[llvm] [AMDGPU] Define constrained multi-dword scalar load instructions. (PR #96161)

[Matt Arsenault via llvm-commits]

================
@@ -167,6 +167,20 @@ multiclass SM_Pseudo_Loads<RegisterClass baseClass,
   def _IMM : SM_Load_Pseudo <opName, baseClass, dstClass, IMM_Offset>;
   def _SGPR : SM_Load_Pseudo <opName, baseClass, dstClass, SGPR_Offset>;
   def _SGPR_IMM : SM_Load_Pseudo <opName, baseClass, dstClass, SGPR_IMM_Offset>;
+
+  // The constrained multi-dword load equivalents with early clobber flag at
+  // the dst operand. They are needed only for codegen and there is no need for
+  // their real opcodes.
+  let SubtargetPredicate = isGFX8Plus,
----------------
arsenm wrote:

Shouldn't really need a separate subtarget predicate for these from the base forms

https://github.com/llvm/llvm-project/pull/96161