[llvm] [AMDGPU] Fix negative immediate offset for unbuffered smem loads (PR #79553)

[Matt Arsenault via llvm-commits]

================
@@ -116,6 +116,10 @@ def gi_smrd_sgpr_imm :
     GIComplexOperandMatcher<s64, "selectSmrdSgprImm">,
     GIComplexPatternEquiv<SMRDSgprImm>;
 
+def gi_smrd_prefetch_imm :
+    GIComplexOperandMatcher<s64, "selectSmrdPrefetchImm">,
+    GIComplexPatternEquiv<SMRDPrefetchImm>;
----------------
arsenm wrote:

This looks like new globalisel support for prefetch, this should be done separately 

https://github.com/llvm/llvm-project/pull/79553