AVX2 in 3.2

The 3.2 release notes mention "Small codegen optimizations, especially
for AVX2." Can someone provide a little more information about that?
What kinds of things were improved for AVX2?

Thanks!

                          -David

Hi David,

There were many changes. For example, efficient lowering of vector casts (trunc, zext, sext), simplified vblend patterns, shuffle patterns, AVX2 gathers, just to name a few.

Nadav

Nadav Rotem <nrotem@apple.com> writes:

Hi David,

There were many changes. For example, efficient lowering of vector
casts (trunc, zext, sext), simplified vblend patterns, shuffle
patterns, AVX2 gathers, just to name a few.

Thanks Nadav, that's very helpful!

                          -David