Jump to content

DistOS 2019F 2019-11-20

From Soma-notes

Revision as of 02:17, 20 March 2020 by Soma (talk | contribs) (Created page with "==Readings== Spanner & Tensorflow * [https://www.usenix.org/conference/osdi12/technical-sessions/presentation/corbett Corbett et al., "Spanner: Google’s Globally-Distribute...")

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Readings

Spanner & Tensorflow

Corbett et al., "Spanner: Google’s Globally-Distributed Database" (OSDI 2012)
Martin Abadi et al., "TensorFlow: A System for Large-Scale Machine Learning" (OSDI 2016)

Discussion Questions

Spanner

How does the functionality of Spanner compare to Google's past database efforts? How does it compare to the other systems we've discussed in class?
What are the key insight(s) that inform the design of Spanner?
Do you think these insights are general? Specifically, can they be used by other systems?

Tensorflow

What problem domain is Tensorflow designed for?
What is the programming model for tensorflow? How does it compare with that of MapReduce?
Why is tensorflow's model a good fit for its problem domain?
How does this model map onto a cluster of workstations?
How general is their approach?

Retrieved from "https://homeostasis.scs.carleton.ca/wiki/index.php?title=DistOS_2019F_2019-11-20&oldid=22554"