[PATCH] D24593: Standford/Bubble sort code restructure

[Mehdi AMINI via llvm-commits]

mehdi_amini added a comment.

In https://reviews.llvm.org/D24593#563106, @evstupac wrote:

> > This is not flaky.
>
> Maybe it is not flaky. But what I'm trying to say that now the test is not ok to measure compiler performance.


I was digging in my archive, because in the past "someone" (didn't remember who) provided great explanations as of why a test case wasn't great for a particular microarchitecture, and I wanted to point at it as an example of the level of information I'd expected from someone to convince about what's going on beyond simply a claim that "this is bad luck with the predictor".

I just found it: https://llvm.org/bugs/show_bug.cgi?id=5615 (See the description, and the attached PPT).
(I noticed when finding it that the name seems familiar...)


https://reviews.llvm.org/D24593