[llvm] [AMDGPU][True16][CodeGen] fix a predicate bug in VGPRImm with f16/bf16 (PR #144942)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Brox Chen (broxigarchen)

<details>
<summary>Changes</summary>

Fixed a typo issue that f16/bf16 VGPRImm patterrn is not guarded by the True16Predicate scope. The curly bracket is misplaced

---
Full diff: https://github.com/llvm/llvm-project/pull/144942.diff


1 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/SIInstructions.td (+9-9) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index 56b15c11a6694..d852d09b556d1 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -2187,17 +2187,17 @@ foreach pred = [NotHasTrue16BitInsts, UseFakeTrue16Insts] in {
       (VGPRImm<(i16 imm)>:$imm),
       (V_MOV_B32_e32 imm:$imm)
     >;
-  }
 
-  // FIXME: Workaround for ordering issue with peephole optimizer where
-  // a register class copy interferes with immediate folding.  Should
-  // use s_mov_b32, which can be shrunk to s_movk_i32
+    // FIXME: Workaround for ordering issue with peephole optimizer where
+    // a register class copy interferes with immediate folding.  Should
+    // use s_mov_b32, which can be shrunk to s_movk_i32
 
-  foreach vt = [f16, bf16] in {
-    def : GCNPat <
-      (VGPRImm<(vt fpimm)>:$imm),
-      (V_MOV_B32_e32 (vt (bitcast_fpimm_to_i32 $imm)))
-    >;
+    foreach vt = [f16, bf16] in {
+      def : GCNPat <
+        (VGPRImm<(vt fpimm)>:$imm),
+        (V_MOV_B32_e32 (vt (bitcast_fpimm_to_i32 $imm)))
+      >;
+    }
   }
 }
 

``````````

</details>


https://github.com/llvm/llvm-project/pull/144942