Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision		 Previous revision
Next revisionBoth sides next revision
workshops:tutorial3 [2018/09/11 17:06] – sbsworkshops:tutorial3 [2018/09/11 17:16] – sbs
Line 1: Line 1:
-====== Tensor Programming with SaC ======+====== PACT'18 tutorial: Tensor Programming with SaC ======
  
 This tutorial gives a brief introduction to the high-level array language [[http://www.sac-home.org/|SaC]] This tutorial gives a brief introduction to the high-level array language [[http://www.sac-home.org/|SaC]]
Line 11: Line 11:
 network algorithms in less than two hours. network algorithms in less than two hours.
  
-===== Schedule =====+===== Schedule (Saturday, November 3rd 2018)  =====
 |14:00 - 16:00| Getting started with array programming in SaC.| |14:00 - 16:00| Getting started with array programming in SaC.|
 |16:00 - 16:30| Coffee break| |16:00 - 16:30| Coffee break|
Line 32: Line 32:
 accelerators, or loop optimisations which lead to code that performs on par accelerators, or loop optimisations which lead to code that performs on par
 with hand-optimised programs. The design of SaC builds on the [[https://www.researchgate.net/publication/308893116_A_Mathematics_of_Arrays|psi-calculus]] as underlying with hand-optimised programs. The design of SaC builds on the [[https://www.researchgate.net/publication/308893116_A_Mathematics_of_Arrays|psi-calculus]] as underlying
-array theory and aligns with a rich history of array languages such as [[https://www.dyalog.com/|APL]], [[https://en.wikipedia.org/wiki/SISAL|SISAL]] or [[http://fortranwiki.org/fortran/show/HomePage|Fortran90]] but provides+array theory and aligns with a rich history of array languages such as [[https://www.dyalog.com/|APL]], [[https://en.wikipedia.org/wiki/SISAL|SISAL]], [[http://fortranwiki.org/fortran/show/HomePage|Fortran90]] or  
 +[[https://mathworks.com/| Matlab]] but provides
 a more generic substrate, suitable for conveniently expressing high-dimensional a more generic substrate, suitable for conveniently expressing high-dimensional
 tensor operations which lie at the core of deep learning applications. tensor operations which lie at the core of deep learning applications.
Line 44: Line 45:
  
 [[http://www.macs.hw.ac.uk/~sbs/|Sven-Bodo Scholz]] and [[http://ashinkarov.github.io/|Artjoms  Šinkarovs]] are computer science researchers working in the area of high-performance compilers and functional languages.  Sven-Bodo Scholz is the original author of the SaC compiler and Artjoms  Šinkarovs is one of the main contributors. [[http://www.macs.hw.ac.uk/~sbs/|Sven-Bodo Scholz]] and [[http://ashinkarov.github.io/|Artjoms  Šinkarovs]] are computer science researchers working in the area of high-performance compilers and functional languages.  Sven-Bodo Scholz is the original author of the SaC compiler and Artjoms  Šinkarovs is one of the main contributors.
-