High Performance Managed Languages. Martin Thompson

Size: px
Start display at page:

Download "High Performance Managed Languages. Martin Thompson"

Transcription

1 High Performance Managed Languages Martin Thompson

2 Really, what s your preferred platform for building HFT applications?

3

4 Why would you build low-latency applications on a GC ed platform?

5

6 Some Context

7 Let s be clear A Managed Runtime is not always a good choice

8 Latency Arbitrage?

9

10 Are native languages faster?

11 Time? Skills & Resources?

12 CPU vs Memory Performance

13 Time to add 2 integers?

14 1 CPU Cycle : < 1ns

15 Average time per element to sum the values in an array of integers?

16 Access Pattern Benchmark Benchmark Score Error Units =========================================== sequential ± ns/op

17 Really??? Less than 1ns per operation?

18

19 What if the access pattern is different?

20 Access Pattern Benchmark Benchmark Score Error Units =========================================== sequential ± ns/op randompage ± ns/op dependentrandompage ± ns/op randomheap ± ns/op dependentrandomheap ± ns/op

21 Data Dependent Loads aka Pointer Chasing!!!

22 Runtime Optimisation

23 Runtime JIT 1. Profile guided optimisations

24 Runtime JIT 1. Profile guided optimisations 2. Bets can be taken and later revoked

25 Branches void foo() { // code if (condition) { // code } } // code

26 Branches void foo() { // code if (condition) { // code Block A } } // code

27 Branches void foo() { // code if (condition) { // code Block A Block B } } // code

28 Branches void foo() { // code if (condition) { // code Block A Block B } } // code Block C

29 Branches void foo() { // code } if (condition) { // code } // code Block A Block B Block C Block A Block C

30 Branches void foo() { // code } if (condition) { // code } // code Block A Block B Block C Block A Block C Block B

31 Subtle Branches int result = (i > 7)? a : b;

32 Subtle Branches int result = (i > 7)? a : b; CMOV vs Branch Prediction

33 Method/Function Inlining void foo() { // code bar(); } // code

34 Method/Function Inlining void foo() { // code bar(); Block A } // code

35 Method/Function Inlining void foo() { // code bar(); Block A } // code bar()

36 Method/Function Inlining void foo() { // code bar(); Block A } // code bar()

37 Method/Function Inlining void foo() { // code bar(); Block A } // code Block B bar()

38 Method/Function Inlining void foo() { // code bar(); Block A Block A } // code Block B bar()

39 Method/Function Inlining void foo() { // code } bar(); // code Block A Block B Block A bar() bar()

40 Method/Function Inlining void foo() { // code } bar(); // code Block A Block B Block A bar() Block B bar()

41 Method/Function Inlining void foo() { // code bar(); i-cache & code bloat? } // code

42 Method/Function Inlining Inlining is THE optimisation. - Cliff Click

43 Loops void foo(int[] array, int length) { for (int i = 0; i < length; i++) { bar(integer.bitcount(array[i])); } }

44 Loops void foo(int[] array, int length) { for (int i = 0; i < length; i += 4) { bar(integer.bitcount(array[i])); bar(integer.bitcount(array[i + 1])); bar(integer.bitcount(array[i + 2])); bar(integer.bitcount(array[i + 3])); } }

45 Loops void foo(int[] array, int length) { for (int i = 0; i < length; i++) { bar(integer.bitcount(array[i])); } } Intrinsics

46 Subtype Polymorphism void draw(shape[] shapes) { for (int i = 0; i < shapes.length; i++) { shapes[i].draw(); } }

47 Subtype Polymorphism void draw(shape[] shapes) { for (int i = 0; i < shapes.length; i++) { shapes[i].draw(); } } void bar(shape shape) { foo(shape.isvisible()); }

48 Subtype Polymorphism void draw(shape[] shapes) { for (int i = 0; i < shapes.length; i++) { shapes[i].draw(); } } void bar(shape shape) { foo(shape.isvisible()); } Class Hierarchy Analysis & Inline Caching

49 Garbage Collection

50 Generational Garbage Collection Only the good die young - Billy Joel

51 TLAB TLAB Generational Garbage Collection Young/New Generation Eden Survivor 0 Survivor 1 Virtual Old Generation Tenured Virtual

52 Modern Hardware (Intel Sandy Bridge) C 1 C n Registers/Buffers <1ns C 1 C n L1 L1 ~4 cycles ~1ns L1 L1 L2 L2 ~12 cycles ~3ns L2 L L3 ~45 cycles ~15ns ~75 cycles ~25ns (dirty hit) L3 PCI-e 3 MC QPI QPI MC PCI-e 3 QPI ~40ns DRAM DRAM 40X IO DRAM DRAM ~65ns DRAM DRAM 40X IO DRAM DRAM * Assumption: 3GHz Processor

53 Broadwell EX 24 cores & 60MB L3 Cache

54 TLAB TLAB Thread Local Allocation Buffers Young/New Generation Eden

55 TLAB TLAB Thread Local Allocation Buffers Young/New Generation Eden Affords locality of reference Avoid false sharing Can have NUMA aware allocation

56 TLAB TLAB Object Survival Young/New Generation Eden Survivor 0 Survivor 1 Virtual

57 TLAB TLAB Object Survival Young/New Generation Eden Survivor 0 Survivor 1 Virtual Aging Policies Compacting Copy NUMA Interleave Fast Parallel Scavenging Only the survivors require work

58 TLAB TLAB Object Promotion Young/New Generation Eden Survivor 0 Survivor 1 Virtual Old Generation Tenured Virtual

59 TLAB TLAB Object Promotion Young/New Generation Eden Survivor 0 Survivor 1 Virtual Old Generation Tenured Virtual Concurrent Collection String Deduplication

60 Compacting Collections

61 Compacting Collections Depth first copy

62 Compacting Collections

63 Compacting Collections OS Pages and cache lines?

64 Stop the World!

65 G1 Concurrent Compaction? E E E Eden O S O S S O O S O H Survivor Old Humongous H O O E Unused O E O O O O H

66 Azul Zing C4 True Concurrent Compacting Collector

67 GC vs Manual Memory Management Not easy to pick a clear winner

68 GC vs Manual Memory Management Not easy to pick a clear winner Managed GC GC Implementation Card Marking Read/Write Barriers Object Headers Background Overhead on CPU and Memory

69 GC vs Manual Memory Management Not easy to pick a clear winner Managed GC GC Implementation Card Marking Read/Write Barriers Object Headers Background Overhead on CPU and Memory Native Malloc Implementation Arena/pool contention Bin Wastage Fragmentation Debugging Effort Inter-thread costs

70 Where next for GC?

71 Object Inlining/Aggregation

72 Algorithms & Design

73 What s most the most important thing for achieving good performance?

74 Time

75 If I had more time, I would have written a shorter letter. - Blaise Pascal

76 Avoiding duplicate work Minimising cache misses Avoiding contention Strength reduction Amortising expensive operations Mechanical Sympathy Choice of algorithms & data structures API design

77 In a large codebase it is really difficult to do everything well

78 The story of Aeron

79 Aeron is an interesting lesson in time to performance

80 Lots of others exist such as the C# Roslyn compiler

81 What Really Matters? Models Codecs Algorithms Data Structures Mechanical Sympathy

82 GC Immutable Data & Concurrency

83 In Closing

84 What does the future hold?

85 Remember Assembly vs Compiled Languages?

86

87

88

89 Questions? Blog: Any intelligent fool can make things bigger, more complex, and more violent. It takes a touch of genius, and a lot of courage, to move in the opposite direction. - Albert Einstein

High Performance Managed Languages. Martin Thompson

High Performance Managed Languages. Martin Thompson High Performance Managed Languages Martin Thompson - @mjpt777 Really, what is your preferred platform for building HFT applications? Why do you build low-latency applications on a GC ed platform? Agenda

More information

A Quest for Predictable Latency Adventures in Java Concurrency. Martin Thompson

A Quest for Predictable Latency Adventures in Java Concurrency. Martin Thompson A Quest for Predictable Latency Adventures in Java Concurrency Martin Thompson - @mjpt777 If a system does not respond in a timely manner then it is effectively unavailable 1. It s all about the Blocking

More information

Low latency & Mechanical Sympathy: Issues and solutions

Low latency & Mechanical Sympathy: Issues and solutions Low latency & Mechanical Sympathy: Issues and solutions Jean-Philippe BEMPEL Performance Architect @jpbempel http://jpbempel.blogspot.com ULLINK 2016 Low latency order router pure Java SE application FIX

More information

The G1 GC in JDK 9. Erik Duveblad Senior Member of Technical Staf Oracle JVM GC Team October, 2017

The G1 GC in JDK 9. Erik Duveblad Senior Member of Technical Staf Oracle JVM GC Team October, 2017 The G1 GC in JDK 9 Erik Duveblad Senior Member of Technical Staf racle JVM GC Team ctober, 2017 Copyright 2017, racle and/or its affiliates. All rights reserved. 3 Safe Harbor Statement The following is

More information

Rectangles All The Way Down. Martin Thompson

Rectangles All The Way Down. Martin Thompson Rectangles All The Way Down Martin Thompson - @mjpt777 The most amazing achievement of the computer software industry is its continuing cancellation of the steady and staggering gains made by the computer

More information

Designing for Performance. Martin Thompson

Designing for Performance. Martin Thompson Designing for Performance Martin Thompson - @mjpt777 Feynman is becoming a real pain. He has the greatest scientific honesty of anyone I ve ever meet - William P Rogers The impact of QED cannot be overestimated.

More information

Running class Timing on Java HotSpot VM, 1

Running class Timing on Java HotSpot VM, 1 Compiler construction 2009 Lecture 3. A first look at optimization: Peephole optimization. A simple example A Java class public class A { public static int f (int x) { int r = 3; int s = r + 5; return

More information

Concurrent Garbage Collection

Concurrent Garbage Collection Concurrent Garbage Collection Deepak Sreedhar JVM engineer, Azul Systems Java User Group Bangalore 1 @azulsystems azulsystems.com About me: Deepak Sreedhar JVM student at Azul Systems Currently working

More information

Java & Coherence Simon Cook - Sales Consultant, FMW for Financial Services

Java & Coherence Simon Cook - Sales Consultant, FMW for Financial Services Java & Coherence Simon Cook - Sales Consultant, FMW for Financial Services with help from Adrian Nakon - CMC Markets & Andrew Wilson - RBS 1 Coherence Special Interest Group Meeting 1 st March 2012 Presentation

More information

Designing for Performance. Martin Thompson

Designing for Performance. Martin Thompson Designing for Performance Martin Thompson - @mjpt777 Is it difficult writing software that has good performance? RDD (Resume Driven Development) http://www.semiconductors.org/main/2015_international_technology_roadmap_for_semiconductors_itrs/

More information

A JVM Does What? Eva Andreasson Product Manager, Azul Systems

A JVM Does What? Eva Andreasson Product Manager, Azul Systems A JVM Does What? Eva Andreasson Product Manager, Azul Systems Presenter Eva Andreasson Innovator & Problem solver Implemented the Deterministic GC of JRockit Real Time Awarded patents on GC heuristics

More information

Compiler construction 2009

Compiler construction 2009 Compiler construction 2009 Lecture 3 JVM and optimization. A first look at optimization: Peephole optimization. A simple example A Java class public class A { public static int f (int x) { int r = 3; int

More information

2011 Oracle Corporation and Affiliates. Do not re-distribute!

2011 Oracle Corporation and Affiliates. Do not re-distribute! How to Write Low Latency Java Applications Charlie Hunt Java HotSpot VM Performance Lead Engineer Who is this guy? Charlie Hunt Lead JVM Performance Engineer at Oracle 12+ years of

More information

THE TROUBLE WITH MEMORY

THE TROUBLE WITH MEMORY THE TROUBLE WITH MEMORY OUR MARKETING SLIDE Kirk Pepperdine Authors of jpdm, a performance diagnostic model Co-founded Building the smart generation of performance diagnostic tooling Bring predictability

More information

Garbage Collection. Hwansoo Han

Garbage Collection. Hwansoo Han Garbage Collection Hwansoo Han Heap Memory Garbage collection Automatically reclaim the space that the running program can never access again Performed by the runtime system Two parts of a garbage collector

More information

JVM Memory Model and GC

JVM Memory Model and GC JVM Memory Model and GC Developer Community Support Fairoz Matte Principle Member Of Technical Staff Java Platform Sustaining Engineering, Copyright 2015, Oracle and/or its affiliates. All rights reserved.

More information

Java Performance Tuning

Java Performance Tuning 443 North Clark St, Suite 350 Chicago, IL 60654 Phone: (312) 229-1727 Java Performance Tuning This white paper presents the basics of Java Performance Tuning and its preferred values for large deployments

More information

JAVA PERFORMANCE. PR SW2 S18 Dr. Prähofer DI Leopoldseder

JAVA PERFORMANCE. PR SW2 S18 Dr. Prähofer DI Leopoldseder JAVA PERFORMANCE PR SW2 S18 Dr. Prähofer DI Leopoldseder OUTLINE 1. What is performance? 1. Benchmarking 2. What is Java performance? 1. Interpreter vs JIT 3. Tools to measure performance 4. Memory Performance

More information

Memory management has always involved tradeoffs between numerous optimization possibilities: Schemes to manage problem fall into roughly two camps

Memory management has always involved tradeoffs between numerous optimization possibilities: Schemes to manage problem fall into roughly two camps Garbage Collection Garbage collection makes memory management easier for programmers by automatically reclaiming unused memory. The garbage collector in the CLR makes tradeoffs to assure reasonable performance

More information

New Java performance developments: compilation and garbage collection

New Java performance developments: compilation and garbage collection New Java performance developments: compilation and garbage collection Jeroen Borgers @jborgers #jfall17 Part 1: New in Java compilation Part 2: New in Java garbage collection 2 Part 1 New in Java compilation

More information

WHO AM I.

WHO AM I. WHO AM I Christoph Engelbert (@noctarius2k) 8+ years of professional Java development Specialized to performance, GC, traffic topics Apache DirectMemory PMC Previous companies incl. Ubisoft and HRS Official

More information

A new Mono GC. Paolo Molaro October 25, 2006

A new Mono GC. Paolo Molaro October 25, 2006 A new Mono GC Paolo Molaro lupus@novell.com October 25, 2006 Current GC: why Boehm Ported to the major architectures and systems Featurefull Very easy to integrate Handles managed pointers in unmanaged

More information

Java Without the Jitter

Java Without the Jitter TECHNOLOGY WHITE PAPER Achieving Ultra-Low Latency Table of Contents Executive Summary... 3 Introduction... 4 Why Java Pauses Can t Be Tuned Away.... 5 Modern Servers Have Huge Capacities Why Hasn t Latency

More information

Shenandoah An ultra-low pause time Garbage Collector for OpenJDK. Christine H. Flood Roman Kennke

Shenandoah An ultra-low pause time Garbage Collector for OpenJDK. Christine H. Flood Roman Kennke Shenandoah An ultra-low pause time Garbage Collector for OpenJDK Christine H. Flood Roman Kennke 1 What does ultra-low pause time mean? It means that the pause time is proportional to the size of the root

More information

Attila Szegedi, Software

Attila Szegedi, Software Attila Szegedi, Software Engineer @asz Everything I ever learned about JVM performance tuning @twitter Everything More than I ever wanted to learned about JVM performance tuning @twitter Memory tuning

More information

NG2C: Pretenuring Garbage Collection with Dynamic Generations for HotSpot Big Data Applications

NG2C: Pretenuring Garbage Collection with Dynamic Generations for HotSpot Big Data Applications NG2C: Pretenuring Garbage Collection with Dynamic Generations for HotSpot Big Data Applications Rodrigo Bruno Luis Picciochi Oliveira Paulo Ferreira 03-160447 Tomokazu HIGUCHI Paper Information Published

More information

Runtime. The optimized program is ready to run What sorts of facilities are available at runtime

Runtime. The optimized program is ready to run What sorts of facilities are available at runtime Runtime The optimized program is ready to run What sorts of facilities are available at runtime Compiler Passes Analysis of input program (front-end) character stream Lexical Analysis token stream Syntactic

More information

Myths and Realities: The Performance Impact of Garbage Collection

Myths and Realities: The Performance Impact of Garbage Collection Myths and Realities: The Performance Impact of Garbage Collection Tapasya Patki February 17, 2011 1 Motivation Automatic memory management has numerous software engineering benefits from the developer

More information

Java Performance Tuning From A Garbage Collection Perspective. Nagendra Nagarajayya MDE

Java Performance Tuning From A Garbage Collection Perspective. Nagendra Nagarajayya MDE Java Performance Tuning From A Garbage Collection Perspective Nagendra Nagarajayya MDE Agenda Introduction To Garbage Collection Performance Problems Due To Garbage Collection Performance Tuning Manual

More information

Chapter 5A. Large and Fast: Exploiting Memory Hierarchy

Chapter 5A. Large and Fast: Exploiting Memory Hierarchy Chapter 5A Large and Fast: Exploiting Memory Hierarchy Memory Technology Static RAM (SRAM) Fast, expensive Dynamic RAM (DRAM) In between Magnetic disk Slow, inexpensive Ideal memory Access time of SRAM

More information

The Garbage-First Garbage Collector

The Garbage-First Garbage Collector The Garbage-First Garbage Collector Tony Printezis, Sun Microsystems Paul Ciciora, Chicago Board Options Exchange #TS-9 Trademarks And Abbreviations (to get them out of the way...) Java Platform, Standard

More information

The Fundamentals of JVM Tuning

The Fundamentals of JVM Tuning The Fundamentals of JVM Tuning Charlie Hunt Architect, Performance Engineering Salesforce.com sfdc_ppt_corp_template_01_01_2012.ppt In a Nutshell What you need to know about a modern JVM to be effective

More information

Acknowledgements These slides are based on Kathryn McKinley s slides on garbage collection as well as E Christopher Lewis s slides

Acknowledgements These slides are based on Kathryn McKinley s slides on garbage collection as well as E Christopher Lewis s slides Garbage Collection Last time Compiling Object-Oriented Languages Today Motivation behind garbage collection Garbage collection basics Garbage collection performance Specific example of using GC in C++

More information

Computer Systems A Programmer s Perspective 1 (Beta Draft)

Computer Systems A Programmer s Perspective 1 (Beta Draft) Computer Systems A Programmer s Perspective 1 (Beta Draft) Randal E. Bryant David R. O Hallaron August 1, 2001 1 Copyright c 2001, R. E. Bryant, D. R. O Hallaron. All rights reserved. 2 Contents Preface

More information

Sustainable Memory Use Allocation & (Implicit) Deallocation (mostly in Java)

Sustainable Memory Use Allocation & (Implicit) Deallocation (mostly in Java) COMP 412 FALL 2017 Sustainable Memory Use Allocation & (Implicit) Deallocation (mostly in Java) Copyright 2017, Keith D. Cooper & Zoran Budimlić, all rights reserved. Students enrolled in Comp 412 at Rice

More information

NUMA in High-Level Languages. Patrick Siegler Non-Uniform Memory Architectures Hasso-Plattner-Institut

NUMA in High-Level Languages. Patrick Siegler Non-Uniform Memory Architectures Hasso-Plattner-Institut NUMA in High-Level Languages Non-Uniform Memory Architectures Hasso-Plattner-Institut Agenda. Definition of High-Level Language 2. C# 3. Java 4. Summary High-Level Language Interpreter, no directly machine

More information

Garbage Collection. Vyacheslav Egorov

Garbage Collection. Vyacheslav Egorov Garbage Collection Vyacheslav Egorov 28.02.2012 class Heap { public: void* Allocate(size_t sz); }; class Heap { public: void* Allocate(size_t sz); void Deallocate(void* ptr); }; class Heap { public: void*

More information

Cross-Layer Memory Management to Reduce DRAM Power Consumption

Cross-Layer Memory Management to Reduce DRAM Power Consumption Cross-Layer Memory Management to Reduce DRAM Power Consumption Michael Jantz Assistant Professor University of Tennessee, Knoxville 1 Introduction Assistant Professor at UT since August 2014 Before UT

More information

Project. there are a couple of 3 person teams. a new drop with new type checking is coming. regroup or see me or forever hold your peace

Project. there are a couple of 3 person teams. a new drop with new type checking is coming. regroup or see me or forever hold your peace Project there are a couple of 3 person teams regroup or see me or forever hold your peace a new drop with new type checking is coming using it is optional 1 Compiler Architecture source code Now we jump

More information

The Z Garbage Collector Scalable Low-Latency GC in JDK 11

The Z Garbage Collector Scalable Low-Latency GC in JDK 11 The Z Garbage Collector Scalable Low-Latency GC in JDK 11 Per Lidén (@perliden) Consulting Member of Technical Staff Java Platform Group, Oracle October 24, 2018 Safe Harbor Statement The following is

More information

Shenandoah: Theory and Practice. Christine Flood Roman Kennke Principal Software Engineers Red Hat

Shenandoah: Theory and Practice. Christine Flood Roman Kennke Principal Software Engineers Red Hat Shenandoah: Theory and Practice Christine Flood Roman Kennke Principal Software Engineers Red Hat 1 Shenandoah Christine Flood Roman Kennke Principal Software Engineers Red Hat 2 Shenandoah Why do we need

More information

CMSC 330: Organization of Programming Languages

CMSC 330: Organization of Programming Languages CMSC 330: Organization of Programming Languages Memory Management and Garbage Collection CMSC 330 - Spring 2013 1 Memory Attributes! Memory to store data in programming languages has the following lifecycle

More information

Algorithms for Dynamic Memory Management (236780) Lecture 4. Lecturer: Erez Petrank

Algorithms for Dynamic Memory Management (236780) Lecture 4. Lecturer: Erez Petrank Algorithms for Dynamic Memory Management (236780) Lecture 4 Lecturer: Erez Petrank!1 March 24, 2014 Topics last week The Copying Garbage Collector algorithm: Basics Cheney s collector Additional issues:

More information

Practicing at the Cutting Edge Learning and Unlearning about Performance. Martin Thompson

Practicing at the Cutting Edge Learning and Unlearning about Performance. Martin Thompson Practicing at the Cutting Edge Learning and Unlearning about Performance Martin Thompson - @mjpt777 Learning and Unlearning 1. Brief History of Java 2. Evolving Design approach 3. An evolving Hardware

More information

A Tour to Spur for Non-VM Experts. Guille Polito, Christophe Demarey ESUG 2016, 22/08, Praha

A Tour to Spur for Non-VM Experts. Guille Polito, Christophe Demarey ESUG 2016, 22/08, Praha A Tour to Spur for Non-VM Experts Guille Polito, Christophe Demarey ESUG 2016, 22/08, Praha From a user point of view We are working on the new Pharo Kernel Bootstrap: create an image from scratch - Classes

More information

Parallel Algorithm Engineering

Parallel Algorithm Engineering Parallel Algorithm Engineering Kenneth S. Bøgh PhD Fellow Based on slides by Darius Sidlauskas Outline Background Current multicore architectures UMA vs NUMA The openmp framework and numa control Examples

More information

Cluster Consensus When Aeron Met Raft. Martin Thompson

Cluster Consensus When Aeron Met Raft. Martin Thompson Cluster When Aeron Met Raft Martin Thompson - @mjpt777 What does mean? con sen sus noun \ kən-ˈsen(t)-səs \ : general agreement : unanimity Source: http://www.merriam-webster.com/ con sen sus noun \ kən-ˈsen(t)-səs

More information

Reducing Hit Times. Critical Influence on cycle-time or CPI. small is always faster and can be put on chip

Reducing Hit Times. Critical Influence on cycle-time or CPI. small is always faster and can be put on chip Reducing Hit Times Critical Influence on cycle-time or CPI Keep L1 small and simple small is always faster and can be put on chip interesting compromise is to keep the tags on chip and the block data off

More information

Garbage Collection Algorithms. Ganesh Bikshandi

Garbage Collection Algorithms. Ganesh Bikshandi Garbage Collection Algorithms Ganesh Bikshandi Announcement MP4 posted Term paper posted Introduction Garbage : discarded or useless material Collection : the act or process of collecting Garbage collection

More information

CS 345. Garbage Collection. Vitaly Shmatikov. slide 1

CS 345. Garbage Collection. Vitaly Shmatikov. slide 1 CS 345 Garbage Collection Vitaly Shmatikov slide 1 Major Areas of Memory Static area Fixed size, fixed content, allocated at compile time Run-time stack Variable size, variable content (activation records)

More information

Habanero Extreme Scale Software Research Project

Habanero Extreme Scale Software Research Project Habanero Extreme Scale Software Research Project Comp215: Garbage Collection Zoran Budimlić (Rice University) Adapted from Keith Cooper s 2014 lecture in COMP 215. Garbage Collection In Beverly Hills...

More information

Hard Real-Time Garbage Collection in Java Virtual Machines

Hard Real-Time Garbage Collection in Java Virtual Machines Hard Real-Time Garbage Collection in Java Virtual Machines... towards unrestricted real-time programming in Java Fridtjof Siebert, IPD, University of Karlsruhe 1 Jamaica Systems Structure Exisiting GC

More information

CMSC 330: Organization of Programming Languages. Memory Management and Garbage Collection

CMSC 330: Organization of Programming Languages. Memory Management and Garbage Collection CMSC 330: Organization of Programming Languages Memory Management and Garbage Collection CMSC330 Fall 2018 1 Memory Attributes Memory to store data in programming languages has the following lifecycle

More information

CS252 S05. Main memory management. Memory hardware. The scale of things. Memory hardware (cont.) Bottleneck

CS252 S05. Main memory management. Memory hardware. The scale of things. Memory hardware (cont.) Bottleneck Main memory management CMSC 411 Computer Systems Architecture Lecture 16 Memory Hierarchy 3 (Main Memory & Memory) Questions: How big should main memory be? How to handle reads and writes? How to find

More information

Operating Systems. File Systems. Thomas Ropars.

Operating Systems. File Systems. Thomas Ropars. 1 Operating Systems File Systems Thomas Ropars thomas.ropars@univ-grenoble-alpes.fr 2017 2 References The content of these lectures is inspired by: The lecture notes of Prof. David Mazières. Operating

More information

CMSC 330: Organization of Programming Languages

CMSC 330: Organization of Programming Languages CMSC 330: Organization of Programming Languages Memory Management and Garbage Collection CMSC 330 Spring 2017 1 Memory Attributes Memory to store data in programming languages has the following lifecycle

More information

Atomicity via Source-to-Source Translation

Atomicity via Source-to-Source Translation Atomicity via Source-to-Source Translation Benjamin Hindman Dan Grossman University of Washington 22 October 2006 Atomic An easier-to-use and harder-to-implement primitive void deposit(int x){ synchronized(this){

More information

Programming Language Implementation

Programming Language Implementation A Practical Introduction to Programming Language Implementation 2014: Week 10 Garbage Collection College of Information Science and Engineering Ritsumeikan University 1 review of last week s topics dynamic

More information

Fast Java Programs. Jacob

Fast Java Programs. Jacob Fast Java Programs Outline Intro The Stack Measuring Architecture Patterns & APIs Q&A Outline Intro The Stack Measuring Architecture Patterns & APIs Q&A Why? Premature optimization (is not a free ticket

More information

Kampala August, Agner Fog

Kampala August, Agner Fog Advanced microprocessor optimization Kampala August, 2007 Agner Fog www.agner.org Agenda Intel and AMD microprocessors Out Of Order execution Branch prediction Platform, 32 or 64 bits Choice of compiler

More information

Java Application Performance Tuning for AMD EPYC Processors

Java Application Performance Tuning for AMD EPYC Processors Java Application Performance Tuning for AMD EPYC Processors Publication # 56245 Revision: 0.70 Issue Date: January 2018 Advanced Micro Devices 2018 Advanced Micro Devices, Inc. All rights reserved. The

More information

4.1 Introduction 4.3 Datapath 4.4 Control 4.5 Pipeline overview 4.6 Pipeline control * 4.7 Data hazard & forwarding * 4.

4.1 Introduction 4.3 Datapath 4.4 Control 4.5 Pipeline overview 4.6 Pipeline control * 4.7 Data hazard & forwarding * 4. Chapter 4: CPU 4.1 Introduction 4.3 Datapath 4.4 Control 4.5 Pipeline overview 4.6 Pipeline control * 4.7 Data hazard & forwarding * 4.8 Control hazard 4.14 Concluding Rem marks Hazards Situations that

More information

Java Garbage Collection Best Practices For Tuning GC

Java Garbage Collection Best Practices For Tuning GC Neil Masson, Java Support Technical Lead Java Garbage Collection Best Practices For Tuning GC Overview Introduction to Generational Garbage Collection The tenured space aka the old generation The nursery

More information

Garbage Collection (aka Automatic Memory Management) Douglas Q. Hawkins. Why?

Garbage Collection (aka Automatic Memory Management) Douglas Q. Hawkins.  Why? Garbage Collection (aka Automatic Memory Management) Douglas Q. Hawkins http://www.dougqh.net dougqh@gmail.com Why? Leaky Abstraction 2 of 3 Optimization Flags Are For Memory Management Unfortunately,

More information

Virtual Memory Primitives for User Programs

Virtual Memory Primitives for User Programs Virtual Memory Primitives for User Programs Andrew W. Appel & Kai Li Department of Computer Science Princeton University Presented By: Anirban Sinha (aka Ani), anirbans@cs.ubc.ca 1 About the Authors Andrew

More information

Generational Garbage Collection Theory and Best Practices

Generational Garbage Collection Theory and Best Practices Chris Bailey, Java Support Architect Generational Garbage Collection Theory and Best Practices Overview Introduction to Generational Garbage Collection The nursery space aka the young generation The tenured

More information

G1 Garbage Collector Details and Tuning. Simone Bordet

G1 Garbage Collector Details and Tuning. Simone Bordet G1 Garbage Collector Details and Tuning Who Am I - @simonebordet Lead Architect at Intalio/Webtide Jetty's HTTP/2, SPDY and HTTP client maintainer Open Source Contributor Jetty, CometD, MX4J, Foxtrot,

More information

Review. Partitioning: Divide heap, use different strategies per heap Generational GC: Partition by age Most objects die young

Review. Partitioning: Divide heap, use different strategies per heap Generational GC: Partition by age Most objects die young Generational GC 1 Review Partitioning: Divide heap, use different strategies per heap Generational GC: Partition by age Most objects die young 2 Single-partition scanning Stack Heap Partition #1 Partition

More information

Garbage Collection. Akim D le, Etienne Renault, Roland Levillain. May 15, CCMP2 Garbage Collection May 15, / 35

Garbage Collection. Akim D le, Etienne Renault, Roland Levillain. May 15, CCMP2 Garbage Collection May 15, / 35 Garbage Collection Akim Demaille, Etienne Renault, Roland Levillain May 15, 2017 CCMP2 Garbage Collection May 15, 2017 1 / 35 Table of contents 1 Motivations and Definitions 2 Reference Counting Garbage

More information

The Z Garbage Collector An Introduction

The Z Garbage Collector An Introduction The Z Garbage Collector An Introduction Per Lidén & Stefan Karlsson HotSpot Garbage Collection Team FOSDEM 2018 Safe Harbor Statement The following is intended to outline our general product direction.

More information

The Z Garbage Collector Low Latency GC for OpenJDK

The Z Garbage Collector Low Latency GC for OpenJDK The Z Garbage Collector Low Latency GC for OpenJDK Per Lidén & Stefan Karlsson HotSpot Garbage Collection Team Jfokus VM Tech Summit 2018 Safe Harbor Statement The following is intended to outline our

More information

Memory. From Chapter 3 of High Performance Computing. c R. Leduc

Memory. From Chapter 3 of High Performance Computing. c R. Leduc Memory From Chapter 3 of High Performance Computing c 2002-2004 R. Leduc Memory Even if CPU is infinitely fast, still need to read/write data to memory. Speed of memory increasing much slower than processor

More information

CS399 New Beginnings. Jonathan Walpole

CS399 New Beginnings. Jonathan Walpole CS399 New Beginnings Jonathan Walpole Memory Management Memory Management Memory a linear array of bytes - Holds O.S. and programs (processes) - Each cell (byte) is named by a unique memory address Recall,

More information

Azul Systems, Inc.

Azul Systems, Inc. 1 Stack Based Allocation in the Azul JVM Dr. Cliff Click cliffc@azulsystems.com 2005 Azul Systems, Inc. Background The Azul JVM is based on Sun HotSpot a State-of-the-Art Java VM Java is a GC'd language

More information

Andrey Akinshin, JetBrains

Andrey Akinshin, JetBrains Let s talk about microbenchmarking Andrey Akinshin, JetBrains DotNext 2016 Helsinki 1/29 2/29 BenchmarkDotNet Today s environment BenchmarkDotNet v0.10.1 Haswell Core i7-4702mq CPU 2.20GHz, Windows 10.NET

More information

JVM Troubleshooting MOOC: Troubleshooting Memory Issues in Java Applications

JVM Troubleshooting MOOC: Troubleshooting Memory Issues in Java Applications JVM Troubleshooting MOOC: Troubleshooting Memory Issues in Java Applications Poonam Parhar JVM Sustaining Engineer Oracle Lesson 1 HotSpot JVM Memory Management Poonam Parhar JVM Sustaining Engineer Oracle

More information

PERFORMANCE ANALYSIS AND OPTIMIZATION OF SKIP LISTS FOR MODERN MULTI-CORE ARCHITECTURES

PERFORMANCE ANALYSIS AND OPTIMIZATION OF SKIP LISTS FOR MODERN MULTI-CORE ARCHITECTURES PERFORMANCE ANALYSIS AND OPTIMIZATION OF SKIP LISTS FOR MODERN MULTI-CORE ARCHITECTURES Anish Athalye and Patrick Long Mentors: Austin Clements and Stephen Tu 3 rd annual MIT PRIMES Conference Sequential

More information

Optimising Multicore JVMs. Khaled Alnowaiser

Optimising Multicore JVMs. Khaled Alnowaiser Optimising Multicore JVMs Khaled Alnowaiser Outline JVM structure and overhead analysis Multithreaded JVM services JVM on multicore An observational study Potential JVM optimisations Basic JVM Services

More information

Why memory hierarchy? Memory hierarchy. Memory hierarchy goals. CS2410: Computer Architecture. L1 cache design. Sangyeun Cho

Why memory hierarchy? Memory hierarchy. Memory hierarchy goals. CS2410: Computer Architecture. L1 cache design. Sangyeun Cho Why memory hierarchy? L1 cache design Sangyeun Cho Computer Science Department Memory hierarchy Memory hierarchy goals Smaller Faster More expensive per byte CPU Regs L1 cache L2 cache SRAM SRAM To provide

More information

Efficient Runtime Tracking of Allocation Sites in Java

Efficient Runtime Tracking of Allocation Sites in Java Efficient Runtime Tracking of Allocation Sites in Java Rei Odaira, Kazunori Ogata, Kiyokuni Kawachiya, Tamiya Onodera, Toshio Nakatani IBM Research - Tokyo Why Do You Need Allocation Site Information?

More information

SABLEJIT: A Retargetable Just-In-Time Compiler for a Portable Virtual Machine p. 1

SABLEJIT: A Retargetable Just-In-Time Compiler for a Portable Virtual Machine p. 1 SABLEJIT: A Retargetable Just-In-Time Compiler for a Portable Virtual Machine David Bélanger dbelan2@cs.mcgill.ca Sable Research Group McGill University Montreal, QC January 28, 2004 SABLEJIT: A Retargetable

More information

Workload Characterization and Optimization of TPC-H Queries on Apache Spark

Workload Characterization and Optimization of TPC-H Queries on Apache Spark Workload Characterization and Optimization of TPC-H Queries on Apache Spark Tatsuhiro Chiba and Tamiya Onodera IBM Research - Tokyo April. 17-19, 216 IEEE ISPASS 216 @ Uppsala, Sweden Overview IBM Research

More information

Fundamentals of GC Tuning. Charlie Hunt JVM & Performance Junkie

Fundamentals of GC Tuning. Charlie Hunt JVM & Performance Junkie Fundamentals of GC Tuning Charlie Hunt JVM & Performance Junkie Who is this guy? Charlie Hunt Currently leading a variety of HotSpot JVM projects at Oracle Held various performance architect roles at Oracle,

More information

Inside the Garbage Collector

Inside the Garbage Collector Inside the Garbage Collector Agenda Applications and Resources The Managed Heap Mark and Compact Generations Non-Memory Resources Finalization Hindering the GC Helping the GC 2 Applications and Resources

More information

Efficient Java (with Stratosphere) Arvid Heise, Large Scale Duplicate Detection

Efficient Java (with Stratosphere) Arvid Heise, Large Scale Duplicate Detection Efficient Java (with Stratosphere) Arvid Heise, Large Scale Duplicate Detection Agenda 2 Bottlenecks Mutable vs. Immutable Caching/Pooling Strings Primitives Final Classloaders Exception Handling Concurrency

More information

Martin Kruliš, v

Martin Kruliš, v Martin Kruliš 1 Optimizations in General Code And Compilation Memory Considerations Parallelism Profiling And Optimization Examples 2 Premature optimization is the root of all evil. -- D. Knuth Our goal

More information

Short-term Memory for Self-collecting Mutators. Martin Aigner, Andreas Haas, Christoph Kirsch, Ana Sokolova Universität Salzburg

Short-term Memory for Self-collecting Mutators. Martin Aigner, Andreas Haas, Christoph Kirsch, Ana Sokolova Universität Salzburg Short-term Memory for Self-collecting Mutators Martin Aigner, Andreas Haas, Christoph Kirsch, Ana Sokolova Universität Salzburg CHESS Seminar, UC Berkeley, September 2010 Heap Management explicit heap

More information

Modern Processor Architectures. L25: Modern Compiler Design

Modern Processor Architectures. L25: Modern Compiler Design Modern Processor Architectures L25: Modern Compiler Design The 1960s - 1970s Instructions took multiple cycles Only one instruction in flight at once Optimisation meant minimising the number of instructions

More information

Dynamic Dispatch and Duck Typing. L25: Modern Compiler Design

Dynamic Dispatch and Duck Typing. L25: Modern Compiler Design Dynamic Dispatch and Duck Typing L25: Modern Compiler Design Late Binding Static dispatch (e.g. C function calls) are jumps to specific addresses Object-oriented languages decouple method name from method

More information

LECTURE 4: LARGE AND FAST: EXPLOITING MEMORY HIERARCHY

LECTURE 4: LARGE AND FAST: EXPLOITING MEMORY HIERARCHY LECTURE 4: LARGE AND FAST: EXPLOITING MEMORY HIERARCHY Abridged version of Patterson & Hennessy (2013):Ch.5 Principle of Locality Programs access a small proportion of their address space at any time Temporal

More information

The benefits and costs of writing a POSIX kernel in a high-level language

The benefits and costs of writing a POSIX kernel in a high-level language 1 / 38 The benefits and costs of writing a POSIX kernel in a high-level language Cody Cutler, M. Frans Kaashoek, Robert T. Morris MIT CSAIL Should we use high-level languages to build OS kernels? 2 / 38

More information

Performance Per Watt. Native code invited back from exile with the Return of the King:

Performance Per Watt. Native code invited back from exile with the Return of the King: 2009-1979-1989 Research: C with Classes, ARM C++ 1989-1999 Mainstream C++ goes to town (& ISO, & space, &c) 1999-2009 Coffee-based languages for productivity Q: Can they do everything important? Native

More information

Convergence of Parallel Architecture

Convergence of Parallel Architecture Parallel Computing Convergence of Parallel Architecture Hwansoo Han History Parallel architectures tied closely to programming models Divergent architectures, with no predictable pattern of growth Uncertainty

More information

Shenandoah: An ultra-low pause time garbage collector for OpenJDK. Christine Flood Roman Kennke Principal Software Engineers Red Hat

Shenandoah: An ultra-low pause time garbage collector for OpenJDK. Christine Flood Roman Kennke Principal Software Engineers Red Hat Shenandoah: An ultra-low pause time garbage collector for OpenJDK Christine Flood Roman Kennke Principal Software Engineers Red Hat 1 Shenandoah Why do we need it? What does it do? How does it work? What's

More information

Memory Management. Goals of Memory Management. Mechanism. Policies

Memory Management. Goals of Memory Management. Mechanism. Policies Memory Management Design, Spring 2011 Department of Computer Science Rutgers Sakai: 01:198:416 Sp11 (https://sakai.rutgers.edu) Memory Management Goals of Memory Management Convenient abstraction for programming

More information

C++ for System Developers with Design Pattern

C++ for System Developers with Design Pattern C++ for System Developers with Design Pattern Introduction: This course introduces the C++ language for use on real time and embedded applications. The first part of the course focuses on the language

More information

Memory management units

Memory management units Memory management units Memory management unit (MMU) translates addresses: CPU logical address memory management unit physical address main memory Computers as Components 1 Access time comparison Media

More information

Memory Hierarchy. Mehran Rezaei

Memory Hierarchy. Mehran Rezaei Memory Hierarchy Mehran Rezaei What types of memory do we have? Registers Cache (Static RAM) Main Memory (Dynamic RAM) Disk (Magnetic Disk) Option : Build It Out of Fast SRAM About 5- ns access Decoders

More information

VIRTUAL MEMORY READING: CHAPTER 9

VIRTUAL MEMORY READING: CHAPTER 9 VIRTUAL MEMORY READING: CHAPTER 9 9 MEMORY HIERARCHY Core! Processor! Core! Caching! Main! Memory! (DRAM)!! Caching!! Secondary Storage (SSD)!!!! Secondary Storage (Disk)! L cache exclusive to a single

More information

Swapping. Operating Systems I. Swapping. Motivation. Paging Implementation. Demand Paging. Active processes use more physical memory than system has

Swapping. Operating Systems I. Swapping. Motivation. Paging Implementation. Demand Paging. Active processes use more physical memory than system has Swapping Active processes use more physical memory than system has Operating Systems I Address Binding can be fixed or relocatable at runtime Swap out P P Virtual Memory OS Backing Store (Swap Space) Main

More information