An Approach to Buffer Management in Java HPC Messaging

1
An Approach to Buffer Management in Java HPC
Messaging

• Mark Baker, Bryan Carpenter, and Aamir Shafi
• Distributed Systems Group
• http//dsg.port.ac.uk

2
Presentation outline

• Introduction,
• The Buffering Layer in MPJ Express,
• Performance Evaluation,
• A Use Case from Computational Cosmology,
• Conclusions.

3
Introduction

• Traditional language based approach to high
  level parallel programming
• HPF, UPC, Co-Array Fortran etc.
• Recently practical parallel programming has
  focused on commodity languages supplemented by
  libraries like MPI
• C, C, Fortran ,
• Cost-effective.
• Therefore, practical approach to raise the
  level of parallel programming
• Use an advanced commodity language.

4
Introduction

• There are several arguments for using Java for
  scientific computing, including
• Portability,
• Compile-time and runtime safety,
• Built-in multi-threading,
• Rapid development,
• Built-in libraries,
• Performance via JIT-compilers.
• MPI was finalized in June 1994 as a standard
  message passing API for technical parallel
  computing
• Java Grande Message Passing Workgroup defined
  Java bindings in 98.

5
Introduction

• MPJ Express is a high quality implementation of a
  Java messaging system, based on Java bindings
• Released September 2005,
• Thread-safe communication devices for TCP and
  Myrinet,
• Implements derived datatypes, communicators,
  and virtual topologies,
• Runtime system for portable bootstrapping,
• Web http//dsg.port.ac.uk/projects/mpj

6
Introduction Java NIO

• Java New I/O
• Non-blocking communication,
• Introduces direct and indirect ByteBuffers
• Direct byte buffer reside in native OS memory,
  unlike normal Java objects,
• The creation of direct byte buffer is costly but
  provide faster I/O.

7
Introduction The Buffering Layer in MPJ Express

• MPJ Express requires a buffering layer
• To use Java NIO
• It is possible to read and write data to and from
  byte buffers onto the wire.
• To use proprietary networks like Myrinet
  efficiently
• Direct byte buffers have memory pointers that can
  be used for Direct Memory Access (DMA) transfers,
  
• Avoid JNI overheads
• No data-copying between JVM and native OS memory.
• It incurs an additional copying overhead though.

8
Presentation outline

• Introduction,
• The Buffering Layer in MPJ Express,
• Performance Evaluation,
• A Use Case from Computational Cosmology,
• Conclusions.

9
Buffering Layer

• An extendable buffering layer (mpjbuf)
• Supports higher and lower levels of MPJ Express,
• Various implementations based on actual storage
  medium
• Direct or indirect ByteBuffers,
• Arrays,
• Native C memory.
• An mpjbuf buffer object consists of
• A static buffer to store primitive datatypes,
• A dynamic buffer to store serialized Java
  objects.
• Creating ByteBuffers on the fly is costly
• Memory management is based on Knuths buddy
  algorithm,
• Two implementations
• Buddy1 - store offset and smaller memory
  footprint,
• Buddy2 - store objects and bigger memory
  footprint.

10
Allocation Time Comparison
11
Faster I/O with direct ByteBuffers
12
Presentation outline

• Introduction,
• The Buffering Layer in MPJ Express,
• Performance Evaluation
• MPJ Express compared to MPICH and mpiJava on
  Fast Ethernet and Myrinet,
• A Use Case from Computational Cosmology,
• Conclusions.

13
Transfer Time on Fast Ethernet
14
Throughput on Fast Ethernet
15
Transfer Time on Myrinet
16
Throughput on Myrinet
17
Presentation outline

• Introduction,
• The Buffering Layer in MPJ Express,
• Performance Evaluation,
• A Use Case from Computational Cosmology,
• Conclusions.

18
Gadget-2

• An experiment to understand Javas performance.
• Gadget-2 is a massively parallel structure
  formation cosmological simulations that is
  written in C
• Simulates the evolution of large systems under
  the influence of gravitational and hydrodynamic
  forces,
• A version was used in Millenium Simulation that
  evolves 1010 dark matter particles from the
  early Universe to the current day
• Executed on 512 nodes using a Terabyte of
  distributed memory,
• Used 350,000 CPU hours over 28 days of elapsed
  time.
• Uses Barnes-hut tree algorithm for calculating
  gravitational forces,
• Domain decomposition based on Peano-Hilbert space
  filling curve.
• We produced a Java version of Gadget-2 using MPJ
  Express for messaging.
• Benchmarking comparison for Colliding Galaxies.

19
Execution Time on Fast Ethernet
20
Execution Time on Myrinet
21
Tree walk time comparison
22
Presentation outline

• Introduction,
• The Buffering Layer in MPJ Express,
• Performance Evaluation,
• A Use Case from Computational Cosmology,
• Conclusions.

23
Summary

• MPJ Express is becoming a production-quality Java
  messaging system
• Communication devices for TCP and Myrinet.
• MPJ Express relies on an intermediate buffering
  layer
• Avoid JNI overheads,
• Possible to use direct ByteBuffers,
• Memory management using Knuths buddy algorithm.
• Java version of Gadget-2
• A use-case from computational cosmology.

24
Conclusions

• We have shown that Java has the potential to be a
  good HPC language.
• The additional overhead of copying can be
  avoided by extending the MPJ API
• Support for sending from and receiving to
  ByteBuffers.
• Future Work
• Exploit thread-safety of MPJ Express by using
  OpenMP parallelism,
• Next release with Myrinet device in the third
  quarter of 2006.

25
Questions
?