Performance of graph and biological analytics on the ibm cell broadband engine processor
This presentation is the property of its rightful owner.
Sponsored Links
1 / 3

Performance of Graph and Biological Analytics on the IBM Cell Broadband Engine Processor PowerPoint PPT Presentation


  • 81 Views
  • Uploaded on
  • Presentation posted in: General

Performance of Graph and Biological Analytics on the IBM Cell Broadband Engine Processor. David A. Bader Tan M. Tran Georgia Institute of Technology. Biological Analytic: SSCA #1. Background and Intent.

Download Presentation

Performance of Graph and Biological Analytics on the IBM Cell Broadband Engine Processor

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Performance of Graph and Biological Analytics on the IBM Cell Broadband Engine Processor

David A. Bader

Tan M. Tran

Georgia Institute of Technology


Biological Analytic: SSCA #1

Background and Intent

  • To develop analytical schemes to identify similarities between sequences of symbols to assist computational biologists

  • Optimize for the IBM Cell Broadband Engine Processor

  • Find common genes and closely matches between sequences

  • Five kernels

  • Methods:

  • Local alignment: Water Smith dynamic programming (Kernel 1)

  • Searching for similarities (Kernels 2 and 3)

  • Global alignment (Kernel 4)

  • Multiple alignment: Center Star method (Kernel 5)

  • Each kernel operates on either the original sequences, the results of the previous kernel, or both

  • To be entirely integer and character based


Graph Analytic: SSCA #2

Background and Intent

  • To develop a scalable synthetic compact application that consists of four kernels requiring irregular access to a large, directed, weight multi-graph

  • Optimize for the IBM Cell Broadband Engine Processor

  • Untimed Scalable Data Generator generates the graph as tuples of vertex pairs and corresponding weights.

  • Methods:

  • Cache-friendly adjacency lists (Kernel 1)

  • Parallel scan to classify larger sets of graph (Kernel 2)

  • Parallel BFS (Kernel 3)

  • Dijkstra Single-Source Shortest Path and Betweenness Centrality algorithms(Kernel 4)

  • David A. Bader and KameshMadduri designed and implemented the first parallel Betweenness Centrality algorithm on symmetric multiprocessors.

  • To be entirely integer and character based


  • Login