Brought to you by Rollbar - Detect, diagnose, defeat errors w/ pip install rollbar

Episode #113: Dedicated AI chips and running old Python faster at Intel

Published Sat, May 27, 2017, recorded Sat, May 20, 2017.


Where do you run your Python code? No, not Python 3, Python 2, PyPy or the other implementations. I'm thinking waaaaay lower than that. This week we are talking about the actual chips that execute our code.

We catch up with David Stewart and meet Suresh Srinivas, and Sergey Maidanov from Intel. We talk about how they are working at the silicon level to make even Python 2 run faster and touch on dedicated AI chips that go beyond just what is possible with GPU-computation.

Links from the show:

Intel Distribution for Python: software.intel.com/en-us/python-distribution
Intel Commits To Nervana Roadmap For AI: forbes.com
David Stewart: evangelists.intel.com/bio/David_Stewart
David on Twitter: @davest
Suresh Srinivas: linkedin.com
Sergey Maidanov: linkedin.com

Sponsored Links
Hired: hired.com/talkpythontome
Talk Python Courses: training.talkpython.fm

Want to go deeper? Check out my courses



Individuals: Support this podcast via Patreon or one-time via Square Cash or . Corporate sponsorship opportunities available here.