[llvm] [AMDGPU] Accept extractelement of a widening cast when folding image ops to a16 (PR #208207)

[Krzysztof Drewniak via llvm-commits]

================
@@ -4018,6 +4018,55 @@ define amdgpu_kernel void @image_load_a16_mip_2d_const_noopt(ptr addrspace(1) %o
   ret void
 }
 
+define amdgpu_kernel void @image_load_a16_mip_2d_sext_vec(ptr addrspace(1) %out, <8 x i32> inreg %rsrc, <2 x i16> %coord) {
----------------
krzysz00 wrote:

Ah, something just looked off about the format, then, my bad

https://github.com/llvm/llvm-project/pull/208207