[llvm] [LV] Support strided load with a stride of -1 (PR #128718)

[Florian Hahn via llvm-commits]

================
@@ -1115,6 +1115,7 @@ class LoopVectorizationCostModel {
     CM_Widen_Reverse, // For consecutive accesses with stride -1.
     CM_Interleave,
     CM_GatherScatter,
+    CM_Strided,
----------------
fhahn wrote:

Do we actually need all the legacy cost model changes? Could we just replace a `VPWidenLoadRecipe (vector-end-pointer) -> VPStridedLoad` if profitable as VPlan-to-VPlan transformation?

https://github.com/llvm/llvm-project/pull/128718