[PATCH] D101844: [MicroBenchmarks] Add initial loop vectorization benchmarks.

[Jon Roelofs via Phabricator via llvm-commits]

jroelofs added a comment.

In D101844#2736630 <https://reviews.llvm.org/D101844#2736630>, @Meinersbur wrote:

> The comparison is part of the time measurements. This doesn't seem useful to be for benchmarking the vectorized and non-vectorized versions together.

My understanding was that googlebench only measures timing in the `for (auto _ : state)` loop, and that the setup before / after isn't counted.


Repository:
  rT test-suite

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D101844/new/

https://reviews.llvm.org/D101844