1. Multicore Processing Wu, Lieh-Hao VMI Class 2010 Computer Science

2. What’s Multicore? Multiple cores in a single chip Improving performance by adding core Became the main stream in recent years - Examples - Core 2 dual, Core 2 Quad, Core-i3/5/7  Intel - Athlon II X2, Phenom II X4, Opteron AMD - Cell Broad Engine  IBM

3. Why Multicore? The difficulties of single core processor’s development - Overheat - Energy consumption - Electron leakage - Example - Intel abandoned the project of 4GHz processor in fall 2004 Multicore processor resolve these problem and has better performance

4. Research Introduction Purpose: - To see the performance difference between single core and multicore processors How: - Use the PS3 as the host machine - Use the CPU of PS3 to execute a series of matrix multiplication - Execute with single core - Execute with multicore - programming tools are needed for handling cores - Record the time and analysis the performance

5. Play Station 3 Physical Components CPU: Cell Broad Engine Memory: 256MB Storage: 80GB Software Yellow Dog Linux Cell SDK

6. Cell Broad Engine Processor Developed by Sony, Toshiba, and IBM jointly. Multicore structure - Power Processing Element x 1 (PPE) - Like a traditional processor - It has its own L1, L2 cache - Synergistic Processing Element x 8 (SPE) - Can be used synchronously - It has 256KB local storage

7. Matrix Multiplication Simple but time consuming Some assumptions are made for research purpose - Dimension is set to N2 - Data type is set to double - Only even numbers are applied

9. Mapping a tree structure as a memory hierarchy

10. Basic idea - Consist of three functions - task<inner>: distribute - task<leaf>: compute - task<ext>: connect

11. Programming in Sequoia To programming in Sequoia, four files are required to run the matrix multiplication. - “Makefile”  for compiling - “matrixmult.sq” Sequoia program - “mapping_ps3.xml”  for mapping - “main.cc”  for starting During the process - Good documentation - Good adaptability for different purposes - Details need to be handled by programmers

12. Cellgen An implicit multicore programming model C/C++ based programming tool Like OpenMP style - OpenMP API Basic idea - Starts after “#pragma cell” - Parameters - public: shared by SPEs - private: each SPE has a copy Scott Schneider Ph.D. Candidate Virginia Tech

13. Programming in Cellgen There are files needed to run matrix multiplication - Two “Makefile”  for compiling - One “matrixmult.cellgen”  Cellgen code - One “double16b_t.h”  for padding column data - suggested by the author to improve performance During the process - Understandable - C/C++ based; easy to catch up. - Lack of documentation - Only “Readme” file is available.

15. Result in Graph (1) The following is the line chart generated from the data of the table. Memory size limit PPE Only Cellgen Sequoia

16. Result in Graph (2)

17. Result Analysis Performance of Cellgen - Unexpected overhead or runtime error may occur and throw the performance back. Performance of Sequoia - According to the stable record, it is about 8 times faster than the execution time of PPE. - Although the memory size is 256MB, performance starts dropping down after 2048 2. - The performance becomes the same with PPE after reaching 4096 2 . - Probably the most of the data are swapped with disk, which is out of the Sequoia’s ability.

18. Conclusion Multicore processor has better performance than single core processor, which is about 8 times faster if the memory space is sufficient. Multicore may also have some unexpected overhead or error, which may draw back the performance like what I have in Cellgen. Multicore processing is art. - In the paper “ Programming Multiprocessors With Explicitly Managed Memory Hierarchies,” Cellgen has better performance than Sequoia does. However, Cellgen doesn’t do well like Sequoia in this research.

19. Reference http://elhabib.at/files/2008/07/yellowdog-vorlage_p1.jpg http://scawley.files.wordpress.com/2008/03/sony_playstation_3_60gb_game_console__brand_new.jpg http://www.5ilight.com/dianzi/upimg/20070222/11H154H0L05A08.jpg http://moss.csc.ncsu.edu/~mueller/cluster/ps3/cell.jpg http://upload.wikimedia.org/wikipedia/en/thumb/e/eb/Matrix_multiplication_diagram_2.svg/313px-Matrix_multiplication_diagram_2.svg.png http://www.stanford.edu/group/sequoia/cgi-bin/node/182 http://www.stanford.edu/group/sequoia/cgi-bin/ http://openmp.org/wp/about-openmp/ http://people.cs.vt.edu/~scschnei/pictures/scott.jpg http://openmp.org/wp/openmp_336x120.gif http://www.ibm.com/developerworks/power/library/pa-cellperf/ Ramanathan, R. M. “Intel® Multi-Core Processors: Making the Move to Quad-Core and Beyond.” Intel Multi-CoreProcessors. pp.3, 15 November 2008 http://www.intel.com/technology/architecture/downloads/quad-core-06.pdf . Sutter, Hurb. “The Free Lunch Is Over: A Fundamental Turn Toward Concurrency in Software.” Dr. Dobb’s Journal, 30(3), March 2005 < http://lyle.smu.edu/~coyle/cse8313/handouts/Free.lunch.over.pdf>. http://www.stanford.edu/group/sequoia/cgi-bin/ http://github.com/scotts/cellgen/ http://en.wikipedia.org/wiki/Cell_(microprocessor) Martin Linklater. "Optimizing Cell Code". Game Developer Magazine, April 2007: pp. 15–18. "To increase fabrication yelds, Sony ships PlayStation 3 Cell processors with only seven working SPEs. And from those seven, one SPE will be used by the operating system for various tasks, This leaves six SPEs for game programmer to use.“ Scott Schneider, Jae-SeungYeom and Dimitrios S. Nikolopoulos. Programming Multiprocessors With Explicitly Managed Memory Hierarchies. IEEE Computer, December, 2009.

20. Questions?