Lesson 1 – Introduction
PV227 – GPU Rendering
Jiˇrí Chmelík, Jan ˇCejka
Fakulta informatiky Masarykovy univerzity
22. 9. 2015
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 1 / 51
Outline
1 Organization
2 Introduction, history
Motivation
History
Pipeline
Shading Languages
Coordinate Spaces and Transforms
Homework
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 2 / 51
Outline
1 Organization
2 Introduction, history
Motivation
History
Pipeline
Shading Languages
Coordinate Spaces and Transforms
Homework
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 3 / 51
Course
First lectures more theoretical, then mostly practical.
Graphics is changing fast → only major language features will be
introduced.
Advanced features of OpenGL will be NOT covered.
Teaching method = seminars → active participation . . .
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 4 / 51
Course
First lectures more theoretical, then mostly practical.
Graphics is changing fast → only major language features will be
introduced.
Advanced features of OpenGL will be NOT covered.
Teaching method = seminars → active participation . . .
Figure: Taken from weebly.com
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 4 / 51
Requirements
To successfully pass the course:
no more than 2 absences,
success in final test (on the spot programming!),
Expectations:
programming skills: C, C++
knowledge of OpenGL (PV112)
basic knowledge of basics principles of computer graphics
(PB009)
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 5 / 51
Requirements
To successfully pass the course:
no more than 2 absences,
success in final test (on the spot programming!),
Expectations:
programming skills: C, C++
knowledge of OpenGL (PV112)
basic knowledge of basics principles of computer graphics
(PB009)
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 5 / 51
Contacts
Jiˇrí Chmelík
office: A412
e-mail: jchmelik@mail.muni.cz
Jan ˇCejka
office: A419
e-mail: 324987@mail.muni.cz
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 6 / 51
Want to know more about GPUs?
There is a “parallel” course:
J006 – Advanced GPU programming with Unity, Mathieu Le Muzic
. . . only this year
deferred rendering
ambient occlusion
marching-cubes
. . .
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 7 / 51
Want to know even more about GPUs?
J006 – Advanced GPU programming with Unity, Mathieu Le Muzic
PV197 – GPU Programming, Jiˇrí Filipoviˇc:
Introduction: motivation for GPU programming, GPU architecture, overview of parallelism
model, basics of CUDA, first demonstration code
GPU hardware and parallelism: detailed hardware description, synchronization, calculation
on GPU – rate of instruction processing, arithmetic precision, example of different
approaches to matrix multiplication – naive versus block-based
Performance of GPUs: memory access optimization, instructions perormance, example of
matrix transposition
CUDA, tools and libraries: detailed description of CUDA API, compilation using nvcc,
debugging, profiling, basic libraries, project assignment
Optimization: general rules for algorithm design for GPU, revision of matrix multiplication,
parallel reduction
Parallelism in general: problem decomposition, dependence analysis, design analysis,
parallel patterns
Metrics of efficiency for GPU: parallel GPU and CPU usage, metrics for performance
prediction of GPU code, demonstration using graphics algorithms, principles of
performance measurement
OpenCL: introduction to OpenCL, differences comparing to CUDA, exploiting OpenCL for
hardware not accessible from CUDA
. . .
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 8 / 51
Outline
1 Organization
2 Introduction, history
Motivation
History
Pipeline
Shading Languages
Coordinate Spaces and Transforms
Homework
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 9 / 51
Outline
1 Organization
2 Introduction, history
Motivation
History
Pipeline
Shading Languages
Coordinate Spaces and Transforms
Homework
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 10 / 51
Motivation
Figure: Taken from shoraspot.com
Figure: Taken from cgsociety.org
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 11 / 51
Why GPU?
graphics computations are costly,
graphics are “embarrassingly parallel”,
increasing model complexity, screen resolution, . . .
GPU is parallel co-processor.
Nice demo: http://youtu.be/-P28LKWTzrI
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 12 / 51
Performance
Figure: Taken from docs.nvidia.com Figure: Taken from docs.nvidia.com
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 13 / 51
Performance
Figure: Taken from docs.nvidia.com
Figure: Taken from docs.nvidia.com
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 14 / 51
Shaders
Shaders are small programmes, that can alter the processing of the
input data. The hardware units they target are called processors. They
come in various flavours:
vertex shader: modifies individual vertices,
geometry shader: operates on whole primitives, can create new
primitives,
tessellation shader: similar to geometry shader, specific for
tesselation,
fragment shader: modifies individual pixel fragments,
compute shader: arbitrary parallel computations.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 15 / 51
Fragment vs Pixel
A pixel represents the contents of the frame buffer at a specific
location.
A fragment is the state required to potentially update a particular
pixel.
A fragment has an associated pixel location, a depth value, and a
set of interpolated parameters.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 16 / 51
Outline
1 Organization
2 Introduction, history
Motivation
History
Pipeline
Shading Languages
Coordinate Spaces and Transforms
Homework
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 17 / 51
Brief History: 1980’s
integrated framebuffer,
draw to display,
tightly CPU controlled,
addition of shaded solids, vertex lighting, rasterization of filled
polygons, depth buffer,
OpenGL in 1989, beginning of graphics pipeline.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 18 / 51
Brief History: 1990’s
Generation 0
fixed graphics pipeline,
half the pipeline on CPU, half on GPU,
1 pixel per cycle, easy to overload → multiple pipelines,
dawn of “cheap” game hardware: 3DFX Voodoo, NVIDIA TNT, ATI
Rage,
developement driven by games: Quake, Doom, . . .
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 19 / 51
Brief History: 1990’s
Generation I
no 2D graphics acceleration; only 3D,
transform part of the pipeline on CPU,
rendering part on GPU (texture mapping, z-buffering,
rasterization),
3DFX Voodoo, 3DFX Voodoo2.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 20 / 51
Brief History: 1990’s
Generation II
entire pipeline on GPU,
term “GPU” introduced for GeForce 256,
AGP instead of PCI bus,
new features: multi-texturing, bump mapping, hardware T&L,
fixed function pipeline.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 21 / 51
Brief History: 2000–2002
Generation III
programmable pipeline (NVIDIA GeForce 3, ATI Radeon 8500),
parts of the pipeline can be change with custom programme,
only vertex shaders,
small assembly language “kernels”.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 22 / 51
Brief History: 2002–2004
Generation IV
“fully” programmable pipeline (NVIDIA GeForce FX, ATI Radeon
9700),
vertex and fragment (pixel) shaders,
dedicated vertex and fragment processors,
floating point support, advanced texture processing → GPGPU.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 23 / 51
Brief History: 2004–2006
Generation V
faster than Moore’s law growth,
PCI-express bus (NVIDIA GeForce 6, ATI Radeon X800),
multiple rendering targets, increased GPU memory,
high level GPU languages with dynamic flow control (Brook, Sh).
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 24 / 51
Brief History: 2006–2009
Generation VI
massively parallel processors,
unified shaders (NVIDIA GeForce 8),
streaming multiprocessor (SM),
addition of geometry shaders,
new general purpose languages: CUDA, OpenCL.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 25 / 51
Unified Shaders
before – different instruction set, capabilities,
now they can do the same (almost – differences of pipeline
position),
gradient merging of instruction sets,
HLSL perspective (http://en.wikipedia.org/wiki/
High-level_shader_language),
currently Shader model 5.0 (compute).
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 26 / 51
Brief History: 2009–?
Generation VII
even more programmability,
cache hierarchy, ECC, unified memory address space,
focus on general computations,
debuggers and profilers.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 27 / 51
Brief Future :D
Generation Vxx
slower rate of performance growth,
focus on the energy efficiency (GFLOP/W),
more CPU like,
emphasis on better programming languages and tools,
merge of graphics and general purpose APIs.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 28 / 51
Outline
1 Organization
2 Introduction, history
Motivation
History
Pipeline
Shading Languages
Coordinate Spaces and Transforms
Homework
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 29 / 51
Graphics Pipeline OpenGL 4.2
The graphics pipeline is a
sequence of stages operating
in parallel and in a fixed order.
Each stage receives its input
from the prior stage and sends
its output to the subsequent
stage.
Figure: Taken from lighthouse3d.com
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 30 / 51
Graphics Pipeline
Figure: Taken from goanna.cs.rmit.edu.au
For more, detailed diagrams, see:
http://openglinsights.com/pipeline.html
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 31 / 51
Why Programmable Pipeline?
Fixed pipeline is limited to algorithms hard-coded into the graphics
chips → narrow class of effects.
Programmability gives the developer almost limitless possibilities.
We cannot combine fixed and programmable pipeline. Once
shader is active it is responsible for the entire stage.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 32 / 51
Shaders (cont.)
Typical tasks done in shaders:
vertex shader: animation, deformation, lighting,
geometry shader: mesh processing,
tessellation shader: tessellation,
fragment shader: shading ;-),
compute shader: almost anything.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 33 / 51
Outline
1 Organization
2 Introduction, history
Motivation
History
Pipeline
Shading Languages
Coordinate Spaces and Transforms
Homework
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 34 / 51
Shader Languages
Cg (C for Graphics), by NVIDIA – no longer under active
development,
HLSL (High Level Shading Language), by Microsoft,
GLSL (OpenGL Shading Language), by Khronos Group.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 35 / 51
Shader Languages Comparison
almost the same capabilities,
conversion tools between them,
Cg and HLSL very similar (different setup),
HLSL DirectX only, GLSL OpenGL only, Cg for both → different
platforms supported.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 36 / 51
Shader Languages Comparison – Compilers
HLSL needs DirectX, Cg needs Cg toolkit [DirectX], GLSL comes
with driver,
HLSL & Cg: toolkit compiler → “same” binary code for all vendors
→ translation to machine code,
GLSL: vendor compiler → “faster” machine code, inconsistencies,
harder to deal with varying hardware,
Cg may have compiler issues on ATI cards.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 37 / 51
Chosen Language
We will use GLSL in this course:
open standard (same as OpenGL),
no install needed,
all platforms, all vendors.
Will will use GLSL 3.30 for OpenGL 3.3
newer features will be mentioned but not demonstrated,
e.g., NVIDIA 9600 GT (released 02/2008) is a OpenGL 2.1/3.3
card.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 38 / 51
OpenGL Evolution
Figure: Taken from news.cnet.com
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 39 / 51
OpenGL Evolution
Released OpenGL Version GLSL Version
1992 1.0 —
2004 2.0 1.10
2006 2.1 1.20
2008 3.0 1.30
2009 3.1 1.40
2009 3.2 1.50
2010 3.3 3.30
2010 4.0 4.0
. . . . . . . . .
2014 4.5 4.5
Table: OpenGL and GLSL versions
For more, see, e. g., following: History of OpenGL
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 40 / 51
Outline
1 Organization
2 Introduction, history
Motivation
History
Pipeline
Shading Languages
Coordinate Spaces and Transforms
Homework
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 41 / 51
Coordinate Spaces and Transforms – Object Space
the pipeline transforms 3D objects into 2D image,
divided into several coordinate spaces beneficial for different
tasks,
transformation starts with polygon representation of the model,
represented in object space (local space),
origin and units chosen according to the model.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 42 / 51
Coordinate Spaces and Transforms – World Space
Figure: Taken from
yaldex.com
objects are composed in a single scene
(share a single world),
represented in world space (model space),
origin and units chosen according to the
scene,
objects are transformed into this space by
modeling transformation as defined by
model matrix,
spatial relations of objects are known
afterwards.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 43 / 51
Coordinate Spaces and Transforms – Eye Space
Figure: Taken from
yaldex.com
the scene is viewed by a camera,
the view is represented in eye space
(camera space),
origin at the eye position, looking down the
the negative Z axis,
objects are transformed into this space by
viewing transformation as defined by view
matrix,
spatial relations of objects are unchanged,
model and view matrix are
combined into modelview matrix
modelview = view × model.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 44 / 51
Coordinate Spaces and Transforms – Clip Space
Figure: Taken from
yaldex.com
the camera defines a viewing volume, space
visible in the final image,
the view is represented as a axis-aligned
cube in clip space,
−w ≤ x ≤ w, −w ≤ y ≤ w, −w ≤ z ≤ w,
objects are transformed into this space by
projection transformation as defined by
projection matrix,
beneficial for frustum clipping polygons
outside the axis-aligned
cube.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 45 / 51
Coordinate Spaces and Transforms – NDC Space
Figure: Taken from
yaldex.com
the clip space is compressed into [-1,1]
range with the perspective divide,
achieved by dividing with w → only 3
coordinates left,
the resulting space is called normalized
device coordinate space,
beneficial for mapping visible primitives to
arbitrarly sized viewports.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 46 / 51
Coordinate Spaces and Transforms – Screen Space
Figure: Taken from
yaldex.com
Pixels coordinates are of form 0 to (width-1),
and from 0 to (height-1), i.e. window
coordinate system (screen space).
Viewport transformation transforms the
[-1,1] range into this system.
Primitives are rasterized in this system.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 47 / 51
Coordinate Spaces and Transforms – Guidelines
During computations the variables must be in the same space,
E. g., vertices, normals and light positions in eye space,
Vertex shader must output the clip coordinates.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 48 / 51
Outline
1 Organization
2 Introduction, history
Motivation
History
Pipeline
Shading Languages
Coordinate Spaces and Transforms
Homework
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 49 / 51
Homework
Recapitulate shader set-up process (shader & program creation;
compilation, running, . . . ),
from PV112 10th
lecture,
from PV227 setup materials.
Try to compile and run examples in “homework” assignment:
most things should be already set – just open, compile and run
(hopefully),
try to briefly look at different setups.
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 50 / 51
Sources
interactive book about shaders: http://pixelshaders.com/
“simple” shader sandbox: http://glslsandbox.com/
advanced sandbox: http://www.kickjs.org/example/
shader_editor/shader_editor.html
shaders Guru’s (I´nigo Quílez) web:
http://www.iquilezles.org/default.html
PV227 – GPU Rendering (FI MUNI) Lesson 1 – Introduction 22. 9. 2015 51 / 51