[llvm] AMDGPU: Fix true16 d16 entry table for DS pseudos (PR #156419)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Matt Arsenault (arsenm)

<details>
<summary>Changes</summary>

This should be trying to use the _gfx9 variants of DS pseudos,
not the base form with m0 uses.

---
Full diff: https://github.com/llvm/llvm-project/pull/156419.diff


1 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/DSInstructions.td (+3-2) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/DSInstructions.td b/llvm/lib/Target/AMDGPU/DSInstructions.td
index 2ff9dfe8a7014..e6a07ebe1cafb 100644
--- a/llvm/lib/Target/AMDGPU/DSInstructions.td
+++ b/llvm/lib/Target/AMDGPU/DSInstructions.td
@@ -127,11 +127,12 @@ multiclass DS_1A1D_NORET_mc<string opName, RegisterClass rc = VGPR_32> {
   }
 }
 
-multiclass DS_1A1D_NORET_t16<string opName, RegisterClass rc = VGPR_32> 
+multiclass DS_1A1D_NORET_t16<string opName, RegisterClass rc = VGPR_32>
 : DS_1A1D_NORET_mc<opName, rc> {
   let has_m0_read = 0 in {
     let True16Predicate = UseRealTrue16Insts in {
-      def "_t16" : DS_1A1D_NORET<opName#"_t16", VGPR_16>, True16D16Table<NAME#"_D16_HI", NAME>;
+      def "_t16" : DS_1A1D_NORET<opName#"_t16", VGPR_16>,
+        True16D16Table<NAME#"_D16_HI", NAME#"_gfx9">;
     }
   }
 }

``````````

</details>


https://github.com/llvm/llvm-project/pull/156419