Coursehero >>
Pennsylvania >>
UPenn >>
TEACHING 221 Course Hero has millions of student submitted documents similar to the one below including study guides, homework solutions, papers, and exam answer keys.
Short A Introduction to Eviews Note You are responsible to get familiar with Eviews as soon as possible. All homeworks are likely to contain questions for which you will need to use this software package. A dataset to experiment with Eviews is available on Blackboard under Course Documents. Eviews is installed on all computers in the undergraduate computer lab (UDAL) on the first floor of the McNeil building. A Short Introduction to Eviews 2 1 Getting help Please refer to the Eviews handbooks, which are very comprehensive. Of the two handbooks that accompany Eviews, the User's Guide will be the more useful for you. It explains all functions of Eviews step-by-step. (The Command and Programming Reference is useful if you want to write batch programs that perform a sequence of steps automatically.) Both manuals are also available in the Eviews help menu itself (as .pdf). Very helpful is also the searchable help index in the Eviews help menu: Help > Index and Help > Find. The best way of getting a first idea of how Eviews works is to experiment with the commands presented here and to try other commands and options and see what happens. 2 Eviews philosophy You can access most of the Eviews functionality via menus. Just browse through the menus, and find the appropriate command. You will then be guided through several windows that prompt you for the information required to perform the command. EViews organizes data, graphs, output, and so forth, as objects. Each of these objects can be copied, saved, cut-and-pasted into other Windows programs, or used for further analysis. A collection of objects can be saved together in a workfile. Since Eviews creates new objects with everything you do, it makes sense to delete unimportant intermediate results to avoid a messy workfile. Please note that you cannot mix data series of different frequencies (annual, quarterly, monthly, weekly, daily) within the same work file page. 3 Creating a workfile To create a new workfile click File > New > Workfile. If you have quarterly data from the first quarter of 1950 until the last quarter of 2005, then the procedure is: Select: "dated - regular frequency", frequency "quarterly", start date: "1950:1", end date "2005:4". Notice that there are already two series in the workfile: c, and resid. They stand for "coefficients" and "residuals". Every time you estimate something, the coefficients are stored in c and the residuals in resid. A Short Introduction to Eviews 3 4 Importing data into Eviews The are two ways to get your dataset into Eviews. When you have only a few observations, you might want to cut-and-paste data into Eviews or even type it in by hand. To do this, you first need to create a workfile of the desired frequency and start and end date. Then you create a series object within this workfile to hold the data by clicking on Object > New Object > Series on the workfile window. Give the series a beautiful name. Then click on Edit+/-, start entering your data. When your are done, click Edit+/- again. For larger datasets, however, you will probably prefer to use the Eviews import function. 1. First convert your raw data into a format that Eviews understands, such as a text file with e.g. comma separated values, a Lotus file, or an Excel file. If you use Excel, for example, make a file with only one spreadsheet. On that sheet, put each series directly next to each other - be sure to start your data in cell A1. Do not put any titles or names to the columns, but - this is very important - remember what data is in each column! Also you need to remember to beginning and end of your sample. Save this file as ".xls" file. 2. Open Eviews. 3. Create a new workfile with the frequency and start and end date of your data. 4. Import the data: Select File > Import > Read Text-Lotus-Excel. At the bottom of the dialogbox, change "Files of type" to "Excel (*.xls)" so that you can see the file. Then browse to find your data. 5. Then you are asked: Data order: select "by observation", if each series occupies one column; or "by series", if each series occupies one row. Upper-left data cell : write "A1". Names of series: write the name of the series you are importing in the right order, for example rgdp rcons rgov rinv or whatever name you give to the series you are importing. Do not change the import sample period. You should have already selected the correct period when you created the workfile. Do 6. a cross-check with your raw data file. Compare the number of observations, check if each series got the correct name. A Short Introduction to Eviews 4 5 Generating a new variable Click the Genr button on the workfile window and then insert the defining equation of your new variable. For example x growth=log(x)-log(x-1). Note that when you write x(-1), Eviews understands that you want x lagged one period. 6 Generating multiple graphs Suppose you want to make a plot of the four variables rgdp rcons rgov rinv. 1. Select your four variables rgdp rcons rgov rinv by keeping the "Ctrl" key pressed and clicking on the series with your mouse pointer. 2. Right click with the mouse and select Open > As Group. 3. Then click View > Graph > Line on the group window and you are done. If you would like to create multiple separate graphs, use View > Multiple Graphs > Line. 4. To preserve your work, click Freeze on the group window and then in the new graph window click Name and enter the desired graph name. 5. Then play around a bit to understand how to format the graph the way you want. For example, to insert a title click Add Text. To shade a certain time period click Line/Shade and then select Shaded area and enter the time span that you wish to shade. If you want to shade several periods which are not connected, you have to repeat this procedure several times. 7 Running a regression 1. In the command window, which is the white area just below the Eviews menu bar, type ls y c x. y stands for the name you gave to your dependent variable, x for whatever name you gave to your independent variable and c is the constant. ls just means least squares. 2. To modify your estimation, click Estimate on the equation window. There you can modify the estimation equation, the estimation method and the sample period. 3. You can save the output using Freeze on the regression window. A Short Introduction to Eviews 5 4. Again, take some time to check out the available views and regression diagnostics in the View menu of the equation window. 8 8.1 Some more hints Changing the sample period To set the workfile sample, simply click on the Sample button in the workfile window, and enter the range, e.g. 2003Q1 2004Q3. @first @last is also possible. For more information on data manipulation you should consult the Eviews help files. Under Help > Eviews Help Topics > Contents you find the chapters Workfile Basics, Object Basics, Basic Data Handling, Working with Data, Series, Groups, Statistical Graphs from Series and Groups, Graphs, Tables and Text Objects and Basic Regression, which cover the topics of this introduction in much more detail. 8.2 Creating a time dummy One common task in time series analysis is the creation a variable that represents the time trend. Eviews has a time trend variable already built-in. If you type @TREND instead of a series name, then this returns a time trend that increases by one for each observation of the workfile. 8.3 Taking differences Eviews also provides a shortcut to compute the first and second differences. If you type d(x) instead of a series name, it means you want to use the first difference of x. 8.4 Scatter plot of regression To create a scatter diagram of x against y, just type: scat x y. Or, you can make a group containing x and y, and then select View > Graph > Scatter with regression in the group window. A Short Introduction to Eviews 6 8.5 Command window and Quick menu Many actions can be done more quickly in the command window, which is the white window below the menu bar, instead of browsing through the menus. For example, transformations are most easily specified there: Type series lgdp = log(gdp), which generates a new series lgdp, the natural log of gdp. Similarly, to generate a new group consisting of gdp and d(gdp), just type group bothgdp gdp d(gdp). If you don't know the name of the command, often the menu Quick contains the procedure you need. 8.6 Exporting Eviews graphs Eviews generates graphs, but they may not look they way you want them to. In order to use an Eviews graph in another program you can save it as a Windows metafile ("*.wmf"). Click Proc > Save graph to disk in the graph window (you may have to Freeze the graph first). Choose "metafile" for Word, or the ".eps" format otherwise, and choose a file path. The picture can then be imported into a Word document using Insert > Picture > From File in Word.
Find millions of documents here - Study Guides, Homework Solutions, Papers, Exam Answer Keys and more.
Course Hero has millions of course related materials that will enable you to learn better, faster and get an A in all your courses.
Below is a small sample set of documents:
Real_and_Nominal_GDP.ppt
Path: UPenn >> ECON >> 2 Fall, 2008
Description: Real and Nominal GDP 12,000 $ Billion Real and Nominal GDP GDP in Current Dollars Real GDP 10,000 8,000 6,000 4,000 2,000 0 1952 1954 1956 1958 1960 1962 1964 1966 1968 1970 1972 1974 1976 1978 1980 1982 1984 1986 1988 1990 1992 1994 1996 199...
lec9.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Lecture 9: The Evolution Of Military Technology And Tactics (I) 1. Introduction To Part II: The Evolution Of War 2. The Military Revolution 3. The Rise Of The Modern Army 4. The Dawn Of The Offensive Era 5.The Evolution Of The Fire Arm 6. The Evoluti...
lec16.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: LECTURE 16: THE LONG PEACE AND AFTER THE COLD WAR 1. THE LIFE OF THE COLD WAR PHASE I: CONFRONTATION (1947-1962) PHASE II: FROM COEXISTENCE TO DTENTE (1963-1978) PHASE III: FROM RENEWED CONFRONTATION TO RAPPROCHEMENT (1979-91) 4. GADDIS: THE LONG PE...
lec26.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture 27: Tentative Conclusions 1. Levels Of Analysis 2. Interrogating Realism 3. Constants In The International System 4. Changes In The International System 5. Goals Of The Course Course Summary: The Levels Of Analysis 1. SYSTEMIC LEVEL 2. INTE...
lec3.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture 3: Comparing Alternative Explanations 1. What Are Theories And Hypotheses? 2. What Is Correlation? 3. Does Correlation Prove Causation? 4. What Is Operationalization? 5. Does Case Selection Matter? 6. What Is Falsifiability? 7. What Are Neces...
lec17.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Lecture 17: The Economic Rise of the West 1. Introduction 2. The Medieval Economy 3. Population Changes 4. The Rise of Trade 5. Mercantilism 6. The Industrial Revolution 7. Why Europe? 8. Trade in the Modern Era Fall of the Western Roman Empire Spe...
lec12.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Lecture 12: War And Society: The Consequences Of Conflict 1. Physical Destruction 2. The Political Costs: Win, Lose, Or Draw 3. Social Cohesion And War 4. Social Groups A) The Working Class And War B) Women And War C) Minorities And War Physical Des...
lec16.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Lecture 16: Nationalism II: Europe And The Developing World 1. Greenfeld\'s Framework Of Nationalism 2. Greenfeld Case Studies A) England B) France C) Russia 3. Nationalism In The Developing World Greenfeld\'s Framework 1. Definition Nationalism Locat...
lec6.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture #6: Power Transitions, Hegemonic Stability, & Interdependence 1. Power Transition Theory A. Internal Power Transition B. External Crossover Point C. Satisfaction Caveat 2. Hegemonic Stability Theory A. Logic Of Theory B. Empirical Evidence 3....
lec24.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture 24: Intervention 1. Why Do States Intervene In The Affairs Of Others? 2. General Means For Intervening 3. Specific Types Of Intervention 4. Somalia, Rwanda, and Kosovo Why Do States Intervene in the Affairs of Others? 1. Imperialists 2. Con...
lec19.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Lecture 19: Late-Late Industrializers 1. Liberal Theory Versus Dependency Theory 2. The Empirical Record: Who Is Right? 3. The Product Cycle 4. Case Studies A) Chile B) South Korea C) Nigeria Development Strategies 1. What is Mercantilism? 2. Libera...
lec10.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Lecture 10: The Evolution Of Military Technology And Tactics (II) 1. The Evolution Of Naval Technology 2. The Industrialization Of War 3. The Advent Of Nuclear Weapons 4. The Evolution Of Issues 5. Why Europe? The Evolution Of Naval Technology 1. Th...
lec5.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Lecture 5: Empires, City-States, City-Leagues, & The Sovereign State 1. Why Did The Sovereign State Come To Dominate The International System? 2. What Is A State? 3. The State In Comparative Perspective: - Feudalism Versus The Modern State 4. Multipl...
lec11.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Lecture 11: Ideas And War 1. Is War Good Or Bad? 2. Social Darwinism 3. Militarism 4. The Cult Of The Offensive 5. Social Orders: Crossbows And The Cavalry 6. Hegemonic Ideas Social Darwinism Charles Darwin: On The Origins Of Species (1859) What i...
apsr96codebook.doc
Path: UPenn >> APSR >> 96 Fall, 2009
Description: Codebook for apsr.xls (Microsoft Excel file) or apsr.dta (Stata file) The data set was used in Rousseau et al. \"Assessing the Dyadic Nature of the Democratic Peace 1918-88\" which appeared in the in the American Political Science Review (1996). year c...
JCR2002b.txt
Path: UPenn >> JCR >> 2002 Fall, 2009
Description: log using junk.log, replace set more off * File: JCR2002b.txt * Date: * Run: tables for Rousseau 2002 Study #2 * program: Stata 5.0 * set matsize 400 * use Study2.dta * Table 7: * Canada only tab pattern1 * China only tab pattern2 * Table 8: * C...
JCR2002a.txt
Path: UPenn >> JCR >> 2002 Fall, 2009
Description: log using junk.log, replace set more off * File: JCR2002a.txt * Date: * Run: tables for Rousseau 2002 Study #1 * program: Stata 5.0 * set matsize 400 * use Study1.dta * Table 1: tab v7bC if v7b<=5 tab v32bC if v32b<=5 tab v40bC if v40b<=5 tab v1...
robots.txt
Path: UPenn >> PSCI >> 618 Fall, 2009
Description: User-agent: * Disallow: / ...
Krasner1972.pdf
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: ...
MaozRussett1993APSR.pdf
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: ...
Lippmann1950.pdf
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: The Cold War Foreign Affairs; Spring 1987; 65, 4; ABI/INFORM Global pg. 869 Reproduced with permission of the copyright owner. Further reproduction prohibited without permission. Reproduced with permission of the copyright owner. Further reproducti...
lec23.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture 23: Do International Norms And Laws Influence Behavior? 1. Cooperation Via Norms 2. Cooperation Via International Law 3. The World Court 4. Evolving Norms: The Concept Of The Just War 5. The International Criminal Court Cooperation Via Norms...
lec12.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture 12: Bureaucratic And Organizational Politics 1. New Level Of Analysis 2. Review Of Realism 3. Rational Decision Making 4. Bureaucratic Politics 5. Organizational Decision Making 6. Examples From International Relations 7. A Critique Of Alliso...
lec20.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture 20: Nuclear Proliferation 1. Nuclear Proliferation: Definition And History 2. The Non-proliferation Treaty (NPT) And Regime 3. Will Coercive Strategies Work? 4. Is Proliferation Even A Bad Thing? 5. Managed Proliferation Nuclear Proliferatio...
lec24landmines.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Lecture: Landmines 1. Background 2. Military Utility of Landmines 3. Arms Control 5. The Conference on Disarmament 6. The Ottawa Process 7. The Future of Arms Control Anti-Personnel Land Mines Background 1. History of Landmines 2. Types of Landmine...
lec13.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture 13: The Individual Level Of Analysis 1. Rational Decision Making 2. Universal Cognitive Biases 3. Cognitive Dissonance 4. Motivated Bias The Levels Of Analysis 1. SYSTEMIC LEVEL 2. INTER-STATE OR REGIME LEVEL 3. DOMESTIC, STATE, OR SOCIETAL...
lec21.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture 21: The Rise of China 1. Historical Background 2. Power Transition Theory 3. Recent Chinese Growth 4. American-Chinese Relations: Sources of Conflict 5. Regional Stability in Asia 6. Will China Become a Democracy? 7. Student Questions Histor...
lec8.ppt
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Lecture #8: Do Regimes Really Facilitate Cooperation? 1. Liberal Institutionalists: Realists Or Idealists? 2. Student Vote: The Future and Cooperation 3. Relative Gains Versus Absolute Gains 4. Regimes In Action: GATT What Are Institutionalists? ...
lec3.ppt
Path: UPenn >> PSCI >> 252 Fall, 2009
Description: Class #3: Evolution Evolution: Biological vs. Cultural The Evolution of Cooperation Studying Evolution: Computer Simulation The Game of Life Agent-Based Modeling Discussion: Epstein and Axtell Biological Evolution What is evolution? Five Ce...
Exer8.doc
Path: UPenn >> PSCI >> 295 Fall, 2009
Description: Exercise # 8: Cross-Tabs and The World Value Systems (WVS) The WVS data can be used to compare values across countries and across time. Today we will be using a subset of the data for ten countries at one point in time (1993). Given the size of the d...
ParameterDictionarySharedIDsim.doc
Path: UPenn >> JCR >> 2005 Fall, 2009
Description: Shared Identity Simulation Parameter Description By David Rousseau and Maurits van der Veen The simulation model describe in this paper is available for download at www.ssc.upenn.edu/~rousseau/ or www.international-affairs.org. (Look for the Simulati...
Exer4.doc
Path: UPenn >> PSCI >> 295 Fall, 2009
Description: Exercise #4: Cross-Tabs and The General Social Survey (GSS) Puzzle #1: Gun Control 1) Do Americans favor or oppose gun control? 2) Are specific groups of the population more or less likely to support gun control? (e. g., men? educated? blacks? rich? ...
DEBRWAN.DOC
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: Political Science 150: International Relations In Theory and Practice. 10. International Organizations and Law: Ethnic Conflict, State Building, & Military Intervention. #24: Week 14: Wednesday, December 4: 2nd DEBATE: Should the UN have intervened i...
Atkinson.doc
Path: UPenn >> PSCI >> 150 Fall, 2009
Description: This is a two part article: PART I: Copyright 1994 The Washington Post The Washington Post View Related Topics January 30, 1994, Sunday, Final Edition SECTION: FIRST SECTION; PAGE A1 LENGTH: 3302 words HEADLINE: The Raid That Went Wrong; How an Elite...
robots.txt
Path: UPenn >> PSCI >> 295 Fall, 2009
Description: User-agent: * Disallow: / ...
cdb92.txt
Path: UPenn >> VR >> 71403 Fall, 2009
Description: V20429 \'HEAD 91 WAGES \' TLOC= 262- 267 1992 Head\'s Income from Wages and Salaries in 1991 (Questions G13 and G24) % nonzero = 68.3 ...
vicpres1.pdf
Path: UPenn >> VR >> 71403 Fall, 2009
Description: High Dimensional Polynomial Interpolation on Sparse Grids: Smolyaks Algorithm Dirk Krueger University of Pennsylvania and NBER Felix Kubler Stanford University Victors Quantitative Macroeconomics Class University of Pennsylvania, November 25, 2003 ...
grow7_conv.pdf
Path: UPenn >> ECON >> 10204 Fall, 2009
Description: 7 Convergence and the World Income Distribution The Convergence Hypothesis Fact: Enormous variation in incomes per worker across countries Question: Do poor countries eventually catch up? Convergence hypothesis: They do, in the right sense! ...
econ70204_mar1618.pdf
Path: UPenn >> EC >> 70204 Fall, 2009
Description: 1 1.1 March 16-18 Lucas Tree Model We will study Lucas Tree Model (Lucas 19781 ) and look at the things that Finance people talk about. Lucas tree model is a simple but powerful model. 1.1.1 The Model Suppose there is a tree which produces random ...
readdat.txt
Path: UPenn >> VR >> 71403 Fall, 2009
Description: @ This program reads and filters the citibase series @ library pgraph; #include c:\\Mydoc\\pigia\\courses\\econ984\\hp.txt; @ execute procedure for hp filter @ nobs=136; @ number of observations @ nser=4; l=1600; @ smoothing paramet...
assert.ppt
Path: UPenn >> CIT >> 597 Fall, 2009
Description: The assert statement About the assert statement The purpose of the assert statement is to give you a way to catch program errors early The assert statement is new in Java 1.4 The assert statement uses a new keyword, assert The new keyword may br...
rails_and_ajax.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: Rails and Ajax Apr 10, 2009 HTML Forms The <form arguments> . </form> tag encloses form elements (and usually includes other HTML as well) The arguments to form tell what to do with the user input action=\"URL\" method=\"get\" Specifies whe...
Author_Guidelines.pdf
Path: UPenn >> RTAS >> 05 Fall, 2009
Description: Author Guidelines for 8.5 x 11-inch Proceedings Manuscripts Author(s) Name(s) Author Affiliation(s) E-mail Abstract The abstract is to be in fully-justified italicized text, at the top of the left-hand column as it is here, below the author informati...
Hull2VD.pdf
Path: UPenn >> CIS >> 610 Fall, 2009
Description: Visualizing the Connection Among Convex Hull, Voronoi Diagram and Delaunay Triangulation John Fisher Department of Computer Science Michigan Technological University Houghton, MI 499311295, USA E-mail: jnfisher@mtu.edu Abstract The convex hull, Voro...
chw1.pdf
Path: UPenn >> CIS >> 610 Fall, 2009
Description: Mathematics 622 Assignment 1 (Shatz) Due Thursday, October 2, 2003 1 Part A (Easier problemsnot for discussion) AI. If V, W are ane varieties, we have dened a morphism from V to W (here, the sheaves of functions OV , OW are being suppressed in the n...
GMAbiblio.pdf
Path: UPenn >> CIS >> 610 Fall, 2009
Description: This is page 535 Printer: Opaque this References [1] Ralph Abraham and Jerrold E. Marsden. Foundations of Mechanics. Addison-Wesley, second edition, 1978. [2] Lars V. Ahlfors and Leo Sario. Riemann Surfaces. Princeton Math. Series, No. 2. Princeton...
cis61005sl0.ppt
Path: UPenn >> CIS >> 610 Fall, 2009
Description: Manifolds, Lie Groups, Lie Algebras, with Applications Kurt W.A.J.H.Y. Reillag (alias Jean Gallier) CIS610, Spring 2005 1 Motivations and Goals 1. Motivations Observation: Often, the set of all objects having some common properties has some topolog...
tensor.ppt
Path: UPenn >> CIS >> 610 Fall, 2009
Description: Tensors and Component Analysis Musawir Ali Tensor: Generalization of an n-dimensional array Vector: order-1 tensor Order-3 tensor Matrix: order-2 tensor Reshaping Tensors Matrix to vector \"Vectorizing\" a matrix = Reshaping Tensors z Order-3 ...
recitations3.doc
Path: UPenn >> CIS >> 260 Fall, 2008
Description: CIS 260 Recitations 3 Feb 6 Problem 1 (Complete proof of example 11 on page 91) Show that there exist irrational numbers x and y such that x y is rational. First, we remind ourselves what the definition of a rational/irrational number is: A real p nu...
projects.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: CIS 700: Project Suresh Venkatasubramanian 1 Guidelines The idea of this project is to take on a more intricate problem involving computations on the GPU, and demonstrate a plausible, efficient implementation of a particular problem. The problem y...
a2.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: CIS 700/010: Assignment 2 Suresh Venkatasubramanian 1 Problem 1: Matrix Operations (40) 1. Implement a GPU algorithm to add two n n matrices. Use the simple approach that runs in n/b passes. 2. Implement a GPU program for multiplying two dense n ...
class9.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: CIS 700/010 Lecture IX Computational Geometry: Distance Fields Suresh Venkatasubramanian Scribed by IkkJin Ahn 1 Denition Given a set of objects, a distance eld is dened at each point by the smallest distance from the point to the objects. Each ob...
lec7.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: CIS 700/010: Matrix Operations I Suresh Venkatasubramanian Scribed by Kennedy Behrman March 3, 2005 1 Matrix operations There are three basic matrix operations that would be part of any GPU matrix toolkit: 1. The inner product of two vectors c = a...
triantos.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: Graphics From a Systems Perspective Nick Triantos, April 2005 Agenda 1. 2. 3. PC System overview Driver components System challenges Copyright NVIDIA Corporation 2004 2005. All rights reserved. System Overview Pentium/AMD K7 Intel CPU RAM Co...
kider-zhao.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: Fast Normalized Cut for Image Segmentation on the GPU Joseph Kider Liming Zhao University of Pennsylvania Abstract Recent advances in the speed and programmability of graphics hardware permit the GPU to grow as a powerful vector coprocessor to the CP...
milo.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: The Cell Processor: Technological Breakthrough or Yet Another Over-hyped Chip? Prof. Milo Martin for CIS700 Agenda Cell overview PlayStation 2 review More on the Cell (from Peter Hofstee\'s HPCA slides) Programming the Cell (brief) Impact & Speculati...
moravanszky.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: Dense Matrix Algebra on the GPU dm Moravnszky NovodeX AG adam.moravanszky@novodex.com 1. Introduction Perhaps the most important innovation of the latest generation of programmable graphics processors (GPUs) is their capability to work with floating...
sorting-kider.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: GPU as a Parallel Machine: Sorting on the GPU CIS 700/010: 3/17/05 Scribed by Joseph T. Kider Jr. 1 .Background Sorting is a fundamental algorithmic building block. One of the most studied problems in computer science is ordering a list of items eff...
UIUCDCS-R-2003-2328-1.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: Cache and Bandwidth Aware Matrix Multiplication on the GPU Jesse D. Hall Nathan A. Carr John C. Hart University of Illinois Abstract Recent advances in the speed and programmability of consumer level graphics hardware has sparked a flurry of researc...
as.pdf
Path: UPenn >> CIS >> 700 Spring, 2006
Description: Radiosity on the GPU Steve Crowe, Adam Micciulla 1 Introduction Ever since its proposal, Radiosity has been a widely used method in Global Illumination rendering. Considering the parallel nature of the problem and the recent advances in GPU techno...
Lecture1.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: CIS700/010:GPUProgrammingand Architecture SureshVenkatasubramanian (suvenkat@saul.cis.upenn.edu) http:/www.cis.upenn.edu/~suvenkat/700/ ATIAnimusicDemo http:/www.cis.upenn.edu/~suvenkat/700/ CPUperformancegrowthisslowing http://www.cis.upenn.edu...
Lecture4.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: CgShadingTutorial(OpenGL) CIS700/010 GPUProgrammingandArchitecture Instructor:Dr.SureshVenkatasubramanian TA:PaulKanyuk Overview WhatisCg? HowtoInstall/RunCgprograms AnatomyofaCgShader. CgExamples RenderTexture WhatisCg? Cgstandsf...
lec15.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: GPUPerformanceAnalysis http:/www.cis.upenn.edu/~suvenkat/700/ 3DAPI: OpenGLor Direct3D GPU Command& DataStream GPU FrontEnd Pretransformed Vertices 3DAPI Commands 3D Application OrGame CPUGPUBoundary(AGP/PCIe) Vertex Index Stream Primitive Assem...
gpusl.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: GPU Programming \"Languages\" http:/www.cis.upenn.edu/~suvenkat/700/ The Language Zoo Sh BrookGPU Renderman Rendertexture SlabOps OpenVidia HLSL Cg GLSL http:/www.cis.upenn.edu/~suvenkat/700/ Some History Cook and Perlin first to develop...
GPU_Data_Transfer.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: Techniques for Data Storage and Transfer in the Graphics Pipeline Shankar Krishnan AT&T Labs Research Graphics Hardware Pipeline Vertex Connectivity Vertices Vertex Transformation Transformed Vertices Primitive Assembly and Rasterization Frag...
Lecture3.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: The programmable pipeline Lecture 3 http:/www.cis.upenn.edu/~suvenkat/700/ 3D API: OpenGL or Direct3D GPU Command & Data Stream GPU Front End Pretransformed Vertices 3D API Commands Programmable pipeline 3D Application Or Game CPUGPU Boundary (A...
milo.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: The Cell Processor: Technological Breakthrough or Yet Another Over-hyped Chip? Prof. Milo Martin for CIS700 Agenda Cell overview PlayStation 2 review More on the Cell (from Peter Hofstees HPCA slides) Programming the Cell (brief) Impact & Speculatio...
lec10.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: RenderTexture Tutorial http:/www.cis.upenn.edu/~suvenkat/700/ A simple example Render an increasing depth field. http:/www.cis.upenn.edu/~suvenkat/700/ Use this to modulate color of a torus oColor = iColor * depth field value http:/www.cis.upe...
Lecture2.ppt
Path: UPenn >> CIS >> 700 Spring, 2006
Description: Understandingthegraphicspipeline Lecture2 http:/www.cis.upenn.edu/~suvenkat/700/ LectureOutline Ahistoricalperspectiveonthegraphicspipeline Dimensionsofinnovation. Wherewearetoday Fixedfunctionvsprogrammablepipelines Acloserlookatthefixedfunct...
ns.doc
Path: UPenn >> CIS >> 700 Spring, 2006
Description: Global Illumination in Real-Time Project Proposal Abstract: Global illumination is a well known technique for producing realistic scenes and overcoming shortcomings of the local lighting model. Common algorithms for solving global illumination rely o...
