Arm Community
Arm Community
  • Site
  • User
  • Site
  • Search
  • User
Arm Community blogs
Arm Community blogs
Embedded and Microcontrollers blog Lots of data but no supercomputer? then build your own with embedded boards
  • Blogs
  • Mentions
  • Sub-Groups
  • Tags
  • Jump...
  • Cancel
More blogs in Arm Community blogs
  • AI blog

  • Announcements

  • Architectures and Processors blog

  • Automotive blog

  • Embedded and Microcontrollers blog

  • Internet of Things (IoT) blog

  • Laptops and Desktops blog

  • Mobile, Graphics, and Gaming blog

  • Operating Systems blog

  • Servers and Cloud Computing blog

  • SoC Design and Simulation blog

  • Tools, Software and IDEs blog

Tags
  • embedded-board
  • i.mx_6
  • Embedded
  • pci_express
  • supercomputing
  • nvidia
  • wandboard
  • freescale
Actions
  • RSS
  • More
  • Cancel
Related blog posts
Related forum threads

Lots of data but no supercomputer? then build your own with embedded boards

David Blaza
David Blaza
May 28, 2015

One of the fun parts of our Exploring the world of ARM based Embedded Computing Boards (ECB) project has been hearing about all the creative ways that embedded computing boards are being used in non traditional ways.  A great example of this is in high volume throughput computing (HVC) which is common in scientific research projects that throw off terabytes of data.  In the past researchers needed access to a supercomputer and a lot of technical support to run their experiments but this paper (attached) from the University of the Witwatersrand in South Africa.  Mitchell Cox and Bruce Mellado wrote a paper on how they might process the data for a radio telescope project called the square kilometer array (SKA, see pic below) which will come online in 2022.

square-kilometre-array-2024-large.jpg

Here's where the numbers get mind boggling,  the SKA will generate data rates of 40 Terabits/second in 2022 so how will it be processed?

Mitchell and Bruce looked at ARM SoCs that were readily available on development kits and posited that using PCI Express they could develop a high throughput system.  Here is their block diagram:

HVC blck.png

Whats even more interesting and relevant to our Embedded Computing Board (ECB) Resource Guide project is they prototyped this concept using the Wandboard which uses Freescale i.MX6 processors based on the ARM Cortex-A9 core.  Here is there setup:

wandboard.jpg

There are single, dual and quad core Wandboards available starting at just $79,  you can find them here.

In future iterations the authors of the paper looked at other ARM SOCs and it looks like the NVIDIA Tegra K1 would give them even greater throughput.

Just goes to show what you can do with a few ARM based dev boards and a passion to problem solve.

High volune omputing paper.pdf
Anonymous
Embedded and Microcontrollers blog
  • Formally verifying a floating-point division routine with Gappa – part 2

    Simon Tatham
    Simon Tatham
    A method of testing whether a numerical error analysis using Gappa really matches the code it is intended to describe.
    • September 4, 2025
  • Formally verifying a floating-point division routine with Gappa – part 1

    Simon Tatham
    Simon Tatham
    Learn the basics of using Gappa for numerical error analysis, using floating-point division in Arm machine code as a case study.
    • September 4, 2025
  • Building Solutions on Arm: A recap of IEEE Arm Community Technothon project presentation

    Fidel Makatia
    Fidel Makatia
    Read Fidel's account from the Arm Community Technothon!
    • December 4, 2024