[llvm] [VPlan] Remove isVector guard in getCostForRecipeWithOpcode. (PR #188126)

[David Sherwood via llvm-commits]

================
@@ -6,14 +6,14 @@ target triple = "arm64-apple-macosx"
 define void @udiv_rhs_opt_cost(ptr %dst) #0 {
 ; CHECK-LABEL: 'udiv_rhs_opt_cost'
 ; CHECK:  LV: Found an estimated cost of 5 for VF 1 For instruction: %div = udiv i8 %iv.trunc, 3
-; CHECK:  Cost of 1 for VF 2: CLONE ir<%div> = udiv vp<[[VP7:%[0-9]+]]>, ir<3>
+; CHECK:  Cost of 5 for VF 2: CLONE ir<%div> = udiv vp<[[VP7:%[0-9]+]]>, ir<3>
----------------
david-arm wrote:

I assume this change occurs because we're now calling `Ctx.getOperandInfo` when VF is scalar? If so, I need to look into this because the cost shouldn't really be going up. :)

https://github.com/llvm/llvm-project/pull/188126