Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Parallella: The Most Energy Efficient Supercomputer on the Planet

Parallella: The Most Energy Efficient Supercomputer on the Planet

Presented at Madison+ Ruby on Saturday, August 22, 2015.
Video: http://rayhightower.com/blog/2015/08/22/madison-ruby-and-parallella/

Supercomputing should be available for everyone who wants it. With that mission in mind, a team of engineers created Parallella, an 18-core supercomputer that’s a little bigger than a credit card. Parallella is open source hardware; the circuit diagrams are on GitHub and the machine runs Linux. Icing on the cake: Parallella is the most energy efficient computer on the planet, and you can buy one for a hundred bucks.

Why does parallel computing matter? How can developers use parallel computing to deliver better results for clients? Let’s explore these questions together.

Curious about the Internet of Things? Check out http://WindyCityThings.com.

2769d4f1f9abeb4dd2438ff636a9e4dc?s=128

Ray Hightower

August 22, 2015
Tweet

Transcript

  1. Madison+ Ruby Madison, WI, USA August 21-22, 2015 The Most

    Energy Efficient Supercomputer on the Planet
  2. Moore’s Law: 2x every 18 months

  3. Moore’s Law: 2x every 18 months Moore’s Law 1993 -

    2013 http://www.washingtonpost.com/blogs/innovations/wp/2015/04/14/10-images-that-explain-the- incredible-power-of-moores-law/ https://www.parallella.org/board/
  4. None
  5. RayHightower.com

  6. RJ-45 Power μUSB μHDMI μSD

  7. RISC ARM 18 cores: 2 ARM + 16 RISC

  8. None
  9. None
  10. None
  11. Watts => Dollars.

  12. None
  13. 17.8 million watts $17.8 million per year

  14. 5 watts for Parallella?

  15. None
  16. http://rayhightower.com/blog/2014/09/09/solar-powered-parallella/

  17. http://rayhightower.com/blog/2014/09/09/solar-powered-parallella/

  18. http://rayhightower.com/blog/2014/09/09/solar-powered-parallella/ 5 volts 1 amp 5 watts Solar!

  19. If one ox could not do the job they did

    not try to grow a bigger ox, but used two oxen. When we need greater computer power, the answer is not to get a bigger computer, but to build systems of computers and operate them in parallel. -Grace Hopper
  20. Reduced Instruction Set Computer RISC

  21. ARM A9

  22. RISC ARM 18 cores: 2 ARM + 16 RISC

  23. None
  24. Hello Epiphany

  25. host.c epiphany.c

  26. None
  27. Find all primes up to 16,000,000. Serial on Parallella.

  28. 1 #include <stdio.h> 2 #include <stdlib.h> 3 #include <math.h> 4

    #include <time.h> 5 6 #define DEFAULT_MAX_TESTS 16000000 7 8 inline int isprime(unsigned long number) 9 { 10 unsigned long i; 11 unsigned long s = sqrt(number); 12 for(i=3;i<=s;i+=2) 13 { 14 if(number % i == 0) 15 return 0; 16 } 17 return 1; 18 } /* Copyright (c) Adapteva, contributed by M. Thompson with modifications by T. Malthouse. */
  29. 8 inline int isprime(unsigned long number) 9 { 10 unsigned

    long i; 11 unsigned long s = sqrt(number); 12 for(i=3;i<=s;i+=2) 13 { 14 if(number % i == 0) 15 return 0; 16 } 17 return 1; 18 } /* Copyright (c) Adapteva, contributed by M. Thompson with modifications by T. Malthouse. */
  30. None
  31. Find all primes up to 16,000,000. Serial on Mac OS

    X.
  32. Same serial code, written in C. Build it on OS

    X.
  33. None
  34. Find all primes up to 16,000,000. Parallel on Parallella.

  35. 27 #include <e-hal.h> 28 29 // Default max number of

    prime tests per core 30 // Used if a limit it not provided in argv[1] 31 #define DEFAULT_MAX_TESTS 500000 32 33 int main(int argc, char *argv[]) 34 { 35 unsigned row, col, coreid, i, j; 36 e_platform_t platform; 37 e_epiphany_t dev; 38 /* Copyright (c) Adapteva, contributed by M. Thompson with modifications by T. Malthouse.*/
  36. None
  37. Serial/Parallella: Serial/Mac: Parallel/Parallella: 237.1 sec 14.4 sec 18.6 sec Summary:

    Finding Primes 18 cores (using one). Up to 1GHz. $150.00 4 cores (using one). 2.7GHz. $2,000.00 18 cores. Up to 1GHz. $150.00
  38. Mandelbrot Set

  39. None
  40. Why?

  41. Finite Element Analysis http://www.ce.ncsu.edu/news/article/21550/making-bridges-more-robust-to-earthquakes/

  42. break? wear out? work? Finite Element Analysis Will it {

  43. Free Body Diagram F F applied friction F gravity F

    normal
  44. Finite Element Analysis http://www.ce.ncsu.edu/news/article/21550/making-bridges-more-robust-to-earthquakes/

  45. https://www.e-education.psu.edu/worldofweather/node/2029 Grid spacing influences accuracy. Weather Prediction

  46. Parallella vs GPU

  47. 384 cores MacBook Pro Video

  48. Specialized vs. General

  49. None
  50. Thanks! RayHightower.com