[llvm] [AMDGPU] Add subtarget feature for v_lshl_add_u64. NFC. (PR #133723)

[Shilei Tian via llvm-commits]

================
@@ -1269,6 +1269,10 @@ def FeatureDynamicVGPRBlockSize32 : SubtargetFeature<"dynamic-vgpr-block-size-32
   "Use a block size of 32 for dynamic VGPR allocation (default is 16)"
 >;
 
+def FeatureLshlAddU64
----------------
shiltian wrote:

We already have something like `FeatureAtomicFMinFMaxF64FlatInsts` right?

https://github.com/llvm/llvm-project/pull/133723