Search Results

Search found 227 results on 10 pages for 'austin huang'.

facebook twitter digg google delicious technorati stumbleupon myspace wordpress linkedin gmail igoogle windows live tumblr viadeo yahoo buzz yahoo mail yahoo bookmarks favorites email print

Page 10/10 | < Previous Page | 6 7 8 9 10 

  • E-Business Suite Technology Sessions at OpenWorld 2012

    - by Max Arderius
    Oracle OpenWorld 2012 is almost here! We're looking forward to updating you on our products, strategy, and roadmaps. This year, the E-Business Suite Applications Technology Group (ATG) will participate in 25 speaker sessions, two Meet the Experts round-table discussions, five demoground booths and seven Special Interest Group meetings as guest speakers. We hope to see you at our sessions.  Please join us to hear the latest news and connect with senior ATG development staff. Here's a downloadable listing of all Applications Technology Group-related sessions with times and locations: FOCUS ON Oracle E-Business Suite - Applications Tools and Technology (PDF) General Sessions GEN8474 - Oracle E-Business Suite - Strategy, Update, and RoadmapCliff Godwin, SVP, Oracle Monday, Oct 1, 12:15 PM - 1:15 PM - Moscone West 2002/2004 In this session, hear Oracle E-Business Suite General Manager Cliff Godwin deliver an update on the Oracle E-Business Suite product line. This session covers the value delivered by the current release of Oracle E-Business Suite, the momentum, and how Oracle E-Business Suite applications integrate into Oracle’s overall applications strategy. You’ll come away with an understanding of the value Oracle E-Business Suite applications deliver now and will deliver in the future. GEN9173 - Optimize and Extend Oracle Applications - The Path to Oracle Fusion ApplicationsNadia Bendjedou, Oracle; Corre Curtice, Bhavish Madurai (CSC) Tuesday, Oct 2, 10:15 AM - 11:15 AM - Moscone West 3002/3004 One of the main objectives of this session is to help organizations build their IT roadmap for the next five years and be aligned with the Oracle Applications strategy in general and the Oracle Fusion Applications strategy in particular. Come hear about some of the common sense, practical steps you can take to optimize the performance of your Oracle Applications today and prepare your path to Oracle Fusion Applications for when your organization is ready to embrace them. Each step you take in adopting Oracle Fusion technology gets you partway to Oracle Fusion Applications. Conference Sessions CON9024 - Oracle E-Business Suite Technology: Latest Features and Roadmap Lisa Parekh, Oracle Monday, Oct 1, 10:45 AM - 11:45 AM - Moscone West 2016 This Oracle development session provides a comprehensive overview of Oracle’s product strategy for Oracle E-Business Suite technology, the capabilities and associated business benefits of recent releases, and a review of capabilities on the product roadmap. This is the cornerstone session for the Oracle E-Business Suite technology stack. Come hear about the latest new usability enhancements of the user interface; systems administration and configuration management tools; security-related updates; and tools and options for extending, customizing, and integrating Oracle E-Business Suite with other applications. CON9021 - Oracle E-Business Suite Future Directions: Deployment and System AdministrationMax Arderius, Oracle Monday, Oct 1, 3:15 PM - 4:15 PM - Moscone West 2016  What’s coming in the next major version of Oracle E-Business Suite 12? This Oracle Development session covers the latest technology stack, including the use of Oracle WebLogic Server (Oracle Fusion Middleware 11g) and Oracle Database 11g Release 2 (11.2). Topics include an architectural overview of the latest updates, installation and upgrade options, new configuration options, and new tools for hot cloning and automated “lights-out” cloning. Come learn how online patching (based on the Oracle Database 11g Release 2 Edition-Based Redefinition feature) will reduce your database patching downtimes to however long it takes to bounce your database server. CON9017 - Desktop Integration in Oracle E-Business Suite 12.1 Padmaprabodh Ambale, Gustavo Jimenez, Oracle Monday, Oct 1, 4:45 PM - 5:45 PM - Moscone West 2016 This presentation covers the latest functional enhancements in Oracle Web Applications Desktop Integrator and Oracle Report Manager, enhanced Microsoft Office support, and greater support for building custom desktop integration solutions. The session also presents tips and tricks for upgrading from Oracle Applications Desktop Integrator to Oracle Web Applications Desktop Integrator and Oracle Report Manager. CON9023 - Oracle E-Business Suite Technology Certification Primer and Roadmap Steven Chan, Oracle Tuesday, Oct 2, 10:15 AM - 11:15 AM - Moscone West 2016  Is your Oracle E-Business Suite technology stack up to date? Are you taking advantage of all the latest options and capabilities? This Oracle development session summarizes the latest certifications and roadmap for the Oracle E-Business Suite technology stack, including elements such as database releases and options, Java, Oracle Forms, Oracle Containers for J2EE, desktop operating systems, browsers, JRE releases, development and Web authoring tools, user authentication and management, business intelligence, Oracle Application Management Packs, security options, clouds, Oracle VM, and virtualization. The session also covers the most commonly asked questions about tech stack component support dates and upgrade implications. CON9028 - Minimizing Oracle E-Business Suite Maintenance DowntimesSantiago Bastidas, Elke Phelps, Oracle Tuesday, Oct 2, 11:45 AM - 12:45 PM - Moscone West 2016 This Oracle development session features a survey of the best techniques sysadmins can use to minimize patching downtimes. It starts with an architectural-level review of Oracle E-Business Suite fundamentals and then moves to a practical view of the various tools and approaches for downtimes. Topics include patching shortcuts, merging patches, distributing worker processes across multiple servers, running ADPatch in noninteractive mode, staged APPL_TOPs, shared file systems, deferring systemwide database tasks, avoiding resource bottlenecks, and more. An added bonus: hear about the upcoming Oracle E-Business Suite 12 online patching capabilities based on the groundbreaking Oracle Database 11g Release 2 Edition-Based Redefinition feature. CON9116 - Extending the Use of Oracle E-Business Suite with the Oracle Endeca PlatformOsama Elkady, Muhannad Obeidat, Oracle Tuesday, Oct 2, 11:45 AM - 12:45 PM - Moscone West 2018 The Oracle Endeca platform includes a leading unstructured data correlation and analytics engine, together with a best-in class catalog search and guided navigation solution, to improve the productivity of all types of users in your enterprise. This development session focuses on the details behind the Oracle Endeca platform’s integration into Oracle E-Business Suite. It demonstrates how easily you can extend the use of the Oracle Endeca platform into other areas of Oracle E-Business Suite and how you can bring in your own data and build new Oracle Endeca applications for Oracle E-Business Suite. CON9005 - Oracle E-Business Suite Integration Best PracticesVeshaal Singh, Oracle, Jeffrey Hand, Zebra Technologies Tuesday, Oct 2, 1:15 PM - 2:15 PM - Moscone West 2018 Oracle is investing across applications and technologies to make the application integration experience easier for customers. Today Oracle has certified Oracle E-Business Suite on Oracle Fusion Middleware 11g and provides a comprehensive set of integration technologies. Learn about Oracle’s integration offering across data- and process-centric integrations. These technologies can be used to address various application integration challenges and styles. In this session, you will get an understanding of how, when, and where you can leverage Oracle’s integration technologies to connect end-to-end business processes across your enterprise, including your Oracle Applications portfolio.  CON9026 - Latest Oracle E-Business Suite 12.1 User Interface and Usability EnhancementsPadmaprabodh Ambale, Oracle Tuesday, Oct 2, 1:15 PM - 2:15 PM - Moscone West 2016 This Oracle development session details the latest UI enhancements to Oracle Application Framework in Oracle E-Business Suite 12.1. Developers will get a detailed look at new features to enhance usability, offer more capabilities for personalization and extensions, and support the development and use of dashboards and Web services. Topics include new rich UI capabilities such as new home page features, Navigator and Favorites pull-down menus, REST interface, embedded widgets for analytics content, Oracle Application Development Framework (Oracle ADF) task flows, third-party widgets, a look-ahead list of values, inline attachments, pop-ups, personalization and extensibility enhancements, business layer extensions, Oracle ADF integration, and mobile devices. CON8805 - Planning Your Oracle E-Business Suite Upgrade from 11i to Release 12.1 and BeyondAnne Carlson, Oracle Tuesday, Oct 2, 5:00 PM - 6:00 PM - Moscone West 3002/3004 Attend this session to hear the latest Oracle E-Business Suite 12.1 upgrade planning tips from Oracle’s support, consulting, development, and IT organizations. You’ll get specific cross-product advice on how to understand the factors that affect your project’s duration, decide on your project’s scope, develop a robust testing strategy, leverage Oracle Support resources, and more. In a nutshell, this session tells you things you need to know before embarking upon your Release 12.1 upgrade project. CON9053 - Advanced Management of Oracle E-Business Suite with Oracle Enterprise ManagerAngelo Rosado, Oracle Tuesday, Oct 2, 5:00 PM - 6:00 PM - Moscone West 2016 The task of managing and monitoring Oracle E-Business Suite environments can be very challenging. Oracle Enterprise Manager is the only product on the market that is designed to monitor and manage all the different technologies that constitute Oracle E-Business Suite applications, including end user, midtier, configuration, host, and database management—to name just a few. Customers that have implemented Oracle Enterprise Manager have experienced dramatic improvements in system visibility and diagnostic capability as well as administrator productivity. The purpose of this session is to highlight the key features and benefits of Oracle Enterprise Manager and Oracle Application Management Suite for Oracle E-Business Suite. CON8809 - Oracle E-Business Suite 12.1 Upgrade Best Practices: Technical InsightIsam Alyousfi, Udayan Parvate, Oracle Wednesday, Oct 3, 10:15 AM - 11:15 AM - Moscone West 3011 This session is ideal for organizations thinking about upgrading to Oracle E-Business Suite 12.1. It covers the fundamentals of upgrading to Release 12.1, including the technology stack components and supported upgrade paths. Hear from Oracle Development about the set of best practices for patching in general and executing the Release 12.1 technical upgrade, with special considerations for minimizing your downtime. Also get to know about relatively recent upgrade resources. CON9032 - Upgrading Your Customizations of Oracle E-Business Suite 12.1Sara Woodhull, Oracle Wednesday, Oct 3, 10:15 AM - 11:15 AM - Moscone West 2016 Have you personalized Oracle Forms or Oracle Application Framework screens in Oracle E-Business Suite? Have you used mod_plsql in Release 11i? Have you extended or customized your Release 11i environment with other tools? The technical options for upgrading these customizations as part of your Oracle E-Business Suite Release 12.1 upgrade can be bewildering. Come to this Oracle development session to learn about selecting the best upgrade approach for your existing customizations. The session will help you understand customization scenarios and use cases, tools, and technologies to ensure that your Oracle E-Business Suite Release 12.1 environment fits your users’ needs closely and that any future customizations will be easy to upgrade. CON9259 - Oracle E-Business Suite Internationalization and Multilingual FeaturesMaher Al-Nubani, Oracle Wednesday, Oct 3, 10:15 AM - 11:15 AM - Moscone West 2018 Oracle E-Business Suite supports more countries, languages, and regions than ever. Come to this Oracle development session to get an overview of internationalization features and capabilities and see new Release 12 features such as calendar support for Hijra and Thai, new group separators, lightweight multilingual support (MLS) setup, new character sets such as AL32UTF, newly supported languages, Mac certifications, Oracle iSetup support for moving MLS setups, new file export options for Unicode, new MLS number spelling options, and more. CON7188 - Mobile Apps for Oracle E-Business Suite with Oracle ADF Mobile and Oracle SOA SuiteSrikant Subramaniam, Joe Huang, Veshaal Singh, Oracle Wednesday, Oct 3, 10:15 AM - 11:15 AM - Moscone West 3001 Follow your mobile customers, employees, and partners with Oracle Fusion Middleware. See how native iPhone and iPad applications can easily be built for Oracle E-Business Suite with the new Oracle ADF Mobile and Oracle SOA Suite. Using Oracle ADF Mobile, developers can quickly develop native applications for Apple iOS and other mobile platforms. The Oracle SOA Suite/Oracle ADF Mobile combination can execute business transactions on Oracle E-Business Suite. This session includes a demo in which a mobile user approves a business transaction in Oracle E-Business Suite and a demo of the tools used to build a native on-device solution. These concepts for mobile applications also apply to other Oracle applications.CON9029 - Oracle E-Business Suite Directions: Slashing Downtimes with Online PatchingKevin Hudson, Oracle Wednesday, Oct 3, 11:45 AM - 12:45 PM - Moscone West 2016 Oracle E-Business Suite will soon include online patching (based on the Oracle Database 11g Release 2 Edition-Based Redefinition feature), which will reduce your database patching downtimes to however long it takes to bounce your database server. This Oracle development session details how online patching works, with special attention to what’s happening at a database object level when database patches are applied to an Oracle E-Business Suite environment that’s still running. Come learn about the operational and system management implications for minimizing maintenance downtimes when applying database patches with this new technology and the related impact on customizations you might have built on top of Oracle E-Business Suite. CON8806 - Upgrading to Oracle E-Business Suite 12.1: Technical and Functional PanelAndrew Katz, Komori America Corporation; Sandra Vucinic, VLAD Group, Inc. ;Srini Chavali, Cummins Inc.; Amrita Mehrok, Nadia Bendjedou, Anne Carlson Oracle Wednesday, Oct 3, 1:15 PM - 2:15 PM - Moscone West 2018 In this panel discussion, Oracle experts, customers, and partners share their experiences in upgrading to the latest release of Oracle E-Business Suite, Release 12.1. The panelists cover aspects of a typical Release 12 upgrade, technical (upgrading the technical infrastructure) as well as functional (upgrading to the new financial infrastructure). Hear directly from the experts who either develop the product or support, implement, or upgrade it, and find out how to apply their lessons learned to your organization. CON9027 - Personalize and Extend Oracle E-Business Suite Applications with Rich MashupsGustavo Jimenez, Padmaprabodh Ambale, Oracle Wednesday, Oct 3, 1:15 PM - 2:15 PM - Moscone West 2016 This session covers the use of several Oracle Fusion Middleware technologies to personalize and extend your existing Oracle E-Business Suite applications. The Oracle Fusion Middleware technologies covered include Oracle Application Development Framework (Oracle ADF), Oracle WebCenter, Oracle Endeca applications, and Oracle Business Intelligence Enterprise Edition with Oracle E-Business Suite Oracle Application Framework applications. CON9036 - Advanced Oracle E-Business Suite Architectures: Maximum Availability, Security, and MoreElke Phelps, Oracle Wednesday, Oct 3, 3:30 PM - 4:30 PM - Moscone West 2016 This session includes architecture diagrams and configuration instructions for building a maximum availability architecture (MAA) that will help you design a disaster recovery solution that fits the needs of your business. Database and application high-availability features it describes include Oracle Data Guard, Oracle Real Application Clusters (Oracle RAC), Oracle Active Data Guard, load-balancing Web and forms services, parallel concurrent processing, and the use of Oracle Exalogic and Oracle Exadata to provide a highly available environment. The session also covers the latest updates to systems management tools, AutoConfig, cloud computing, virtualization, and Oracle WebLogic Server and provides sneak previews of upcoming functionality. CON9047 - Efficiently Scaling Oracle E-Business Suite on Oracle Exadata and Oracle ExalogicIsam Alyousfi, Nishit Rao, Oracle Wednesday, Oct 3, 5:00 PM - 6:00 PM - Moscone West 2016 Oracle Exadata and Oracle Exalogic are designed from the ground up with optimizations in software and hardware to deliver superfast performance for mission-critical applications such as Oracle E-Business Suite. Oracle E-Business Suite applications run three to eight times as fast on the Oracle Exadata/Oracle Exalogic platform in standard benchmark tests. Besides performance, customers benefit from simplified support, enhanced manageability, and the ability to consolidate multiple Oracle E-Business Suite instances. Attend this session to understand best practices for Oracle E-Business Suite deployment on Oracle Exalogic and Oracle Exadata through customer case studies. Learn how adopting the Exa* platform increases efficiency, simplifies scaling, and boosts performance for peak loads. CON8716 - Web Services and SOA Integration Options for Oracle E-Business SuiteRekha Ayothi, Veshaal Singh, Oracle Thursday, Oct 4, 11:15 AM - 12:15 PM - Moscone West 2016 This Oracle development session provides a deep dive into a subset of the Web services and SOA-related integration options available to Oracle E-Business Suite systems integrators. It offers a technical look at Oracle E-Business Suite Integrated SOA Gateway, Oracle SOA Suite, Oracle Application Adapters for Data Integration for Oracle E-Business Suite, and other Web services options for integrating Oracle E-Business Suite with other applications. Systems integrators and developers will get an overview of the latest integration capabilities and technologies available out of the box with Oracle E-Business Suite and possibly a sneak preview of upcoming functionality and features. CON9030 - Recommendations for Oracle E-Business Suite Performance TuningIsam Alyousfi, Samer Barakat, Oracle Thursday, Oct 4, 11:15 AM - 12:15 PM - Moscone West 2018 Need to squeeze more performance out of your existing servers? This packed Oracle development session summarizes practical tips and lessons learned from performance-tuning and benchmarking the world’s largest Oracle E-Business Suite environments. Apps sysadmins will learn concrete tips and techniques for identifying and resolving performance bottlenecks on all layers, with special attention to application- and database-tier servers. Learn about tuning Oracle Forms, Oracle Concurrent Manager, Apache, and Oracle Discoverer. Track down memory leaks and other issues at the Java and JVM layers. The session also covers Oracle E-Business Suite product-level tuning, including Oracle Workflow, Oracle Order Management, Oracle Payroll, and other modules. CON3429 - Using Oracle ADF with Oracle E-Business Suite: The Full Integration ViewSiva Puthurkattil, Lake County; Juan Camilo Ruiz, Sara Woodhull, Oracle Thursday, Oct 4, 11:15 AM - 12:15 PM - Moscone West 3003 Oracle E-Business Suite delivers functionality for handling the core business of your organization. However, user requirements and new technologies are driving an emerging need to implement new types of user interfaces for these applications. This session provides an overview of how to use Oracle Application Development Framework (Oracle ADF) to deliver cutting-edge Web 2.0 and mobile rich user interfaces that front existing Oracle E-Business Suite processes, and it also explores all the existing types of integration between the two worlds. CON9020 - Integrating Oracle E-Business Suite with Oracle Identity Management SolutionsSunil Ghosh, Elke Phelps, Oracle Thursday, Oct 4, 12:45 PM - 1:45 PM - Moscone West 2016 Need to integrate Oracle E-Business Suite with Microsoft Windows Kerberos, Active Directory, CA Netegrity SiteMinder, or other third-party authentication systems? Want to understand your options when Oracle Premier Support for Oracle Single Sign-On ends in December 2011? This Oracle Development session covers the latest certified integrations with Oracle Access Manager 11g and Oracle Internet Directory 11g, which can be used individually or as bridges for integrating with third-party authentication solutions. The session presents an architectural overview of how Oracle Access Manager, its WebGate and AccessGate components, and Oracle Internet Directory work together, with implications for Oracle Discoverer, Oracle Portal, and other Oracle Fusion identity management products. CON9019 - Troubleshooting, Diagnosing, and Optimizing Oracle E-Business Suite TechnologyGustavo Jimenez, Oracle Thursday, Oct 4, 2:15 PM - 3:15 PM - Moscone West 2016 This session covers how you can proactively diagnose Oracle E-Business Suite applications, including extensions built with Oracle Fusion Middleware technologies such as Oracle Application Development Framework (Oracle ADF) and Oracle WebCenter to catch potential issues in the middle tier before they become more serious. Topics include debugging, logging infrastructure, warning signs, performance tuning, information required when logging service requests, general JVM optimization, and an overall picture of all the moving parts that make it possible for Oracle E-Business Suite to isolate and fix problems. Also learn how Oracle Diagnostics Framework will help prevent downtime caused by failures. CON9031 - The Top 10 Things You Can Do to Secure Your Oracle E-Business Suite InstanceEric Bing, Erik Graversen, Oracle Thursday, Oct 4, 2:15 PM - 3:15 PM - Moscone West 2018 Learn the top 10 things you can do to secure your applications and your sensitive data. This Oracle development session for system administrators and security professionals explores some of the most important and overlooked things you can do to secure your Oracle E-Business Suite instance. It also covers data masking and other mechanisms for protecting sensitive data. Special Interest Groups (SIG) Some of our most senior staff have been invited to participate on the following SIG meetings as guest speakers: SIG10525 - OAUG - Archive & Purge SIGBrian Bent - Pre-Sales Engineer, TierData, Inc. Sunday, Sep 30, 10:30 AM - 12:00 PM - Moscone West 3011 The Archive and Purge SIG is an organization in which users can share their experiences and solicit functional and technical advice on archiving and purging data in Oracle E-Business Suite. This session provides an opportunity for users to network and share best practices, tips, and tricks. Guest: Oracle E-Business Suite Database Performance, Archive & Purging - Q&A SessionIsam Alyousfi, Senior Director, Applications Performance, Oracle SIG10547 - OAUG - Oracle E-Business (EBS) Applications Technology SIGSrini Chavali - IT Director, Cummins Inc Sunday, Sep 30, 10:30 AM - 12:00 PM - Moscone West 3018 The general purpose of the EBS Applications Technology SIG is to inform and educate its members about current and future components of the tech stack as they relate to Oracle E-Business Suite. Attend this meeting for networking and education and to share best practices. Guest: Oracle E-Business Suite Technology Certification Roadmap - Presentation and Q&ASteven Chan, Sr. Director, Applications Technology Group, Oracle SIG10559 - OAUG - User Management SIGSusan Behn - VP of Oracle Delivery, Infosemantics, Inc. Sunday, Sep 30, 10:30 AM - 12:00 PM - Moscone West 3024 The E-Business Suite User Management SIG focuses on the components of user management that enable Oracle E-Business Suite users to define administrative functions and manage users’ access to functions and data based on roles within an organization—rather than the user’s individual identity—which is referred to as role-based access control (RBAC). This meeting includes an introduction to Oracle User Management that covers the Oracle User Management building blocks and presents an example of creating a security policy.Guest: Security and User Management - Q&A SessionEric Bing, Sr. Director, EBS Security, OracleSara Woodhull, Principal Product Manager, Applications Technology Group, Oracle SIG10515 - OAUG – Upgrade SIGBarbara Matthews - Consultant, On Call DBASandra Vucinic, VLAD Group, Inc. Sunday, Sep 30, 12:00 PM - 2:00 PM - Moscone West 3009 This Upgrade SIG session starts with a business meeting and then features a Q&A panel discussion on Oracle E-Business Suite upgrade topics. The session• Reviews Upgrade SIG goals and objectives• Provides answers, during the Q&A session, to questions related to Oracle E-Business Suite upgrades• Shares “real world” experiences, tips, and techniques for Oracle E-Business Suite upgrades to Release 12.1. Guest: Oracle E-Business Suite Upgrade - Q&A SessionAnne Carlson - Sr. Director, Oracle E-Business Suite Product Strategy, OracleUdayan Parvate - Director, EBS Release Engineering, OracleSuzana Ferrari, Sr. Principal Consultant, OracleIsam Alyousfi, Sr. Director, Applications Performance, Oracle SIG10552 - OAUG - Oracle E-Business Suite SIGDonna Rosentrater - Manager, Global Sourcing & Procurement Systems, TJX Sunday, Sep 30, 12:15 PM - 1:45 PM - Moscone West 3020 The E-Business Suite SIG, affiliated with OAUG, supports Oracle E-Business Suite users through networking, education, and sharing of best practices. This SIG meeting will feature a general discussion of Oracle E-Business Suite product strategies in Release 12 and migration to Oracle Fusion Applications. Guest: Oracle E-Business Suite - Q&A SessionJeanne Lowell, Vice President, EBS Product Strategy, OracleNadia Bendjedou, Sr. Director, Product Strategy, Oracle SIG10556 - OAUG - SysAdmin SIGRandy Giefer - Sr Systems and Security Architect, Solution Beacon, LLC Sunday, Sep 30, 12:15 PM - 1:45 PM - Moscone West 3022 The SysAdmin SIG provides a forum in which OAUG members and participants can share updates, tips, and successful practices relating to system administration in an Oracle applications environment. The SysAdmin SIG strives to enable system administrators to become more effective and efficient in their jobs by providing them with access to people and information that can increase their system administration knowledge and experience. Attend this meeting to network, share best practices, and benefit from educational content. Guest: Oracle E-Business Suite 12.2 Online Patching- Presentation and Q&AKevin Hudson, Sr. Director, Applications Technology Group, Oracle SIG10553 - OAUG - Database SIGMichael Brown - Senior DBA, COLIBRI LTD LC Sunday, Sep 30, 2:00 PM - 3:15 PM - Moscone West 3020 The OAUG Database SIG provides an opportunity for applications database administrators to learn from and share their experiences with supporting the various Oracle applications environments. This session will include a brief business meeting followed by a short presentation. It will end with an open discussion among the attendees about items of interest to those present. Guest: Oracle E-Business Suite Database Performance - Presentation and Q&AIsam Alyousfi, Sr. Director, Applications Performance, Oracle Meet the Experts We're planning two round-table discussions where you can review your questions with senior E-Business Suite ATG staff: MTE9648 - Meet the Experts for Oracle E-Business Suite: Planning Your Upgrade Jeanne Lowell - VP, EBS Product Strategy, Oracle John Abraham - Sr. Principal Product Manager, Oracle Nadia Bendjedou - Sr. Director - Product Strategy, Oracle Anne Carlson - Sr. Director, Applications Technology Group, Oracle Udayan Parvate - Director, EBS Release Engineering, Oracle Isam Alyousfi, Sr. Director, Applications Performance, Oracle Monday, Oct 1, 3:15 PM - 4:15 PM - Moscone West 2001A Don’t miss this Oracle Applications Meet the Experts session with experts who specialize in Oracle E-Business Suite upgrade best practices. This is the place where attendees can have informal and semistructured but open one-on-one discussions with Strategy and Development regarding Oracle Applications strategy and your specific business and IT strategy. The experts will be available to discuss the value of the latest releases and share insights into the best path for your enterprise, so come ready with your questions. Space is limited, so make sure you register. MTE9649 - Meet the Oracle E-Business Suite Tools and Technology Experts Lisa Parekh - Vice President, Technology Integration, Oracle Steven Chan - Sr. Director, Oracle Elke Phelps - Sr. Principal Product Manager, Applications Technology Group, Oracle Max Arderius - Manager, Applications Technology Group, Oracle Tuesday, Oct 2, 1:15 PM - 2:15 PM - Moscone West 2001A Don’t miss this Oracle Applications Meet the Experts session with experts who specialize in Oracle E-Business Suite technology. This is the place where attendees can have informal and semistructured but open one-on-one discussions with Strategy and Development regarding Oracle Applications strategy and your specific business and IT strategy. The experts will be available to discuss the value of the latest releases and share insights into the best path for your enterprise, so come ready with your questions. Space is limited, so make sure you register. Demos We have five booths in the exhibition demogrounds this year, where you can try ATG technologies firsthand and get your questions answered. Please stop by and meet our staff at the following locations: Advanced Architecture and Technology Stack for Oracle E-Business Suite (W-067) New User Productivity Capabilities in Oracle E-Business Suite (W-065) End-to-End Management of Oracle E-Business Suite (W-063) Oracle E-Business Suite 12.1 Technical Upgrade Best Practices (W-066) SOA-Based Integration for Oracle E-Business Suite (W-064)

    Read the article

  • How John Got 15x Improvement Without Really Trying

    - by rchrd
    The following article was published on a Sun Microsystems website a number of years ago by John Feo. It is still useful and worth preserving. So I'm republishing it here.  How I Got 15x Improvement Without Really Trying John Feo, Sun Microsystems Taking ten "personal" program codes used in scientific and engineering research, the author was able to get from 2 to 15 times performance improvement easily by applying some simple general optimization techniques. Introduction Scientific research based on computer simulation depends on the simulation for advancement. The research can advance only as fast as the computational codes can execute. The codes' efficiency determines both the rate and quality of results. In the same amount of time, a faster program can generate more results and can carry out a more detailed simulation of physical phenomena than a slower program. Highly optimized programs help science advance quickly and insure that monies supporting scientific research are used as effectively as possible. Scientific computer codes divide into three broad categories: ISV, community, and personal. ISV codes are large, mature production codes developed and sold commercially. The codes improve slowly over time both in methods and capabilities, and they are well tuned for most vendor platforms. Since the codes are mature and complex, there are few opportunities to improve their performance solely through code optimization. Improvements of 10% to 15% are typical. Examples of ISV codes are DYNA3D, Gaussian, and Nastran. Community codes are non-commercial production codes used by a particular research field. Generally, they are developed and distributed by a single academic or research institution with assistance from the community. Most users just run the codes, but some develop new methods and extensions that feed back into the general release. The codes are available on most vendor platforms. Since these codes are younger than ISV codes, there are more opportunities to optimize the source code. Improvements of 50% are not unusual. Examples of community codes are AMBER, CHARM, BLAST, and FASTA. Personal codes are those written by single users or small research groups for their own use. These codes are not distributed, but may be passed from professor-to-student or student-to-student over several years. They form the primordial ocean of applications from which community and ISV codes emerge. Government research grants pay for the development of most personal codes. This paper reports on the nature and performance of this class of codes. Over the last year, I have looked at over two dozen personal codes from more than a dozen research institutions. The codes cover a variety of scientific fields, including astronomy, atmospheric sciences, bioinformatics, biology, chemistry, geology, and physics. The sources range from a few hundred lines to more than ten thousand lines, and are written in Fortran, Fortran 90, C, and C++. For the most part, the codes are modular, documented, and written in a clear, straightforward manner. They do not use complex language features, advanced data structures, programming tricks, or libraries. I had little trouble understanding what the codes did or how data structures were used. Most came with a makefile. Surprisingly, only one of the applications is parallel. All developers have access to parallel machines, so availability is not an issue. Several tried to parallelize their applications, but stopped after encountering difficulties. Lack of education and a perception that parallelism is difficult prevented most from trying. I parallelized several of the codes using OpenMP, and did not judge any of the codes as difficult to parallelize. Even more surprising than the lack of parallelism is the inefficiency of the codes. I was able to get large improvements in performance in a matter of a few days applying simple optimization techniques. Table 1 lists ten representative codes [names and affiliation are omitted to preserve anonymity]. Improvements on one processor range from 2x to 15.5x with a simple average of 4.75x. I did not use sophisticated performance tools or drill deep into the program's execution character as one would do when tuning ISV or community codes. Using only a profiler and source line timers, I identified inefficient sections of code and improved their performance by inspection. The changes were at a high level. I am sure there is another factor of 2 or 3 in each code, and more if the codes are parallelized. The study’s results show that personal scientific codes are running many times slower than they should and that the problem is pervasive. Computational scientists are not sloppy programmers; however, few are trained in the art of computer programming or code optimization. I found that most have a working knowledge of some programming language and standard software engineering practices; but they do not know, or think about, how to make their programs run faster. They simply do not know the standard techniques used to make codes run faster. In fact, they do not even perceive that such techniques exist. The case studies described in this paper show that applying simple, well known techniques can significantly increase the performance of personal codes. It is important that the scientific community and the Government agencies that support scientific research find ways to better educate academic scientific programmers. The inefficiency of their codes is so bad that it is retarding both the quality and progress of scientific research. # cacheperformance redundantoperations loopstructures performanceimprovement 1 x x 15.5 2 x 2.8 3 x x 2.5 4 x 2.1 5 x x 2.0 6 x 5.0 7 x 5.8 8 x 6.3 9 2.2 10 x x 3.3 Table 1 — Area of improvement and performance gains of 10 codes The remainder of the paper is organized as follows: sections 2, 3, and 4 discuss the three most common sources of inefficiencies in the codes studied. These are cache performance, redundant operations, and loop structures. Each section includes several examples. The last section summaries the work and suggests a possible solution to the issues raised. Optimizing cache performance Commodity microprocessor systems use caches to increase memory bandwidth and reduce memory latencies. Typical latencies from processor to L1, L2, local, and remote memory are 3, 10, 50, and 200 cycles, respectively. Moreover, bandwidth falls off dramatically as memory distances increase. Programs that do not use cache effectively run many times slower than programs that do. When optimizing for cache, the biggest performance gains are achieved by accessing data in cache order and reusing data to amortize the overhead of cache misses. Secondary considerations are prefetching, associativity, and replacement; however, the understanding and analysis required to optimize for the latter are probably beyond the capabilities of the non-expert. Much can be gained simply by accessing data in the correct order and maximizing data reuse. 6 out of the 10 codes studied here benefited from such high level optimizations. Array Accesses The most important cache optimization is the most basic: accessing Fortran array elements in column order and C array elements in row order. Four of the ten codes—1, 2, 4, and 10—got it wrong. Compilers will restructure nested loops to optimize cache performance, but may not do so if the loop structure is too complex, or the loop body includes conditionals, complex addressing, or function calls. In code 1, the compiler failed to invert a key loop because of complex addressing do I = 0, 1010, delta_x IM = I - delta_x IP = I + delta_x do J = 5, 995, delta_x JM = J - delta_x JP = J + delta_x T1 = CA1(IP, J) + CA1(I, JP) T2 = CA1(IM, J) + CA1(I, JM) S1 = T1 + T2 - 4 * CA1(I, J) CA(I, J) = CA1(I, J) + D * S1 end do end do In code 2, the culprit is conditionals do I = 1, N do J = 1, N If (IFLAG(I,J) .EQ. 0) then T1 = Value(I, J-1) T2 = Value(I-1, J) T3 = Value(I, J) T4 = Value(I+1, J) T5 = Value(I, J+1) Value(I,J) = 0.25 * (T1 + T2 + T5 + T4) Delta = ABS(T3 - Value(I,J)) If (Delta .GT. MaxDelta) MaxDelta = Delta endif enddo enddo I fixed both programs by inverting the loops by hand. Code 10 has three-dimensional arrays and triply nested loops. The structure of the most computationally intensive loops is too complex to invert automatically or by hand. The only practical solution is to transpose the arrays so that the dimension accessed by the innermost loop is in cache order. The arrays can be transposed at construction or prior to entering a computationally intensive section of code. The former requires all array references to be modified, while the latter is cost effective only if the cost of the transpose is amortized over many accesses. I used the second approach to optimize code 10. Code 5 has four-dimensional arrays and loops are nested four deep. For all of the reasons cited above the compiler is not able to restructure three key loops. Assume C arrays and let the four dimensions of the arrays be i, j, k, and l. In the original code, the index structure of the three loops is L1: for i L2: for i L3: for i for l for l for j for k for j for k for j for k for l So only L3 accesses array elements in cache order. L1 is a very complex loop—much too complex to invert. I brought the loop into cache alignment by transposing the second and fourth dimensions of the arrays. Since the code uses a macro to compute all array indexes, I effected the transpose at construction and changed the macro appropriately. The dimensions of the new arrays are now: i, l, k, and j. L3 is a simple loop and easily inverted. L2 has a loop-carried scalar dependence in k. By promoting the scalar name that carries the dependence to an array, I was able to invert the third and fourth subloops aligning the loop with cache. Code 5 is by far the most difficult of the four codes to optimize for array accesses; but the knowledge required to fix the problems is no more than that required for the other codes. I would judge this code at the limits of, but not beyond, the capabilities of appropriately trained computational scientists. Array Strides When a cache miss occurs, a line (64 bytes) rather than just one word is loaded into the cache. If data is accessed stride 1, than the cost of the miss is amortized over 8 words. Any stride other than one reduces the cost savings. Two of the ten codes studied suffered from non-unit strides. The codes represent two important classes of "strided" codes. Code 1 employs a multi-grid algorithm to reduce time to convergence. The grids are every tenth, fifth, second, and unit element. Since time to convergence is inversely proportional to the distance between elements, coarse grids converge quickly providing good starting values for finer grids. The better starting values further reduce the time to convergence. The downside is that grids of every nth element, n > 1, introduce non-unit strides into the computation. In the original code, much of the savings of the multi-grid algorithm were lost due to this problem. I eliminated the problem by compressing (copying) coarse grids into continuous memory, and rewriting the computation as a function of the compressed grid. On convergence, I copied the final values of the compressed grid back to the original grid. The savings gained from unit stride access of the compressed grid more than paid for the cost of copying. Using compressed grids, the loop from code 1 included in the previous section becomes do j = 1, GZ do i = 1, GZ T1 = CA(i+0, j-1) + CA(i-1, j+0) T4 = CA1(i+1, j+0) + CA1(i+0, j+1) S1 = T1 + T4 - 4 * CA1(i+0, j+0) CA(i+0, j+0) = CA1(i+0, j+0) + DD * S1 enddo enddo where CA and CA1 are compressed arrays of size GZ. Code 7 traverses a list of objects selecting objects for later processing. The labels of the selected objects are stored in an array. The selection step has unit stride, but the processing steps have irregular stride. A fix is to save the parameters of the selected objects in temporary arrays as they are selected, and pass the temporary arrays to the processing functions. The fix is practical if the same parameters are used in selection as in processing, or if processing comprises a series of distinct steps which use overlapping subsets of the parameters. Both conditions are true for code 7, so I achieved significant improvement by copying parameters to temporary arrays during selection. Data reuse In the previous sections, we optimized for spatial locality. It is also important to optimize for temporal locality. Once read, a datum should be used as much as possible before it is forced from cache. Loop fusion and loop unrolling are two techniques that increase temporal locality. Unfortunately, both techniques increase register pressure—as loop bodies become larger, the number of registers required to hold temporary values grows. Once register spilling occurs, any gains evaporate quickly. For multiprocessors with small register sets or small caches, the sweet spot can be very small. In the ten codes presented here, I found no opportunities for loop fusion and only two opportunities for loop unrolling (codes 1 and 3). In code 1, unrolling the outer and inner loop one iteration increases the number of result values computed by the loop body from 1 to 4, do J = 1, GZ-2, 2 do I = 1, GZ-2, 2 T1 = CA1(i+0, j-1) + CA1(i-1, j+0) T2 = CA1(i+1, j-1) + CA1(i+0, j+0) T3 = CA1(i+0, j+0) + CA1(i-1, j+1) T4 = CA1(i+1, j+0) + CA1(i+0, j+1) T5 = CA1(i+2, j+0) + CA1(i+1, j+1) T6 = CA1(i+1, j+1) + CA1(i+0, j+2) T7 = CA1(i+2, j+1) + CA1(i+1, j+2) S1 = T1 + T4 - 4 * CA1(i+0, j+0) S2 = T2 + T5 - 4 * CA1(i+1, j+0) S3 = T3 + T6 - 4 * CA1(i+0, j+1) S4 = T4 + T7 - 4 * CA1(i+1, j+1) CA(i+0, j+0) = CA1(i+0, j+0) + DD * S1 CA(i+1, j+0) = CA1(i+1, j+0) + DD * S2 CA(i+0, j+1) = CA1(i+0, j+1) + DD * S3 CA(i+1, j+1) = CA1(i+1, j+1) + DD * S4 enddo enddo The loop body executes 12 reads, whereas as the rolled loop shown in the previous section executes 20 reads to compute the same four values. In code 3, two loops are unrolled 8 times and one loop is unrolled 4 times. Here is the before for (k = 0; k < NK[u]; k++) { sum = 0.0; for (y = 0; y < NY; y++) { sum += W[y][u][k] * delta[y]; } backprop[i++]=sum; } and after code for (k = 0; k < KK - 8; k+=8) { sum0 = 0.0; sum1 = 0.0; sum2 = 0.0; sum3 = 0.0; sum4 = 0.0; sum5 = 0.0; sum6 = 0.0; sum7 = 0.0; for (y = 0; y < NY; y++) { sum0 += W[y][0][k+0] * delta[y]; sum1 += W[y][0][k+1] * delta[y]; sum2 += W[y][0][k+2] * delta[y]; sum3 += W[y][0][k+3] * delta[y]; sum4 += W[y][0][k+4] * delta[y]; sum5 += W[y][0][k+5] * delta[y]; sum6 += W[y][0][k+6] * delta[y]; sum7 += W[y][0][k+7] * delta[y]; } backprop[k+0] = sum0; backprop[k+1] = sum1; backprop[k+2] = sum2; backprop[k+3] = sum3; backprop[k+4] = sum4; backprop[k+5] = sum5; backprop[k+6] = sum6; backprop[k+7] = sum7; } for one of the loops unrolled 8 times. Optimizing for temporal locality is the most difficult optimization considered in this paper. The concepts are not difficult, but the sweet spot is small. Identifying where the program can benefit from loop unrolling or loop fusion is not trivial. Moreover, it takes some effort to get it right. Still, educating scientific programmers about temporal locality and teaching them how to optimize for it will pay dividends. Reducing instruction count Execution time is a function of instruction count. Reduce the count and you usually reduce the time. The best solution is to use a more efficient algorithm; that is, an algorithm whose order of complexity is smaller, that converges quicker, or is more accurate. Optimizing source code without changing the algorithm yields smaller, but still significant, gains. This paper considers only the latter because the intent is to study how much better codes can run if written by programmers schooled in basic code optimization techniques. The ten codes studied benefited from three types of "instruction reducing" optimizations. The two most prevalent were hoisting invariant memory and data operations out of inner loops. The third was eliminating unnecessary data copying. The nature of these inefficiencies is language dependent. Memory operations The semantics of C make it difficult for the compiler to determine all the invariant memory operations in a loop. The problem is particularly acute for loops in functions since the compiler may not know the values of the function's parameters at every call site when compiling the function. Most compilers support pragmas to help resolve ambiguities; however, these pragmas are not comprehensive and there is no standard syntax. To guarantee that invariant memory operations are not executed repetitively, the user has little choice but to hoist the operations by hand. The problem is not as severe in Fortran programs because in the absence of equivalence statements, it is a violation of the language's semantics for two names to share memory. Codes 3 and 5 are C programs. In both cases, the compiler did not hoist all invariant memory operations from inner loops. Consider the following loop from code 3 for (y = 0; y < NY; y++) { i = 0; for (u = 0; u < NU; u++) { for (k = 0; k < NK[u]; k++) { dW[y][u][k] += delta[y] * I1[i++]; } } } Since dW[y][u] can point to the same memory space as delta for one or more values of y and u, assignment to dW[y][u][k] may change the value of delta[y]. In reality, dW and delta do not overlap in memory, so I rewrote the loop as for (y = 0; y < NY; y++) { i = 0; Dy = delta[y]; for (u = 0; u < NU; u++) { for (k = 0; k < NK[u]; k++) { dW[y][u][k] += Dy * I1[i++]; } } } Failure to hoist invariant memory operations may be due to complex address calculations. If the compiler can not determine that the address calculation is invariant, then it can hoist neither the calculation nor the associated memory operations. As noted above, code 5 uses a macro to address four-dimensional arrays #define MAT4D(a,q,i,j,k) (double *)((a)->data + (q)*(a)->strides[0] + (i)*(a)->strides[3] + (j)*(a)->strides[2] + (k)*(a)->strides[1]) The macro is too complex for the compiler to understand and so, it does not identify any subexpressions as loop invariant. The simplest way to eliminate the address calculation from the innermost loop (over i) is to define a0 = MAT4D(a,q,0,j,k) before the loop and then replace all instances of *MAT4D(a,q,i,j,k) in the loop with a0[i] A similar problem appears in code 6, a Fortran program. The key loop in this program is do n1 = 1, nh nx1 = (n1 - 1) / nz + 1 nz1 = n1 - nz * (nx1 - 1) do n2 = 1, nh nx2 = (n2 - 1) / nz + 1 nz2 = n2 - nz * (nx2 - 1) ndx = nx2 - nx1 ndy = nz2 - nz1 gxx = grn(1,ndx,ndy) gyy = grn(2,ndx,ndy) gxy = grn(3,ndx,ndy) balance(n1,1) = balance(n1,1) + (force(n2,1) * gxx + force(n2,2) * gxy) * h1 balance(n1,2) = balance(n1,2) + (force(n2,1) * gxy + force(n2,2) * gyy)*h1 end do end do The programmer has written this loop well—there are no loop invariant operations with respect to n1 and n2. However, the loop resides within an iterative loop over time and the index calculations are independent with respect to time. Trading space for time, I precomputed the index values prior to the entering the time loop and stored the values in two arrays. I then replaced the index calculations with reads of the arrays. Data operations Ways to reduce data operations can appear in many forms. Implementing a more efficient algorithm produces the biggest gains. The closest I came to an algorithm change was in code 4. This code computes the inner product of K-vectors A(i) and B(j), 0 = i < N, 0 = j < M, for most values of i and j. Since the program computes most of the NM possible inner products, it is more efficient to compute all the inner products in one triply-nested loop rather than one at a time when needed. The savings accrue from reading A(i) once for all B(j) vectors and from loop unrolling. for (i = 0; i < N; i+=8) { for (j = 0; j < M; j++) { sum0 = 0.0; sum1 = 0.0; sum2 = 0.0; sum3 = 0.0; sum4 = 0.0; sum5 = 0.0; sum6 = 0.0; sum7 = 0.0; for (k = 0; k < K; k++) { sum0 += A[i+0][k] * B[j][k]; sum1 += A[i+1][k] * B[j][k]; sum2 += A[i+2][k] * B[j][k]; sum3 += A[i+3][k] * B[j][k]; sum4 += A[i+4][k] * B[j][k]; sum5 += A[i+5][k] * B[j][k]; sum6 += A[i+6][k] * B[j][k]; sum7 += A[i+7][k] * B[j][k]; } C[i+0][j] = sum0; C[i+1][j] = sum1; C[i+2][j] = sum2; C[i+3][j] = sum3; C[i+4][j] = sum4; C[i+5][j] = sum5; C[i+6][j] = sum6; C[i+7][j] = sum7; }} This change requires knowledge of a typical run; i.e., that most inner products are computed. The reasons for the change, however, derive from basic optimization concepts. It is the type of change easily made at development time by a knowledgeable programmer. In code 5, we have the data version of the index optimization in code 6. Here a very expensive computation is a function of the loop indices and so cannot be hoisted out of the loop; however, the computation is invariant with respect to an outer iterative loop over time. We can compute its value for each iteration of the computation loop prior to entering the time loop and save the values in an array. The increase in memory required to store the values is small in comparison to the large savings in time. The main loop in Code 8 is doubly nested. The inner loop includes a series of guarded computations; some are a function of the inner loop index but not the outer loop index while others are a function of the outer loop index but not the inner loop index for (j = 0; j < N; j++) { for (i = 0; i < M; i++) { r = i * hrmax; R = A[j]; temp = (PRM[3] == 0.0) ? 1.0 : pow(r, PRM[3]); high = temp * kcoeff * B[j] * PRM[2] * PRM[4]; low = high * PRM[6] * PRM[6] / (1.0 + pow(PRM[4] * PRM[6], 2.0)); kap = (R > PRM[6]) ? high * R * R / (1.0 + pow(PRM[4]*r, 2.0) : low * pow(R/PRM[6], PRM[5]); < rest of loop omitted > }} Note that the value of temp is invariant to j. Thus, we can hoist the computation for temp out of the loop and save its values in an array. for (i = 0; i < M; i++) { r = i * hrmax; TEMP[i] = pow(r, PRM[3]); } [N.B. – the case for PRM[3] = 0 is omitted and will be reintroduced later.] We now hoist out of the inner loop the computations invariant to i. Since the conditional guarding the value of kap is invariant to i, it behooves us to hoist the computation out of the inner loop, thereby executing the guard once rather than M times. The final version of the code is for (j = 0; j < N; j++) { R = rig[j] / 1000.; tmp1 = kcoeff * par[2] * beta[j] * par[4]; tmp2 = 1.0 + (par[4] * par[4] * par[6] * par[6]); tmp3 = 1.0 + (par[4] * par[4] * R * R); tmp4 = par[6] * par[6] / tmp2; tmp5 = R * R / tmp3; tmp6 = pow(R / par[6], par[5]); if ((par[3] == 0.0) && (R > par[6])) { for (i = 1; i <= imax1; i++) KAP[i] = tmp1 * tmp5; } else if ((par[3] == 0.0) && (R <= par[6])) { for (i = 1; i <= imax1; i++) KAP[i] = tmp1 * tmp4 * tmp6; } else if ((par[3] != 0.0) && (R > par[6])) { for (i = 1; i <= imax1; i++) KAP[i] = tmp1 * TEMP[i] * tmp5; } else if ((par[3] != 0.0) && (R <= par[6])) { for (i = 1; i <= imax1; i++) KAP[i] = tmp1 * TEMP[i] * tmp4 * tmp6; } for (i = 0; i < M; i++) { kap = KAP[i]; r = i * hrmax; < rest of loop omitted > } } Maybe not the prettiest piece of code, but certainly much more efficient than the original loop, Copy operations Several programs unnecessarily copy data from one data structure to another. This problem occurs in both Fortran and C programs, although it manifests itself differently in the two languages. Code 1 declares two arrays—one for old values and one for new values. At the end of each iteration, the array of new values is copied to the array of old values to reset the data structures for the next iteration. This problem occurs in Fortran programs not included in this study and in both Fortran 77 and Fortran 90 code. Introducing pointers to the arrays and swapping pointer values is an obvious way to eliminate the copying; but pointers is not a feature that many Fortran programmers know well or are comfortable using. An easy solution not involving pointers is to extend the dimension of the value array by 1 and use the last dimension to differentiate between arrays at different times. For example, if the data space is N x N, declare the array (N, N, 2). Then store the problem’s initial values in (_, _, 2) and define the scalar names new = 2 and old = 1. At the start of each iteration, swap old and new to reset the arrays. The old–new copy problem did not appear in any C program. In programs that had new and old values, the code swapped pointers to reset data structures. Where unnecessary coping did occur is in structure assignment and parameter passing. Structures in C are handled much like scalars. Assignment causes the data space of the right-hand name to be copied to the data space of the left-hand name. Similarly, when a structure is passed to a function, the data space of the actual parameter is copied to the data space of the formal parameter. If the structure is large and the assignment or function call is in an inner loop, then copying costs can grow quite large. While none of the ten programs considered here manifested this problem, it did occur in programs not included in the study. A simple fix is always to refer to structures via pointers. Optimizing loop structures Since scientific programs spend almost all their time in loops, efficient loops are the key to good performance. Conditionals, function calls, little instruction level parallelism, and large numbers of temporary values make it difficult for the compiler to generate tightly packed, highly efficient code. Conditionals and function calls introduce jumps that disrupt code flow. Users should eliminate or isolate conditionls to their own loops as much as possible. Often logical expressions can be substituted for if-then-else statements. For example, code 2 includes the following snippet MaxDelta = 0.0 do J = 1, N do I = 1, M < code omitted > Delta = abs(OldValue ? NewValue) if (Delta > MaxDelta) MaxDelta = Delta enddo enddo if (MaxDelta .gt. 0.001) goto 200 Since the only use of MaxDelta is to control the jump to 200 and all that matters is whether or not it is greater than 0.001, I made MaxDelta a boolean and rewrote the snippet as MaxDelta = .false. do J = 1, N do I = 1, M < code omitted > Delta = abs(OldValue ? NewValue) MaxDelta = MaxDelta .or. (Delta .gt. 0.001) enddo enddo if (MaxDelta) goto 200 thereby, eliminating the conditional expression from the inner loop. A microprocessor can execute many instructions per instruction cycle. Typically, it can execute one or more memory, floating point, integer, and jump operations. To be executed simultaneously, the operations must be independent. Thick loops tend to have more instruction level parallelism than thin loops. Moreover, they reduce memory traffice by maximizing data reuse. Loop unrolling and loop fusion are two techniques to increase the size of loop bodies. Several of the codes studied benefitted from loop unrolling, but none benefitted from loop fusion. This observation is not too surpising since it is the general tendency of programmers to write thick loops. As loops become thicker, the number of temporary values grows, increasing register pressure. If registers spill, then memory traffic increases and code flow is disrupted. A thick loop with many temporary values may execute slower than an equivalent series of thin loops. The biggest gain will be achieved if the thick loop can be split into a series of independent loops eliminating the need to write and read temporary arrays. I found such an occasion in code 10 where I split the loop do i = 1, n do j = 1, m A24(j,i)= S24(j,i) * T24(j,i) + S25(j,i) * U25(j,i) B24(j,i)= S24(j,i) * T25(j,i) + S25(j,i) * U24(j,i) A25(j,i)= S24(j,i) * C24(j,i) + S25(j,i) * V24(j,i) B25(j,i)= S24(j,i) * U25(j,i) + S25(j,i) * V25(j,i) C24(j,i)= S26(j,i) * T26(j,i) + S27(j,i) * U26(j,i) D24(j,i)= S26(j,i) * T27(j,i) + S27(j,i) * V26(j,i) C25(j,i)= S27(j,i) * S28(j,i) + S26(j,i) * U28(j,i) D25(j,i)= S27(j,i) * T28(j,i) + S26(j,i) * V28(j,i) end do end do into two disjoint loops do i = 1, n do j = 1, m A24(j,i)= S24(j,i) * T24(j,i) + S25(j,i) * U25(j,i) B24(j,i)= S24(j,i) * T25(j,i) + S25(j,i) * U24(j,i) A25(j,i)= S24(j,i) * C24(j,i) + S25(j,i) * V24(j,i) B25(j,i)= S24(j,i) * U25(j,i) + S25(j,i) * V25(j,i) end do end do do i = 1, n do j = 1, m C24(j,i)= S26(j,i) * T26(j,i) + S27(j,i) * U26(j,i) D24(j,i)= S26(j,i) * T27(j,i) + S27(j,i) * V26(j,i) C25(j,i)= S27(j,i) * S28(j,i) + S26(j,i) * U28(j,i) D25(j,i)= S27(j,i) * T28(j,i) + S26(j,i) * V28(j,i) end do end do Conclusions Over the course of the last year, I have had the opportunity to work with over two dozen academic scientific programmers at leading research universities. Their research interests span a broad range of scientific fields. Except for two programs that relied almost exclusively on library routines (matrix multiply and fast Fourier transform), I was able to improve significantly the single processor performance of all codes. Improvements range from 2x to 15.5x with a simple average of 4.75x. Changes to the source code were at a very high level. I did not use sophisticated techniques or programming tools to discover inefficiencies or effect the changes. Only one code was parallel despite the availability of parallel systems to all developers. Clearly, we have a problem—personal scientific research codes are highly inefficient and not running parallel. The developers are unaware of simple optimization techniques to make programs run faster. They lack education in the art of code optimization and parallel programming. I do not believe we can fix the problem by publishing additional books or training manuals. To date, the developers in questions have not studied the books or manual available, and are unlikely to do so in the future. Short courses are a possible solution, but I believe they are too concentrated to be much use. The general concepts can be taught in a three or four day course, but that is not enough time for students to practice what they learn and acquire the experience to apply and extend the concepts to their codes. Practice is the key to becoming proficient at optimization. I recommend that graduate students be required to take a semester length course in optimization and parallel programming. We would never give someone access to state-of-the-art scientific equipment costing hundreds of thousands of dollars without first requiring them to demonstrate that they know how to use the equipment. Yet the criterion for time on state-of-the-art supercomputers is at most an interesting project. Requestors are never asked to demonstrate that they know how to use the system, or can use the system effectively. A semester course would teach them the required skills. Government agencies that fund academic scientific research pay for most of the computer systems supporting scientific research as well as the development of most personal scientific codes. These agencies should require graduate schools to offer a course in optimization and parallel programming as a requirement for funding. About the Author John Feo received his Ph.D. in Computer Science from The University of Texas at Austin in 1986. After graduate school, Dr. Feo worked at Lawrence Livermore National Laboratory where he was the Group Leader of the Computer Research Group and principal investigator of the Sisal Language Project. In 1997, Dr. Feo joined Tera Computer Company where he was project manager for the MTA, and oversaw the programming and evaluation of the MTA at the San Diego Supercomputer Center. In 2000, Dr. Feo joined Sun Microsystems as an HPC application specialist. He works with university research groups to optimize and parallelize scientific codes. Dr. Feo has published over two dozen research articles in the areas of parallel parallel programming, parallel programming languages, and application performance.

    Read the article

facebook twitter digg google delicious technorati stumbleupon myspace wordpress linkedin gmail igoogle windows live tumblr viadeo yahoo buzz yahoo mail yahoo bookmarks favorites email print

< Previous Page | 6 7 8 9 10