[llvm] [AMDGPU][True16][CodeGen] fix v_mov_b16_t16 index in folding pass (PR #161764)

[Brox Chen via llvm-commits]

https://github.com/broxigarchen created https://github.com/llvm/llvm-project/pull/161764

With true16 mode v_mov_b16_t16 is added as new foldable copy inst, but the src operand is in different index.

There is a bug in folding pass that are not using the correct src index for  v_mov_b16_t16.

>From 3b37d7809f0b5795afcad58a5d4698bd05f3113b Mon Sep 17 00:00:00 2001
From: guochen2 <guochen2 at amd.com>
Date: Thu, 2 Oct 2025 22:17:53 -0400
Subject: [PATCH] fix v_mov_b16_t16 indexing

---
 llvm/lib/Target/AMDGPU/SIFoldOperands.cpp |  4 +++-
 llvm/lib/Target/AMDGPU/SIInstrInfo.cpp    | 26 +++++++++++++++++++++++
 llvm/lib/Target/AMDGPU/SIInstrInfo.h      |  1 +
 3 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
index fed37788802b9..c0eee325b9114 100644
--- a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -931,7 +931,9 @@ static MachineOperand *lookUpCopyChain(const SIInstrInfo &TII,
   for (MachineInstr *SubDef = MRI.getVRegDef(SrcReg);
        SubDef && TII.isFoldableCopy(*SubDef);
        SubDef = MRI.getVRegDef(Sub->getReg())) {
-    MachineOperand &SrcOp = SubDef->getOperand(1);
+    unsigned SrcIdx = TII.getFoldableCopySrcIdx(*SubDef);
+    MachineOperand &SrcOp = SubDef->getOperand(SrcIdx);
+
     if (SrcOp.isImm())
       return &SrcOp;
     if (!SrcOp.isReg() || SrcOp.getReg().isPhysical())
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 56435a50c87ad..28dfae5c116cb 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -3435,6 +3435,32 @@ bool SIInstrInfo::isFoldableCopy(const MachineInstr &MI) {
   }
 }
 
+unsigned SIInstrInfo::getFoldableCopySrcIdx(const MachineInstr &MI) {
+  switch (MI.getOpcode()) {
+  case AMDGPU::V_MOV_B16_t16_e32:
+  case AMDGPU::V_MOV_B16_t16_e64:
+    return 2;
+  case AMDGPU::V_MOV_B32_e32:
+  case AMDGPU::V_MOV_B32_e64:
+  case AMDGPU::V_MOV_B64_PSEUDO:
+  case AMDGPU::V_MOV_B64_e32:
+  case AMDGPU::V_MOV_B64_e64:
+  case AMDGPU::S_MOV_B32:
+  case AMDGPU::S_MOV_B64:
+  case AMDGPU::S_MOV_B64_IMM_PSEUDO:
+  case AMDGPU::COPY:
+  case AMDGPU::WWM_COPY:
+  case AMDGPU::V_ACCVGPR_WRITE_B32_e64:
+  case AMDGPU::V_ACCVGPR_READ_B32_e64:
+  case AMDGPU::V_ACCVGPR_MOV_B32:
+  case AMDGPU::AV_MOV_B32_IMM_PSEUDO:
+  case AMDGPU::AV_MOV_B64_IMM_PSEUDO:
+    return 1;
+  default:
+    assert(0 && "MI is not a foldable copy");
+  }
+}
+
 static constexpr AMDGPU::OpName ModifierOpNames[] = {
     AMDGPU::OpName::src0_modifiers, AMDGPU::OpName::src1_modifiers,
     AMDGPU::OpName::src2_modifiers, AMDGPU::OpName::clamp,
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.h b/llvm/lib/Target/AMDGPU/SIInstrInfo.h
index a21089f8e0fcc..cc59acf1ebd94 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.h
@@ -417,6 +417,7 @@ class SIInstrInfo final : public AMDGPUGenInstrInfo {
                                   const MachineInstr &MIb) const override;
 
   static bool isFoldableCopy(const MachineInstr &MI);
+  static unsigned getFoldableCopySrcIdx(const MachineInstr &MI);
 
   void removeModOperands(MachineInstr &MI) const;