[llvm] [AMDGPU] Enable vectorization of i8 values. (PR #134934)

[Gheorghe-Teodor Bercea via llvm-commits]

================
@@ -1419,6 +1419,10 @@ unsigned TargetTransformInfo::getMaxNumArgs() const {
   return TTIImpl->getMaxNumArgs();
 }
 
+bool TargetTransformInfo::canVectorizei8s() const {
----------------
doru1004 wrote:

Right, I think the name of that hook can be improved. The word vectorize in there is not quite correct.

https://github.com/llvm/llvm-project/pull/134934