The Fifth Elephant 2015

A conference on data, machine learning, and distributed and parallel computing

Hardware Accelerated Big Data Processing

Submitted by Reetinder Sidhu (@sidhu1f) on Monday, 15 June 2015

videocam_off

Technical level

Intermediate

Section

Crisp Talk

Status

Confirmed & Scheduled

View proposal in schedule

Vote on this proposal

Login to vote

Total votes:  +6

Objective

Expect attendees to obtain:

  • Clear understanding of FPGAs (Field Programmable Gate Arrays), and their pros/cons over software on microprocessors for big data
  • Better understanding of suitability of FPGAs for attendees’ own big data applications
  • Overview of state of the art in FPGA based big data processing

Description

Use of FPGAs (Field Programmable Gate Arrays) for big data processing has recently started rising:

  • Intel Buying [FPGA] Chipmaker Altera For $16.7 Billion (Forbes, 1-6-15)
  • Microsoft Supercharges Bing Search with [FPGA] Programmable Chips (Wired, 6-16-14)

Whats the big deal? Proposed talk aims to elucidate. Outline:

  • Quick, intuitive, technical introduction to FPGAs and their key benefits over software for big data
  • Computation structures that are useful for big data processing and can be efficiently implemented on FPGAs
  • Pros/cons, challenges/opportunities in FPGA use for big data
  • Concrete use-case of FPGA accelerated XML data processing using novel tree automata based compact implementation that is multiple times faster than a Xeon processor

Speaker bio

Reetinder Sidhu currently leads project LEAP (Logic Engines for Accelerated Processing) in Tech Mahindra’s Intrapreneurship Program. He has a PhD (EE, FPGA area) from University of Southern California and an MS (computer engg.) from Indian Institute of Science.

He is an active FOSS user and enthusiast since the days Linux came on floppies and installing gcc involved compiling the compiler…

Comments

Login with Twitter or Google to leave a comment