[llvm] [AMDGPU][GlobalISel] Reduce instruction count for store in global addrspace for non-powers-of-2 (PR #206043)

[Krzysztof Drewniak via llvm-commits]

================

----------------
krzysz00 wrote:

Isn't there a subvector extract you can use here?

https://github.com/llvm/llvm-project/pull/206043