USING JAVA HARTSTONE BENCHMARK IN A REAL-TIME SYSTEMS COURSE

Size: px
Start display at page:

Download "USING JAVA HARTSTONE BENCHMARK IN A REAL-TIME SYSTEMS COURSE"

Transcription

1 USING JAVA HARTSTONE BENCHMARK IN A REAL-TIME SYSTEMS COURSE Andy Ju An Wang 1 Abstract This paper shows how a Java benchmark program can be utilized in a real-time systems course to emphasize fundamental concepts and principles in hard real-time systems. Benchmark programs are used to compare the relative speeds of computers and language implementations. The Java Hartstone benchmark was used in our course project to test various Java virtual machines (JVMs) for their suitability of supporting hard real time applications. With the Java Hartstone benchmark, our experiment was carried out using all four benchmark experiments under controlled conditions to provide reliable analysis. The characteristics and expected behavior of the benchmark are described, actual results from the benchmark testing are presented and analyzed, and the lessons learned about using real-time benchmark programs in a real-time systems course are discussed. Index Terms Benchmark testing, Hartstone benchmark, Java virtual machines, real-time systems, real-time performance 1. INTRODUCTION One of the difficulties of teaching a real-time course is to help students distinguishing real-time software from conventional software and understanding issues of timecritical computing in a "real" environment. Textbooks (for instance, [5,6,7]) provide good examples for hard real-time systems like air traffic control systems, process monitor and control systems, missile-guiding systems, etc. None of them, however, can be practiced by students in a classroom setting. Hard real-time systems are those where it is absolutely imperative that responses occur within the specified deadline. Missing a hard deadline can result in catastrophic consequences or loss of system performance. The primary issue in meeting deadlines in a real-time system is that multiple tasks can compete for shared resources such as processors, memory, and I/O devices. Higher processor speed or higher communication bandwidth is important to meet system timing requirements, but speed alone is not enough. A well-designed scheduler is also important to ensure that a hard real-time system meets its performance requirements. Our experience shows that understanding basic concepts of task scheduling helps students to capture major characteristics of real-time systems. Instead of asking students to design and implement their own scheduling algorithms, we ask our students to learn a benchmark program for real-time systems, and use the benchmark program to compare different Java virtual machines for their suitability in hard real-time applications. Benchmark programs are used to compare the relative speeds of computers and language implementations. One of the most important benchmarks for real-time systems is the Whetstone benchmark [1]. It is a synthetic benchmark, which means that rather than performing any useful function, it is constructed based on the instruction frequencies of a representative set of programs. The Hartstone benchmark originally began as a specification at the Software Engineering Institute at Carnegie Mellon University in 1989, which specified five different series of experiments that would analyze an Ada runtime system for its suitability in a hard real-time environment. The name Hartstone was derived from Hard Real Time and the fact that the workloads are based on the well-known Whetstone benchmark. After about one year, an Ada implementation for the first series of experiments described in the specification was released, as well as results for a number of Ada runtime systems. Since then, Hartstone has been an influential benchmark in evaluating Ada systems [1, 2, 3, 4]. Java Hartstone is a Java implementation based on the Ada version Hartstone to test the suitability of Java virtual machines for hard real-time applications. It consists of four experiments, creating five separate threads, each of which will run at a specific frequency, and execute a fixed amount of work each time it is awakened. The work it executes is an altered Whetstone benchmark, designed to execute 1 Whetstone instructions, and it executes that workload a given number of times. The baseline test involves five tasks given the following frequencies and workloads in Table 1: Task TABLE I FIVE TASKS IN THE BASELINE TEST Frequency (Hz) Workload (Work Units) Work Units/Second 1 Andy Ju An Wang, School of Computing and Software Engineering, Southern Polytechnic State University, 11 S Marietta Parkway, Marietta, GA 36 jwang@spsu.edu S2F-25

2 When running each of the four experiments, a series of tests start, each running 1 seconds, until a failure occurs that represents one missed deadline or a number or percentage of missed deadlines. The raw speed of the system is calculated by running the workload in a single thread. The system s utilization is calculated by dividing the number of work units performed in the last test by the raw speed. This percentage indicates how much of the computational power of the system can be used and still be able to meet its deadlines. For each successive test, the experiments alter the parameters in the following way: Experiment 1: The highest frequency task (#5) has its frequency increased by the frequency of the next highest (#4). This experiment tests if the system can switch between threads quickly and if it can handle fine-grained scheduling. Experiment 2: The frequencies of all the tasks are scaled by 1% (so the second test is 11%, third is 12%, 13%, and so on). This tests the performance of the system on an increasing workload, but with task frequencies increasing evenly. Experiment 3: The workload each task performs at each activation is increased by 1. This experiment increases the workload gradually, but has no effect on switching overhead because task frequencies are not changed. Experiment 4: A new task is created with frequency and workload equal to that of the middle task (#3), so the second test has 6 tasks running, the third has 7, and so on. This determines the number of tasks a system can handle and still meet real-time deadlines. The author used Java Hartstone benchmark successfully in our CS6283 Real-Time System course. For the purpose of this course, four common Java virtual machines were selected as the target systems as demonstrated in Table II: TABLE II FOUR JAVA VIRTUAL MACHINES UNDER TEST Name Version Vendor Justification java Sun Microsystems, Inc. Original Java reference implementation, widely used java 1.3 IBM Strong supporter for Java, big player in computer industry pvm NewMonics, Inc. jrockit Appeal Virtual Machines AB With real-time capabilities for embedded systems Highly scalable, combining OO optimization techniques Our selection of JVMs for testing was largely based on their appealing features claimed by the vendors. For instance, the PERC JVM (pvm) can be tuned to prefer runtime performance, startup time or memory footprint. It is available for a variety of operating systems and processors. JRockit by Appeal is a highly scalable, adaptive, optimized JVM with full JDK1.3 support. It combines object-oriented optimization techniques with a highly scalable runtime architecture. As a result, JRockit allows mo re threads, faster I/O and better memory management than any other JVMs running on the same hardware. It is interesting to test their capability for supporting hard real-time applications with a standard benchmark program. The next section introduces the methods and procedures of running Java Hartstone benchmark. Section 3 provides some of our experiment results. Section 4 discusses the interpretations of the results. Conclusions and discussions are summarized in Section METHODS AND PROCEDURES The PERC3.1.1 product comes with a source version of the Java Hartstone benchmark. We used this version to build and run the Hartstone tests. For the convenience of writing, we describe only here the methods and procedures on a Windows platform. Similar methods can be applied on other computing platforms to run Java Hartstone benchmark. The first step is to start up a command window to compile the Java Hartstone source files using an appropriate compiler. The experiment presented here used the IBM compiler with the following command: jikes benchmarks/hartstone/*.java When running an experiment, it is necessary to run a baseline test to determine what frequency and workload settings to use. The command we need to run Hartstone is as below: -e <experiment #> -t 1 where <VM> is the name of the Java virtual machine to use, and experiment# is the experiment number (1-4). For instance, with the command java benchmarks.hartstone.hartstone e 1 t 1, the output will be the following: Sleep granularity: 1 ms currenttimemillis() granularity: 1 ms Experiment: Increasing Frequency Experiment (PH1) Raw speed in Work Units Per Second (WUPS): Test 1 characteristics: Task # Freq. (Hz) WU/Period WU/Second Workload util S2F-26

3 % 3. INTERPRETING THE RESULTS Step size: % Test 1 results: Test duration (seconds): 1. Task # Met Missed Skipped Average Late (msec) Most Late When it prints its results, we need to look at the total utilization that the test reached, which should be around 2%. If not, we need to scale the baseline task frequencies or workloads to bring the baseline utilization to about 2%. Otherwise, the experiment will probably take longer time to complete, though the final result should not change. For instance, the above output shows that only about 2% of utilization was reached. Usually it is recommended to scale the workload before scaling the frequency, because all Java VMs are limited to a 1-ms accurate timer, so scaling the frequency too high in the baseline test could cause premature failure due to timer problems. Use -w <n> to scale the workload of each task by a factor of n, and -f <n> to scale the frequencies by a factor of n. Once we figured out suitable frequency and workload scales (f and w), we can run Hartstone as follows: -e <experiment#> -full -f <f> -w <w> As the experiment progresses, results will be printed for the baseline test, the last test that ran with no missed deadlines, the first test with failed deadlines, and the last test ran. Once complete, take note of the total utilization percentage of the last successful test, which is the VM s score for that experiment. That is the utilization at which the VM can run at and still meet hard real-time requirements. Additional options for the command line can be found in [4]. With the machine configuration listed in Appendix A at the end of this paper, we used the following commands to complete the experiment: -e 1 -full -f 2 -w 5 -e 2 -full -f 2 -w 5 -e 3 -full -f 1 -w 1 -e 4 -full -f 1 -w 1 These commands were first applied to Sun JVM and then repeated for PERC JVM, JRockit JVM, and IBM JVM. The first important value output by Java Hartstone benchmark is the raw speed of the system. The raw speed shows the total number of workloads per second the system can handle running the workloads on a single thread. The raw speed represents full utilization of the system. The workload utilization is used to determine the percentage of utilization of the system by dividing the workloads completed by the last test to succeed by the raw speed in workload units per second. The frequency is the number of times per second the workload units will be performed. The most important result for each experiment is the utilization percentage from the last test in the experiment to succeed. This value can be considered a score for that experiment as well as a measurement of how well the VM is able to utilize its full capability for real-time systems. Also important is the work units per period completed by the last successful test. This value is a sum of the total work units that the VM was able to successfully complete for an experiment. The work units per period summed for the last test makes a useful value to measure the performance of the Java virtual machine on an identical machine configuration. Each experiment increases the workload in different ways to test different capabilities of the JVM. Each task set consists of five tasks. Experiment 1 tries to test the system s ability to schedule an increasing number of tasks per second as it increases the frequency of task 5 each test run while leaving the other tasks alone. This means that task 5 will try to schedule more per second. This tests the VM s ability to schedule tasks as an ever decreasing granularity and to switch rapidly between processes as it tries to complete the workload for all the running threads. This experiment s results are related to how much system overhead the VM requires. Experiment 2 increases the frequency of each task in the test set by 1% for each new test until the deadline is missed. Each task does the same workload per period but by increasing the frequency the total number of periods increases, increasing the total workload for each task. This tests the systems ability to handle more work at higher frequency rates. As in experiment 1, with experiment 2 increases the frequency, overhead of scheduling threads is increased. Experiment 3 increases the workloads of each task by 1 work unit each new test and does not change the frequency for the tasks. Unlike the previous experiments, this test does not increase the system overhead of scheduling the workloads, it just schedules more work. This tests the systems ability to handle an increasing workload but with no increasing scheduling overhead. Experiment 4 actually adds new tasks each time it runs. Unlike the other tests, the workload and frequency stays the same while the number of tasks increases each time. This experiment will show how well the system can handle a large number of tasks as the previous experiments only ran five tasks each time. S2F-27

4 4. EXPERIMENTING RESULTS Scaled Frequency Experiment 2 As demonstrated in Table III below, the Increasing Frequency Experiment (experiment 1) as illustrated in Figure 1 showed that the PERC VM had the highest percentage of utilization. But when we inspect the numbers further it is obvious that the IBM VM had the best performance with a raw speed of 5769 and 19.44% utilization for 112 work units per second (WUPS) TABLE III TESTING RESULT IN EXPERIMENT 1 Sun VM JRockit VM Perc VM IBM VM Increasing Frequency Experiment 1 1 FIGURE. 2 THE RESULT FOR EXPERIMENT 2 On the Increasing Workload Experiment (Experiment 3), the IBM VM had the highest percent utilization as well as the highest WUPS, as illustrated in Table V and Figure 3 below. TABLE V TESTING RESULT IN EXPERIMENT 3 Sun VM JRockit VM Perc VM IBM VM Increasing Workload Experiment FIGURE. 1 THE RESULT FOR EXPERIMENT Table IV and Figure 2 below summarize the testing result for the Experiment 2. The Scaled Frequency Experiment also showed the PERC VM with the highest percent utilization but once again the IBM VM was the top performer with 42.44% utilization of over 584,38 raw speed WUPS given it over 248, WUPS utilization. TABLE IV TESTING RESULT IN EXPERIMENT 2 Sun VM JRockit VM Perc VM IBM VM FIGURE. 3 THE RESULT FOR EXPERIMENT 3 The Increasing Tasks Experiment (Experiment 4, Table VI, and Figure 4) showed the PERC VM with the highest percent utilization but once again the IBM VM outperformed it with 368, WUPS utilized out of 584,38.13 raw speed WUPS. S2F-28

5 TABLE VI TESTING RESULT IN EXPERIMENT 4 Sun VM JRockit VM Perc VM IBM VM Increasing Tasks Experiment 4 FIGURE. 4 THE RESULT FOR EXPERIMENT 4 Figure 5 compares the four JVMs in terms of their workload utilizations. If we just compared the percentage of workload utilization, the PERC VM was the winner in all categories by the Increasing Workload Experiment. But the IBM VM was hands down the highest performing VM with the Sun VM closely behind it. The JRockit VM showed good raw speed performance but the workload utilization percentages were the lowest in every experiment. One thing that stood out from the benchmark output for the JRockit was the Sleep Granularity value. JRockit had a 53 ms sleep granularity while the other VM s had only a 1 ms sleep granularity. This likely explains JRockit low performance with thread scheduling. 12 Virtual Machine Utilization 5. CONCLUSIONS AND DISCUSSION The Java Hartstone benchmark provides a useful way to test a Java VM for real-time system handling performance. The IBM VM was clearly the workhorse of all the VM s with higher work units per second than any of the others and higher work units per second utilization. Even at a low percent utilization, the IBM VM was just able to handle more work and more thread scheduling. But one limiting factor to the whole test was the test machine configuration. Windows 2 is far from a real-time operating system with many other background OS threads running while a real real-time operating system (RTOS) would probably only have the single embedded system process running on the whole OS, thus it would be much better at handling thread scheduling request from just its single running process. The Java Hartstone benchmark might be better run on an embedded system version of Java running on an embedded system to truly test a systems real-time performance. In our real-time systems course, students were divided into several groups to testing different Java virtual machines with the same benchmark program. It was interesting to discover that testing results were slightly different due to the fact that different hardware and software platforms were used by different groups. One potential future work is to find a calculating method to sum up and average the results obtained from different groups so that we could reach a statistical and consistent assessment for selected Java virtual machines. Another issue is to make the experiment reproducible. For instance, we ought to compile the Java Hartstone benchmark program using only one compiler and test all the selected Java virtual machines with the same byte-code. Background running processes and user interference, like moving the mouse around, should be minimized during the testing process. Moreover, we should first scale up workload before scaling frequency due to the timing granularity of Java virtual machines. Finally, it is interesting to test more Java virtual machines to have a complete comparison among JVMs in terms of their suitability for hard real-time applications. 1 8 ACKNOWLEDGMENT % Sun VM JRockit VM Perc VM IBM VM The author would like to express his thanks to all the students in CS6283 Real-Time Systems (fall 21), especially Jim Knupp, Venkatesh Baglodi, Yiming Ji, Xing Dong, Mili Naik, Kanchan Nigam, Abraham Jacob, and Li Yi for their well-done project work and experimental effort. Experiment 1 Experiment 2 Experiment 3 Experiment 4 FIGURE. 5 COMPARE THE UTILIZATION S2F-29

6 REFERENCES [1] Weiderman, N., Hartstone: Synthetic Benchmark Requirements for Hard Real-Time Applications, CMU/SEI-89-TR-23, June [2] Donohoe, P., Shapiro, R., and Weiderman, N., Hardstone Benchmark Results and Anaylisis, CMU/SEI-9-TR-7, June 199. [3] Donohoe, P., Shapiro, R., and Weiderman, N., Hardstone Benchmark User s Guide, Version 1., CMU/SEI-9-UG-1, March 199. [4] NewMonics, Inc., PERC3.1.1 User Manual, 21. [5] Laplante P.A., Real-Time Systems Design and Analysis, An Engineer s Handbook, 2 nd ed, IEEE Press, [6] Shaw A.C., Real-Time Systems and Software, John Wiley & Sons, Inc., 21. [7] Burns A. and Wellings A., Real-Time Systems and Programming Languages, Ada 95, Real-Time Java and Real-Time POSIX, 3 rd ed., Addison Wesley, 21. Appendix A Test machine configuration Hardware: IA32 CPU: 1.8 GHz Pentium 4 FPU: Integrated Number of CPUs: 1 Cache size per CPU: 15MB Memory: 1 Gigabyte SDRAM PC133 Disk subsystem: 1 2 Gigabyte EIDE Network interface: NA Software Operating System: Java VM s: Sun JDK IBM 1.3 Perc PVM JRockit 1.3 Java VM s release version Sun 1.3.1_1 IBM 1.3. Perc PVM JRockit Other software: File system type: System Tuning parameters : Background load: System state: Windows 2 Professional Service Pack 2 none NTFS none none Single user (single-user login) S2F-3

Method-Level Phase Behavior in Java Workloads

Method-Level Phase Behavior in Java Workloads Method-Level Phase Behavior in Java Workloads Andy Georges, Dries Buytaert, Lieven Eeckhout and Koen De Bosschere Ghent University Presented by Bruno Dufour dufour@cs.rutgers.edu Rutgers University DCS

More information

An Oracle White Paper September Oracle Utilities Meter Data Management Demonstrates Extreme Performance on Oracle Exadata/Exalogic

An Oracle White Paper September Oracle Utilities Meter Data Management Demonstrates Extreme Performance on Oracle Exadata/Exalogic An Oracle White Paper September 2011 Oracle Utilities Meter Data Management 2.0.1 Demonstrates Extreme Performance on Oracle Exadata/Exalogic Introduction New utilities technologies are bringing with them

More information

Java Jitters - The Effects of Java on Jitter in a Continuous Media Server

Java Jitters - The Effects of Java on Jitter in a Continuous Media Server Introduction Java Jitters - The Effects of Java on Jitter in a Continuous Media Server Mark Claypool and Jonathan Tanner Computer Science Department, Worcester Polytechnic Institute {claypool,jtanner}@cs.wpi.edu

More information

JavaOS. David Burhans 2/3/2003 CS384 Dr. Taylor

JavaOS. David Burhans 2/3/2003 CS384 Dr. Taylor JavaOS David Burhans 2/3/2003 CS384 Dr. Taylor Table of Contents JavaOS... 1 Table of Contents...i Table of Figures...ii Background... 1 Java... 1 Bytecode... 2 JavaOS... 2 Supported Computing Models...

More information

... WebSphere 6.1 and WebSphere 6.0 performance with Oracle s JD Edwards EnterpriseOne 8.12 on IBM Power Systems with IBM i

... WebSphere 6.1 and WebSphere 6.0 performance with Oracle s JD Edwards EnterpriseOne 8.12 on IBM Power Systems with IBM i 6.1 and 6.0 performance with Oracle s JD Edwards EnterpriseOne 8.12 on IBM Power Systems with IBM i........ Gerrie Fisk IBM Oracle ICC June 2008 Copyright IBM Corporation, 2008. All Rights Reserved. All

More information

CS Computer Architecture

CS Computer Architecture CS 35101 Computer Architecture Section 600 Dr. Angela Guercio Fall 2010 Structured Computer Organization A computer s native language, machine language, is difficult for human s to use to program the computer

More information

ECE902 Virtual Machine Final Project: MIPS to CRAY-2 Binary Translation

ECE902 Virtual Machine Final Project: MIPS to CRAY-2 Binary Translation ECE902 Virtual Machine Final Project: MIPS to CRAY-2 Binary Translation Weiping Liao, Saengrawee (Anne) Pratoomtong, and Chuan Zhang Abstract Binary translation is an important component for translating

More information

Analyzing Cache Bandwidth on the Intel Core 2 Architecture

Analyzing Cache Bandwidth on the Intel Core 2 Architecture John von Neumann Institute for Computing Analyzing Cache Bandwidth on the Intel Core 2 Architecture Robert Schöne, Wolfgang E. Nagel, Stefan Pflüger published in Parallel Computing: Architectures, Algorithms

More information

z/vm Large Memory Linux on System z

z/vm Large Memory Linux on System z December 2007 z/vm Large Memory Linux on System z 1 Table of Contents Objectives... 3 Executive summary... 3 Summary... 3 Hardware equipment and software environment... 4 Host hardware... 5 Network setup...

More information

Unit 2 : Computer and Operating System Structure

Unit 2 : Computer and Operating System Structure Unit 2 : Computer and Operating System Structure Lesson 1 : Interrupts and I/O Structure 1.1. Learning Objectives On completion of this lesson you will know : what interrupt is the causes of occurring

More information

Fiji VM Safety Critical Java

Fiji VM Safety Critical Java Fiji VM Safety Critical Java Filip Pizlo, President Fiji Systems Inc. Introduction Java is a modern, portable programming language with wide-spread adoption. Goal: streamlining debugging and certification.

More information

Microsoft RemoteFX for Remote Desktop Virtualization Host Capacity Planning Guide for Windows Server 2008 R2 Service Pack 1

Microsoft RemoteFX for Remote Desktop Virtualization Host Capacity Planning Guide for Windows Server 2008 R2 Service Pack 1 Microsoft RemoteFX for Remote Desktop Virtualization Host Capacity Planning Guide for Windows Server 2008 R2 Service Pack 1 Microsoft Corporation Published: March 2011 Abstract Microsoft RemoteFX delivers

More information

Reporting Performance Results

Reporting Performance Results Reporting Performance Results The guiding principle of reporting performance measurements should be reproducibility - another experimenter would need to duplicate the results. However: A system s software

More information

Oracle s JD Edwards EnterpriseOne IBM POWER7 performance characterization

Oracle s JD Edwards EnterpriseOne IBM POWER7 performance characterization Oracle s JD Edwards EnterpriseOne IBM POWER7 performance characterization Diane Webster IBM Oracle International Competency Center January 2012 Copyright IBM Corporation, 2012. All Rights Reserved. All

More information

San Jose State University College of Science Department of Computer Science CS151, Object-Oriented Design, Sections 1,2 and 3, Spring 2017

San Jose State University College of Science Department of Computer Science CS151, Object-Oriented Design, Sections 1,2 and 3, Spring 2017 San Jose State University College of Science Department of Computer Science CS151, Object-Oriented Design, Sections 1,2 and 3, Spring 2017 Course and Contact Information Instructor: Dr. Kim Office Location:

More information

Page 1. Program Performance Metrics. Program Performance Metrics. Amdahl s Law. 1 seq seq 1

Page 1. Program Performance Metrics. Program Performance Metrics. Amdahl s Law. 1 seq seq 1 Program Performance Metrics The parallel run time (Tpar) is the time from the moment when computation starts to the moment when the last processor finished his execution The speedup (S) is defined as the

More information

Separating Access Control Policy, Enforcement, and Functionality in Extensible Systems. Robert Grimm University of Washington

Separating Access Control Policy, Enforcement, and Functionality in Extensible Systems. Robert Grimm University of Washington Separating Access Control Policy, Enforcement, and Functionality in Extensible Systems Robert Grimm University of Washington Extensions Added to running system Interact through low-latency interfaces Form

More information

A CPU Scheduling Algorithm Simulator

A CPU Scheduling Algorithm Simulator A CPU Scheduling Algorithm Simulator Sukanya Suranauwarat School of Applied Statistics, National Institute of Development Administration, 118 Seri Thai Rd., Bangkapi, Bangkok 10240, Thailand sukanya@as.nida.ac.th

More information

An XML-Based Automation Framework For Benchmarking Multiple Virtual Machines Travis Finch, St. Edward s University

An XML-Based Automation Framework For Benchmarking Multiple Virtual Machines Travis Finch, St. Edward s University An XML-Based Automation Framework For Benchmarking Multiple Virtual Machines Travis Finch, St. Edward s University Abstract Server virtualization provides a mechanism to use system resources more efficiently

More information

ECE519 Advanced Operating Systems

ECE519 Advanced Operating Systems IT 540 Operating Systems ECE519 Advanced Operating Systems Prof. Dr. Hasan Hüseyin BALIK (10 th Week) (Advanced) Operating Systems 10. Multiprocessor, Multicore and Real-Time Scheduling 10. Outline Multiprocessor

More information

Lecture 3 Notes Topic: Benchmarks

Lecture 3 Notes Topic: Benchmarks Lecture 3 Notes Topic: Benchmarks What do you want in a benchmark? o benchmarks must be representative of actual workloads o first few computers were benchmarked based on how fast they could add/multiply

More information

San José State University Department of Computer Science CS151, Object Oriented Design, Section 04, Fall, 2016 (42968)

San José State University Department of Computer Science CS151, Object Oriented Design, Section 04, Fall, 2016 (42968) San José State University Department of Computer Science CS151, Object Oriented Design, Section 04, Fall, 2016 (42968) Course and Contact Information Instructor: Office Location: Vidya Rangasayee MH229

More information

CMSC 611: Advanced Computer Architecture

CMSC 611: Advanced Computer Architecture CMSC 611: Advanced Computer Architecture Performance Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted from Hennessy & Patterson / 2003 Elsevier Science

More information

Hierarchical PLABs, CLABs, TLABs in Hotspot

Hierarchical PLABs, CLABs, TLABs in Hotspot Hierarchical s, CLABs, s in Hotspot Christoph M. Kirsch ck@cs.uni-salzburg.at Hannes Payer hpayer@cs.uni-salzburg.at Harald Röck hroeck@cs.uni-salzburg.at Abstract Thread-local allocation buffers (s) are

More information

... Characterizing IBM Power Systems POWER7+ and Solid State Drive Performance with Oracle s JD Edwards EnterpriseOne

... Characterizing IBM Power Systems POWER7+ and Solid State Drive Performance with Oracle s JD Edwards EnterpriseOne Characterizing IBM Power Systems POWER7+ and Solid State Drive Performance with Oracle s JD Edwards EnterpriseOne........ John Brock Dan Sundt IBM Rochester March 2014 Copyright IBM Corporation, 2014.

More information

Terminal Services Scalability Study

Terminal Services Scalability Study Terminal Services Scalability Study Part 1 The Effect of CPS 4.0 Microsoft Windows Terminal Services Citrix Presentation Server 4.0 June 2007 Table of Contents 1 Executive summary 3 2 Introduction 4 2.1

More information

Windows Server 2016 Impact on VDI: Benchmark Results. By Mark Plettenberg, Ryan Bijkerk and Omar Bouhaj

Windows Server 2016 Impact on VDI: Benchmark Results. By Mark Plettenberg, Ryan Bijkerk and Omar Bouhaj Windows Server 2016 Impact on VDI: Benchmark Results By Mark Plettenberg, Ryan Bijkerk and Omar Bouhaj Disclosure and Warranty The information, concepts, and ideas contained in this document are the property

More information

Multiprocessor Systems. Chapter 8, 8.1

Multiprocessor Systems. Chapter 8, 8.1 Multiprocessor Systems Chapter 8, 8.1 1 Learning Outcomes An understanding of the structure and limits of multiprocessor hardware. An appreciation of approaches to operating system support for multiprocessor

More information

i960 Microprocessor Performance Brief October 1998 Order Number:

i960 Microprocessor Performance Brief October 1998 Order Number: Performance Brief October 1998 Order Number: 272950-003 Information in this document is provided in connection with Intel products. No license, express or implied, by estoppel or otherwise, to any intellectual

More information

Operating Systems. Lecture 09: Input/Output Management. Elvis C. Foster

Operating Systems. Lecture 09: Input/Output Management. Elvis C. Foster Operating Systems 141 Lecture 09: Input/Output Management Despite all the considerations that have discussed so far, the work of an operating system can be summarized in two main activities input/output

More information

Interactive Game Design with Greenfoot YEAR 1 Greenfoot Single-player Interactive Game

Interactive Game Design with Greenfoot YEAR 1 Greenfoot Single-player Interactive Game MESA VIRTUAL COMPUTER SCIENCE COMPETITION CYBER RULES 2018 Interactive Game Design with Greenfoot YEAR 1 Greenfoot Single-player Interactive Game Level: Type of Contest: Composition of Team: Number of

More information

SOFT 437. Software Performance Analysis. Ch 7&8:Software Measurement and Instrumentation

SOFT 437. Software Performance Analysis. Ch 7&8:Software Measurement and Instrumentation SOFT 437 Software Performance Analysis Ch 7&8: Why do we need data? Data is required to calculate: Software execution model System execution model We assumed that we have required data to calculate these

More information

Multiprocessor and Real- Time Scheduling. Chapter 10

Multiprocessor and Real- Time Scheduling. Chapter 10 Multiprocessor and Real- Time Scheduling Chapter 10 Classifications of Multiprocessor Loosely coupled multiprocessor each processor has its own memory and I/O channels Functionally specialized processors

More information

Jazz: A Tool for Demand-Driven Structural Testing

Jazz: A Tool for Demand-Driven Structural Testing Jazz: A Tool for Demand-Driven Structural Testing J. Misurda, J. A. Clause, J. L. Reed, P. Gandra, B. R. Childers, and M. L. Soffa Department of Computer Science University of Pittsburgh Pittsburgh, Pennsylvania

More information

Performance Tuning VTune Performance Analyzer

Performance Tuning VTune Performance Analyzer Performance Tuning VTune Performance Analyzer Paul Petersen, Intel Sept 9, 2005 Copyright 2005 Intel Corporation Performance Tuning Overview Methodology Benchmarking Timing VTune Counter Monitor Call Graph

More information

Course specification

Course specification The University of Southern Queensland Course specification Description: Database Applications Development with Oracle Subject CIS Cat-nbr 2004 Academic group: Academic org: Student contribution band: ASCED

More information

CS370: System Architecture & Software [Fall 2014] Dept. Of Computer Science, Colorado State University

CS370: System Architecture & Software [Fall 2014] Dept. Of Computer Science, Colorado State University Frequently asked questions from the previous class survey CS 370: SYSTEM ARCHITECTURE & SOFTWARE [CPU SCHEDULING] Shrideep Pallickara Computer Science Colorado State University OpenMP compiler directives

More information

Lab 2: Threads and Processes

Lab 2: Threads and Processes CS333: Operating Systems Lab Lab 2: Threads and Processes Goal The goal of this lab is to get you comfortable with writing basic multi-process / multi-threaded applications, and understanding their performance.

More information

Course specification

Course specification The University of Southern Queensland Course specification Description: Java Programming Subject CIS Cat-nbr 3001 Class 45196 Term 2, 2005 Mode EXT Units 1.00 Campus Toowoomba Academic group: Academic

More information

Performance Report: Multiprotocol Performance Test of VMware ESX 3.5 on NetApp Storage Systems

Performance Report: Multiprotocol Performance Test of VMware ESX 3.5 on NetApp Storage Systems NETAPP TECHNICAL REPORT Performance Report: Multiprotocol Performance Test of VMware ESX 3.5 on NetApp Storage Systems A Performance Comparison Study of FC, iscsi, and NFS Protocols Jack McLeod, NetApp

More information

Future of JRockit & Tools

Future of JRockit & Tools Future of JRockit & Tools Or finding the right layer to attack Joakim Dahlstedt 15 September 2004 A Short Background on JRockit Server-centric JVM Java compatible (most of the Java libraries are Suns)

More information

SoftNAS Cloud Performance Evaluation on AWS

SoftNAS Cloud Performance Evaluation on AWS SoftNAS Cloud Performance Evaluation on AWS October 25, 2016 Contents SoftNAS Cloud Overview... 3 Introduction... 3 Executive Summary... 4 Key Findings for AWS:... 5 Test Methodology... 6 Performance Summary

More information

Albis: High-Performance File Format for Big Data Systems

Albis: High-Performance File Format for Big Data Systems Albis: High-Performance File Format for Big Data Systems Animesh Trivedi, Patrick Stuedi, Jonas Pfefferle, Adrian Schuepbach, Bernard Metzler, IBM Research, Zurich 2018 USENIX Annual Technical Conference

More information

System Requirements. SuccessMaker 7

System Requirements. SuccessMaker 7 System Requirements SuccessMaker 7 Copyright 2015 Pearson Education, Inc. or one or more of its direct or indirect affiliates. All rights reserved. Pearson and SuccessMaker are registered trademarks, in

More information

IBM Daeja ViewONE Virtual Performance and Scalability

IBM Daeja ViewONE Virtual Performance and Scalability Summary White Paper January 2016 IBM Daeja ViewONE Virtual 4.1.5 Performance and Scalability Copyright IBM Corporation 2016 Enterprise Content Management www.ibm.com No part of this document may be reproduced

More information

TEST REPORT. JUNE 2007 SPECjbb2005 performance and power consumption on Dell and HP blade servers

TEST REPORT. JUNE 2007 SPECjbb2005 performance and power consumption on Dell and HP blade servers TEST REPORT JUNE 2007 SPECjbb2005 performance and power Executive summary Dell Inc. (Dell) commissioned Principled Technologies (PT) to measure the SPECjbb2005 performance per watt of the following dual-socket

More information

Last class: OS and Architecture. OS and Computer Architecture

Last class: OS and Architecture. OS and Computer Architecture Last class: OS and Architecture OS and Computer Architecture OS Service Protection Interrupts System Calls IO Scheduling Synchronization Virtual Memory Hardware Support Kernel/User Mode Protected Instructions

More information

Last class: OS and Architecture. Chapter 3: Operating-System Structures. OS and Computer Architecture. Common System Components

Last class: OS and Architecture. Chapter 3: Operating-System Structures. OS and Computer Architecture. Common System Components Last class: OS and Architecture Chapter 3: Operating-System Structures System Components Operating System Services System Calls System Programs System Structure Virtual Machines System Design and Implementation

More information

Performance of Multithreaded Chip Multiprocessors and Implications for Operating System Design

Performance of Multithreaded Chip Multiprocessors and Implications for Operating System Design Performance of Multithreaded Chip Multiprocessors and Implications for Operating System Design Based on papers by: A.Fedorova, M.Seltzer, C.Small, and D.Nussbaum Pisa November 6, 2006 Multithreaded Chip

More information

Ch. 7: Benchmarks and Performance Tests

Ch. 7: Benchmarks and Performance Tests Ch. 7: Benchmarks and Performance Tests Kenneth Mitchell School of Computing & Engineering, University of Missouri-Kansas City, Kansas City, MO 64110 Kenneth Mitchell, CS & EE dept., SCE, UMKC p. 1/3 Introduction

More information

P2P Multimedia File Sharing Application using Socket Programming

P2P Multimedia File Sharing Application using Socket Programming 1 von 6 04.02.2009 17:47 Project 40% towards module grade Due date: Week 13 (the week of 13 th April to 17 th April) Team size: 5 members per team P2P Multimedia File Sharing Application using Socket Programming

More information

Operating Systems (2INC0) 2017/18

Operating Systems (2INC0) 2017/18 Operating Systems (2INC0) 2017/18 Memory Management (09) Dr. Courtesy of Dr. I. Radovanovic, Dr. R. Mak (figures from Bic & Shaw) System Architecture and Networking Group Agenda Reminder: OS & resources

More information

HTRC Data API Performance Study

HTRC Data API Performance Study HTRC Data API Performance Study Yiming Sun, Beth Plale, Jiaan Zeng Amazon Indiana University Bloomington {plale, jiaazeng}@cs.indiana.edu Abstract HathiTrust Research Center (HTRC) allows users to access

More information

A Comparison of Scheduling Latency in Linux, PREEMPT_RT, and LITMUS RT. Felipe Cerqueira and Björn Brandenburg

A Comparison of Scheduling Latency in Linux, PREEMPT_RT, and LITMUS RT. Felipe Cerqueira and Björn Brandenburg A Comparison of Scheduling Latency in Linux, PREEMPT_RT, and LITMUS RT Felipe Cerqueira and Björn Brandenburg July 9th, 2013 1 Linux as a Real-Time OS 2 Linux as a Real-Time OS Optimizing system responsiveness

More information

Improving Real-Time Performance on Multicore Platforms Using MemGuard

Improving Real-Time Performance on Multicore Platforms Using MemGuard Improving Real-Time Performance on Multicore Platforms Using MemGuard Heechul Yun University of Kansas 2335 Irving hill Rd, Lawrence, KS heechul@ittc.ku.edu Abstract In this paper, we present a case-study

More information

Design Patterns for Real-Time Computer Music Systems

Design Patterns for Real-Time Computer Music Systems Design Patterns for Real-Time Computer Music Systems Roger B. Dannenberg and Ross Bencina 4 September 2005 This document contains a set of design patterns for real time systems, particularly for computer

More information

VM & VSE Tech Conference May Orlando Session M70

VM & VSE Tech Conference May Orlando Session M70 VM & VSE Tech Conference May 2000 - Orlando Session M70 Bill Bitner VM Performance 607-752-6022 bitner@vnet.ibm.com Last Updated: April10,2000 RETURN TO INDEX Disclaimer Legal Stuff The information contained

More information

Java in Virtual Machines on VMware ESX: Best Practices

Java in Virtual Machines on VMware ESX: Best Practices Java in Virtual Machines on VMware ESX: Best Practices TABLE OF CONTENTS 1. SUMMARY OF BEST PRACTICES...1 1.1 Java in Virtual Machines on ESX...1 1.2. Running Applications in ESX Virtual Machines...2 2.

More information

DELL EMC CX4 EXCHANGE PERFORMANCE THE ADVANTAGES OF DEPLOYING DELL/EMC CX4 STORAGE IN MICROSOFT EXCHANGE ENVIRONMENTS. Dell Inc.

DELL EMC CX4 EXCHANGE PERFORMANCE THE ADVANTAGES OF DEPLOYING DELL/EMC CX4 STORAGE IN MICROSOFT EXCHANGE ENVIRONMENTS. Dell Inc. DELL EMC CX4 EXCHANGE PERFORMANCE THE ADVANTAGES OF DEPLOYING DELL/EMC CX4 STORAGE IN MICROSOFT EXCHANGE ENVIRONMENTS Dell Inc. October 2008 Visit www.dell.com/emc for more information on Dell/EMC Storage.

More information

Student User Guide Table Of Contents

Student User Guide Table Of Contents Student User Guide Table Of Contents Getting Started... 1 Using myitlab... 1 Getting Started in myitlab... 1 Contacting myitlab Student Support... 1 myitlab System Requirements... 1 Logging in to myitlab...

More information

SoftNAS Cloud Performance Evaluation on Microsoft Azure

SoftNAS Cloud Performance Evaluation on Microsoft Azure SoftNAS Cloud Performance Evaluation on Microsoft Azure November 30, 2016 Contents SoftNAS Cloud Overview... 3 Introduction... 3 Executive Summary... 4 Key Findings for Azure:... 5 Test Methodology...

More information

Course specification

Course specification The University of Southern Queensland Course specification Description: Java Programming Subject CIS Cat-nbr 3001 Class 40549 Term 1, 2005 Mode ONC Units 1.00 Campus Wide Bay Academic group: Academic org:

More information

Spring It takes a really bad school to ruin a good student and a really fantastic school to rescue a bad student. Dennis J.

Spring It takes a really bad school to ruin a good student and a really fantastic school to rescue a bad student. Dennis J. Operating Systems * *Throughout the course we will use overheads that were adapted from those distributed from the textbook website. Slides are from the book authors, modified and selected by Jean Mayo,

More information

Accurate emulation of CPU performance

Accurate emulation of CPU performance Accurate emulation of CPU performance Tomasz Buchert 1 Lucas Nussbaum 2 Jens Gustedt 1 1 INRIA Nancy Grand Est 2 LORIA / Nancy - Université Validation of distributed systems Approaches: Theoretical approach

More information

Multiprocessor scheduling

Multiprocessor scheduling Chapter 10 Multiprocessor scheduling When a computer system contains multiple processors, a few new issues arise. Multiprocessor systems can be categorized into the following: Loosely coupled or distributed.

More information

P6 Compression Server White Paper Release 8.2 December 2011 Copyright Oracle Primavera P6 Compression Server White Paper Copyright 2005, 2011, Oracle and/or its affiliates. All rights reserved. Oracle

More information

6.2 DATA DISTRIBUTION AND EXPERIMENT DETAILS

6.2 DATA DISTRIBUTION AND EXPERIMENT DETAILS Chapter 6 Indexing Results 6. INTRODUCTION The generation of inverted indexes for text databases is a computationally intensive process that requires the exclusive use of processing resources for long

More information

Benchmarking Enterprise SSDs

Benchmarking Enterprise SSDs Whitepaper March 2013 Benchmarking Enterprise SSDs When properly structured, benchmark tests enable IT professionals to compare solid-state drives (SSDs) under test with conventional hard disk drives (HDDs)

More information

Run and Reporting Rules for VMware View Planner Updated July 17, 2013

Run and Reporting Rules for VMware View Planner Updated July 17, 2013 Run and Reporting Rules for VMware View Planner Updated July 17, 2013 1 Introduction These View Planner Run and Reporting Rules define how to correctly measure and report performance using the View Planner

More information

PennBench: A Benchmark Suite for Embedded Java

PennBench: A Benchmark Suite for Embedded Java WWC5 Austin, TX. Nov. 2002 PennBench: A Benchmark Suite for Embedded Java G. Chen, M. Kandemir, N. Vijaykrishnan, And M. J. Irwin Penn State University http://www.cse.psu.edu/~mdl Outline Introduction

More information

Bhaavyaa Kapoor Person #

Bhaavyaa Kapoor Person # Bhaavyaa Kapoor Person # 5002-6253 } Andrew File System } The Prototype } Changes for Performance } Effect of Changes for Performance } Comparison with A Remote-Open File System } Conclusion } Joined project

More information

A Disk Head Scheduling Simulator

A Disk Head Scheduling Simulator A Disk Head Scheduling Simulator Steven Robbins Department of Computer Science University of Texas at San Antonio srobbins@cs.utsa.edu Abstract Disk head scheduling is a standard topic in undergraduate

More information

Performance COE 403. Computer Architecture Prof. Muhamed Mudawar. Computer Engineering Department King Fahd University of Petroleum and Minerals

Performance COE 403. Computer Architecture Prof. Muhamed Mudawar. Computer Engineering Department King Fahd University of Petroleum and Minerals Performance COE 403 Computer Architecture Prof. Muhamed Mudawar Computer Engineering Department King Fahd University of Petroleum and Minerals What is Performance? How do we measure the performance of

More information

A Simple Model for Estimating Power Consumption of a Multicore Server System

A Simple Model for Estimating Power Consumption of a Multicore Server System , pp.153-160 http://dx.doi.org/10.14257/ijmue.2014.9.2.15 A Simple Model for Estimating Power Consumption of a Multicore Server System Minjoong Kim, Yoondeok Ju, Jinseok Chae and Moonju Park School of

More information

Course and Unix Intro

Course and Unix Intro Course and Unix Intro Comp-206 : Introduction to Software Systems Lecture 1 Alexandre Denault Computer Science McGill University Fall 2006 Instructor Alexandre Denault Graduate student, working in the

More information

Multimedia-Systems. Operating Systems. Prof. Dr.-Ing. Ralf Steinmetz Prof. Dr. rer. nat. Max Mühlhäuser Prof. Dr.-Ing. Wolfgang Effelsberg

Multimedia-Systems. Operating Systems. Prof. Dr.-Ing. Ralf Steinmetz Prof. Dr. rer. nat. Max Mühlhäuser Prof. Dr.-Ing. Wolfgang Effelsberg Multimedia-Systems Operating Systems Prof. Dr.-Ing. Ralf Steinmetz Prof. Dr. rer. nat. Max Mühlhäuser Prof. Dr.-Ing. Wolfgang Effelsberg WE: University of Mannheim, Dept. of Computer Science Praktische

More information

WebSphere Application Server Base Performance

WebSphere Application Server Base Performance WebSphere Application Server Base Performance ii WebSphere Application Server Base Performance Contents WebSphere Application Server Base Performance............. 1 Introduction to the WebSphere Application

More information

Java On Steroids: Sun s High-Performance Java Implementation. History

Java On Steroids: Sun s High-Performance Java Implementation. History Java On Steroids: Sun s High-Performance Java Implementation Urs Hölzle Lars Bak Steffen Grarup Robert Griesemer Srdjan Mitrovic Sun Microsystems History First Java implementations: interpreters compact

More information

Oracle Event Processing Extreme Performance on Sparc T5

Oracle Event Processing Extreme Performance on Sparc T5 Oracle Event Processing Extreme Performance on Sparc T5 An Oracle Event Processing (OEP) Whitepaper ORACLE WHITE PAPER AUGUST 2014 Table of Contents Introduction 2 OEP Architecture 2 Server Architecture

More information

Creating the Fastest Possible Backups Using VMware Consolidated Backup. A Design Blueprint

Creating the Fastest Possible Backups Using VMware Consolidated Backup. A Design Blueprint Creating the Fastest Possible Backups Using VMware Consolidated Backup A Design Blueprint George Winter Technical Product Manager NetBackup Symantec Corporation Agenda Overview NetBackup for VMware and

More information

CS 140 Programming with Objects

CS 140 Programming with Objects CS 140 Programming with Objects Instructor: Tom Bartenstein Course Web Page: http://www.cs.binghamton.edu/~tbartens/cs140_fall_2017/ 1 Catalog Description Provides the foundations of software development

More information

Computer Science Window-Constrained Process Scheduling for Linux Systems

Computer Science Window-Constrained Process Scheduling for Linux Systems Window-Constrained Process Scheduling for Linux Systems Richard West Ivan Ganev Karsten Schwan Talk Outline Goals of this research DWCS background DWCS implementation details Design of the experiments

More information

Operating Systems (2INC0) 2018/19. Introduction (01) Dr. Tanir Ozcelebi. Courtesy of Prof. Dr. Johan Lukkien. System Architecture and Networking Group

Operating Systems (2INC0) 2018/19. Introduction (01) Dr. Tanir Ozcelebi. Courtesy of Prof. Dr. Johan Lukkien. System Architecture and Networking Group Operating Systems (2INC0) 20/19 Introduction (01) Dr. Courtesy of Prof. Dr. Johan Lukkien System Architecture and Networking Group Course Overview Introduction to operating systems Processes, threads and

More information

Performance Impact of Multithreaded Java Server Applications

Performance Impact of Multithreaded Java Server Applications Performance Impact of Multithreaded Java Server Applications Yue Luo, Lizy K. John Laboratory of Computer Architecture ECE Department University of Texas at Austin 1/2/01 1 Outline Motivation VolanoMark

More information

Revisiting the Past 25 Years: Lessons for the Future. Guri Sohi University of Wisconsin-Madison

Revisiting the Past 25 Years: Lessons for the Future. Guri Sohi University of Wisconsin-Madison Revisiting the Past 25 Years: Lessons for the Future Guri Sohi University of Wisconsin-Madison Outline VLIW OOO Superscalar Enhancing Superscalar And the future 2 Beyond pipelining to ILP Late 1980s to

More information

Course specification STAFFING OTHER REQUISITES RATIONALE SYNOPSIS. The University of Southern Queensland

Course specification STAFFING OTHER REQUISITES RATIONALE SYNOPSIS. The University of Southern Queensland The University of Southern Queensland Course specification The current and official versions of the course specifications are available on the web at .

More information

Analysis of Derby Performance

Analysis of Derby Performance Analysis of Derby Performance Staff Engineer Olav Sandstå Senior Engineer Dyre Tjeldvoll Sun Microsystems Database Technology Group This is a draft version that is subject to change. The authors can be

More information

... IBM AIX performance and tuning tips for Oracle s JD Edwards EnterpriseOne web server

... IBM AIX performance and tuning tips for Oracle s JD Edwards EnterpriseOne web server IBM AIX performance and tuning tips for Oracle s JD Edwards EnterpriseOne web server Applies to JD Edwards EnterpriseOne 9.0 with tools release 8.98 or 9.1........ Diane Webster IBM Oracle International

More information

Workload Optimized Systems: The Wheel of Reincarnation. Michael Sporer, Netezza Appliance Hardware Architect 21 April 2013

Workload Optimized Systems: The Wheel of Reincarnation. Michael Sporer, Netezza Appliance Hardware Architect 21 April 2013 Workload Optimized Systems: The Wheel of Reincarnation Michael Sporer, Netezza Appliance Hardware Architect 21 April 2013 Outline Definition Technology Minicomputers Prime Workstations Apollo Graphics

More information

CS 31: Intro to Systems Operating Systems Overview. Kevin Webb Swarthmore College March 31, 2015

CS 31: Intro to Systems Operating Systems Overview. Kevin Webb Swarthmore College March 31, 2015 CS 31: Intro to Systems Operating Systems Overview Kevin Webb Swarthmore College March 31, 2015 Reading Quiz OS: Turn undesirable into desirable Turn undesirable inconveniences: reality Complexity of hardware

More information

Lecture 1: Course Introduction and Overview Prof. Randy H. Katz Computer Science 252 Spring 1996

Lecture 1: Course Introduction and Overview Prof. Randy H. Katz Computer Science 252 Spring 1996 Lecture 1: Course Introduction and Overview Prof. Randy H. Katz Computer Science 252 Spring 1996 RHK.S96 1 Computer Architecture Is the attributes of a [computing] system as seen by the programmer, i.e.,

More information

IBM Unica Campaign Family Version Publication Date: June 7, Recommended Software Environments and Minimum System Requirements

IBM Unica Campaign Family Version Publication Date: June 7, Recommended Software Environments and Minimum System Requirements IBM Unica Campaign Family Version 8.5.0 Publication Date: June 7, 2011 Recommended Software Environments and Minimum System Requirements Copyright Copyright IBM 2011 IBM Corporation Reservoir Place North

More information

Condusiv s V-locity VM Accelerates Exchange 2010 over 60% on Virtual Machines without Additional Hardware

Condusiv s V-locity VM Accelerates Exchange 2010 over 60% on Virtual Machines without Additional Hardware openbench Labs Executive Briefing: March 13, 2013 Condusiv s V-locity VM Accelerates Exchange 2010 over 60% on Virtual Machines without Additional Hardware Optimizing I/O for Increased Throughput and Reduced

More information

Reducing the Overhead of Dynamic Compilation

Reducing the Overhead of Dynamic Compilation Reducing the Overhead of Dynamic Compilation Chandra Krintz y David Grove z Derek Lieber z Vivek Sarkar z Brad Calder y y Department of Computer Science and Engineering, University of California, San Diego

More information

W H I T E P A P E R. Comparison of Storage Protocol Performance in VMware vsphere 4

W H I T E P A P E R. Comparison of Storage Protocol Performance in VMware vsphere 4 W H I T E P A P E R Comparison of Storage Protocol Performance in VMware vsphere 4 Table of Contents Introduction................................................................... 3 Executive Summary............................................................

More information

Interaction of JVM with x86, Sparc and MIPS

Interaction of JVM with x86, Sparc and MIPS Interaction of JVM with x86, Sparc and MIPS Sasikanth Avancha, Dipanjan Chakraborty, Dhiral Gada, Tapan Kamdar {savanc1, dchakr1, dgada1, kamdar}@cs.umbc.edu Department of Computer Science and Electrical

More information

Untyped Memory in the Java Virtual Machine

Untyped Memory in the Java Virtual Machine Untyped Memory in the Java Virtual Machine Andreas Gal and Michael Franz University of California, Irvine {gal,franz}@uci.edu Christian W. Probst Technical University of Denmark probst@imm.dtu.dk July

More information

Chapter. Focus of the Course. Object-Oriented Software Development. program design, implementation, and testing

Chapter. Focus of the Course. Object-Oriented Software Development. program design, implementation, and testing Introduction 1 Chapter 5 TH EDITION Lewis & Loftus java Software Solutions Foundations of Program Design 2007 Pearson Addison-Wesley. All rights reserved Focus of the Course Object-Oriented Software Development

More information

Contents Overview of the Compression Server White Paper... 5 Business Problem... 7

Contents Overview of the Compression Server White Paper... 5 Business Problem... 7 P6 Professional Compression Server White Paper for On-Premises Version 17 July 2017 Contents Overview of the Compression Server White Paper... 5 Business Problem... 7 P6 Compression Server vs. Citrix...

More information

Fundamentals of Programming. By Budditha Hettige

Fundamentals of Programming. By Budditha Hettige Fundamentals of Programming By Budditha Hettige Overview Exercises (Previous Lesson) The JAVA Programming Languages Java Virtual Machine Characteristics What is a class? JAVA Standards JAVA Keywords How

More information