[llvm] cb73271 - [AMDGPU][CodeGen] use vt in VGPRimm pattern (#131016)

[via llvm-commits]

Author: Brox Chen
Date: 2025-03-13T07:58:19+07:00
New Revision: cb73271be12a40c7d885813733e11fd90eb3ed10

URL: https://github.com/llvm/llvm-project/commit/cb73271be12a40c7d885813733e11fd90eb3ed10
DIFF: https://github.com/llvm/llvm-project/commit/cb73271be12a40c7d885813733e11fd90eb3ed10.diff

LOG: [AMDGPU][CodeGen] use vt in VGPRimm pattern (#131016)

There seems to be a typo error introduced by
https://github.com/llvm/llvm-project/commit/2033767d68ed9aabcf1ad5d2bdd7541b272a05fd

Correct this pattern to use vt.

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/SIInstructions.td

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index 985337da1909d..de77401eb0137 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -2268,7 +2268,7 @@ foreach pred = [NotHasTrue16BitInsts, UseFakeTrue16Insts] in {
 
   foreach vt = [f16, bf16] in {
     def : GCNPat <
-      (VGPRImm<(f16 fpimm)>:$imm),
+      (VGPRImm<(vt fpimm)>:$imm),
       (V_MOV_B32_e32 (vt (bitcast_fpimm_to_i32 $imm)))
     >;
   }