Using Standard Industry Benchmarks Chapter 7 CSE807.

Slides:



Advertisements
Similar presentations
11 Measuring performance Kosarev Nikolay MIPT Feb, 2010.
Advertisements

Workloads Experimental environment prototype real sys exec- driven sim trace- driven sim stochastic sim Live workload Benchmark applications Micro- benchmark.
Lecture 2c: Benchmarks. Benchmarking Benchmark is a program that is run on a computer to measure its performance and compare it with other machines Best.
Chapter 4 M. Keshtgary Spring 91 Type of Workloads.
Chapter 1 CSF 2009 Computer Performance. Defining Performance Which airplane has the best performance? Chapter 1 — Computer Abstractions and Technology.
1 Part II Web Performance Modeling: basic concepts © 1998 Menascé & Almeida. All Rights Reserved.
Chapter 4 Assessing and Understanding Performance Bo Cheng.
CIS629 Fall Lecture Performance Overview Execution time is the best measure of performance: simple, intuitive, straightforward. Two important.
Copyright © 1998 Wanda Kunkle Computer Organization 1 Chapter 2.5 Comparing and Summarizing Performance.
Computer ArchitectureFall 2007 © September 17, 2007 Karem Sakallah CS-447– Computer Architecture.
CS/ECE 3330 Computer Architecture Chapter 1 Performance / Power.
Assessing and Understanding Performance B. Ramamurthy Chapter 4.
1 Lecture 11: Digital Design Today’s topics:  Evaluating a system  Intro to boolean functions.
Chapter 4 Assessing and Understanding Performance
Measuring Performance Chapter 12 CSE807. Performance Measurement To assist in guaranteeing Service Level Agreements For capacity planning For troubleshooting.
1 Multiple class queueing networks Mean Value Analysis - Open queueing networks - Closed queueing networks.
1 Lecture 10: FP, Performance Metrics Today’s topics:  IEEE 754 representations  FP arithmetic  Evaluating a system Reminder: assignment 4 due in a.
CIS429/529 Winter 07 - Performance - 1 Performance Overview Execution time is the best measure of performance: simple, intuitive, straightforward. Two.
Rung-Bin Lin Chapter 1: Fundamental of Computer Design1-1 Chapter 1. Fundamentals of Computer Design Introduction –Performance Improvement due to (1).
CMSC 611: Advanced Computer Architecture Benchmarking Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted.
 Introduction Introduction  Definition of Operating System Definition of Operating System  Abstract View of OperatingSystem Abstract View of OperatingSystem.
Lecture 2: Technology Trends and Performance Evaluation Performance definition, benchmark, summarizing performance, Amdahl’s law, and CPI.
Computer System Lifecycle Chapter 1. Introduction Computer System users, administrators, and designers are all interested in performance evaluation. Whether.
Performance & Benchmarking. What Matters? Which airplane has best performance:
Introduction to HP LoadRunner Getting Familiar with LoadRunner >>>>>>>>>>>>>>>>>>>>>>
1 Computer Performance: Metrics, Measurement, & Evaluation.
Where Has This Performance Improvement Come From? Technology –More transistors per chip –Faster logic Machine Organization/Implementation –Deeper pipelines.
Performance of Web Applications Introduction One of the success-critical quality characteristics of Web applications is system performance. What.
BİL 221 Bilgisayar Yapısı Lab. – 1: Benchmarking.
Memory/Storage Architecture Lab Computer Architecture Performance.
Recap Technology trends Cost/performance Measuring and Reporting Performance What does it mean to say “computer X is faster than computer Y”? E.g. Machine.
1 CHAPTER 2 THE ROLE OF PERFORMANCE. 2 Performance Measure, Report, and Summarize Make intelligent choices Why is some hardware better than others for.
C OMPUTER O RGANIZATION AND D ESIGN The Hardware/Software Interface 5 th Edition Chapter 1 Computer Abstractions and Technology Sections 1.5 – 1.11.
1 Wenguang WangRichard B. Bunt Department of Computer Science University of Saskatchewan November 14, 2000 Simulating DB2 Buffer Pool Management.
Chapter 1: Introduction. 1.2 Silberschatz, Galvin and Gagne ©2005 Operating System Concepts Chapter 1: Introduction What Operating Systems Do Computer-System.
Computer Architecture
1 Seoul National University Performance. 2 Performance Example Seoul National University Sonata Boeing 727 Speed 100 km/h 1000km/h Seoul to Pusan 10 hours.
Performance Lecture notes from MKP, H. H. Lee and S. Yalamanchili.
Chapter 3 System Performance and Models Introduction A system is the part of the real world under study. Composed of a set of entities interacting.
CMSC 611: Advanced Computer Architecture Benchmarking Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some material adapted.
1 Part VII Component-level Performance Models for the Web © 1998 Menascé & Almeida. All Rights Reserved.
Simics: A Full System Simulation Platform Synopsis by Jen Miller 19 March 2004.
Measuring the Capacity of a Web Server USENIX Sympo. on Internet Tech. and Sys. ‘ Koo-Min Ahn.
OPERATING SYSTEMS CS 3530 Summer 2014 Systems and Models Chapter 03.
Performance Performance
Hyun-Jin Choi, CORE Lab. E.E. 1 httperf – A Tool for Measuring Web Server Performance Dec Choi, Hyun-Jin David Mosberger and Tai Jin HP Research.
1 Lecture 2: Performance, MIPS ISA Today’s topics:  Performance equations  MIPS instructions Reminder: canvas and class webpage:
September 10 Performance Read 3.1 through 3.4 for Wednesday Only 3 classes before 1 st Exam!
UNIT-3 Performance Evaluation UNIT-3 IT2031. Web Server Hardware and Performance Evaluation Key question is whether a company should host their own Web.
Performance Analysis Topics Measuring performance of systems Reasoning about performance Amdahl’s law Systems I.
Chapter 1 — Computer Abstractions and Technology — 1 Uniprocessor Performance Constrained by power, instruction-level parallelism, memory latency.
CMSC 611: Advanced Computer Architecture Performance & Benchmarks Some material adapted from Mohamed Younis, UMBC CMSC 611 Spr 2003 course slides Some.
 Computer hardware refers to the physical parts of a computer and related devices. Internal hardware devices include motherboards, hard drives,
Measuring Performance Based on slides by Henri Casanova.
Computer Architecture & Operations I
Measuring Performance II and Logic Design
Lecture 2: Performance Evaluation
CS161 – Design and Architecture of Computer Systems
4- Performance Analysis of Parallel Programs
Performance Lecture notes from MKP, H. H. Lee and S. Yalamanchili.
Performance Performance The CPU Performance Equation:
Uniprocessor Performance
Morgan Kaufmann Publishers
CSCE 212 Chapter 4: Assessing and Understanding Performance
Capacity Analysis, cont. Realistic Server Performance
Performance of computer systems
Language Processors Application Domain – ideas concerning the behavior of a software. Execution Domain – Ideas implemented in Computer System. Semantic.
Performance of computer systems
Performance of computer systems
Performance And Scalability In Oracle9i And SQL Server 2000
Presentation transcript:

Using Standard Industry Benchmarks Chapter 7 CSE807

Reasons For Using Benchmarks Real Workload impractical to set up Costly, hard to measure Unknown for most part Benchmarks Set of well-defined representative programs to be run on different systems and networks to compare performance

Nature of Benchmarks Measurable and Repeatable Used for Monitoring and Diagnostics Used for Capacity Planning Can be confusing if customer workload does not match with the benchmark Best for comparing systems Complementary source of information in capacity studies

Nature of Benchmarks (cont.) Users want fast Response Time and high availability Managers ask –How many transactions/minute can the system handle –How many requests/minute can the web site service –What is the system’s operational cost –What is the initial hardware & installation cost –How to determine standard measure of system performance

Performance Measures Server Measures –CPU speed – MIPS - millions of instructions per second RISC - Reduced Instruction Set Computer CISC - Complex Instructions Set Computer Web Servers Measures –Inclusive of Clients and Server –Network related effects –Throughput –Latency

Benchmarks Hierarchy Synthetic - Basic Operations, very limited utility –Dhrystone -Speed for fixed point computations –Whetstone -Speed for floating point computations Toy Benchmarks –Small programs implementing classical puzzles –Does not help in predicting performance for any real workload

Benchmarks Hierarchy (cont.) Kernels – Livermore Loops and Linpack – Mainly for CPU performance – Not used for performance perceived by users Real Programs – SPEC and TPC – C compiler, UNIX utilities, debit & credit bank transactions etc. – Used to obtain most accurate picture of the system performance perceived by the user

Avoiding Pitfalls Understand the benchmark environment –Processor specification, memory, I/O subsystem, network and software(OS, DB) Compare your system with benchmark –Similarity and dissimilarity in the environment Representativeness of workload –Similarity and dissimilarity of the workload

Properties of a good benchmark Relevant - it must provide meaningful performance measure within a specific problem domain Understandable - results should be simple and easy to understand Scaleable - must be applicable to wide range of systems (costs, performance) Acceptable - should present unbiased results that are recognized by users and vendors

Component Level Benchmarks CPU - SPECxx –CINT Compute-intensive Integer performance –CFP Floating point performance –Designed for performance of computer processor, memory architecture and compiler –SPECratio is Ratio of Reference time to run time –SPECint is the geometric mean of eight normalized ratios

Component Level (cont.) File Servers - synthetic benchmark that model a workload of input mix to file server –LADDIS - measure NFS server performance –measured at various load levels –generates throughput and average response time –parameters can be modified and adjusted to get a workload representing a user environment –50 msec is an arbitrary reference point

System Level Benchmarks Transaction Processing Systems Measure the CPU, I/O subsystem, the network, database, compilers and the OS TPC - Transaction Processing Council –TPC-B measures database transactions –TPC-A also measures network performance –TPC-C measure order-entry applications –TPC-D for decision support systems

System Level Benchmarks(cont.) Web Servers - simulate web browsers (assume no transmission errors) Webstone - simulates server and client processes, spawns a predefined number of clients for HTTP requests to server –Results include Throughput and Latency –Little’s Load Factor (LLF) gives degree of concurrency –Avg. # of connections equal to Connection rate times Avg. residence time

System Level Benchmarks(cont.) SPECweb - uses logs from popular web servers –workload parameters are fixed unlike LADDIS –result of SPECweb is the server’s maximum throughput –Response time is for server only, does not include network delays