Presented as a pre-conference tutorial at the GPU Technology Conference in San Jose on September 20, 2010. Learn about NVIDIA's OpenGL 4.1 functionality available now on Fermi-based GPUs.

4. OpenGL Leverage SceniX CompleX OptiX Parallel Nsight Cg

5. Example of Hybrid Rendering with OptiX OptiX (Ray tracing) OpenGL (Rasterization)

6. Parallel Nsight Provides OpenGL Profiling Configure Application Trace Settings

7. Parallel Nsight Provides OpenGL Profiling Magnified trace options shows specific OpenGL (and Cg) tracing options

8. Parallel Nsight Provides OpenGL Profiling

9. Parallel Nsight Provides OpenGL Profiling Trace of mix of OpenGL and CUDA shows glFinish & OpenGL draw calls

10. OpenGL In Every NVIDIA Business

17. OpenGL Interoperability Multi-GPU

24. NVIDIA OpenGL 4 DirectX 11 superset All of Fermi exposed!

25. OpenGL Version Progression OpenGL 2.0 2.1 OpenGL 3.0 3.1 3.2 3.3 OpenGL 4.0 4.1 OpenGL 1.0 1.1 1.2.1 1.3 1.4 1.5 Silicon Graphics heritage DirectX 9 era GPUs DirectX 10 era GPUs DirectX 11 era GPUs (2008-2010) (1992-2003) (2004-2007) (2010-)

30. OpenGL 3.2 Conceptual Processing Flow (pre-2010) Vertex processing Pixel processing Texture mapping Geometric primitive assembly & processing Image primitive processing Transform feedback Pixel unpacking Pixel packing Vertex assembly pixels in framebuffer object textures texture buffer objects texture image specification image rectangles, bitmaps primitive topology, transformed vertex data vertex texture fetches pixel pack buffer objects pixel unpack buffer objects vertex buffer objects transform feedback buffer objects buffer data, unmap buffer geometry texture fetches primitive batch type, vertex indices, vertex attributes primitive batch type, vertex data fragment texture fetches pixel image or texture image specification map buffer, get buffer data transformed vertex attributes image and bitmap fragments point, line, and polygon fragments pixels to pack unpacked pixels pixels fragments filtered texels buffer data vertices Legend programmable operations fixed-function operations copy pixels, copy texture image Buffer store uniform/ parameters buffer objects Fragment processing stenciling, depth testing, blending, accumulation OpenGL 3.2 Raster operations Framebuffer Command parser

31. Vertex processing Pixel processing Texture mapping Geometric primitive assembly & processing Image primitive processing Transform feedback Pixel unpacking Pixel packing Vertex assembly pixels in framebuffer object textures texture buffer objects texture image specification image rectangles, bitmaps primitive topology, transformed vertex data vertex texture fetches pixel pack buffer objects pixel unpack buffer objects vertex buffer objects transform feedback buffer objects buffer data, unmap buffer geometry texture fetches primitive batch type, vertex indices, vertex attributes primitive batch type, vertex data fragment texture fetches pixel image or texture image specification map buffer, get buffer data transformed vertex attributes image and bitmap fragments point, line, and polygon fragments pixels to pack unpacked pixels pixels fragments filtered texels buffer data vertices Legend programmable operations fixed-function operations copy pixels, copy texture image Buffer store Fragment processing stenciling, depth testing, blending, accumulation Control point processing Patch assembly & processing Patch tessellation generation Patch evaluation processing patch control points transformed control points transformed patch transformed patch, bivariate domain transformed patch tessellation texture fetches patch topology, evaluated patch vertex patch data OpenGL 4.1 Raster operations Framebuffer Command parser

46. Double Precision in OpenGL Shaders Double-precision magnified 970,000x Single-precision magnified 970,000x Mandelbrot set interactively visualized

47. Mix of Double- and Single-Precision fp32 fp32 fp32 fp32 fp32 fp32 fp32 fp32 fp32 fp32 fp32 fp32

52. Programmable Tessellation Data Flow vertex shader clipping, setup, & rasterization fragment shader assembled primitive fragments index to vertex attribute puller indices primitive topology & in-band vertex attributes vertex attributes vertex shader geometry shader clipping, setup, & rasterization fragment shader OpenGL 4.0 added tessellation shaders assembled primitive fragments index to vertex attribute puller indices primitive topology & in-band vertex attributes vertex attributes tessellation control (hull) shader tessellation evaluation (domain) shader tessellation generator level-of-detail parameters patch control points & parameters fine primitive topology (u, v) coordinates primitive stream control points control point (vertex) shader vertex attributes rectangular & triangluar patch OpenGL 3.2 programmable fixed-function Legend geometry shader primitive stream

54. Tessellated Triangle and Quad Notice fractional tessellation scheme in wire-frame pattern

56. Bezier Triangle Patch Bezier triangle’s tessellation Bezier triangle’s control point hull

57. Bezier Triangle Control Points b 300 b 210 b 120 b 030 b 021 b 012 b 003 b 102 b 201 b 111 P(u,v) = u 3 b 300 + 3 u 2 v b 210 + 3 uv 2 b 120 + v 3 b 030 + 3 u 2 w b 201 + 6 uvw b 111 + 3 v 2 w b 021 + 3 uw 2 b 102 + 3 uw 2 b 012 + w 3 b 003 where w=1-u-v

59. Bi-cubic Patch Mesh b 00 b 10 b 20 b 30 b 01 b 11 b 21 b 31 b 02 b 12 b 22 b 32 b 03 b 13 b 23 b 33

60. Bi-cubic Quadrilateral Patch Bi-cubic patch’s tessellation Bi-cubic patch’s control point hull

61. Surfaces are Determined by Their Control Points Moving control points displaces the evaluated surfaces

62. Utah Teapot: Bi-cubic Patch Mesh

63. Ed Catmull’s Gumbo

65. Amplification of Standard Triangle Meshes Original faceted mesh Tessellation results in triangle amplification with curvature Results of Phong shading of curved

66. Art Pipeline for Tessellation … Generate LODs Displaced Surface GPU Control Cage Smooth Surface Polygon Mesh

71. Simple Example Rendered Original single triangle Adaptive tessellation automatically tessellates distant, small triangle less and close, large triangle more Visualization of barycentric weights used by tessellation evaluation shader

76. Adaptive PN Triangles Tessellation Rendered Visualization of barycentric weights used by tessellation evaluation shader Original monkey head faceted mesh Tessellated & Phong shaded Wire frame of adaptive tessellation

84. OpenGL 4.1

98. What got ( er, didn’t get ) deprecated? Feature Hardware accelerated YES Line stipple YES Quadrilaterals (GL_QUAD*) and polygons YES Regular (non-sprite) points YES Two-sided lighting YES, key cases optimized to be faster than shaders Fixed-function vertex processing YES Edge flags YES Immediate mode YES Line widths > 1

99. What got ( er, didn’t get ) deprecated? Feature Hardware accelerated YES GL_DEPTH_TEXTURE_MODE YES ALPHA, LUMINANCE, LUMINANCE_ALPHA, INTENSITY texture formats Driver accelerated for speed glBitmap YES glPixelZoom YES glDrawPixels CPU vector instructions + GPU Pixel transfer modes YES Polygon stipple YES Separate polygon draw modes: glPolygonMode

100. What got ( er, didn’t get ) deprecated? Feature Hardware accelerated YES Auxiliary color buffers YES glCopyPixels YES, fp16 Accumulation buffer YES Alpha test YES Fixed-function fragment processing YES Automatic mipmap generation YES Texture borders YES Texture GL_CLAMP wrap mode

101. What got ( er, didn’t get ) deprecated? Feature Hardware accelerated Best advice : Overwhelming majority of deprecated features are fully hardware-accelerated by NVIDIA GPUs and their drivers so take advantage of them—they aren’t going away Think of these features as what you lack in Direct3D YES Color material No, but could be by Fermi Evaluators No, but selection could be Selection and feedback modes Highly optimized by NVIDIA, fastest way to send geometry Display lists Ignored, always fastest + nicest Hints No Attribute stacks

109. Only Cross Platform 3D API

110. OpenGL Leverage

112. Questions?