The reason is that MemorySSA has to be moveable

LGTM; thanks again!

Just a few style nits for you, and this LGTM. I assume rnk and serge-sans-paille are content, so I'm happy to check this in for you once these are addressed.

MSSA bits LGTM (to reiterate, as do the CFLAA bits). Leaving the rest of the patch to the other reviewers

LGTM; thanks!

Thanks for this!

Overall approach LGTM for this selective caching behavior.

This LGTM; feel free to submit after Aaron stamps this.

I think that addresses all of the concerns people have put forward; given rnk's comment about one more round of fixes, this LGTM. Will check this in for you shortly.

I think we should do one more round of fixes, we can commit that for you, and then move on to the next steps

LGTM; thanks again!

Thanks for this! Functionally, this looks good. My comments are mostly just simplicity/readability nitpicks.

Looks solid to me overall; just a few nits.

I think @george.burgess.iv is the right person because he appears a lot in git blame :)

Thanks for working on this!

Thanks again!

Thanks for this!

Thank you all for helping with this!

Thanks again!

Thanks for doing this! Just two nits for you :)

Deferring to Chandler's LGTM for the approach + first patch; changes since then LGTM.

LGTM with one more nit. Thanks again!

Thanks for this!

LGTM; thanks!

Thanks! Just a tiny nit

Thanks for this!

LGTM after one nit is addressed.

I would prefer to do the flag-flip separately though, in case it unearths some problematic usage.

Thanks for this!

Thanks for this!

Thanks for this!

Thanks!

LGTM; thanks again.

LGTM modulo a naming nit. If you're happy with the suggestion, feel free to submit. Thanks!

Thanks!

This LGTM at a high level; just a handful of nits for you, and I think this should be good to submit

Thanks for this!

Thanks for this! I like it when patches are small and split up like this one :)

MemorySSA changes LGTM, modulo one comment. Thanks!

Chrome OS developed a dependency (perf, not functional) on things in .text.hot coming before things in .text. Namely, they have code that maps the first N MB of Chrome's .text section to hugepages, under the assumption that the code near the beginning of the binary will be hotter than the code near the end of the binary.

(Also thanks for the reminder that I still need to update this with commentary for the purely-cmake-based approach. :) )

Thanks again! :)

Thanks for the feedback!

Addressed feedback

It may make sense to iterate, as you say, but that can/should be a different patch.

I notice that you're using LLVM_BUILD_INSTRUMENTED=IR, which corresponds to -fprofile-generate (IR-level profiling), instead of -fprofile-instr-generate (clang-level profiling). Did you play around with both and observe that IR-level profiling gave you better results?

Thanks for pointing that out!

And numbers for building ${large_project}, as promised:

Rebase, and only run this in the non-prelink full-LTO pipeline

You mentioned a 1.9% degradation with the current placement. Did you happen to try any other locations in the pipeline?

Ping :)

LGTM assuming the _run_benchmark changes are undone.

Thanks again!

Thank you!

Address feedback

Landed these a while back; closing.

Thanks again! :)

Thanks!

Woo! Thank you very much for the review (and for bearing with me in your repeated requests to minimize this patch :) ).

Address feedback

LGTM too.

Thanks for this! LGTM after erichkeane's comments are resolved.

Shrunk the diff as requested; the few pre-commit patches required to make this build are available as one patch in https://reviews.llvm.org/D52245 .

This looks good to me, but like said, I don't have sufficient context to stamp it with great confidence.

LGTM, modulo one nit. Thanks!

Thanks for this!

LGTM. Thanks for this!

Thanks!

I have zero context on the various ways we can/do add instructions to a BB, so I can't immediately be helpful with the tricky part of this review. :) I've no complaints about the general direction of this patch, though.

LGTM after the requested nit. Thanks again!

LGTM. Thanks again!

Thanks for this!

Thanks for this!

Lots of nits, and a few functional concerns. For the functional concerns that revolve around dubious edge additions, I'm happy with fixes or "it's impossible for that to actually happen; added a comment explaining that."

Looks fine to me, though I'd prefer if someone familiar with this code had a look, as well.

LGTM with a few comments. Thanks!

I'm not entirely through this patch (I hope to make more progress in the coming few days), but this is what I have for now. Logic's looking solid so far; I'm just nitpicky. :)

George, let me know if you agree with using the generic one and I'll abandon this revision. Thanks!

Never touched this code, so all I can offer is a style nit. Thanks for the patch!

Workaround committed as r339411