample accessibility determined accessibility Accessibility can be limited by any window, depth or all of & stencil tests Scissor test, depth test, stencil test, view frustum, user-defined clip planes, sample mask, stipple pattern, and window ownership stroke per-sample point Point containment w.r.t. the stroked path is determined operations containment Replace stencil value of contained samples Stroke stencil stencil stenciling update: buffer specific replace
  • 43.
    cover stroke “Stencil, thenCover” path command path front-end Path Stroke Covering path projective object Specify a path per-path transform Specify arbitrary path fill region transformation operations clipping & Projective (4x4) allowed scissoring sample Depth values can be generated for depth testing accessibility Sample accessibility determined per-sample window, depth Accessibility can be limited by any & stencil tests operations or all of Scissor test, depth test, stencil test, view frustum, stencil user-defined clip planes, per-fragment or update sample mask, stipple pattern, per-sample typically zero and window ownership shading Conservative covering geometry uses stencil to “cover” stroked path programmable Determined by prior stencil step color stencil path buffer shading buffer
  • 44.
    First-class, Resolution-independent Font Support Fonts are a standard, first-class part of all path rendering systems Foreign to 3D graphics systems such as OpenGL and Direct3D, but natural for path rendering Because letter forms in fonts have outlines defined with paths TrueType, PostScript, and OpenType fonts all use outlines to specify glyphs NV_path_rendering makes font support easy Can specify a range of path objects with A specified font Sequence or range of Unicode character points No requirement for applications use font API to load glyphs You can also load glyphs “manually” from your own glyph outlines Functionality provides OS portability and meets needs of applications with mundane font requirements
  • 45.
    Handling Common PathRendering Functionality: Filtering GPUs are highly efficient at image filtering Fast texture mapping  Qt Mipmapping Anisotropic filtering Wrap modes Moiré CPUs aren't really artifacts  GPU  Cairo
  • 46.
    Handling Uncommon PathRendering Functionality: Projection Projection “just works” Because GPU does everything with perspective-correct interpolation
  • 47.
    Projective Path RenderingSupport Compared  GPU  Skia  Cairo  Qt flawless yes, but bugs unsupported unsupported correct correct unsupported unsupported correct wrong unsupported unsupported
  • 48.
    Path Geometric Queries glIsPointInFillPathNV determine if object-space (x,y) position is inside or outside path, given a winding number mask glIsPointInStrokePathNV determine if object-space (x,y) position is inside the stroke of a path accounts for dash pattern, joins, and caps glGetPathLengthNV returns approximation of geometric length of a given sub-range of path segments glPointAlongPathNV returns the object-space (x,y) position and 2D tangent vector a given offset into a specified path object Useful for “text follows a path” Queries are modeled after OpenVG queries
  • 49.
    Accessible Samples ofa Transformed Path When stenciled or covered, a path is transformed by OpenGL’s current modelview-projection matrix Allows for arbitrary 4x4 projective transform Means (x,y,0,1) object-space coordinate can be transformed to have depth Fill or stroke stenciling affects “accessible” samples A samples is not accessible if any of these apply to the sample clipped by user-defined or view frustum clip planes discarded by the polygon stipple, if enabled discarded by the pixel ownership test discarded by the scissor test, if enabled discarded by the depth test, if enabled displaced by the polygon offset from glPathStencilDepthOffsetNV discarded by the depth test, if enabled discarded by the (implicitly enabled) stencil test specified by glPathStencilFuncNV where the read mask is the bitwise AND of the glPathStencilFuncNV read mask and the bit-inversion of the effective mask parameter of the stenciling operation
  • 50.
    Mixing Depth Bufferingand Path Rendering PostScript tigers surrounding Utah teapot Plus overlaid TrueType font rendering No textures involved, no multi-pass
  • 51.
  • 52.
    3D Path RenderingDetails Stencil step uses GLfloat slope = -0.05; GLint bias = -1; glPathStencilDepthOffsetNV(slope, bias); glDepthFunc(GL_LESS); glEnable(GL_DEPTH_TEST); Stenciling step uses glPathCoverDepthFuncNV(GL_ALWAYS); Observation Stencil step is testing—but not writing—depth Stencil won’t be updated if stencil step fails depth test at a sample Cover step is writing—but not testing—depth Cover step doesn’t need depth test because stencil test would only pass if prior stencil step’s depth test passed Tricky, but neat because minimal mode changes involved
  • 53.
    Without glPathStencilDepthOffset Bad Things Happen Each tiger is layered 240 paths Without the depth offset during the stencil step, all the—essentially co-planar—layers would Z-fight as shown below terrible z-fighting artifacts
  • 54.
    Path Transformation Process Path object-space coordinates object (x,y,0,1) Modelview eye-space coordinates color/fog/tex coordinates matrix (xe,ye,ze,we) + attributes color/fog/tex coords. User-defined Object-space clip planes color/fog/tex Eye-space generation color/fog/tex generation clipped eye-space coordinates (xe,ye,ze,we) + attributes clipped clip-space Projection clip-space coordinates View-frustum coordinates to path matrix (xc,yc,zc,wc) + attributes clip planes (xc,yc,zc,wc) + attributes stenciling or covering
  • 55.
    Clip Planes Workwith Path Rendering Scene showing a Welsh dragon clipped to all 64 combinations of 6 clip planes enabled & disabled
  • 56.
    Path Rendering Workswith Scissoring and Stippling too Scene showing a tiger scissoring into 9 regions Tiger with two different polygon stipple patterns
  • 57.
    Rendering Paths Clippedto Some Other Arbitrary Path Example clipping the PostScript tiger to a heart constructed from two cubic Bezier curves unclipped tiger tiger with pink background clipped to heart
  • 58.
    Complex Clipping Example tiger is 240 paths cowboy clip is the union of 1,366 paths result of clipping tiger to the union of all the cowboy paths
  • 59.
    Arbitrary Programmable GPUShading with Path Rendering During the “cover” step, you can do arbitrary fragment processing Could be Fixed-function fragment processing OpenGL assembly programs Cg shaders compiled to assembly with Cg runtime OpenGL Shading Language (GLSL) shaders Your pick—they all work! Remember: Your vertex, geometry, & tessellation shaders ignored during cover step (Even your fragment shader is ignored during the “stencil” step)
  • 60.
    Example of BumpMapping on Path Rendered Text Phrase “Brick wall!” is path rendered and bump mapped with a Cg fragment shader light source position
  • 61.
    Anti-aliasing Discussion Good anti-aliasing is a big deal for path rendering Particularly true for font rendering of small point sizes Features of glyphs are often on the scale of a pixel or less NV_path_rendering uses multiple stencil samples per pixel for reasonable antialiasing Otherwise, image quality is poor 4 samples/pixel bare minimum 8 or 16 samples/pixel is pretty sufficient But 16 requires expensive 2x2 supersampling of 4x multisampling 16x is extremely memory intensive Alternative: quality vs. performance tradeoff Fast enough to render multiple passes to improve quality Approaches Accumulation buffer Alpha accumulation
  • 62.
    Anti-aliasing Strategy Benefits Benefits from GPU’s existing hardware AA strategies GPU Multiple color-stencil-depth rendered samples per pixel coverage NOT 4, 8, or 16 samples per pixel conflated with Rotated grid sub-positions opacity Fast downsampling by GPU Avoids conflating coverage & opacity Cairo, Qt, Skia, Maintains distinct color sample and Direct2D per sample location rendered Centroid sampling shows dark Fast enough for temporal cracks artifacts due to conflating schemes artifacts coverage with >>60 fps means multi-pass opacity, notice improves quality background bleeding
  • 63.
    Real Flash Scene same scene, GPU-rendered without conflation conflation artifacts abound, rendered by Skia conflation is aliasing & edge coverage percents are un-predicable in general; means conflated pixels flicker when animated slowly
  • 64.
    GPU Advantages Fast, quality filtering Mipmapping of gradient color ramps essentially free Includes anisotropic filtering (up to 16x) Filtering is post-conversion from sRGB Full access to programmable shading No fixed palette of solid color / gradient / pattern brushes Bump mapping, shadow mapping, etc.—it’s all available to you Blending Supports native blending in sRGB color space Both colors converted to linear RGB Then result is converted stored as sRGB Freely mix 3D and path rendering in same framebuffer Path rendering buffer can be depth tested against 3D So can 3D rendering be stenciled against path rendering Obviously performance is MUCH better than CPUs
  • 65.
    Improved Color Space: sRGB Path Rendering Radial color gradient example Modern GPUs have native support for moving from saturated red to blue perceptually-correct for sRGB framebuffer blending sRGB texture filtering No reason to tolerate uncorrected linear RGB color artifacts! More intuitive for artists to control  linear RGB Negligible expense for GPU to perform transition between saturated red and saturated blue has sRGB-correct rendering dark purple region However quite expensive for software path renderers to perform sRGB rendering Not done in practice  sRGB perceptually smooth transition from saturated red to saturated blue
  • 66.
    Trying Out NV_path_rendering Operating system support 2000, XP, Vista, Windows 7, Linux, FreeBSD, and Solaris Unfortunately no Mac support GPU support GeForce 8 and up (Tesla and beyond) Most efficient on Fermi and Kepler GPUs Current performance can be expected to improve Shipping since NVIDIA’s Release 275 drivers Available since summer 2011 New Release 300 drivers have remarkable NV_path_rendering performance Try it, you’ll like it
  • 67.
    Learning NV_path_rendering Whitepaper + source code available “Getting Started with NV_path_rendering” Explains Path specification “Stencil, then Cover” API usage Instanced rendering for text and glyphs
  • 68.
    NV_path_rendering SDK Examples A set of NV_path_rendering examples of varying levels of complexity Most involved example is an accelerated SVG viewer Not a complete SVG implementation Compiles on Windows and Linux Standard makefiles for Linux Use Visual Studio 2008 for Windows
  • 69.
    Whitepapers “Getting Startedwith NV_path_rendering”
  • 70.
    Whitepapers “Mixing 3Dand Path Rendering”
  • 71.
    SDK Example Walkthrough(1) pr_basic—simplest example pr_hello_world—kerned, underlined, of path filling & stroking stroked, and linear gradient filled text pr_welsh_dragon—filled layers pr_gradient—path with holes with texture applied
  • 72.
    SDK Example Walkthrough(2) pr_font_file—loading glyphs from a font file pr_korean—rendering UTF-8 string of Korea with the GL_FONT_FILE_NV target characters pr_shaders—use Cg shaders to bump map text with brick-wall texture
  • 73.
    SDK Example Walkthrough(3) pr_text_wheel—render projected gradient pr_tiger—classic PostScript tiger rendered text as spokes of a wheel as filled & stroked path layers pr_warp_tiger—warp the tiger with a free projective transform click & drag the bounding rectangle corners to change the projection
  • 74.
    SDK Example Walkthrough(4) pr_tiger3d—multiple projected and depth tested pr_svg—GPU-accelerated SVG viewer tigers + 3D teapot + overlaid text pr_pick—test points to determine if they are in the filled and/or stroked region of a complex path
  • 75.
    Conclusions GPU-acceleration of2D resolution-independent graphics is coming HTML 5 and low-power requirements are demanding it “Stencil, then Cover” approach Very fast Quality, functionality, and features Available today through NV_path_rendering Shipping today NV_path_rendering resources available
  • 76.
  • 77.
    More Information Bestcurrent driver: use OpenGL 4.3 beta driver http://www.nvidia.com/content/devzone/opengl-driver-4.3.html Or try www.nvidia.com/drivers Grab the latest Beta drivers for your OS & GPU Latest drivers greatly improve instanced stencil step performance! Developer resources http://developer.nvidia.com/nv-path-rendering Whitepapers, FAQ, specification NVprSDK—software development kit NVprDEMOs—pre-compiled Windows demos OpenGL Extension Wrangler (GLEW) has API support Email: [email protected]
  • 78.
    Don’t Forget the20th Anniversary Party Date: August 8th 2012 ( today! ) Location: JW Marriott Los Angeles at LA Live Venue: Gold Ballroom – Salon 1
  • 79.
    Other OpenGL-related NVIDIA Sessions at SIGGRAPH GPU Ray Tracing and OptiX Wednesday in West Hall 503, 3:50 PM - 4:50 PM David McAllister, OptiX Manager, NVIDIA Phillip Miller, Director, Workstation Software Product Management, NVIDIA Voxel Cone Tracing & Sparse Voxel Octree for Real-time Global Illumination Wednesday in NVIDIA Booth, 3:50 PM - 4:50 PM Cyril Crassin, Postdoctoral Research Scientist, NVIDIA Research OpenSubdiv: High Performance GPU Subdivision Surface Drawing Thursday in NVIDIA Booth, 10:00 AM - 10:30 AM Pixar Animation Studios GPU Team, Pixar nvFX : A New Scene & Material Effect Framework for OpenGL and DirectX Thursday in NVIDIA Booth, 2:00 PM - 2:30 PM Tristan Lorach, Developer Relations Senior Engineer, NVIDIA

Editor's Notes

  • #35 NV_path_rendering provides a new third pipeline—in addition to the vertex and pixel pipelines—for rendering pixels