Kiek Kainuoja GigaFlopas? arba Trimačio Vaizdo Spartintuvai

Slides:



Advertisements
Similar presentations
COMPUTER GRAPHICS SOFTWARE.
Advertisements

Kayvon Fatahalian, Jeremy Sugerman, Pat Hanrahan
Understanding the graphics pipeline Lecture 2 Original Slides by: Suresh Venkatasubramanian Updates by Joseph Kider.
Status – Week 257 Victor Moya. Summary GPU interface. GPU interface. GPU state. GPU state. API/Driver State. API/Driver State. Driver/CPU Proxy. Driver/CPU.
Interactive Deformation and Visualization of Level-Set Surfaces Using Graphics Hardware Aaron Lefohn Joe Kniss Charles Hansen Ross Whitaker Aaron Lefohn.
Brook for GPUs Ian Buck, Tim Foley, Daniel Horn, Jeremy Sugerman, Kayvon Fatahalian, Mike Houston, Pat Hanrahan Stanford University DARPA Site Visit, UNC.
Status – Week 259 Victor Moya. Summary OpenGL Traces. OpenGL Traces. DirectX Traces. DirectX Traces. Proxy CPU. Proxy CPU. Command Processor. Command.
3D Graphics Processor Architecture Victor Moya. PhD Project Research on architecture improvements for future Graphic Processor Units (GPUs). Research.
Shadow Volumes on Programmable Graphics Hardware Speaker: Alvin Date: 2003/11/3 EUROGRAPHICS 2003.
Interactive, GPU-Based Level Sets for 3D Segmentation Aaron Lefohn Joshua Cates Ross Whitaker University of Utah Aaron Lefohn Joshua Cates Ross Whitaker.
IN4151 Introduction 3D graphics 1 Introduction to 3D computer graphics part 2 Viewing pipeline Multi-processor implementation GPU architecture GPU algorithms.
GPU Simulator Victor Moya. Summary Rendering pipeline for 3D graphics. Rendering pipeline for 3D graphics. Graphic Processors. Graphic Processors. GPU.
ATI GPUs and Graphics APIs Mark Segal. ATI Hardware X1K series 8 SIMD vertex engines, 16 SIMD fragment (pixel) engines 3-component vector + scalar ALUs.
Evolution of the Programmable Graphics Pipeline Patrick Cozzi University of Pennsylvania CIS Spring 2011.
Status – Week 283 Victor Moya. 3D Graphics Pipeline Akeley & Hanrahan course. Akeley & Hanrahan course. Fixed vs Programmable. Fixed vs Programmable.
Vertex & Pixel Shaders CPS124 – Computer Graphics Ferdinand Schober.
Status – Week 260 Victor Moya. Summary shSim. shSim. GPU design. GPU design. Future Work. Future Work. Rumors and News. Rumors and News. Imagine. Imagine.
GPU Tutorial 이윤진 Computer Game 2007 가을 2007 년 11 월 다섯째 주, 12 월 첫째 주.
GPU Graphics Processing Unit. Graphics Pipeline Scene Transformations Lighting & Shading ViewingTransformations Rasterization GPUs evolved as hardware.
Desktop with Direct3D 10 capable hardware Laptop with Direct3D 10 capable hardware Direct3D 9 capable hardware Older or no graphics hardware.
Interactive Visualization of Volumetric Data on Consumer PC Hardware: Introduction Daniel Weiskopf Graphics Hardware Trends Faster development than Moore’s.
Background image by chromosphere.deviantart.com Fella in following slides by devart.deviantart.com DM2336 Programming hardware shaders Dioselin Gonzalez.
Ray Tracing and Photon Mapping on GPUs Tim PurcellStanford / NVIDIA.
REAL-TIME VOLUME GRAPHICS Christof Rezk Salama Computer Graphics and Multimedia Group, University of Siegen, Germany Eurographics 2006 Real-Time Volume.
Performance and Energy Efficiency of GPUs and FPGAs
Introduction to Hardware. What is binary? We use the decimal (base 10) number system Binary is the base 2 number system Ten different numbers are used.
Computationally Efficient Histopathological Image Analysis: Use of GPUs for Classification of Stromal Development Olcay Sertel 1,2, Antonio Ruiz 3, Umit.
Computer Graphics Graphics Hardware
GPUs and Accelerators Jonathan Coens Lawrence Tan Yanlin Li.
GPU Shading and Rendering Shading Technology 8:30 Introduction (:30–Olano) 9:00 Direct3D 10 (:45–Blythe) Languages, Systems and Demos 10:30 RapidMind.
Interactive Time-Dependent Tone Mapping Using Programmable Graphics Hardware Nolan GoodnightGreg HumphreysCliff WoolleyRui Wang University of Virginia.
Cg Programming Mapping Computational Concepts to GPUs.
1 SIC / CoC / Georgia Tech MAGIC Lab Rossignac GPU  Precision, Power, Programmability –CPU: x60/decade, 6 GFLOPS,
CSE 690: GPGPU Lecture 7: Matrix Multiplications Klaus Mueller Computer Science, Stony Brook University.
Tone Mapping on GPUs Cliff Woolley University of Virginia Slides courtesy Nolan Goodnight.
A Closer Look At GPUs By Kayvon Fatahalian and Mike Houston Presented by Richard Stocker.
Jie Chen. 30 Multi-Processors each contains 8 cores at 1.4 GHz 4GB GDDR3 memory offers ~100GB/s memory bandwidth.
Xbox MB system memory IBM 3-way symmetric core processor ATI GPU with embedded EDRAM 12x DVD Optional Hard disk.
A Neural Network Implementation on the GPU By Sean M. O’Connell CSC 7333 Spring 2008.
May 8, 2007Farid Harhad and Alaa Shams CS7080 Overview of the GPU Architecture CS7080 Final Class Project Supervised by: Dr. Elias Khalaf By: Farid Harhad.
Introduction to Hardware. What is binary? We use the decimal (base 10) number system Binary is the base 2 number system Ten different numbers are used.
Sony PlayStation 3 Sony also laid out the technical specs of the device. The PlayStation 3 will feature the much-vaunted Cell processor, which will run.
GPUs – Graphics Processing Units Applications in Graphics Processing and Beyond COSC 3P93 – Parallel ComputingMatt Peskett.
Hardware Requirements for Different Gaming Platforms.
Debunking the 100X GPU vs. CPU Myth An Evaluation of Throughput Computing on CPU and GPU Present by Chunyi Victor W Lee, Changkyu Kim, Jatin Chhugani,
Linear Algebra Operators for GPU Implementation of Numerical Algorithms J. Krüger R. Westermann computer graphics & visualization Technical University.
Geometry processing on GPUs Jens Krüger Technische Universität München.
From Turing Machine to Global Illumination Chun-Fa Chang National Taiwan Normal University.
Mapping Computational Concepts to GPUs Mark Harris NVIDIA.
UW EXTENSION CERTIFICATE PROGRAM IN GAME DEVELOPMENT 2 ND QUARTER: ADVANCED GRAPHICS The GPU.
Dynamic Geometry Displacement Jens Krüger Technische Universität München.
Introduction to Hardware. What is binary? We use the decimal (base 10) number system Binary is the base 2 number system Ten different numbers are used.
Postmortem: Deferred Shading in Tabula Rasa Rusty Koonce NCsoft September 15, 2008.
Sobolev(+Node 6, 7) Showcase +K20m GPU Accelerator.
Our Graphics Environment Landscape Rendering. Hardware  CPU  Modern CPUs are multicore processors  User programs can run at the same time as other.
1 Geometry for Game. Geometry Geometry –Position / vertex normals / vertex colors / texture coordinates Topology Topology –Primitive »Lines / triangles.
Computer Graphics Graphics Hardware
GPU Architecture and Its Application
Chapter 1 An overview on Computer Graphics
Video RAM Presented by GHOLAMREZA KAKAMANSHADI
Programmable Pipelines
Chapter 1 An overview on Computer Graphics
Graphics Processing Unit
From Turing Machine to Global Illumination
Understanding Theory and application of 3D
CSC 2231: Parallel Computer Architecture and Programming GPUs
Graphics Processing Unit
Computer Graphics Graphics Hardware
Ray Tracing on Programmable Graphics Hardware
RADEON™ 9700 Architecture and 3D Performance
Presentation transcript:

Kiek Kainuoja GigaFlopas? arba Trimačio Vaizdo Spartintuvai Aras Pranckevičius, IFM-9/1

PC vs 3D spartintuvas 11.2 44.1 (~200) 55 107 64 256 6.4 21.8 1220 P4@2.8GHz 256MB DDR400 R350@380MHz 128MB DDR380 GFLOPS 11.2 44.1 (~200) Tranzistorių, M 55 107 RAM magistralės plotis, bitais 64 256 RAM greitis, GB/s 6.4 21.8 Kaina, Lt 1220 1370 MFLOPS/Lt 9.18 32.19

3D spartintuvas ATi Radeon 9700Pro

Ką daro? Tekstūruoti trikampiai Nieko daugiau! Viršūnių transformacijos Vertex shader Veiksmai kiekvienam vaizduojamam taškui Pixel shader Nieko daugiau!

Architektūra CPU RAM VRAM GPU Monitorius AGP

Veiksmai/duomenys Vertex shader Pixel Konstantos Tekstūros Viršūnės Perspektyva Atkirtimas Trikampiai Interpoliavimas Rasterizacija Pixel Konstantos Alpha testas Z testas Stencil testas Tekstūros Viršūnės

Spartinančios atmintys (kešai) Vertex shader Perspektyva Atkirtimas Trikampiai Interpoliavimas Rasterizacija Pixel Konstantos Alpha testas Z testas Stencil testas Tekstūros Viršūnės

Ypatybės Beveik nėra duomenų priklausomybių Aišku, iš kur skaitoma Aišku, kur rašoma Niekada nerašoma ten, iš kur skaitoma Skaičiavimo programos žinomos iš anksto Tvarkyklės gali jas optimizuoti Superkonvejerizacija Šimtai ir tūkstančiai

Skaičiavimai Daug duomenų su ta pačia programa Single Program Multiple Data Lygiagretūs skaičiavimai Pvz., 4 ar 8 atskiri konvejeriai SIMD 4D vektoriai, arba 3D vektoriai + skaliaras

Viršūnių apdorojimas (R300) Vienu taktu – 9 FLOP SIMD: 4xFMAD Viena sudėtinga operacija (rcp,rsq,log,exp,...) 4 nepriklausomi konvejeriai 32 registrai po 4 float 4*(4*2+1)*400MHz = 14.4 GFLOPS

Fragmentų apdorojimas (R300) Vienu taktu – 10 FLOP SIMD: 4xFMAD Viena sudėtinga operacija (rcp,rsq,log,exp,...) Viena tekstūros adreso operacija 8 nepriklausomi konvejeriai 32 registrai po 4 float (24 bitų) 8*(4*2+1+1)*400MHz = 32.0 GFLOPS

Kitos operacijos Neprogramuojamos (kolkas) Bi/tri-tiesinis filtravimas 56 IOPS * 8 konv * 400MHz = 89.6 GIOPS Trikampių paruošimas/skaidymas Trikampių atributų interpoliavimas

Kur tai dėti Kompiuteriniai žaidimai/grafika Visi jau tai daro Vektoriniai/srautiniai skaičiavimai! Vaizdų apdorojimas Veiksmai su matricomis Skaičiuojamoji geometrija ... ir t.t.

www.gpgpu.org Sparse Matrix Solvers on GPU Interactive 3D Brain Tumor Segmentation Deformation of Level Set Surfaces Fast Fourier Transform on GPU Radiosity on Graphics Hardware Dense Matrix Algebra on GPU Simulation of Cloud Dynamics