GPU(Graphics Processing Unit) with a Focus on Nvidia GeForce 6 Series. By: Binesh Tuladhar Clay Smith

Size: px
Start display at page:

Download "GPU(Graphics Processing Unit) with a Focus on Nvidia GeForce 6 Series. By: Binesh Tuladhar Clay Smith"

Transcription

1 GPU(Graphics Processing Unit) with a Focus on Nvidia GeForce 6 Series By: Binesh Tuladhar Clay Smith

2 Overview History of GPU s GPU Definition Classical Graphics Pipeline Geforce 6 Series Architecture Vertex and Fragment Processors Traditional Architecture vs Super Scalar Architecture GPU features Functional and Shader Model 3.0 Fragment Processor Performance Future of GPU s

3 History Early GPU s -designed for primitive graphics operations 1990 s -2D graphics accelerators evolved Mid 1990 s late 1990 s -CPU assisted 3D graphics for PC s and gaming consoles - 3D hardware supporting T&L Modern GPU s -Programmable Graphics Pipeline with pixel and vertex shaders

4 GPU Definition Graphics rendering device GPU Rendering Wire Frame 3D Object

5 Definition contd... Consists of processor which is used for floating point calculations and rendering of 2D/3D images Processors either attached to graphics card or integrated in system board Decreases work load of CPU Gives improved system performance and gives realistic effect to images, videos and games

6 Classical Graphics Pipeline VERTEX T & L evolved to vertex TRIANGLE Traingle, point, line setup PIXEL ROP Flat shading, texturing, eventually pixel shading Blending, Z buffering, antialiasing MEMORY Wider and faster over years

7 Definition Contd... GPU interfaces with the CPU using fast buses like AGP (uptp 2GB/sec for 8X AGP PCI Express (upto 8GB/sec) Bus speeds are important because textures and vertex data needs to come from CPU to GPU

8 GeForce 6 Series Architecture

9 GeForce 6 Series Vertex Processor Vertex data received from host CPU Allow programs that performs transformation, skinning and other per-vertex operations. All operations are 32 bit floating point (fp32) precision per component Vertex cache present- stores vertex data These vertices are grouped intyo primitives- points, lines, traingles

10 Cull/Clip, Rasterization and Z-Cull Cull/Clip - Removes invisible primitives and performs plane equation on data for rasterization Rasterization -computes pixel coverage and uses Z-cull to discard pixels blocked by objects Z-Cull - eliminates pixel based on the depth

11 GeForce 6 Series Fragment Processor Fragment a candidate pixel texture and fragments unis operates on quads (squares of 4 pixels) Works on groups of 100 of pixels at a time in SIMD fashion Uses texture caches or units to fetch data from memory

12 Fragement Processor Contd... Shader units can perform 8 math ops (w/o texture fetch) or 4 math ops (with texture fetch ) in each clock cycle Fog calculation done in the end out = FogColor * fogfraction + SrcColor * (1-fogFraction) Pixels almost ready for framebuffer

13 Z-Compare and Blending Fragments aree passed through Z-compare and Blending units Operations: Depth testing Stencil tests Alpha operations Final color write to target surface

14 Memory Divided into independent partitions each with its own DRAM s Independent partitions increase latency and efficiency regardless of size of data transferred Gives GPU a wide 256 bits of flexible memory subsystem Allows streaming for small memory accesses (32 bytes) at 35 GB/sec In low end system, system memory shared as graphics memory

15 Traditional Architecture TEXTURE SHADER = 4 Ops/Pixel 1 Texture/Pixel at full speed 4 Components 1 Op/Component 4 Ops/Pixel Traditional non scalar shader architecture has only one shader unit Can process only upto 4 operations per cycle

16 Super-scalar Architecture SHADER Unit 1 TEXTURE 4 Components 1 Op/Component 4 Ops/Pixel OR 1 Texture/Pixel at Full Speed superscalar architecture has a second shader unit doubles pixel operations per cycle SHADER Unit 2 4 Components 1 Op/Component 4 Ops/Pixel Can process upto 8 operations per cycle = 8 Ops/Pixel

17 GPU Features Functional Features Geometric Instancing Vertex stream frequency - hardware support for looping over a subset of vertices Example: rendering the same objectmultiple times at diff locations (grass, soldiers, people in stadium)

18 GPU Features Contd... Early culling and clipping - remove nonvisible primitives at high rate Rasterization - rendering supports point sprites Aliased and anti-aliased lines Aliased and antialiased triangles Z-Cull - Allows high-speed removal of hidden surfaces Occlusion Query - Keeps a record of the number of fragments passing or failing the depth test and reports it to the CPU

19 GPU Features Contd... Texturing -Textures can now directly be fetched into the vertex program. Shadow Buffer Support - Fetches shadow buffer as a projective texture and performs z compares of the shadow buffer data to distance from light.

20 Shader Model 3.0 Features Increased instruction count (upto instructions.) Fragment processor; multiple render targets. Dynamic flow control branching Vertex texturing More temporary registers.

21 Shader Model 3.0 Features Contd.. Co-issue -Two separate operations can concurrently execute on different parts of a four-wide register Dual Issue -Independent instructions can be executed on independent units in computational pipeline

22 Fragment Processor Performance fp32 and fp16 precision support for intermediate calculations Ability to perform four wide, coissue multiply-add(mad) or four-term dot product (DP4), plus a four-wide, coissueable and dual-issuable multiply instruction per clock in series. Dedicated fp16 normalization hardware

23 Future of GPU s High end graphics card to support graphical applications games requiring high resolutions and faster refresh rates Increase speeds of hardware such as memory and processor More compact, low power, low cost GPU s Empirical testing of infield operation

24 Bibliography Emmett Kilgariff, Randima Fernando (2005). "The GeForce 6 Series GPU Architecture." Excerpted from GPU Gems 2 Copyright 2005 by NVIDIA Corporation. Available online at: James Fung (2005), Computer Vision on GPU, University of Toronto, Available online at: Ajit Datar, Apurva Padhye Graphics Processing Unit Architecture (GPU Arch), Available online at: NVIDIA (2006)"Technical Brief NVIDIA GeForce 8800 GPU Architecture Overview" November 2006 Copyright 2006 NVIDIA Corporation. Available online at: NVIDIA (2004) Technical Brief The GeForce 6 Series of GPUs High Performance and Quality for Complex Image Effects, 2004 by Nvidia Corporation. Available online at: Files%5Cb2eb9657-4f0f-4df6-86bd- 739ee6fcef58/GeForce6SeriesofGPUs_v1.pdf]

The GeForce 6 Series GPU Architecture

The GeForce 6 Series GPU Architecture Chapter 30 The GeForce 6 Series GPU Architecture Emmett Kilgariff NVIDIA Corporation Randima Fernando NVIDIA Corporation The previous chapter described how GPU architecture has changed as a result of computational

More information

Evolution of Graphics Pipelines

Evolution of Graphics Pipelines Evolution of Graphics Pipelines 1 Understanding the Graphics Heritage the era of fixed-function graphics pipelines the stages to render triangles 2 Programmable Real-Time Graphics programmable vertex and

More information

Graphics Hardware and Graphics Programming Interfaces

Graphics Hardware and Graphics Programming Interfaces Graphics Hardware and Graphics Programming Interfaces Mark Segal segal@ati.com Graphics Hardware High Level I/O CPU R300, etc. Northbridge AGP 8X Host Interface Main Memory Other Important Graphics Stuff

More information

Computer Graphics Hardware An Overview

Computer Graphics Hardware An Overview Computer Graphics Hardware An Overview Graphics System Monitor Input devices CPU/Memory GPU Raster Graphics System Raster: An array of picture elements Based on raster-scan TV technology The screen (and

More information

The Evolution of Computer Graphics. SVP, Content & Technology, NVIDIA

The Evolution of Computer Graphics. SVP, Content & Technology, NVIDIA The Evolution of Computer Graphics Tony Tamasi SVP, Content & Technology, NVIDIA Graphics Make great images intricate shapes complex optical effects seamless motion Make them fast invent clever techniques

More information

Chapter 2 GRAPHICAL PROCESSING UNITS. 2.1 Overview

Chapter 2 GRAPHICAL PROCESSING UNITS. 2.1 Overview Chapter 2 GRAPHICAL PROCESSING UNITS 2.1 Overview Knowledge of the operations supported by GPUs and how data is processed in GPUs is necessary in order to understand how GPUs can be leveraged for cryptographic

More information

Image courtesy of DICE. The Graphics Pipeline

Image courtesy of DICE. The Graphics Pipeline Image courtesy of DICE The Graphics Pipeline What do we want? Computer-generated imagery (CGI) in real-time. Computationally extremely demanding Full HD at 60 Hz: 1920 1080 60 Hz = 124 Mpx/s And that s

More information

GeForce3: Lightspeed Memory Architecture

GeForce3: Lightspeed Memory Architecture GeForce3: Lightspeed Memory Architecture GeForce3: Lightspeed Memory Architecture Creating a real-time realistic 3D environment on a mainstream PC is the driving ambition of thousands of hardware and software

More information

Spring 2011 Prof. Hyesoon Kim

Spring 2011 Prof. Hyesoon Kim Spring 2011 Prof. Hyesoon Kim Application Geometry Rasterizer Frame Buffer Fixed pipeline processor More and more CISC style processors OpenGL API~= One instruction Programmable parallel processors Scatter/Gather

More information

Understanding the graphics pipeline. Lecture 2 Original Slides by: Suresh Venkatasubramanian Updates by Joseph Kider

Understanding the graphics pipeline. Lecture 2 Original Slides by: Suresh Venkatasubramanian Updates by Joseph Kider Understanding the graphics pipeline Lecture 2 Original Slides by: Suresh Venkatasubramanian Updates by Joseph Kider Lecture Outline A historical perspective on the graphics pipeline Dimensions of innovation.

More information

InfiniteReality TM Graphics Power Through Complexity

InfiniteReality TM Graphics Power Through Complexity InfiniteReality TM Graphics Power Through Complexity John Montrym Brian McClendon Advanced Systems Division 1 Outline Goals Architecture Performance Verification Project Statistics 2 Goals Major Application

More information

3D Graphics for Embedded Systems

3D Graphics for Embedded Systems EuroGraphics Italian Chapter Catania, Feb 24 th 2006 3D Graphics for Embedded Systems From standards, through R&D to applicable innovations Massimiliano Barone Imaging, Rendering, Human Machine Interaction

More information

Evolution of the Programmable Graphics Pipeline

Evolution of the Programmable Graphics Pipeline Administrivia Evolution of the Patrick Cozzi University of Pennsylvania CIS 565 - Spring 2011 Tip: google cis 565 Slides posted before each class Tentative assignment dates on website 1 st assignment handed

More information

Programmable graphics pipeline. Adapted from Suresh Venkatasubramanian UPenn

Programmable graphics pipeline. Adapted from Suresh Venkatasubramanian UPenn Programmable graphics pipeline Adapted from Suresh Venkatasubramanian UPenn Lecture Outline A historical perspective on the graphics pipeline Dimensions of innovation. Where we are today Fixed-function

More information

The Graphics Pipeline

The Graphics Pipeline Announcements The Graphics Pipeline Homework 3 due 02/27 Project kickoff 02/27 Patrick Cozzi University of Pennsylvania CIS 565 - Spring 2012 Course Contents Agenda Mobile Brief Graphics Review Graphics

More information

GPU Architecture. Michael Doggett ATI

GPU Architecture. Michael Doggett ATI GPU Architecture Michael Doggett ATI GPU Architecture RADEON X1800/X1900 Microsoft s XBOX360 Xenos GPU GPU research areas ATI - Driving the Visual Experience Everywhere Products from cell phones to super

More information

Recent Trends. GPU Computation Strategies & Tricks. ...but Bandwidth is Expensive. Compute is Cheap. Optimizing for GPUs. Compute vs.

Recent Trends. GPU Computation Strategies & Tricks. ...but Bandwidth is Expensive. Compute is Cheap. Optimizing for GPUs. Compute vs. Recent Trends GPU Computation Strategies & Tricks Ian Buck NVIDIA 2 Compute is Cheap...but Bandwidth is Expensive parallelism to keep 100s of ALUs per chip busy shading is highly parallel millions of fragments

More information

Recent Advances and Future Trends in Graphics Hardware. Michael Doggett Architect November 23, 2005

Recent Advances and Future Trends in Graphics Hardware. Michael Doggett Architect November 23, 2005 Recent Advances and Future Trends in Graphics Hardware Michael Doggett Architect November 23, 2005 Overview XBOX360 GPU : Xenos Rendering performance GPU architecture Unified shader Memory Export Texture/Vertex

More information

GPGPU Computing. Yong Cao

GPGPU Computing. Yong Cao GPGPU Computing Yong Cao Why Graphics Card? It s powerful! A quiet trend Copyright 2009 by Yong Cao Why Graphics Card? It s powerful! Processor Processing Units FLOPs per Unit Clock Speed Processing Power

More information

Computer Graphics Rendering Pipeline

Computer Graphics Rendering Pipeline Computer Graphics Rendering Pipeline Univ.-Prof. Dr. Matthias Harders Summer semester 2015 Content Rendering process Graphics pipeline Application programming interfaces Shader programming 1 1 Computer-Generated

More information

Shader Model 3.0. Ashu Rege. NVIDIA Developer Technology Group

Shader Model 3.0. Ashu Rege. NVIDIA Developer Technology Group Shader Model 3.0 Ashu Rege NVIDIA Developer Technology Group Talk Outline Quick Intro GeForce 6 Series (NV4X family) New Vertex Shader Features Vertex Texture Fetch Longer Programs and Dynamic Flow Control

More information

OpenGL and the graphics pipeline

OpenGL and the graphics pipeline OpenGL and the graphics pipeline COSC342 Lecture 21 17 May 2016 Jim Clark and the founding of SGI Jim Clark s PhD is from Utah. Invented the geometry engine while at Stanford. Founded SGI in 1982 Iris

More information

Interface feeds and speeds. 3D Buzzwords. Bandwidth Gravity of Modern Computer Systems

Interface feeds and speeds. 3D Buzzwords. Bandwidth Gravity of Modern Computer Systems Bandwidth Gravity of Modern Computer Systems Lecture 8: GPU Architectures Prof. Aaron Lanterman School of Electrical and Computer Engineering Georgia Institute of Technology The bandwidth between key components

More information

Optimizing the Graphics Pipeline. Cem Cebenoyan and Matthias Wloka

Optimizing the Graphics Pipeline. Cem Cebenoyan and Matthias Wloka Optimizing the Graphics Pipeline Cem Cebenoyan and Matthias Wloka Overview CPU application driver GPU potential bottlenecks The bottleneck determines overall throughput In general, the bottleneck varies

More information

GPU Architecture Overview. John Owens UC Davis

GPU Architecture Overview. John Owens UC Davis GPU Architecture Overview John Owens UC Davis The Right-Hand Turn [H&P Figure 1.1] Why? [Architecture Reasons] ILP increasingly difficult to extract from instruction stream Control hardware dominates µprocessors

More information

Graphics Cards and Graphics Processing Units. Ben Johnstone Russ Martin November 15, 2011

Graphics Cards and Graphics Processing Units. Ben Johnstone Russ Martin November 15, 2011 Graphics Cards and Graphics Processing Units Ben Johnstone Russ Martin November 15, 2011 Contents Graphics Processing Units (GPUs) Graphics Pipeline Architectures 8800-GTX200 Fermi Cayman Performance Analysis

More information

Chapter 11. NVIDIA Shading. Mark Kilgard

Chapter 11. NVIDIA Shading. Mark Kilgard Chapter 11. NVIDIA Shading Mark Kilgard Chapter 11: NVIDIA Shading Mark J. Kilgard NVIDIA Corporation Austin, Texas This chapter provides details about NVIDIA s GPU hardware architecture and API support.

More information

Data Storage and Transfer in OpenGL. Kurt Akeley NVIDIA Corporation NVIDIA U Presentation, 25 July 2003

Data Storage and Transfer in OpenGL. Kurt Akeley NVIDIA Corporation NVIDIA U Presentation, 25 July 2003 Data Storage and Transfer in OpenGL Kurt Akeley NVIDIA Corporation NVIDIA U Presentation, 25 July 2003 Outline Data movement is the issue Memory types Design examples Buffer objects Superbuffers (in process)

More information

GPUs: Doing More Than Just Games. Mark Gahagan CSE 141 November 29, 2012

GPUs: Doing More Than Just Games. Mark Gahagan CSE 141 November 29, 2012 GPUs: Doing More Than Just Games Mark Gahagan CSE 141 November 29, 2012 Outline Introduction: Why multicore at all? Background: What is a GPU? Quick Look: Warps and Threads (SIMD) NVIDIA Tesla: The First

More information

Lecture 1 Computer Graphics Hardware

Lecture 1 Computer Graphics Hardware Lecture 1 Computer Graphics Hardware Basic graphics hardware Display devices Video controller Memory CPU System bus CG show /http://www.youtube.com/watch?v=ligways5urw&feature=related 1 Display Devices

More information

Programming Graphics Hardware. Randy Fernando, Cyril Zeller

Programming Graphics Hardware. Randy Fernando, Cyril Zeller Randy Fernando, Cyril Zeller Overview of the Tutorial 10:45 Introduction to the Hardware Graphics Pipeline Cyril Zeller 12:00 Lunch 14:00 High-Level Shading Languages Randy Fernando 15:15 break 15:45 GPU

More information

Implementation of a 3D Graphics Rasterizer with Texture and Slim Shader on FPGA

Implementation of a 3D Graphics Rasterizer with Texture and Slim Shader on FPGA Research Inventy: International Journal Of Engineering And Science Vol.2, Issue 8 (March 2013), Pp 01-05 Issn(e): 2278-4721, Issn(p):2319-6483, Www.Researchinventy.Com Implementation of a 3D Graphics Rasterizer

More information

sequence of operations to generate an image using objectorder

sequence of operations to generate an image using objectorder graphics pipeline 1 graphics pipeline sequence of operations to generate an image using objectorder processing primitives processed one-at-a-time software pipeline: e.g. Renderman high-quality and efficiency

More information

Maximizing OpenGL Performance for GPUs

Maximizing OpenGL Performance for GPUs GDC Tutorial: Advanced OpenGL Game Development Maximizing OpenGL Performance for GPUs March 8, 2000 John F. Spitzer john.spitzer@nvidia.com Developer Relations Engineer NVIDIA Corporation Potential Bottlenecks

More information

Klaus Mueller, Wei Xu, Ziyi Zheng Fang Xu

Klaus Mueller, Wei Xu, Ziyi Zheng Fang Xu MIC-GPU: High-Performance Computing for Medical Imaging on Programmable Graphics Hardware (GPUs) Entertainment Graphics: Virtual Realism for the Masses Computer games need to have: realistic appearance

More information

Interactive Computer Graphics

Interactive Computer Graphics Interactive Computer Graphics Polygon Pipeline Prof. Dr. Marc Erich Latoschik Dipl.-Inform. Dennis Wiebusch Chair of Human-Computer Interaction Julius Maximilian University Würzburg April 28, 2015 Interactive

More information

Fermi GF100 Graphics Processing Unit (GPU) Craig M. Wittenbrink, Emmett Kilgariff, Arjun Prabhu

Fermi GF100 Graphics Processing Unit (GPU) Craig M. Wittenbrink, Emmett Kilgariff, Arjun Prabhu Fermi GF100 Graphics Processing Unit (GPU) Craig M. Wittenbrink, Emmett Kilgariff, Arjun Prabhu Acknowledgements We would like to thank Jonah Alben, John Robinson, Mark Daly, Henry Moreton, and the entire

More information

Xbox 360 GPU and Radeon HD Michael Doggett Principal Member of Technical Staff Marlborough, Massachusetts October 29, 2007

Xbox 360 GPU and Radeon HD Michael Doggett Principal Member of Technical Staff Marlborough, Massachusetts October 29, 2007 Xbox 360 GPU and Radeon HD 2900 Michael Doggett Principal Member of Technical Staff Marlborough, Massachusetts October 29, 2007 Overview Introduction to 3D Graphics Xbox 360 GPU Radeon 2900 Pipeline Blocks

More information

Radeon HD Michael Doggett

Radeon HD Michael Doggett Radeon HD 2900 Michael Doggett August 5, 2007 Overview Starting Point Requirements Top level Pipeline Blocks from top to bottom Command Processor Shader Setup Engine Ultra Threaded Dispatch Processor ShaderCore

More information

Image Processing and Computer Graphics. Rendering Pipeline. Matthias Teschner. Computer Science Department University of Freiburg

Image Processing and Computer Graphics. Rendering Pipeline. Matthias Teschner. Computer Science Department University of Freiburg Image Processing and Computer Graphics Rendering Pipeline Matthias Teschner Computer Science Department University of Freiburg Outline introduction rendering pipeline vertex processing primitive processing

More information

Overview. ITCS 4010/5010:Game Engine Design 1 Pipeline Optimization

Overview. ITCS 4010/5010:Game Engine Design 1 Pipeline Optimization Overview Locating the bottleneck Performance measurements Optimizations Balancing the pipeline Other optimizations: multi-processing, parallel processing ITCS 4010/5010:Game Engine Design 1 Pipeline Optimization

More information

OpenGL Performance Tuning

OpenGL Performance Tuning OpenGL Performance Tuning Evan Hart ATI Pipeline slides courtesy John Spitzer - NVIDIA Overview What to look for in tuning How it relates to the graphics pipeline Modern areas of interest Vertex Buffer

More information

CS130 : Computer Graphics Lecture 2: Graphics Pipeline. Tamar Shinar Computer Science & Engineering UC Riverside

CS130 : Computer Graphics Lecture 2: Graphics Pipeline. Tamar Shinar Computer Science & Engineering UC Riverside CS130 : Computer Graphics Lecture 2: Graphics Pipeline Tamar Shinar Computer Science & Engineering UC Riverside Raster Devices and Images Raster Devices Raster Display Hearn, Baker, Carithers virtually

More information

Lecture 5: The Graphics Pipeline

Lecture 5: The Graphics Pipeline CSE 690: GPGPU Lecture 5: The Graphics Pipeline Klaus Mueller Computer Science, Stony Brook University adapted from: Suresh Venkatasubramanian, U Penn The Fixed Function Pipeline GPU Command & Data Stream

More information

Siddharth Deokar Graduate Research Student Department of Computer Science University of Minnesota Duluth. Advised by Pete Willemsen

Siddharth Deokar Graduate Research Student Department of Computer Science University of Minnesota Duluth. Advised by Pete Willemsen Siddharth Deokar Graduate Research Student Department of Computer Science University of Minnesota Duluth Advised by Pete Willemsen May 22, 2009 Outline Problem Overview Background System Overview Sorting

More information

GPU vs. CPU Rasterization. James Doverspike

GPU vs. CPU Rasterization. James Doverspike GPU vs. CPU Rasterization James Doverspike jdovers1@jhu.edu Abstract Today, almost all personal computers rely on GPUs to achieve realtime rendering of complex 3-D scenes. This paper seeks to reevaluate

More information

PowerVR Hardware. Architecture Overview for Developers

PowerVR Hardware. Architecture Overview for Developers Public Imagination Technologies PowerVR Hardware Copyright Imagination Technologies Limited. All Rights Reserved. This publication contains proprietary information which is subject to change without notice

More information

The 3D Graphics Rendering Pipeline

The 3D Graphics Rendering Pipeline The 3D Graphics Rendering Pipeline Animação e Visualização Tridimensional João Madeiras Pereira Which Visualization? Interactive Real-Time Rendering 3D scenes Realism Real-Time Interaction Application

More information

CS 563 Advanced Topics in Computer Graphics Pipeline Optimization. by Mike Schmidt

CS 563 Advanced Topics in Computer Graphics Pipeline Optimization. by Mike Schmidt CS 563 Advanced Topics in Computer Graphics Pipeline Optimization by Mike Schmidt Outline The Assembly Line Pipelines Defined Pipeline Problems The Graphics Pipeline Finding Bottlenecks Bottleneck Stages

More information

Radeon HD 2900 and Geometry Generation. Michael Doggett

Radeon HD 2900 and Geometry Generation. Michael Doggett Radeon HD 2900 and Geometry Generation Michael Doggett September 11, 2007 Overview Introduction to 3D Graphics Radeon 2900 Starting Point Requirements Top level Pipeline Blocks from top to bottom Command

More information

Evolution of the Programmable Graphics Pipeline

Evolution of the Programmable Graphics Pipeline Evolution of the Graphics Pipeline Lecture 2 Original Slides by: Suresh Venkatasubramanian Updates by Joseph Kider Course Roadmap Graphics Pipeline (GLSL) GP (GLSL) Briefly Computing (CUDA, OpenCL) Choose

More information

Visual Computing from Intel

Visual Computing from Intel Larrabee: A Many-Core x86 Architecture for Visual Computing from Intel Prof. Hsien-Hsin Hsin S. Lee School of Electrical and Computer Engineering Georgia Tech Disclaimer: The materials of this presentation

More information

NVIDIA GeForce GTX 580 GPU Datasheet

NVIDIA GeForce GTX 580 GPU Datasheet NVIDIA GeForce GTX 580 GPU Datasheet NVIDIA GeForce GTX 580 GPU Datasheet 3D Graphics Full Microsoft DirectX 11 Shader Model 5.0 support: o NVIDIA PolyMorph Engine with distributed HW tessellation engines

More information

Touchstone -A Fresh Approach to Multimedia for the PC

Touchstone -A Fresh Approach to Multimedia for the PC Touchstone -A Fresh Approach to Multimedia for the PC Emmett Kilgariff Martin Randall Silicon Engineering, Inc Presentation Outline Touchstone Background Chipset Overview Sprite Chip Tiler Chip Compressed

More information

Practical Performance Analysis and Tuning

Practical Performance Analysis and Tuning Practical Performance Analysis and Tuning Ashu Rege and Clint Brewer NVIDIA Developer Technology Group Overview Basic principles in practice Practice identifying the problems (and win prizes) Learn how

More information

Core/Many-Core Architectures and Programming. Prof. Huiyang Zhou

Core/Many-Core Architectures and Programming.  Prof. Huiyang Zhou ST: CDA 6938 Multi-Core/Many Core/Many-Core Architectures and Programming http://csl.cs.ucf.edu/courses/cda6938/ Prof. Huiyang Zhou School of Electrical Engineering and Computer Science University of Central

More information

Glaze3D. Glaze3D. Petri Nordlund. Chief Architect Bitboys Oy.

Glaze3D. Glaze3D. Petri Nordlund. Chief Architect Bitboys Oy. Petri Nordlund Chief Architect (pnord@bitboys.fi) Introduction is a new consumer-level 2D/3D-graphics accelerator chip Fillrate: 1200 million texels / second Designed and developed by, a Finnish 3D-graphics

More information

Introduction to GP-GPUs. Advanced Computer Architectures, Cristina Silvano, Politecnico di Milano 1

Introduction to GP-GPUs. Advanced Computer Architectures, Cristina Silvano, Politecnico di Milano 1 Introduction to GP-GPUs Advanced Computer Architectures, Cristina Silvano, Politecnico di Milano 1 GPU Architectures: How do we reach here? NVIDIA Fermi, 512 Processing Elements (PEs) 2 What Can It Do?

More information

High-Performance Software Rasterization on GPUs. NVIDIA Research

High-Performance Software Rasterization on GPUs. NVIDIA Research High-Performance Software Rasterization on GPUs Samuli Laine Tero Karras NVIDIA Research Graphics and Programmability Graphics pipeline (OpenGL/D3D) Driven by dedicated hardware Executes user code in shaders

More information

Introduction to Computer Graphics

Introduction to Computer Graphics Introduction to Computer Graphics Torsten Möller TASC 8021 778-782-2215 torsten@sfu.ca www.cs.sfu.ca/~torsten Today What is computer graphics? Contents of this course Syllabus Overview of course topics

More information

Shader Model 3.0, Best Practices. Phil Scott Technical Developer Relations, EMEA

Shader Model 3.0, Best Practices. Phil Scott Technical Developer Relations, EMEA Shader Model 3.0, Best Practices Phil Scott Technical Developer Relations, EMEA Overview Short Pipeline Overview CPU Bound new optimization opportunities Obscure bits of the pipeline that can trip you

More information

a conservative approach in this proposal. 2 Note that there are several steps and details missing from this description but for the purposes of this

a conservative approach in this proposal. 2 Note that there are several steps and details missing from this description but for the purposes of this 3.0 Graphics Processing Units (GPU) Today s commodity graphics cards are built upon a programmable, data parallel architecture that in many cases is capable of out-performing the CPU in computational rates.

More information

CS 563 Advanced Topics in Computer Graphics Chapter 15: Graphics Hardware. by Dan Adams

CS 563 Advanced Topics in Computer Graphics Chapter 15: Graphics Hardware. by Dan Adams CS 563 Advanced Topics in Computer Graphics Chapter 15: Graphics Hardware by Dan Adams Topics Buffers Color, Z, W, Stereo, Stencil, and Accumulation Buffers Hardware Architecture Pipelining and Parallelization

More information

Graphics Pipeline. Rendering Operations: Clipping, Rasterization, & Hidden Surface Removal

Graphics Pipeline. Rendering Operations: Clipping, Rasterization, & Hidden Surface Removal Graphics Pipeline Rendering Operations: Clipping, Rasterization, & Hidden Surface Removal Adapted from 3D Computer Graphics by Alan Watt Third Edition, Pearson Education Limited, 2000 1 Graphics Pipeline

More information

Models and Architectures

Models and Architectures Models and Architectures 1 Objectives Learn the basic design of a graphics system Examine software components for an interactive graphics system Introduce pipeline architecture 2 The pen-plotter model

More information

NVIDIA S TEGRA K1 SYSTEM-ON-CHIP. Michael Ditty, Tegra Architecture Co-authors: John Montrym, Craig Wittenbrink

NVIDIA S TEGRA K1 SYSTEM-ON-CHIP. Michael Ditty, Tegra Architecture Co-authors: John Montrym, Craig Wittenbrink NVIDIA S TEGRA K1 SYSTEM-ON-CHIP Michael Ditty, Tegra Architecture Co-authors: John Montrym, Craig Wittenbrink Tegra K1 Kepler Battery Saver Core GPU CPU Kepler GPU (192 CUDA Cores) Open GL 4.4, OpenGL

More information

Fast Computation of Database Operations using Graphics Processors

Fast Computation of Database Operations using Graphics Processors Fast Computation of Database Operations using Graphics Processors Naga K. Govindaraju Brandon Lloyd Wei Wang Ming Lin Dinesh Manocha University of North Carolina at Chapel Hill {naga, blloyd, weiwang,

More information

CS 450: COMPUTER GRAPHICS THE GRAPHICS PIPELINE SPRING 2016 DR. MICHAEL J. REALE

CS 450: COMPUTER GRAPHICS THE GRAPHICS PIPELINE SPRING 2016 DR. MICHAEL J. REALE CS 450: COMPUTER GRAPHICS THE GRAPHICS PIPELINE SPRING 2016 DR. MICHAEL J. REALE GRAPHICS PIPELINE We ve got this and we want this Graphics pipeline Generates (or renders) a 2D image given a 3D scene of

More information

Introduction to GPGPU. Tiziano Diamanti t.diamanti@cineca.it

Introduction to GPGPU. Tiziano Diamanti t.diamanti@cineca.it t.diamanti@cineca.it Agenda From GPUs to GPGPUs GPGPU architecture CUDA programming model Perspective projection Vectors that connect the vanishing point to every point of the 3D model will intersecate

More information

The Graphics Pipeline

The Graphics Pipeline The Graphics Pipeline Topics 1. Defining graphics architectures 2. The graphics pipeline 3. Computation and bandwidth requirements 1 Papers Required 1. The design of the OpenGL graphics interface, M. Segal

More information

Computer Graphics and GPGPU Programming

Computer Graphics and GPGPU Programming Computer Graphics and GPGPU Programming Donato D Ambrosio Department of Mathematics and Computer Science and Center of Excellence for High Performace Computing Cubo 22B, University of Calabria, Rende 87036,

More information

Part I: Graphics Pipeline

Part I: Graphics Pipeline About Me Analytical Graphics, Inc. An Introduction to GPUs and WebGL n A few videos Patrick Cozzi @pjcozzi pjcozzi@siggraph.org Analytical Graphics, Inc. University of Pennsylvania See http://www.seas.upenn.edu/~pcozzi/

More information

Overview. Technology Details

Overview. Technology Details Overview D/AVE HD is an evolution in the D/AVE family supporting high quality 2D rendering and basic 3D rendering for displays up to 4K x 4K. Targeting modern graphics applications on high resolution displays

More information

The Graphics Pipeline. CS2150 Anthony Jones

The Graphics Pipeline. CS2150 Anthony Jones The Graphics Pipeline CS2150 Anthony Jones Introduction What is this lecture about? The graphics pipeline as a whole With examples from the video games industry Definition The sequence of steps that are

More information

3D Graphics Hardware Graphics II Spring 1999

3D Graphics Hardware Graphics II Spring 1999 3D Graphics Hardware 15-463 Graphics II Spring 1999 Topics Graphics Architecture Uniprocessor Acceleration Front-End Multiprocessing Pipelined Parallel Back-End Multiprocessing Pipelined Parallel Graphics

More information

LU-GPU: Efficient Algorithms for Solving Dense Linear Systems on Graphics Hardware

LU-GPU: Efficient Algorithms for Solving Dense Linear Systems on Graphics Hardware LU-GPU: Efficient Algorithms for Solving Dense Linear Systems on Graphics Hardware Nico Galoppo, Naga K. Govindaraju, Michael Henson, Dinesh Manocha http://gamma.cs.unc.edu/lu-gpu Goals Demonstrate advantages

More information

Open GL and Graphics Hardware

Open GL and Graphics Hardware Open GL and Graphics Hardware Overview of OpenGL Pipeline Architecture Alternatives How many of you have programmed in OpenGL? How extensively? 2 What is OpenGL? A low-level graphics API for 2D and 3D

More information

CS230 : Computer Graphics Lecture 8. Tamar Shinar Computer Science & Engineering UC Riverside

CS230 : Computer Graphics Lecture 8. Tamar Shinar Computer Science & Engineering UC Riverside CS230 : Computer Graphics Lecture 8 Tamar Shinar Computer Science & Engineering UC Riverside 3D graphics pipeline Vertices Vertex processor Clipper and primitive assembler Rasterizer Fragment processor

More information

G8x Hardware Architecture

G8x Hardware Architecture G8x Hardware Architecture 1 G80 Architecture First DirectX 10 compatible GPU Unified shader architecture Scalar processors Includes new hardware features designed for general purpose computation shared

More information

Graphics Pipeline & APIs

Graphics Pipeline & APIs Graphics Pipeline & APIs One person prepares Xmas cards: Pipelines fold write pack fold write pack glclear (GL_COLOR_BUFFER_BIT GL_DEPTH_BUFFER_BIT); glpushmatrix (); gltranslatef (-0.15, -0.15, solidz);

More information

Computer Graphics I - An Overview -

Computer Graphics I - An Overview - Computer Graphics I - An Overview - Sandro Spina Computer Graphics and Simulation Group Computer Science Department University of Malta 1 Welcome The course is being organised by CGSG. Course Outline :

More information

Image Synthesis. Transparency. computer graphics & visualization

Image Synthesis. Transparency. computer graphics & visualization Image Synthesis Transparency Inter-Object realism Covers different kinds of interactions between objects Increasing realism in the scene Relationships between objects easier to understand Shadows, Reflections,

More information

L20: GPU Architecture and Models

L20: GPU Architecture and Models L20: GPU Architecture and Models scribe(s): Abdul Khalifa 20.1 Overview GPUs (Graphics Processing Units) are large parallel structure of processing cores capable of rendering graphics efficiently on displays.

More information

Software Rasterization on GPUs. NVIDIA Research

Software Rasterization on GPUs. NVIDIA Research Software Rasterization on GPUs Samuli Laine Jacopo Pantaleoni NVIDIA Research Outline Rasterization Laine, Karras: High-Performance Software Rasterization on GPUs. Proceedings of High-Performance Graphics

More information

GPUs Under the Hood. Prof. Aaron Lanterman School of Electrical and Computer Engineering Georgia Institute of Technology

GPUs Under the Hood. Prof. Aaron Lanterman School of Electrical and Computer Engineering Georgia Institute of Technology GPUs Under the Hood Prof. Aaron Lanterman School of Electrical and Computer Engineering Georgia Institute of Technology Bandwidth Gravity of modern computer systems The bandwidth between key components

More information

Next-Gen Tile-Based GPUs. Maurice Ribble

Next-Gen Tile-Based GPUs. Maurice Ribble Next-Gen Tile-Based GPUs Maurice Ribble The Agenda Introduction to tile based rendering Tiling is most common in mobile systems List of common tiling hardware features Resolves Explanation of the different

More information

CS148: Introduction to Computer Graphics and Imaging Programmable Graphics Pipelines. Topics

CS148: Introduction to Computer Graphics and Imaging Programmable Graphics Pipelines. Topics CS148: Introduction to Computer Graphics and Imaging Programmable Graphics Pipelines Topics The fixed-function graphics pipeline Programmable stages Vertex shaders Fragment shaders GL shading language

More information

Computer Graphics (CS 543) Lecture 1 (Part 1): Introduction to Computer Graphics

Computer Graphics (CS 543) Lecture 1 (Part 1): Introduction to Computer Graphics Computer Graphics (CS 543) Lecture 1 (Part 1): Introduction to Computer Graphics Prof Emmanuel Agu Computer Science Dept. Worcester Polytechnic Institute (WPI) What is Computer Graphics (CG)? Computer

More information

Basics of GPU-Based Programming

Basics of GPU-Based Programming Institute of Visualization and Interactive Systems University of Stuttgart IEEE Visualization 2004 Tutorial: Interactive Texture-Based Flow Visualization Overview Rendering pipeline on current GPUs Low-level

More information

Computer Graphics Hardware Acceleration for Embedded Level Systems. Topics

Computer Graphics Hardware Acceleration for Embedded Level Systems. Topics Computer Graphics Hardware Acceleration for Embedded Level Systems Brian Murray 02-15-2002 Why? Topics Introduction to Computer Graphics Object Representation Object Rasterization Graphics Hardware Goals

More information

DirectX 11. Introduction

DirectX 11. Introduction DirectX 11 Introduction Origins Prior to DirectX, game makers were struggling with hardware incompatibilities, making it almost impossible for everyone to enjoy the same games. As the industry faced the

More information

Memory: Xbox 360 vs. Playstation 3. Xbox 360 high-level architecture. Xbox 360 s Xenon vs. Playstation 3 s Cell 10/29/09

Memory: Xbox 360 vs. Playstation 3. Xbox 360 high-level architecture. Xbox 360 s Xenon vs. Playstation 3 s Cell 10/29/09 10/29/09 Memory: Xbox 360 vs. Playstation 3 Xbox 360-512 MB, 700 MHz, GDDR3, shared by CPU and GPU CPU accesses memory through the GPU! GPU has 10 MB RAM embedded frame buffer Architectural Comparison:

More information

The OpenGL Rendering Pipeline

The OpenGL Rendering Pipeline The OpenGL Rendering Pipeline The Rendering Pipeline The process to generate two-dimensional images from given virtual cameras and 3D objects The pipeline stages implement various core graphics rendering

More information

Technical Brief. The GeForce 6 Series of GPUs: High Performance and Quality for Complex Image Effects

Technical Brief. The GeForce 6 Series of GPUs: High Performance and Quality for Complex Image Effects Technical Brief The GeForce 6 Series of GPUs: High Performance and Quality for Complex Image Effects Richer, More Vibrant Images in the GeForce 6 Series The NVIDIA GeForce 6 Series of graphics processing

More information

GPU Physics. Mark Harris NVIDIA Developer Technology

GPU Physics. Mark Harris NVIDIA Developer Technology GPU Physics Mark Harris NVIDIA Developer Technology Game Physics Enhance game experience through simulation Simulate objects and interactions between them Rigid bodies, particles, rag dolls, cloth, fluids,

More information

GPU Physics. Simon Green NVIDIA Developer Technology

GPU Physics. Simon Green NVIDIA Developer Technology GPU Physics Simon Green NVIDIA Developer Technology What is Game Physics? Enhances game experience by simulating the motion of objects based on the laws of physics Simulates objects and interactions between

More information

Clever Shader Tricks. Nick Thibieroz European Developer Relations v2.1

Clever Shader Tricks. Nick Thibieroz European Developer Relations v2.1 Clever Shader Tricks Nick Thibieroz European Developer Relations MrT@ati.com v2.1 Introduction Harnessing the power of dynamic flow control The power of maths Skyboxes Understanding Z Harnessing the Power

More information

Optimizing the Graphics Pipeline

Optimizing the Graphics Pipeline Optimizing the Graphics Pipeline Matthias M Wloka Overview Underlying principles Identify the problems Learn how to fix the problems Questions and Answers Performance Lore CPU and GPU: Dual-Processor System

More information

The Computer Graphics Pipeline

The Computer Graphics Pipeline The Computer Graphics Pipeline vertices Vertex Processor Clipper and Assembler Rasterizer Fragment Processor pixels Programmable vs. Fixed Function Pipeline SIMD ECS 175 Chapter 2: The Computer Graphics

More information