[mcint]

They trained (and report) two optimization strategies:

- inline-for-size

  We trained the inlining-for-size policy on a large internal software package containing 30k modules. The trained policy is generalizable when applied to compile other software and achieves a 3% ~ 7% size reduction.

- regalloc

  with 0.3% ~1.5% improvements in queries per second (QPS) on a set of internal large-scale datacenter applications

  Try it Yourself
  Check out the open-sourced end-to-end data collection and training solution on github and a demo that uses policy gradient to train an inlining-for-size policy.

  https://github.com/google/ml-compiler-opt

  https://github.com/google/ml-compiler-opt/blob/main/docs/demo/demo.md

With code, that's awesome—what I like to see.

[shostack]

For those not familiar with the space, how significant an impact is this, particularly at Google scale?