[AMDGPU] Fix for the lost CarryOut/CarryIn register operands in S_ADD/SUB_CO_PSEUDO.

Summary: This fixes the 5b898bddff51 bug when the carry-in and carry-out registers became lost in lowering S_ADD/SUB_CO_PSEUDO.

Reviewers: rampitec, arsenm

Reviewed By: arsenm

Subscribers: msearles, arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D80158

diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index 18d0836..5392abf 100644 (file)
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -5248,18 +5248,24 @@ void SIInstrInfo::moveToVALU(MachineInstr &TopInst,
                          ? AMDGPU::V_ADDC_U32_e64
                          : AMDGPU::V_SUBB_U32_e64;
       const auto *CarryRC = RI.getRegClass(AMDGPU::SReg_1_XEXECRegClassID);
-      Register DummyCReg = MRI.createVirtualRegister(CarryRC);
-      Register CarryReg = MRI.createVirtualRegister(CarryRC);
+
+      Register CarryInReg = Inst.getOperand(4).getReg();
+      if (!MRI.constrainRegClass(CarryInReg, CarryRC)) {
+        Register NewCarryReg = MRI.createVirtualRegister(CarryRC);
+        BuildMI(*MBB, &Inst, Inst.getDebugLoc(), get(AMDGPU::COPY), NewCarryReg)
+            .addReg(CarryInReg);
+      }
+
+      Register CarryOutReg = Inst.getOperand(1).getReg();
+
       Register DestReg = MRI.createVirtualRegister(RI.getEquivalentVGPRClass(
           MRI.getRegClass(Inst.getOperand(0).getReg())));
-      BuildMI(*MBB, &Inst, Inst.getDebugLoc(), get(AMDGPU::COPY), CarryReg)
-          .addReg(Inst.getOperand(4).getReg());
       MachineInstr *CarryOp =
           BuildMI(*MBB, &Inst, Inst.getDebugLoc(), get(Opc), DestReg)
-              .addReg(DummyCReg, RegState::Define | RegState::Dead)
+              .addReg(CarryOutReg, RegState::Define)
               .add(Inst.getOperand(2))
               .add(Inst.getOperand(3))
-              .addReg(CarryReg, RegState::Kill)
+              .addReg(CarryInReg)
               .addImm(0);
       legalizeOperands(*CarryOp);
       MRI.replaceRegWith(Inst.getOperand(0).getReg(), DestReg);

diff --git a/llvm/test/CodeGen/AMDGPU/s_add_co_pseudo_lowering.mir b/llvm/test/CodeGen/AMDGPU/s_add_co_pseudo_lowering.mir
new file mode 100644 (file)
index 0000000..40bdf8e
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/s_add_co_pseudo_lowering.mir
@@ -0,0 +1,50 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-fix-sgpr-copies  %s -o - | FileCheck -check-prefix=GCN %s
+---
+name:            s_add_co_pseudo_test
+tracksRegLiveness: true
+body:             |
+
+  bb.0:
+    liveins: $vgpr0, $vgpr1, $vgpr2, $sgpr0, $sgpr1, $sgpr2
+    ; GCN-LABEL: name: s_add_co_pseudo_test
+    ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $sgpr0, $sgpr1, $sgpr2
+    ; GCN: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+    ; GCN: [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF
+    ; GCN: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+    ; GCN: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+    ; GCN: [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr0
+    ; GCN: [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr1
+    ; GCN: [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr2
+    ; GCN: [[COPY6:%[0-9]+]]:sgpr_32 = COPY [[COPY3]]
+    ; GCN: [[V_MUL_LO_U32_:%[0-9]+]]:vgpr_32 = V_MUL_LO_U32 [[COPY]], [[COPY4]], implicit $exec
+    ; GCN: [[V_ADD_I32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_I32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_I32_e64 killed [[V_MUL_LO_U32_]], [[COPY6]], 0, implicit $exec
+    ; GCN: [[S_MUL_HI_U32_:%[0-9]+]]:sreg_32 = S_MUL_HI_U32 [[COPY4]], [[COPY5]]
+    ; GCN: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 -614296167
+    ; GCN: [[V_MUL_LO_U32_1:%[0-9]+]]:vgpr_32 = V_MUL_LO_U32 [[COPY]], [[COPY3]], implicit $exec
+    ; GCN: [[COPY7:%[0-9]+]]:vgpr_32 = COPY killed [[S_MOV_B32_]]
+    ; GCN: [[V_ADDC_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADDC_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADDC_U32_e64 killed [[V_MUL_LO_U32_1]], [[COPY7]], [[V_ADD_I32_e64_1]], 0, implicit $exec
+    ; GCN: [[V_MUL_HI_U32_:%[0-9]+]]:vgpr_32 = V_MUL_HI_U32 [[COPY4]], [[V_ADDC_U32_e64_]], implicit $exec
+    ; GCN: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 -181084736
+    ; GCN: [[V_MUL_LO_U32_2:%[0-9]+]]:vgpr_32 = V_MUL_LO_U32 [[V_MUL_HI_U32_]], [[S_MOV_B32_1]], implicit $exec
+    ; GCN: [[COPY8:%[0-9]+]]:vgpr_32 = COPY killed [[S_MOV_B32_1]]
+    ; GCN: [[V_ADDC_U32_e64_2:%[0-9]+]]:vgpr_32, [[V_ADDC_U32_e64_3:%[0-9]+]]:sreg_64_xexec = V_ADDC_U32_e64 [[COPY8]], killed [[V_MUL_LO_U32_2]], [[V_ADDC_U32_e64_1]], 0, implicit $exec
+    %0:vgpr_32 = COPY $vgpr0
+    %6:sreg_32 = COPY %0
+    %1:vgpr_32 = COPY $vgpr1
+    %2:vgpr_32 = COPY $vgpr2
+    %3:sreg_32 = COPY $sgpr0
+    %4:sreg_32 = COPY $sgpr1
+    %5:sreg_32 = COPY $sgpr2
+    %20:vgpr_32 = COPY %3
+    %7:sreg_32 = S_MUL_I32 %6, %4
+    %9:vgpr_32, %10:sreg_64_xexec = V_ADD_I32_e64 killed %7, %20, 0, implicit $exec
+    %8:sreg_32 = S_MUL_HI_U32 %4, %5
+    %11:sreg_32 = S_MOV_B32 -614296167
+    %12:sreg_32 = S_MUL_I32 %6, %3
+    %14:sreg_32, %13:sreg_64_xexec = S_ADD_CO_PSEUDO killed %12, killed %11, killed %10, implicit-def dead $scc
+    %15:sreg_32 = S_MUL_HI_U32 %4, %14
+    %16:sreg_32 = S_MOV_B32 -181084736
+    %17:sreg_32 = S_MUL_I32 %15, %16
+    %19:sreg_32, %18:sreg_64_xexec = S_ADD_CO_PSEUDO killed %16, killed %17, killed %13, implicit-def dead $scc
+...