DOCSLIB.ORG

Wind River Simics

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Wind River Simics Wind River Simics Simics allows companies to become Table of Contents Networks and Buses ......................4 more competitive by enabling improved Target RTOS Support .....................4 Optimize Your Entire Product product capability and quality while Life Cycle .............................................2 Capabilities ....................................5 reducing technical risk, schedule risk, and development cost across the full Platform Engineering .....................2 Modeling ........................................5 product development life cycle. Application Development ..............2 Host Support ..................................5 System Integration and Test ..........3 Target Support ....................................5 Simics virtual platforms can be as complex or as simple as your actual Project Management ......................3 Target Devices ................................5 physical hardware. They can contain Quick and Efficient Modeling ..............4 Target CPU Architectures ...............5 multi-core processors, multiple processor Features and Capabilities ....................4 SoC Families ...................................6 boards, or multiple-board systems. This Scalability .......................................4 Commercial Board Virtual provides the ability to debug your Connectivity/Interface ...................4 Platforms ........................................6 system as a whole, instead of just debugging individual pieces. Simics virtual platforms can contain a mix of Wind River Simics allows product teams to hardware for software development and different target hardware architectures, adopt a development methodology where testing. Simics virtual platforms are including mixed endian architectures. physical system hardware is replaced by unique. They are fast and accurate enough Simics virtual platforms eliminate Simics virtual platforms running on a to run a full software stack from hypervisor problems associated with using physical workstation or a PC. The virtual platform to application, and they guarantee hardware for product development such can run the same binary software as the repeatable software execution, full as limited target availability, flaky physical hardware and is fast enough to visibility/control of the virtual target prototype hardware, and hardware be used as an alternative to physical hardware, and true reverse execution. delays. Simics improves a project’s workflow by • Executable specification supporting true iterative development, • Scalable from single hands-on system architecture investiga- board to many boards tions, and the ability to begin software • Fast enough to run real development independent of hardware software loads • Mixed CPU architecture • Utilize virtual availability. By taking advantage of systems Define development system Simics as a consistent platform through- • Multi-core • Run the same binaries out the development process, teams are • Networking used by physical hardware able to improve their entire product • Save, share, restore development life cycle to shorten Deploy Develop complete system time-to-market and customer adoption. states Overall expenses are lowered and a • Force system fault conditions higher-quality product is delivered to the • Virtual platform • Execute in reverse to • Interim virtual platforms market place, increasing the satisfaction find source of bugs for early user feedback of your customers. • Demos, training, and tech support Figure 1: Wind River Simics supports the full product life cycle Optimize Your Entire Product Life Cycle The entire product development team—including hardware architects, hardware designers, software designers, software testers, system integrators, and system testers—can utilize virtual platforms. Virtual platforms also reduce costs of technical support activities when you need to maintain unique variants of hardware for each of your customers. In addition, virtual platforms can be used by sales and marketing teams to demonstrate new product capability and by customers for training purposes. What Simics Can Do for You Figure 2: Debugging software with Wind River Simics Define System Architecture • Leave paper behind and create an Platform Engineering access to physical hardware. Because a “executable specification.” The platform engineering team is virtual platform is entirely software • Make design decisions: How many comprised of hardware architects, configurable, it evolves much faster than CPUs? DSP or GPP? Cache size? hardware designers, and low-level physical hardware. This allows architec- Which software optimizations? software developers. The platform ture investigations and foundation software to be completed much earlier Develop Software engineering team defines and creates the product’s hardware architecture, than would be possible with traditional • Eliminate scheduling problems development approaches. due to limited target hardware system design, and foundation software. availability. In contrast to the paper trail that has Application Development • Perform “impossible” debugging. been traditionally used during the • Send a bit-exact system snapshot architecture phase, virtual platforms The application development team file to another developer for enable a hands-on resolution of technical architects, writes, optimizes, and tests collaboration. issues: software. Application development can • Say goodbye to “nonrepeatable be challenging when bugs.” • Use multi-core, accelerators, or both? • Eliminate big-bang integration: • Execute a function in GPP or DSP? • Key portions of the application come Start early and integrate progres- • What memory size and speed? from different development teams. sively. • Access to prototype hardware, debug The creation of a system’s foundation • Improve quality by testing tools, or instruments is limited. software—firmware, boot code, operat- hardware corner cases. • Debugging a single application requires ing system, and device drivers—can • Develop software applications access to the entire system. across heterogeneous OS environ- quickly become challenging if • Some bugs are only visible when run on the complete system. ments and hardware architectures. • Hardware is not yet available or • Bugs previously observed are not easily prototypes are not reliable. repeatable. Deploy Virtual Platforms • The hardware spec keeps changing. • You are developing multi-core applica- • Deploy virtual platforms to support • It is not possible to access key device tions. field teams. registers. • Demo your system on a laptop. Simics has supported application develop- The Simics virtual platform evolves with • Support new customer configura- ment on simulated systems comprised of the hardware design ensuring that tions easily and inexpensively. more than 50 boards and 700 processors, developers remain productive without 2 | Wind River Simics Traditional Product Life Cycle Product Life Cycle with VSD Resources Reduced Time-to-Market Software Increased Revenue Software Engineering Resources Engineering Resources Hardware Integration Hardware Integration and Test and Test Time Time Figure 3: Wind River Simics reduces time-to–market, compared to traditional product development including multi-core systems, heteroge- System Integration and Test engineer has only to freeze the system neous designs, multi-OS, and network System integration and test tasks can and send the checkpoint file to the distributed systems. Simics provides introduce significant risks to the success- software engineering team for guaran- complete control of hardware and time, ful delivery of the product, especially if teed bug duplication and subsequent support for seemingly impossible debug correction. • The hardware is late but the delivery scenarios, and complete run-to-run deadline has not moved. repeatability. As a result, individual • Tests cannot be completed due to lack Project Management developers and application teams work of target hardware. Project managers focus on higher-level more efficiently through the ability to • A hardware glitch interrupts tests, aspects of a program to ensure success- share system snapshots and to work with costing hours to restart or redo. ful completion and delivery of their the same compile/link/debug tools that • System faults cannot be forced without products: they are accustomed to using on physical physically breaking the hardware. target hardware. • Bugs do not reproduce themselves from • Design reviews run-to-run. • Hardware/software team collaboration A Simics virtual platform makes it much and communications easier to force, find, repeat, isolate, and When a virtual platform is used, integra- • Improved quality kill bugs by doing the following: tion can begin much earlier in the • Looming delivery deadlines development process. Now “integration” • Risk reduction • Running the same binaries that work on moves from a single high-profile task on the physical target Traditional development approaches, the Gantt chart to an evolving lower-risk • Freezing, saving, and restoring Simics where the hardware team moves on to activity that progresses forward as systems snapshots the next project immediately upon software becomes available. This progres- • Leveraging full visibility and control of delivery of the platform, can result in every device, register, and communica- sive integration approach can identify schedule delays, loss of features, or tions interface (e.g., Ethernet, virtual system problems much earlier than rework because the engineering
Load more

Recommended publications
  • Intel® Strongarm® SA-1110 High- Performance, Low-Power Processor for Portable Applied Computing Devices
    Advance Copy Intel® StrongARM® SA-1110 High- Performance, Low-Power Processor For Portable Applied Computing Devices PRODUCT HIGHLIGHTS ■ Innovative Application Specific Standard Product (ASSP) delivers leadership performance, integration and low power for palm-size devices, PC companions, smart phones and other emerging portable applied computing devices As businesses and individuals rely increasingly on portable applied ■ High-speed 100 MHz memory bus and a computing devices to simplify their lives and boost their productivity, flexible memory these devices have to perform more complex functions quickly and controller that adds efficiently. To satisfy ever-increasing customer demands to support for SDRAM, communicate and access information ‘anytime, anywhere’, SMROM, and variable- manufacturers need technologies that deliver high-performance, robust latency I/O devices — provides design functionality and versatility while meeting the small-size and low-power flexibility, scalability and restrictions of portable, battery-operated products. Intel designed the high memory bandwidth SA-1110 processor with all of these requirements in mind. ■ Rich development The Intel® SA-1110 is a highly integrated 32-bit StrongARM® environment enables processor that incorporates Intel design and process technology along leading edge products with the power efficiency of the ARM* architecture. The SA-1110 is while reducing time- to-market software compatible with the ARM V4 architecture while utilizing a high-performance micro-architecture that is optimized to take advantage of Intel process technology. The Intel SA-1110 provides the performance, low power, integration and cost benefits of the Intel SA-1100 processor plus a high speed memory bus, flexible memory controller and the ability to handle variable-latency I/O devices.
    [Show full text]
  • Comparison of Contemporary Real Time Operating Systems
    ISSN (Online) 2278-1021 IJARCCE ISSN (Print) 2319 5940 International Journal of Advanced Research in Computer and Communication Engineering Vol. 4, Issue 11, November 2015 Comparison of Contemporary Real Time Operating Systems Mr. Sagar Jape1, Mr. Mihir Kulkarni2, Prof.Dipti Pawade3 Student, Bachelors of Engineering, Department of Information Technology, K J Somaiya College of Engineering, Mumbai1,2 Assistant Professor, Department of Information Technology, K J Somaiya College of Engineering, Mumbai3 Abstract: With the advancement in embedded area, importance of real time operating system (RTOS) has been increased to greater extent. Now days for every embedded application low latency, efficient memory utilization and effective scheduling techniques are the basic requirements. Thus in this paper we have attempted to compare some of the real time operating systems. The systems (viz. VxWorks, QNX, Ecos, RTLinux, Windows CE and FreeRTOS) have been selected according to the highest user base criterion. We enlist the peculiar features of the systems with respect to the parameters like scheduling policies, licensing, memory management techniques, etc. and further, compare the selected systems over these parameters. Our effort to formulate the often confused, complex and contradictory pieces of information on contemporary RTOSs into simple, analytical organized structure will provide decisive insights to the reader on the selection process of an RTOS as per his requirements. Keywords:RTOS, VxWorks, QNX, eCOS, RTLinux,Windows CE, FreeRTOS I. INTRODUCTION An operating system (OS) is a set of software that handles designed known as Real Time Operating System (RTOS). computer hardware. Basically it acts as an interface The motive behind RTOS development is to process data between user program and computer hardware.
    [Show full text]
  • Fax86: an Open-Source FPGA-Accelerated X86 Full-System Emulator
    FAx86: An Open-Source FPGA-Accelerated x86 Full-System Emulator by Elias El Ferezli A thesis submitted in conformity with the requirements for the degree of Master of Applied Science (M.A.Sc.) Graduate Department of Electrical and Computer Engineering University of Toronto Copyright c 2011 by Elias El Ferezli Abstract FAx86: An Open-Source FPGA-Accelerated x86 Full-System Emulator Elias El Ferezli Master of Applied Science (M.A.Sc.) Graduate Department of Electrical and Computer Engineering University of Toronto 2011 This thesis presents FAx86, a hardware/software full-system emulator of commodity computer systems using x86 processors. FAx86 is based upon the open-source IA-32 full-system simulator Bochs and is implemented over a single Virtex-5 FPGA. Our first prototype uses an embedded PowerPC to run the software portion of Bochs and off- loads the instruction decoding function to a low-cost hardware decoder since instruction decode was measured to be the most time consuming part of the software-only emulation. Instruction decoding for x86 architectures is non-trivial due to their variable length and instruction encoding format. The decoder requires only 3% of the total LUTs and 5% of the BRAMs of the FPGA's resources making the design feasible to replicate for many- core emulator implementations. FAx86 prototype boots Linux Debian version 2.6 and runs SPEC CPU 2006 benchmarks. FAx86 improves simulation performance over the default Bochs by 5 to 9% depending on the workload. ii Acknowledgements I would like to begin by thanking my supervisor, Professor Andreas Moshovos, for his patient guidance and continuous support throughout this work.
    [Show full text]
  • IXP400 Software's Programmer's Guide
    Intel® IXP400 Software Programmer’s Guide June 2004 Document Number: 252539-002c Intel® IXP400 Software Contents INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL® PRODUCTS. EXCEPT AS PROVIDED IN INTEL'S TERMS AND CONDITIONS OF SALE FOR SUCH PRODUCTS, INTEL ASSUMES NO LIABILITY WHATSOEVER, AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY RELATING TO SALE AND/OR USE OF INTEL PRODUCTS, INCLUDING LIABILITY OR WARRANTIES RELATING TO FITNESS FOR A PARTICULAR PURPOSE, MERCHANTABILITY, OR INFRINGEMENT OF ANY PATENT, COPYRIGHT, OR OTHER INTELLECTUAL PROPERTY RIGHT. Intel Corporation may have patents or pending patent applications, trademarks, copyrights, or other intellectual property rights that relate to the presented subject matter. The furnishing of documents and other materials and information does not provide any license, express or implied, by estoppel or otherwise, to any such patents, trademarks, copyrights, or other intellectual property rights. Intel products are not intended for use in medical, life saving, life sustaining, critical control or safety systems, or in nuclear facility applications. The Intel® IXP400 Software v1.2.2 may contain design defects or errors known as errata which may cause the product to deviate from published specifications. Current characterized errata are available on request. MPEG is an international standard for video compression/decompression promoted by ISO. Implementations of MPEG CODECs, or MPEG enabled platforms may require licenses from various entities, including Intel Corporation. This document and the software described in it are furnished under license and may only be used or copied in accordance with the terms of the license. The information in this document is furnished for informational use only, is subject to change without notice, and should not be construed as a commitment by Intel Corporation.
    [Show full text]
  • Comparative Architectures
    Comparative Architectures CST Part II, 16 lectures Lent Term 2006 David Greaves [email protected] Slides Lectures 1-13 (C) 2006 IAP + DJG Course Outline 1. Comparing Implementations • Developments fabrication technology • Cost, power, performance, compatibility • Benchmarking 2. Instruction Set Architecture (ISA) • Classic CISC and RISC traits • ISA evolution 3. Microarchitecture • Pipelining • Super-scalar { static & out-of-order • Multi-threading • Effects of ISA on µarchitecture and vice versa 4. Memory System Architecture • Memory Hierarchy 5. Multi-processor systems • Cache coherent and message passing Understanding design tradeoffs 2 Reading material • OHP slides, articles • Recommended Book: John Hennessy & David Patterson, Computer Architecture: a Quantitative Approach (3rd ed.) 2002 Morgan Kaufmann • MIT Open Courseware: 6.823 Computer System Architecture, by Krste Asanovic • The Web http://bwrc.eecs.berkeley.edu/CIC/ http://www.chip-architect.com/ http://www.geek.com/procspec/procspec.htm http://www.realworldtech.com/ http://www.anandtech.com/ http://www.arstechnica.com/ http://open.specbench.org/ • comp.arch News Group 3 Further Reading and Reference • M Johnson Superscalar microprocessor design 1991 Prentice-Hall • P Markstein IA-64 and Elementary Functions 2000 Prentice-Hall • A Tannenbaum, Structured Computer Organization (2nd ed.) 1990 Prentice-Hall • A Someren & C Atack, The ARM RISC Chip, 1994 Addison-Wesley • R Sites, Alpha Architecture Reference Manual, 1992 Digital Press • G Kane & J Heinrich, MIPS RISC Architecture
    [Show full text]
  • Arm C Language Extensions Documentation Release ACLE Q1 2019
    Arm C Language Extensions Documentation Release ACLE Q1 2019 Arm Limited. Mar 21, 2019 Contents 1 Preface 1 1.1 Arm C Language Extensions.......................................1 1.2 Abstract..................................................1 1.3 Keywords.................................................1 1.4 How to find the latest release of this specification or report a defect in it................1 1.5 Confidentiality status...........................................1 1.5.1 Proprietary Notice.......................................2 1.6 About this document...........................................3 1.6.1 Change control.........................................3 1.6.1.1 Change history.....................................3 1.6.1.2 Changes between ACLE Q2 2018 and ACLE Q1 2019................3 1.6.1.3 Changes between ACLE Q2 2017 and ACLE Q2 2018................3 1.6.2 References...........................................3 1.6.3 Terms and abbreviations....................................3 1.7 Scope...................................................4 2 Introduction 5 2.1 Portable binary objects..........................................5 3 C language extensions 7 3.1 Data types................................................7 3.1.1 Implementation-defined type properties............................7 3.2 Predefined macros............................................8 3.3 Intrinsics.................................................8 3.3.1 Constant arguments to intrinsics................................8 3.4 Header files................................................8
    [Show full text]
  • AASP Brief 031704F.Pdf
    servicebrief Avnet Avenue Service Provider Program Avnet Design Services has teamed up with the top design service companies in North America to provide you with superior component, board and system level solutions. In cooperation with Avnet Design Services, you can access these pre-screened and certified design service providers. WHAT is the Avnet Avenue Service Provider Program? A geographically dispersed and technical diverse network of design service providers available to fulfill your design service needs Avnet's seven partners are the top design service companies in North America The program compliments Avnet Design Services' ASIC and FPGA design service offerings by providing additional component, board and system-level design services WHY use an Avnet Avenue Service Provider? Time to Market The program provides additional technical resources to assist you in meeting your time to market requirements Value All Providers are selected based on their ability to provide cost competitive solutions Experience All Providers have proven experience completing a wide array of projects on time and within budget Less Risk All Providers are pre-screened and certified to ensure your success Technology The program provides you with single source access to a broad range of services and technical expertise Scale All Providers are capable of supporting the full range of design service requirements from very large to small HOW do I access the Avnet Avenue Service Provider Program? Contact your local Avnet Representative or call 1-800-585-1602 so that
    [Show full text]
  • Ramp: Research Accelerator for Multiple Processors
    ..................................................................................................................................................................................................................................................... RAMP: RESEARCH ACCELERATOR FOR MULTIPLE PROCESSORS ..................................................................................................................................................................................................................................................... THE RAMP PROJECT’S GOAL IS TO ENABLE THE INTENSIVE, MULTIDISCIPLINARY INNOVATION John Wawrzynek THAT THE COMPUTING INDUSTRY WILL NEED TO TACKLE THE PROBLEMS OF PARALLEL David Patterson PROCESSING. RAMP ITSELF IS AN OPEN-SOURCE, COMMUNITY-DEVELOPED, FPGA-BASED University of California, EMULATOR OF PARALLEL ARCHITECTURES. ITS DESIGN FRAMEWORK LETS A LARGE, Berkeley COLLABORATIVE COMMUNITY DEVELOP AND CONTRIBUTE REUSABLE, COMPOSABLE DESIGN Mark Oskin MODULES. THREE COMPLETE DESIGNS—FOR TRANSACTIONAL MEMORY, DISTRIBUTED University of Washington SYSTEMS, AND DISTRIBUTED-SHARED MEMORY—DEMONSTRATE THE PLATFORM’S POTENTIAL. Shih-Lien Lu ...... In 2005, the computer hardware N Prototyping a new architecture in Intel industry took a historic change of direction: hardware takes approximately four The major microprocessor companies all an- years and many millions of dollars, nounced that their future products would even at only research quality. Christoforos Kozyrakis be single-chip multiprocessors, and that N Software
    [Show full text]
  • Computer Architectures an Overview
    Computer Architectures An Overview PDF generated using the open source mwlib toolkit. See http://code.pediapress.com/ for more information. PDF generated at: Sat, 25 Feb 2012 22:35:32 UTC Contents Articles Microarchitecture 1 x86 7 PowerPC 23 IBM POWER 33 MIPS architecture 39 SPARC 57 ARM architecture 65 DEC Alpha 80 AlphaStation 92 AlphaServer 95 Very long instruction word 103 Instruction-level parallelism 107 Explicitly parallel instruction computing 108 References Article Sources and Contributors 111 Image Sources, Licenses and Contributors 113 Article Licenses License 114 Microarchitecture 1 Microarchitecture In computer engineering, microarchitecture (sometimes abbreviated to µarch or uarch), also called computer organization, is the way a given instruction set architecture (ISA) is implemented on a processor. A given ISA may be implemented with different microarchitectures.[1] Implementations might vary due to different goals of a given design or due to shifts in technology.[2] Computer architecture is the combination of microarchitecture and instruction set design. Relation to instruction set architecture The ISA is roughly the same as the programming model of a processor as seen by an assembly language programmer or compiler writer. The ISA includes the execution model, processor registers, address and data formats among other things. The Intel Core microarchitecture microarchitecture includes the constituent parts of the processor and how these interconnect and interoperate to implement the ISA. The microarchitecture of a machine is usually represented as (more or less detailed) diagrams that describe the interconnections of the various microarchitectural elements of the machine, which may be everything from single gates and registers, to complete arithmetic logic units (ALU)s and even larger elements.
    [Show full text]
  • Network Processors: Building Block for Programmable Networks
    NetworkNetwork Processors:Processors: BuildingBuilding BlockBlock forfor programmableprogrammable networksnetworks Raj Yavatkar Chief Software Architect Intel® Internet Exchange Architecture [email protected] 1 Page 1 Raj Yavatkar OutlineOutline y IXP 2xxx hardware architecture y IXA software architecture y Usage questions y Research questions Page 2 Raj Yavatkar IXPIXP NetworkNetwork ProcessorsProcessors Control Processor y Microengines – RISC processors optimized for packet processing Media/Fabric StrongARM – Hardware support for Interface – Hardware support for multi-threading y Embedded ME 1 ME 2 ME n StrongARM/Xscale – Runs embedded OS and handles exception tasks SRAM DRAM Page 3 Raj Yavatkar IXP:IXP: AA BuildingBuilding BlockBlock forfor NetworkNetwork SystemsSystems y Example: IXP2800 – 16 micro-engines + XScale core Multi-threaded (x8) – Up to 1.4 Ghz ME speed RDRAM Microengine Array Media – 8 HW threads/ME Controller – 4K control store per ME Switch MEv2 MEv2 MEv2 MEv2 Fabric – Multi-level memory hierarchy 1 2 3 4 I/F – Multiple inter-processor communication channels MEv2 MEv2 MEv2 MEv2 Intel® 8 7 6 5 y NPU vs. GPU tradeoffs PCI XScale™ Core MEv2 MEv2 MEv2 MEv2 – Reduce core complexity 9 10 11 12 – No hardware caching – Simpler instructions Î shallow MEv2 MEv2 MEv2 MEv2 Scratch pipelines QDR SRAM 16 15 14 13 Memory – Multiple cores with HW multi- Controller Hash Per-Engine threading per chip Unit Memory, CAM, Signals Interconnect Page 4 Raj Yavatkar IXPIXP 24002400 BlockBlock DiagramDiagram Page 5 Raj Yavatkar XScaleXScale
    [Show full text]
  • Strongarm™ SA-1100 Microprocessor for Portable
    StrongARM™ SA-1100 Microprocessor for Portable Applications Brief Datasheet Product Features The StrongARM™ SA-1100 Microprocessor (SA-1100) is a device targeted to provide portable applications with high-end computing performance without requiring users to sacrifice available battery time. The SA-1100 incorporates a 32-bit StrongARM™ RISC processor with instruction and data cache, memory-management unit (MMU), and read/write buffers running at 133/190 MHz. In addition, the SA-1100 provides system support logic, multiple serial communication channels, a color/gray scale LCD controller, PCMCIA support for up to two sockets, and general-purpose I/O ports. ■ High performance ■ 208-pin thin quad flat pack (LQFP) —150 Dhrystone 2.1 MIPS @ 133 MHz ■ 256 mini-ball grid array (mBGA) —220 Dhrystone 2.1 MIPS @ 190 MHz ■ Low power (normal mode)† ■ 32-way set-associative caches —<230 mW @1.5 V/133 MHz —16 Kbyte instruction cache —<330 mW @1.5 V/190 MHz —8 Kbyte write-back data cache ■ Integrated clock generation ■ 32-entry MMUs —Internal phase-locked loop (PLL) —Maps 4 Kbyte, 8 Kbyte, or 1 Mbyte —3.686-MHz oscillator —32.768-kHz oscillator ■ Power-management features ■ Write buffer —Normal (full-on) mode —8-entry, between 1 and 16 bytes each —Idle (power-down) mode —Sleep (power-down) mode ■ Big and little endian operating modes ■ Read buffer —4-entry, 1, 4, or 8 words ■ 3.3-V I/O interface ■ Memory bus —Interfaces to ROM, Flash, SRAM, and DRAM —Supports two PCMCIA sockets † Power dissipation, particularly in idle mode, is strongly dependent on the details of the system design Order Number: 278087-002 November 1998 Information in this document is provided in connection with Intel products.
    [Show full text]
  • Selected Project Reports, Spring 2005 Advanced OS & Distributed Systems
    Selected Project Reports, Spring 2005 Advanced OS & Distributed Systems (15-712) edited by Garth A. Gibson and Hyang-Ah Kim Jangwoo Kim††, Eriko Nurvitadhi††, Eric Chung††; Alex Nizhner†, Andrew Biggadike†, Jad Chamcham†; Srinath Sridhar∗, Jeffrey Stylos∗, Noam Zeilberger∗; Gregg Economou∗, Raja R. Sambasivan∗, Terrence Wong∗; Elaine Shi∗, Yong Lu∗, Matt Reid††; Amber Palekar†, Rahul Iyer† May 2005 CMU-CS-05-138 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 †Information Networking Institute ∗Department of Computer Science ††Department of Electrical and Computer Engineering Abstract This technical report contains six final project reports contributed by participants in CMU’s Spring 2005 Advanced Operating Systems and Distributed Systems course (15-712) offered by professor Garth Gibson. This course examines the design and analysis of various aspects of operating systems and distributed systems through a series of background lectures, paper readings, and group projects. Projects were done in groups of two or three, required some kind of implementation and evalution pertaining to the classrom material, but with the topic of these projects left up to each group. Final reports were held to the standard of a systems conference paper submission; a standard well met by the majority of completed projects. Some of the projects will be extended for future submissions to major system conferences. The reports that follow cover a broad range of topics. These reports present a characterization of synchronization behavior
    [Show full text]