AlphaDev uncovered new sorting algorithms that led to improvements in the LLVM libc++ sorting library that were up to 70% faster for shorter sequences and about 1.7% faster for sequences exceeding 250,000 elements.

You are viewing a single thread.
View all comments View context
2 points

I wonder if their paper has a plot of the speedups against number of elements. Did they just stop measuring at 250k? What was the shape of the curve?

permalink
report
parent
reply
1 point

I didn’t bother reading, not so interested in AI stuff. But since they highlight these results, it likely does not get better for higher numbers.

permalink
report
parent
reply
1 point

I’ll bet it just ends up being the limitations of memory bandwidth to stuff things into registers for the optimized algorithm. Or, something like Mojo’s autotuning finds the best way to partition the work for the hardware.

permalink
report
parent
reply

Programming

!programming@beehaw.org

Create post

All things programming and coding related. Subcommunity of Technology.


This community’s icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.

Community stats

  • 73

    Monthly active users

  • 320

    Posts

  • 3.3K

    Comments