GeneralPurpose Computation on Graphics Hardware

1
General-Purpose Computation on Graphics Hardware
2
Introduction

• David Luebke
  University of Virginia

3
Course Introduction

• The GPU on commodity video cards has evolved into
  an extremely flexible and powerful processor
• Programmability
• Precision
• Power
• This course will address how to harness that
  power for general-purpose computation

4
Motivation Computational Power

• GPUs are fast
• 3 GHz Pentium4 theoretical 6 GFLOPS, 5.96 GB/sec
  peak
• GeForceFX 5900 observed 20 GFLOPs, 25.3 GB/sec
  peak
• GPUs are getting faster, faster
• CPUs annual growth ? 1.5 ? decade growth ? 60
• GPUs annual growth gt 2.0 ? decade growth gt 1000

Courtesy Kurt Akeley,Ian Buck Tim Purcell, GPU
Gems (see course notes)
5
MotivationComputational Power
GPU
CPU
Courtesy Naga Govindaraju
6
An Aside Computational Power

• Why are GPUs getting faster so fast?
• Arithmetic intensity the specialized nature of
  GPUs makes it easier to use additional
  transistors for computation not cache
• Economics multi-billion dollar video game market
  is a pressure cooker that drives innovation

7
MotivationFlexible and precise

• Modern GPUs are deeply programmable
• Programmable pixel, vertex, video engines
• Solidifying high-level language support
• Modern GPUs support high precision
• 32 bit floating point throughout the pipeline
• High enough for many (not all) applications

8
MotivationThe Potential of GPGPU

• The power and flexibility of GPUs makes them an
  attractive platform for general-purpose
  computation
• Example applications range from in-game physics
  simulation to conventional computational science
• Goal make the inexpensive power of the GPU
  available to developers as a sort of
  computational coprocessor

9
The ProblemDifficult To Use

• GPUs designed for and driven by video games
• Programming model is unusual tied to computer
  graphics
• Programming environment is tightly constrained
• Underlying architectures are
• Inherently parallel
• Rapidly evolving (even in basic feature set!)
• Largely secret
• Cant simply port code written for the CPU!

10
Course goals

• A detailed introduction to general-purpose
  computing on graphics hardware
• We emphasize
• Core computational building blocks
• Strategies and tools for programming GPUs
• Tips tricks, perils pitfalls of GPU
  programming
• Several case studies to bring it all together

11
Why a SIGGRAPH Course?

• Why SIGGRAPH, instead of (say) Supercomputing?
• Many graphics applications stand to benefit from
  GPGPU
• Hot topic case studies tone mapping, level
  sets, fluids
• Keeping computation on-card!
• Many graphics applications strive for visual
  plausibility rather than rigorous scientific
  realism
• Better tolerate GPU limitations in precision,
  memory
• Well suited as GPGPU early adopters
• GPGPU programming still requires expertise of
  SIGGRAPH audience

12
Course Prerequisites

• We assume
• Familiarity with interactive graphics and
  computer graphics hardware
• Ideally, some experience programming vertex
  pixel shaders
• Target audience
• Researchers interested in GPGPU
• Graphics and games developers interested in
  incorporating these techniques into their
  applications
• Attendees wishing a survey of this exciting new
  field

13
Course Topics

• GPU building blocks
• Languages and tools
• Effective GPU programming
• GPGPU case studies

14
Course Topics Details

• GPU building blocks
• Linear algebra
• Sorting and searching
• Database operations
• Languages and tools
• High-level languages
• Debugging tools

15
Course Topics Details

• Effective GPU programming
• Efficient data-parallel programming
• Data formatting addressing
• GPU computation strategies tricks
• Case studies in GPGPU Programming
• Physically-based simulation on GPUs
• Ray tracing photon mapping on GPUs
• Tone mapping on GPUs
• Level sets on GPUs

16
SpeakersIn Order of Appearance

• David Luebke, University of Virginia
• Mark Harris, NVIDIA
• Jens Krüger, TU-Munich
• Tim Purcell, Stanford (NVIDIA)
• Naga Govindaraju, University of North Carolina
• Ian Buck, Stanford
• Cliff Woolley, University of Virginia
• Aaron Lefohn, University of California Davis

17
Course ScheduleGPU Building Blocks
Luebke Harris Krüger Purcell

• 830 Introduction
• Welcome, overview, the graphics pipeline
• 900 Mapping computational concepts to the GPU
• Streaming, Resources, CPU-GPU analogies,
  branching
• 920 Linear algebra
• Representations, operations, example algorithms
• 955 Sorting searching (part 1)
• Bitonic sort, binary search
• 1015 Break

18
Course ScheduleLanguages Tools
Purcell Govindaraju Buck Purcell

• 1030 Sorting searching (part 2)
• Nearest-neighbor search
• 1045 Database operations
• Queries, boolean predicates, aggregation
• 1115 High-level languages
• Cg/HLSL/GLslang, Sh, Brook
• 1145 Debugging tools
• imdebug, DirectX/OpenGL shader IDEs, ShadeSmith
• 1215 Lunch break

19
Course ScheduleEffective GPU Programming
Woolley Lefohn Buck All

• 145 Efficient data-parallel GPU programming
• Computational frequency, profiling, load
  balancing
• 215 Data formatting addressing
• Memory layout, data structures
• 245 GPU Computation Strategies Tricks
• Precision, performance, scatter, branching
• 315 Q A
• Questions for the speakers?
• 330 Break

20
Course ScheduleGPGPU Case Studies
Harris Woolley Lefohn Purcell

• 345 Physically-based simulation on GPUs
• Reaction-diffusion, fluids, clouds
• 410 Tone mapping on GPUs
• High-dynamic range images, tone mapping
• 435 Level sets on GPUs
• Streaming level sets, visualization, segmentation
• 500 Global illumination on GPUs
• Ray tracing, photon mapping
• 530 Wrap!

21
GPU FundamentalsThe Graphics Pipeline
GPU
CPU
Graphics State
Application
Transform
Rasterizer
Shade
VideoMemory(Textures)
Vertices(3D)
Xformed,LitVertices(2D)
Fragments(pre-pixels)
Finalpixels(Color, Depth)
Render-to-texture

• A simplified graphics pipeline
• Note that pipe widths vary
• Many caches, FIFOs, and so on not shown

22
GPU FundamentalsThe Modern Graphics Pipeline
GPU
CPU
Graphics State
VertexProcessor
FragmentProcessor
Application
VertexProcessor
Rasterizer
PixelProcessor
VideoMemory(Textures)
Vertices(3D)
Xformed,LitVertices(2D)
Fragments(pre-pixels)
Finalpixels(Color, Depth)
Render-to-texture

• Programmable vertex processor!

• Programmable pixel processor!

23
GPU Pipeline Transform

• Vertex Processor (multiple operate in parallel)
• Transform from world space to image space
• Compute per-vertex lighting

24
GPU Pipeline Rasterizer

• Rasterizer
• Convert geometric rep. (vertex) to image rep.
  (fragment)
• Fragment image fragment
• Pixel associated data color, depth, stencil,
  etc.
• Interpolate per-vertex quantities across pixels

25
GPU Pipeline Shade

• Fragment Processors (multiple in parallel)
• Compute a color for each pixel
• Optionally read colors from textures (images)

26
Coming Up

• Next Mapping computational concepts to the GPU
• Also coming up
• Core building blocks for GPGPU computing
• Memory layout, data structures, and algorithms
• Detailed advice on writing high performance GPGPU
  code
• Lots of examples