Cog VM Evolution. Clément Béra. Thursday, August 25, 16

Size: px
Start display at page:

Download "Cog VM Evolution. Clément Béra. Thursday, August 25, 16"

Transcription

1 Cog VM Evolution Clément Béra

2 Cog VM? Smalltalk virtual machine Default VM for Pharo Squeak Newspeak Cuis

3 Cog Philosophy Open source (MIT) Simple Is the optimization / feature worth the added complexity? Cross-Platform (Processors, OS, 32/64 bits)

4 Execution engine VM Execution engine Plugins: graphics, file, etc.

5 Execution engine Interpreter JIT Memory Manager (including GC)

6 Evolution User and Customer driven Where did we start? What problems did we solve?

7 Starting blocks Interpreter VM Made by Dan Ingalls Team Simple Interpreter Spaghetti stack Smart but simple Memory Manager

8 Performance! Short-term delivery Performance for 3D application

9 Performance! Short-term delivery Performance for 3D application Fast Interpreter

10 Stack VM Context-to-stack Mapping 85% of context allocation removed No copying of arguments New hash logic Primitive function caching

11 Issue Closure implementation No temporaries BlockAlreadyEvaluated error Non obvious bugs New implementation

12 Binary Tree benchmark Interpreter Stack Cog V1 Cog V2 Spur Sista

13 More Performance! Short-term delivery Performance for 3D application

14 More Performance! Short-term delivery Performance for 3D application First JIT compiler

15 Cog VM x86 back-end Simple machine code generation Except inline caches

16 Binary Tree benchmark Interpreter Stack Cog V1 Cog V2 Spur Sista

17 JIT Abstractions Machine back-end x86 Object Representation V3 Cogit Implementation SimpleStackCogit

18 Yet More Performance! Short-term delivery Performance for 3D application

19 Yet More Performance! Short-term delivery Performance for 3D application Second JIT compiler

20 Cog VM Machine code generation Linear scan register allocation Avoids many stack operations Register-based calling convention

21 Binary Tree benchmark Interpreter Stack Cog V1 Cog V2 Spur Sista

22 JIT Abstractions Machine back-end x86 Object Representation V3 Cogit Implementation SimpleStackCogit StackToRegisterMappingCogit

23 Newspeak support? Newspeak is Smalltalk-like New kind of sends

24 Newspeak support? Multiple bytecode set support Newspeak specific operations Interpreter Machine code generation

25 64 bits? Images larger than 1 or 2 Gb? Moving objects during FFI call-backs? Even more performance! Ephemerons? Become is so slow it cannot be used.

26 64 bits? Images larger than 1 or 2 Gb? Moving objects during FFI call-backs? Even more performance! Ephemerons? Become is so slow it cannot be used. Short-term delivery

27 64 bits? Images larger than 1 or 2 Gb? Moving objects during FFI call-backs? Even more performance! Ephemerons? Become is so slow it cannot be used. Short-term delivery New Memory Manager

28 Spur Memory Manager Class-table (efficient caches and compactness) Efficient scavenging Fast become Pinned objects Segmented Memory New object layouts (Ephemerons, ShortArrays) Memory representation 64-bits compatible

29 Binary Tree benchmark Interpreter Stack Cog V1 Cog V2 Spur Sista

30 JIT Abstractions Machine back-end x86 Object Representation V3 Spur32 Cogit Implementation SimpleStackCogit StackToRegisterMappingCogit Spur64 32 bits 64 bits

31 Raspberry Pi performance? Scratch support

32 Raspberry Pi performance? Scratch support ARMv6 support

33 ARMv6 support JIT ARMv6 back-end JIT abstraction over literal management JIT abstraction over CISC / RISC

34 JIT Abstractions Machine back-end Object Representation Literal Manager Cogit Implementation x86 ARMv6 MIPSEL V3 Spur32 Spur64 Inline Outline SimpleStackCogit StackToRegisterMappingCogit 32 bits 64 bits

35 Ryan (contributor) Working with the Dart VM Dart runs on more platform than Newspeak.

36 Ryan (contributor) Working with the Dart VM Dart runs on more platform than Newspeak. MIPSEL support

37 JIT Abstractions Machine back-end Object Representation Literal Manager Cogit Implementation x86 ARMv6 MIPSEL V3 Spur32 Spur64 Inline Outline SimpleStackCogit StackToRegisterMappingCogit 32 bits 64 bits

38 64 bits support? 64 bits library binding Heap over 2Gb

39 64 bits support? 64 bits library binding Heap over 2Gb x64 support Immediate float

40 JIT Abstractions Machine back-end Object Representation Literal Manager Cogit Implementation x86 ARMv6 MIPSEL x64 V3 Spur32 Spur64 Inline Outline SimpleStackCogit StackToRegisterMappingCogit 32 bits 64 bits

41 Yet even more performance! Computation lasting 3 to 6 hours

42 Yet even more performance! Computation lasting 3 to 6 hours Speculative optimizations

43 Sista VM The program introspects Optimize the code for performance Deoptimize when it took incorrect decisions

44 Issues Bytecode set Literal mutability Closure implementation

45 Bytecode set limitations? Code generator tools

46 Sista bytecode set Lifting encoding limitations Encode instructions for the Sista / Lowcode

47 Efficient modification trackers? Literal inconsistency?

48 Efficient modification trackers? Literal inconsistency? Read-only objects IWST talk this afternoon Hopefully allows more compiler optimizations

49 Closure implementation Method and closure get more similar Simplifies part of the VM Simplifies the runtime compiler

50 Integration Closed alpha version Integrating dependencies: Bytecode set integrated Read-only objects integrated (but disabled) Closure implementation in progress

51 Binary Tree benchmark Interpreter Stack Cog V1 Cog V2 Spur Sista

52 JIT Abstractions Machine back-end Object Representation Literal Manager Cogit Implementation x86 ARMv6 MIPSEL x64 V3 Spur32 Spur64 Inline Outline SimpleStackCogit StackToRegisterMappingCogit RegisterAllocatingCogit SistaCogit 32 bits 64 bits

53 Image compaction? Sometimes, large images when saving

54 Image compaction? Sometimes, large images when saving Better compactor

55 Pauses? 0.5 second freezes in UI application

56 Pauses? 0.5 second freezes in UI application Incremental GC

57 Many hidden parts...

58 C compiler warning? C generated from Slang Many were fixed Towards compilation with -WAll -WError

59 Faster arithmetic? LargeInteger plugin more efficient Computation moved from 8bits to 32 bits Different compilation flags

60 Slang? Slang-to-C compiler Many improvements Type inference

61 Contribution

62 Cog VM team Started with Eliot Miranda Many more contributors now: Tim Rowledge Clément Béra (myself) Nicolas Cellier Fabio Niephaus & Tim Felgentreff Ryan Macnak

63 Conclusion Lots of new features and improvements over years A lot more is incoming If you want to support, talk to us! ARMv8? Incremental GC? Performance (escaping, floats)?

Sista: Improving Cog s JIT performance. Clément Béra

Sista: Improving Cog s JIT performance. Clément Béra Sista: Improving Cog s JIT performance Clément Béra Main people involved in Sista Eliot Miranda Over 30 years experience in Smalltalk VM Clément Béra 2 years engineer in the Pharo team Phd student starting

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

A Partial Read Barrier for Efficient Support of Live Object-oriented Programming

A Partial Read Barrier for Efficient Support of Live Object-oriented Programming A Partial Read Barrier for Efficient Support of Live Object-oriented Programming Eliot Miranda, Clément Béra To cite this version: Eliot Miranda, Clément Béra. A Partial Read Barrier for Efficient Support

More information

Sista: Saving Optimized Code in Snapshots for Fast Start-Up

Sista: Saving Optimized Code in Snapshots for Fast Start-Up Sista: Saving Optimized Code in Snapshots for Fast Start-Up Clément Béra, Eliot Miranda, Tim Felgentreff, Marcus Denker, Stéphane Ducasse To cite this version: Clément Béra, Eliot Miranda, Tim Felgentreff,

More information

Lowcode: Extending Pharo with C Types to Improve Performance. Ronie Salgado. Stéphane Ducasse. Abstract. 1. Two worlds of programming languages

Lowcode: Extending Pharo with C Types to Improve Performance. Ronie Salgado. Stéphane Ducasse. Abstract. 1. Two worlds of programming languages Accepted to IWST2016 Lowcode: Extending Pharo with C Types to Improve Performance Ronie Salgado Pleiad Lab, DCC, University of Chile roniesalg@gmail.com Stéphane Ducasse RMoD, INRIA Lille stephane.ducasse@inria.fr

More information

RSqueak/VM Building a fast, malleable VM with students

RSqueak/VM Building a fast, malleable VM with students RSqueak/VM Building a fast, malleable VM with students Hasso-Plattner-Institut Potsdam Software Architecture Group Tim Felgentreff, Tobias Pape, Patrick Rein, Robert Hirschfeld http://www.hpi.uni-potsdam.de/swa/

More information

A low Overhead Per Object Write Barrier for the Cog VM

A low Overhead Per Object Write Barrier for the Cog VM A low Overhead Per Object Write Barrier for the Cog VM Clément Bera To cite this version: Clément Bera. A low Overhead Per Object Write Barrier for the Cog VM. IWST 16, 2016, Pragues, Czech Republic. Proceedings

More information

Sista: a Metacircular Architecture for Runtime Optimisation Persistence

Sista: a Metacircular Architecture for Runtime Optimisation Persistence Sista: a Metacircular Architecture for Runtime Optimisation Persistence Clément Béra To cite this version: Clément Béra. Sista: a Metacircular Architecture for Runtime Optimisation Persistence. Programming

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

Optimization Techniques

Optimization Techniques Smalltalk Implementation: Optimization Techniques Prof. Harry Porter Portland State University 1 Optimization Ideas Just-In-Time (JIT) compiling When a method is first invoked, compile it into native code.

More information

A bytecode set for adaptive optimizations

A bytecode set for adaptive optimizations A bytecode set for adaptive optimizations Clément Béra, Eliot Miranda To cite this version: Clément Béra, Eliot Miranda. A bytecode set for adaptive optimizations. International Workshop on Smalltalk Technologies,

More information

IWST In conjunction with the 22th International Smalltalk Joint Conference Cambridge, England, August 19, 2014

IWST In conjunction with the 22th International Smalltalk Joint Conference Cambridge, England, August 19, 2014 IWST 2014 Proceedings of the 6th edition of the International Workshop on Smalltalk Technologies In conjunction with the 22th International Smalltalk Joint Conference Cambridge, England, August 19, 2014

More information

Smalltalk Implementation

Smalltalk Implementation Smalltalk Implementation Prof. Harry Porter Portland State University 1 The Image The object heap The Virtual Machine The underlying system (e.g., Mac OS X) The ST language interpreter The object-memory

More information

CSE P 501 Compilers. Java Implementation JVMs, JITs &c Hal Perkins Winter /11/ Hal Perkins & UW CSE V-1

CSE P 501 Compilers. Java Implementation JVMs, JITs &c Hal Perkins Winter /11/ Hal Perkins & UW CSE V-1 CSE P 501 Compilers Java Implementation JVMs, JITs &c Hal Perkins Winter 2008 3/11/2008 2002-08 Hal Perkins & UW CSE V-1 Agenda Java virtual machine architecture.class files Class loading Execution engines

More information

Agenda. CSE P 501 Compilers. Java Implementation Overview. JVM Architecture. JVM Runtime Data Areas (1) JVM Data Types. CSE P 501 Su04 T-1

Agenda. CSE P 501 Compilers. Java Implementation Overview. JVM Architecture. JVM Runtime Data Areas (1) JVM Data Types. CSE P 501 Su04 T-1 Agenda CSE P 501 Compilers Java Implementation JVMs, JITs &c Hal Perkins Summer 2004 Java virtual machine architecture.class files Class loading Execution engines Interpreters & JITs various strategies

More information

<Insert Picture Here> Symmetric multilanguage VM architecture: Running Java and JavaScript in Shared Environment on a Mobile Phone

<Insert Picture Here> Symmetric multilanguage VM architecture: Running Java and JavaScript in Shared Environment on a Mobile Phone Symmetric multilanguage VM architecture: Running Java and JavaScript in Shared Environment on a Mobile Phone Oleg Pliss Pavel Petroshenko Agenda Introduction to Monty JVM Motivation

More information

code://rubinius/technical

code://rubinius/technical code://rubinius/technical /GC, /cpu, /organization, /compiler weeee!! Rubinius New, custom VM for running ruby code Small VM written in not ruby Kernel and everything else in ruby http://rubini.us git://rubini.us/code

More information

Kasper Lund, Software engineer at Google. Crankshaft. Turbocharging the next generation of web applications

Kasper Lund, Software engineer at Google. Crankshaft. Turbocharging the next generation of web applications Kasper Lund, Software engineer at Google Crankshaft Turbocharging the next generation of web applications Overview Why did we introduce Crankshaft? Deciding when and what to optimize Type feedback and

More information

Announcements. My office hours are today in Gates 160 from 1PM-3PM. Programming Project 3 checkpoint due tomorrow night at 11:59PM.

Announcements. My office hours are today in Gates 160 from 1PM-3PM. Programming Project 3 checkpoint due tomorrow night at 11:59PM. IR Generation Announcements My office hours are today in Gates 160 from 1PM-3PM. Programming Project 3 checkpoint due tomorrow night at 11:59PM. This is a hard deadline and no late submissions will be

More information

Building Robust Embedded Software

Building Robust Embedded Software Building Robust Embedded Software by Lars Bak, OOVM A/S Demands of the Embedded Industy Increased reliability Low cost -> resource constraints Dynamic software updates in the field Real-time capabilities

More information

6.828: OS/Language Co-design. Adam Belay

6.828: OS/Language Co-design. Adam Belay 6.828: OS/Language Co-design Adam Belay Singularity An experimental research OS at Microsoft in the early 2000s Many people and papers, high profile project Influenced by experiences at

More information

JamaicaVM Java for Embedded Realtime Systems

JamaicaVM Java for Embedded Realtime Systems JamaicaVM Java for Embedded Realtime Systems... bringing modern software development methods to safety critical applications Fridtjof Siebert, 25. Oktober 2001 1 Deeply embedded applications Examples:

More information

Outline Smalltalk Overview Pragmatic Smalltalk Closing. Pragmatic Smalltalk. David Chisnall. February 7,

Outline Smalltalk Overview Pragmatic Smalltalk Closing. Pragmatic Smalltalk. David Chisnall. February 7, February 7, 2009 http://etoileos.com Outline Using The Smalltalk Family Smalltalk - first dynamic, object-oriented, language. Self - Smalltalk without classes. JavaScript - Self with Java syntax. A Quick

More information

High-Level Language VMs

High-Level Language VMs High-Level Language VMs Outline Motivation What is the need for HLL VMs? How are these different from System or Process VMs? Approach to HLL VMs Evolutionary history Pascal P-code Object oriented HLL VMs

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

BEAMJIT: An LLVM based just-in-time compiler for Erlang. Frej Drejhammar

BEAMJIT: An LLVM based just-in-time compiler for Erlang. Frej Drejhammar BEAMJIT: An LLVM based just-in-time compiler for Erlang Frej Drejhammar 140407 Who am I? Senior researcher at the Swedish Institute of Computer Science (SICS) working on programming languages,

More information

Crossing Abstraction Barriers When Debugging in Dynamic Languages

Crossing Abstraction Barriers When Debugging in Dynamic Languages Crossing Abstraction Barriers When Debugging in Dynamic Languages Bastian Kruck, Tobias Pape, Tim Felgentreff, Robert Hirschfeld Hasso Plattner Institute Universtiy of Potsdam {firstname.lastname}@student.hpi.uni-potsdam.de

More information

BEAMJIT, a Maze of Twisty Little Traces

BEAMJIT, a Maze of Twisty Little Traces BEAMJIT, a Maze of Twisty Little Traces A walk-through of the prototype just-in-time (JIT) compiler for Erlang. Frej Drejhammar 130613 Who am I? Senior researcher at the Swedish Institute

More information

Index. object lifetimes, and ownership, use after change by an alias errors, use after drop errors, BTreeMap, 309

Index. object lifetimes, and ownership, use after change by an alias errors, use after drop errors, BTreeMap, 309 A Arithmetic operation floating-point arithmetic, 11 12 integer numbers, 9 11 Arrays, 97 copying, 59 60 creation, 48 elements, 48 empty arrays and vectors, 57 58 executable program, 49 expressions, 48

More information

EITF20: Computer Architecture Part2.1.1: Instruction Set Architecture

EITF20: Computer Architecture Part2.1.1: Instruction Set Architecture EITF20: Computer Architecture Part2.1.1: Instruction Set Architecture Liang Liu liang.liu@eit.lth.se 1 Outline Reiteration Instruction Set Principles The Role of Compilers MIPS 2 Main Content Computer

More information

Extensibility in GNUstep & Étoilé

Extensibility in GNUstep & Étoilé Extensibility in GNUstep & Étoilé GNU Hackers 2011 http://www.gnustep.org http://www.etoileos.com Objective-C & GNUstep Objective-C Created by Brad Cox and Tom Love in 1986 to package C libraries in Smalltalk-like

More information

Towards Lean 4: Sebastian Ullrich 1, Leonardo de Moura 2.

Towards Lean 4: Sebastian Ullrich 1, Leonardo de Moura 2. Towards Lean 4: Sebastian Ullrich 1, Leonardo de Moura 2 1 Karlsruhe Institute of Technology, Germany 2 Microsoft Research, USA 1 2018/12/12 Ullrich, de Moura - Towards Lean 4: KIT The Research An University

More information

Benzo: Reflective Glue for Low-level Programming

Benzo: Reflective Glue for Low-level Programming Benzo: Reflective Glue for Low-level Programming Camillo Bruni Stéphane Ducasse Igor Stasenko RMoD, INRIA Lille - Nord Europe, France http://rmod.lille.inria.fr Guido Chari Departamento de Computación,

More information

Jaguar: Enabling Efficient Communication and I/O in Java

Jaguar: Enabling Efficient Communication and I/O in Java Jaguar: Enabling Efficient Communication and I/O in Java Matt Welsh and David Culler UC Berkeley Presented by David Hovemeyer Outline ' Motivation ' How it works ' Code mappings ' External objects ' Pre

More information

Pause-Less GC for Improving Java Responsiveness. Charlie Gracie IBM Senior Software charliegracie

Pause-Less GC for Improving Java Responsiveness. Charlie Gracie IBM Senior Software charliegracie Pause-Less GC for Improving Java Responsiveness Charlie Gracie IBM Senior Software Developer charlie_gracie@ca.ibm.com @crgracie charliegracie 1 Important Disclaimers THE INFORMATION CONTAINED IN THIS

More information

PyPy - How to not write Virtual Machines for Dynamic Languages

PyPy - How to not write Virtual Machines for Dynamic Languages PyPy - How to not write Virtual Machines for Dynamic Languages Institut für Informatik Heinrich-Heine-Universität Düsseldorf ESUG 2007 Scope This talk is about: implementing dynamic languages (with a focus

More information

Atomic Install in Newspeak

Atomic Install in Newspeak Atomic Install in Newspeak Gilad Bracha & Ryan Macnak Joint work with the Newspeak team at Cadence 1 Newspeak Overview Purely object-oriented, class-based, dynamically typed in the tradition of Smalltalk

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

Titan: A System Programming Language made for Lua

Titan: A System Programming Language made for Lua Titan: A System Programming Language made for Lua Hugo Musso Gualandi, PUC-Rio in collaboration with André Maidl, Fabio Mascarenhas, Gabriel Ligneul and Hisham Muhammad Part 1: Why Titan We started out

More information

plisp: A Friendly Lisp IDE for Beginners Rajesh Jayaprakash Tata Consultancy Services Chennai, India

plisp: A Friendly Lisp IDE for Beginners Rajesh Jayaprakash Tata Consultancy Services Chennai, India plisp: A Friendly Lisp IDE for Beginners Rajesh Jayaprakash Tata Consultancy Services Chennai, India Overview Basics What is plisp? Motivation Features Internals Language Object Model Compiler/Debugger

More information

Design Issues. Subroutines and Control Abstraction. Subroutines and Control Abstraction. CSC 4101: Programming Languages 1. Textbook, Chapter 8

Design Issues. Subroutines and Control Abstraction. Subroutines and Control Abstraction. CSC 4101: Programming Languages 1. Textbook, Chapter 8 Subroutines and Control Abstraction Textbook, Chapter 8 1 Subroutines and Control Abstraction Mechanisms for process abstraction Single entry (except FORTRAN, PL/I) Caller is suspended Control returns

More information

JOP: A Java Optimized Processor for Embedded Real-Time Systems. Martin Schoeberl

JOP: A Java Optimized Processor for Embedded Real-Time Systems. Martin Schoeberl JOP: A Java Optimized Processor for Embedded Real-Time Systems Martin Schoeberl JOP Research Targets Java processor Time-predictable architecture Small design Working solution (FPGA) JOP Overview 2 Overview

More information

Parsing Scheme (+ (* 2 3) 1) * 1

Parsing Scheme (+ (* 2 3) 1) * 1 Parsing Scheme + (+ (* 2 3) 1) * 1 2 3 Compiling Scheme frame + frame halt * 1 3 2 3 2 refer 1 apply * refer apply + Compiling Scheme make-return START make-test make-close make-assign make- pair? yes

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

A program execution is memory safe so long as memory access errors never occur:

A program execution is memory safe so long as memory access errors never occur: A program execution is memory safe so long as memory access errors never occur: Buffer overflows, null pointer dereference, use after free, use of uninitialized memory, illegal free Memory safety categories

More information

Introductions. GemStone Update for ESUG Agenda. What is GemStone/S? GS/S: Smalltalk Environment. GS/S: Database System 8/30/2009.

Introductions. GemStone Update for ESUG Agenda. What is GemStone/S? GS/S: Smalltalk Environment. GS/S: Database System 8/30/2009. GemStone Update for ESUG 2009 James Foster, GemStone Systems, Inc. Introductions James Foster QA, Seaside, Consulting, Training Dale Henrichs Seaside Lead Martin McClure GBS Lead Monty Williams MagLev,

More information

TRANSLATING DART TO EFFICIENT JAVASCRIPT. Kasper Lund Google

TRANSLATING DART TO EFFICIENT JAVASCRIPT. Kasper Lund Google TRANSLATING DART TO EFFICIENT JAVASCRIPT Kasper Lund Google Translating Dart to efficient JavaScript Kasper Lund, Google Who am I? Kasper Lund, software engineer at Google Projects OOVM: Embedded Smalltalk

More information

A Status Update of BEAMJIT, the Just-in-Time Compiling Abstract Machine. Frej Drejhammar and Lars Rasmusson

A Status Update of BEAMJIT, the Just-in-Time Compiling Abstract Machine. Frej Drejhammar and Lars Rasmusson A Status Update of BEAMJIT, the Just-in-Time Compiling Abstract Machine Frej Drejhammar and Lars Rasmusson 140609 Who am I? Senior researcher at the Swedish Institute of Computer Science

More information

Hardware-Supported Pointer Detection for common Garbage Collections

Hardware-Supported Pointer Detection for common Garbage Collections 2013 First International Symposium on Computing and Networking Hardware-Supported Pointer Detection for common Garbage Collections Kei IDEUE, Yuki SATOMI, Tomoaki TSUMURA and Hiroshi MATSUO Nagoya Institute

More information

What is Computer Architecture?

What is Computer Architecture? What is Computer Architecture? Architecture abstraction of the hardware for the programmer instruction set architecture instructions: operations operands, addressing the operands how instructions are encoded

More information

Garbage Collection and Efficiency in Dynamic Metacircular Runtimes An Experience Report

Garbage Collection and Efficiency in Dynamic Metacircular Runtimes An Experience Report Garbage Collection and Efficiency in Dynamic Metacircular Runtimes An Experience Report Abstract Javier Pimás Palantir Solutions javierpimas@gmail.com Jean Baptiste Arnaud Palantir Solutions jbarnaud@caesarsystems.com

More information

Virtual Machines and Dynamic Translation: Implementing ISAs in Software

Virtual Machines and Dynamic Translation: Implementing ISAs in Software Virtual Machines and Dynamic Translation: Implementing ISAs in Software Krste Asanovic Laboratory for Computer Science Massachusetts Institute of Technology Software Applications How is a software application

More information

Managed runtimes & garbage collection. CSE 6341 Some slides by Kathryn McKinley

Managed runtimes & garbage collection. CSE 6341 Some slides by Kathryn McKinley Managed runtimes & garbage collection CSE 6341 Some slides by Kathryn McKinley 1 Managed runtimes Advantages? Disadvantages? 2 Managed runtimes Advantages? Reliability Security Portability Performance?

More information

Compiling Techniques

Compiling Techniques Lecture 10: Introduction to 10 November 2015 Coursework: Block and Procedure Table of contents Introduction 1 Introduction Overview Java Virtual Machine Frames and Function Call 2 JVM Types and Mnemonics

More information

New Compiler Optimizations in the Java HotSpot Virtual Machine

New Compiler Optimizations in the Java HotSpot Virtual Machine New Compiler Optimizations in the Java HotSpot Virtual Machine Steve Dever Steve Goldman Kenneth Russell Sun Microsystems, Inc. TS-3412 Copyright 2006, Sun Microsystems Inc., All rights reserved. 2006

More information

Managed runtimes & garbage collection

Managed runtimes & garbage collection Managed runtimes Advantages? Managed runtimes & garbage collection CSE 631 Some slides by Kathryn McKinley Disadvantages? 1 2 Managed runtimes Portability (& performance) Advantages? Reliability Security

More information

Faster Programs with Guile 3

Faster Programs with Guile 3 Faster Programs with Guile 3 FOSDEM 2019, Brussels Andy Wingo wingo@igalia.com wingolog.org @andywingo this What? talk Your programs are faster with Guile 3! How? The path to Guile 3 Where? The road onward

More information

Running R Faster. Tomas Kalibera

Running R Faster. Tomas Kalibera Running R Faster Tomas Kalibera My background: computer scientist, R user. My FastR experience: Implementing a new R VM in Java. New algorithms, optimizations help Frame representation, variable lookup

More information

55:132/22C:160, HPCA Spring 2011

55:132/22C:160, HPCA Spring 2011 55:132/22C:160, HPCA Spring 2011 Second Lecture Slide Set Instruction Set Architecture Instruction Set Architecture ISA, the boundary between software and hardware Specifies the logical machine that is

More information

Field Analysis. Last time Exploit encapsulation to improve memory system performance

Field Analysis. Last time Exploit encapsulation to improve memory system performance Field Analysis Last time Exploit encapsulation to improve memory system performance This time Exploit encapsulation to simplify analysis Two uses of field analysis Escape analysis Object inlining April

More information

A Trace-based Java JIT Compiler Retrofitted from a Method-based Compiler

A Trace-based Java JIT Compiler Retrofitted from a Method-based Compiler A Trace-based Java JIT Compiler Retrofitted from a Method-based Compiler Hiroshi Inoue, Hiroshige Hayashizaki, Peng Wu and Toshio Nakatani IBM Research Tokyo IBM Research T.J. Watson Research Center April

More information

Chapter 3:: Names, Scopes, and Bindings

Chapter 3:: Names, Scopes, and Bindings Chapter 3:: Names, Scopes, and Bindings Programming Language Pragmatics Michael L. Scott Some more things about NFAs/DFAs We said that a regular expression can be: A character (base case) A concatenation

More information

FTL WebKit s LLVM based JIT

FTL WebKit s LLVM based JIT FTL WebKit s LLVM based JIT Andrew Trick, Apple Juergen Ributzka, Apple LLVM Developers Meeting 2014 San Jose, CA WebKit JS Execution Tiers OSR Entry LLInt Baseline JIT DFG FTL Interpret bytecode Profiling

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

Heap, Variables, References, and Garbage. CS152. Chris Pollett. Oct. 13, 2008.

Heap, Variables, References, and Garbage. CS152. Chris Pollett. Oct. 13, 2008. Heap, Variables, References, and Garbage. CS152. Chris Pollett. Oct. 13, 2008. Outline. Dynamic Allocation. Variables and Constants. Aliases and Problems. Garbage. Introduction. On Wednesday, we were talking

More information

Tizen/Artik IoT Lecture Chapter 3. JerryScript Parser & VM

Tizen/Artik IoT Lecture Chapter 3. JerryScript Parser & VM 1 Tizen/Artik IoT Lecture Chapter 3. JerryScript Parser & VM Sungkyunkwan University Contents JerryScript Execution Flow JerryScript Parser Execution Flow Lexing Parsing Compact Bytecode (CBC) JerryScript

More information

Exupery A Native Code Compiler for Squeak

Exupery A Native Code Compiler for Squeak Exupery A Native Code Compiler for Squeak Bryce Kampjes Contents 1 Introduction 2 2 The Problem 2 2.1 Smalltalk and Squeak................................... 2 2.2 Modern Hardware....................................

More information

Benchmarking/Profiling (In)sanity

Benchmarking/Profiling (In)sanity Benchmarking/Profiling (In)sanity It all started when I stumbled upon AppendableWriter in guava which is nothing more than an adapter class that adapts an Appendable to a Writer. When looking over the

More information

Dynamic Languages Strike Back. Steve Yegge Stanford EE Dept Computer Systems Colloquium May 7, 2008

Dynamic Languages Strike Back. Steve Yegge Stanford EE Dept Computer Systems Colloquium May 7, 2008 Dynamic Languages Strike Back Steve Yegge Stanford EE Dept Computer Systems Colloquium May 7, 2008 What is this talk about? Popular opinion of dynamic languages: Unfixably slow Not possible to create IDE-quality

More information

G Programming Languages - Fall 2012

G Programming Languages - Fall 2012 G22.2110-003 Programming Languages - Fall 2012 Lecture 2 Thomas Wies New York University Review Last week Programming Languages Overview Syntax and Semantics Grammars and Regular Expressions High-level

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

Type Feedback for Bytecode Interpreters

Type Feedback for Bytecode Interpreters Type Feedback for Bytecode Interpreters Michael Haupt, Robert Hirschfeld, Marcus Denker To cite this version: Michael Haupt, Robert Hirschfeld, Marcus Denker. Type Feedback for Bytecode Interpreters. ICOOOLPS

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

WELCOME TO PERL = Tuesday, June 4, 13

WELCOME TO PERL = Tuesday, June 4, 13 WELCOME TO PERL11 5 + 6 = 11 http://perl11.org/ Stavanger 2012 Moose + p5-mop Workshop Text Preikestolen Will Braswell Ingy döt net Austin 2012 PERL 11 5 + 6 = 11 perl11.org Will Braswell, Ingy döt net,

More information

ART JIT in Android N. Xueliang ZHONG Linaro ART Team

ART JIT in Android N. Xueliang ZHONG Linaro ART Team ART JIT in Android N Xueliang ZHONG Linaro ART Team linaro-art@linaro.org 1 Outline Android Runtime (ART) and the new challenges ART Implementation in Android N Tooling Performance Data & Findings Q &

More information

Computer Components. Software{ User Programs. Operating System. Hardware

Computer Components. Software{ User Programs. Operating System. Hardware Computer Components Software{ User Programs Operating System Hardware What are Programs? Programs provide instructions for computers Similar to giving directions to a person who is trying to get from point

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

Traditional Smalltalk Playing Well With Others Performance Etoile. Pragmatic Smalltalk. David Chisnall. August 25, 2011

Traditional Smalltalk Playing Well With Others Performance Etoile. Pragmatic Smalltalk. David Chisnall. August 25, 2011 Étoilé Pragmatic Smalltalk David Chisnall August 25, 2011 Smalltalk is Awesome! Pure object-oriented system Clean, simple syntax Automatic persistence and many other great features ...but no one cares

More information

Java Performance: The Definitive Guide

Java Performance: The Definitive Guide Java Performance: The Definitive Guide Scott Oaks Beijing Cambridge Farnham Kbln Sebastopol Tokyo O'REILLY Table of Contents Preface ix 1. Introduction 1 A Brief Outline 2 Platforms and Conventions 2 JVM

More information

JSR 292 Cookbook: Fresh Recipes with New Ingredients

JSR 292 Cookbook: Fresh Recipes with New Ingredients JSR 292 Cookbook: Fresh Recipes with New Ingredients John Rose Christian Thalinger Sun Microsystems Overview Got a language cooking on the JVM? JSR 292, a set of major changes to the JVM architecture,

More information

MoarVM. A metamodel-focused runtime for NQP and Rakudo. Jonathan Worthington

MoarVM. A metamodel-focused runtime for NQP and Rakudo. Jonathan Worthington MoarVM A metamodel-focused runtime for NQP and Rakudo Jonathan Worthington What does a VM typically do? Execute instructions (possibly by interpreting, possibly by JIT compilation, often a combination)

More information

Unboxing Sum Types. Johan Tibell - FP-Syd

Unboxing Sum Types. Johan Tibell - FP-Syd Unboxing Sum Types Johan Tibell - FP-Syd 2017-05-24 Work in (slow) progress Ömer Sinan Ağacan Ryan Newton José Manuel Calderón Trilla I NULL Reason 1: Job security Program received signal SIGSEGV, Segmentation

More information

Comp 311 Principles of Programming Languages Lecture 21 Semantics of OO Languages. Corky Cartwright Mathias Ricken October 20, 2010

Comp 311 Principles of Programming Languages Lecture 21 Semantics of OO Languages. Corky Cartwright Mathias Ricken October 20, 2010 Comp 311 Principles of Programming Languages Lecture 21 Semantics of OO Languages Corky Cartwright Mathias Ricken October 20, 2010 Overview I In OO languages, data values (except for designated non-oo

More information

Advanced Computer Architecture

Advanced Computer Architecture ECE 563 Advanced Computer Architecture Fall 2007 Lecture 14: Virtual Machines 563 L14.1 Fall 2009 Outline Types of Virtual Machine User-level (or Process VMs) System-level Techniques for implementing all

More information

Bugloo: A Source Level Debugger for Scheme Programs Compiled into JVM Bytecode

Bugloo: A Source Level Debugger for Scheme Programs Compiled into JVM Bytecode Bugloo: A Source Level Debugger for Scheme Programs Compiled into JVM Bytecode Damien Ciabrini Manuel Serrano firstname.lastname@sophia.inria.fr INRIA Sophia Antipolis 2004 route des Lucioles - BP 93 F-06902

More information

6.172 Performance Engineering of Software Systems Spring Lecture 9. P after. Figure 1: A diagram of the stack (Image by MIT OpenCourseWare.

6.172 Performance Engineering of Software Systems Spring Lecture 9. P after. Figure 1: A diagram of the stack (Image by MIT OpenCourseWare. 6.172 Performance Engineering of Software Systems Spring 2009 Lecture 9 MIT OpenCourseWare Dynamic Storage Allocation Stack allocation: LIFO (last-in-first-out) Array and pointer A used unused P before

More information

Python Implementation Strategies. Jeremy Hylton Python / Google

Python Implementation Strategies. Jeremy Hylton Python / Google Python Implementation Strategies Jeremy Hylton Python / Google Python language basics High-level language Untyped but safe First-class functions, classes, objects, &c. Garbage collected Simple module system

More information

23 rd ESUG Conference Brescia, Italy July 13-17, Dino2

23 rd ESUG Conference Brescia, Italy July 13-17, Dino2 23 rd ESUG Conference Brescia, Italy July 13-17, 2015 Dino2 The Evolution of the VA Smalltalk Virtual Machine John O Keefe Chief Technical Officer Instantiations, Inc. Why am I giving the presentation

More information

Optimising large dynamic code bases.

Optimising large dynamic code bases. Optimising large dynamic code bases. Who am I? Duncan MacGregor Lead Software Engineer on the Magik on Java project at General Electric in Cambridge Aardvark179 on twitter 2 What is Magik? Dynamic, weakly

More information

Ahead of Time (AOT) Compilation

Ahead of Time (AOT) Compilation Ahead of Time (AOT) Compilation Vaibhav Choudhary (@vaibhav_c) Java Platforms Team https://blogs.oracle.com/vaibhav Copyright 2018, Oracle and/or its affiliates. All rights reserved. Safe Harbor Statement

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

Non-numeric types, boolean types, arithmetic. operators. Comp Sci 1570 Introduction to C++ Non-numeric types. const. Reserved words.

Non-numeric types, boolean types, arithmetic. operators. Comp Sci 1570 Introduction to C++ Non-numeric types. const. Reserved words. , ean, arithmetic s s on acters Comp Sci 1570 Introduction to C++ Outline s s on acters 1 2 3 4 s s on acters Outline s s on acters 1 2 3 4 s s on acters ASCII s s on acters ASCII s s on acters Type: acter

More information

CS 3330 Final Exam Spring 2016 Computing ID:

CS 3330 Final Exam Spring 2016 Computing ID: S 3330 Spring 2016 Final xam Variant O page 1 of 10 mail I: S 3330 Final xam Spring 2016 Name: omputing I: Letters go in the boxes unless otherwise specified (e.g., for 8 write not 8 ). Write Letters clearly:

More information

EITF20: Computer Architecture Part2.1.1: Instruction Set Architecture

EITF20: Computer Architecture Part2.1.1: Instruction Set Architecture EITF20: Computer Architecture Part2.1.1: Instruction Set Architecture Liang Liu liang.liu@eit.lth.se 1 Outline Reiteration Instruction Set Principles The Role of Compilers MIPS 2 Main Content Computer

More information

PICOBIT: A Compact Scheme System for Microcontrollers

PICOBIT: A Compact Scheme System for Microcontrollers PICOBIT: A Compact Scheme System for Microcontrollers Vincent St-Amour Université de Montréal (now at Northeastern University) Marc Feeley Université de Montréal 21st Symposium on the Implementation and

More information

Compilers and Code Optimization EDOARDO FUSELLA

Compilers and Code Optimization EDOARDO FUSELLA Compilers and Code Optimization EDOARDO FUSELLA The course covers Compiler architecture Pre-requisite Front-end Strong programming background in C, C++ Back-end LLVM Code optimization A case study: nu+

More information

Faster Haskell. Neil Mitchell

Faster Haskell. Neil Mitchell Faster Haskell Neil Mitchell www.cs.york.ac.uk/~ndm The Goal Make Haskell faster Reduce the runtime But keep high-level declarative style Full automatic - no special functions Different from foldr/build,

More information

Know Your Engines How to Make Your JavaScript Fast

Know Your Engines How to Make Your JavaScript Fast Know Your Engines How to Make Your JavaScript Fast Dave Mandelin 8 November 2011 O Reilly Velocity Europe JavaScript is getting really fast and programs are getting crazy Bullet physics engine (ammo.js)

More information

Structure of Programming Languages Lecture 10

Structure of Programming Languages Lecture 10 Structure of Programming Languages Lecture 10 CS 6636 4536 Spring 2017 CS 6636 4536 Lecture 10: Classes... 1/23 Spring 2017 1 / 23 Outline 1 1. Types Type Coercion and Conversion Type Classes, Generics,

More information

CSC C69: OPERATING SYSTEMS

CSC C69: OPERATING SYSTEMS CSC C69: OPERATING SYSTEMS Tutorial 1 Thursday, Jan 17, 2013 TA: Ioan Stefanovici (ioan@cs.toronto.edu) HOW DO YOU SUCCEED IN THIS COURSE? Show up to lectures & tutorials (way too much material) Work on

More information