[AMDGPU] Do not combine dpp mov reading physregs

We cannot be sure physregs will stay unchanged.

Differential Revision: https://reviews.llvm.org/D69065

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@375033 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/GCNDPPCombine.cpp b/lib/Target/AMDGPU/GCNDPPCombine.cpp
index f8adda72950b03e76117209df7b19d1cbf28ec77..98678873e37cb3f039d6ca9c9ded15f8024a3d46 100644 (file)
--- a/lib/Target/AMDGPU/GCNDPPCombine.cpp
+++ b/lib/Target/AMDGPU/GCNDPPCombine.cpp
@@ -375,7 +375,13 @@ bool GCNDPPCombine::combineDPPMov(MachineInstr &MovMI) const {
   bool BoundCtrlZero = BCZOpnd->getImm();
 
   auto *OldOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::old);
+  auto *SrcOpnd = TII->getNamedOperand(MovMI, AMDGPU::OpName::src0);
   assert(OldOpnd && OldOpnd->isReg());
+  assert(SrcOpnd && SrcOpnd->isReg());
+  if (OldOpnd->getReg().isPhysical() || SrcOpnd->getReg().isPhysical()) {
+    LLVM_DEBUG(dbgs() << "  failed: dpp move reads physreg\n");
+    return false;
+  }
 
   auto * const OldOpndValue = getOldOpndValue(*OldOpnd);
   // OldOpndValue is either undef (IMPLICIT_DEF) or immediate or something else

diff --git a/test/CodeGen/AMDGPU/dpp_combine.mir b/test/CodeGen/AMDGPU/dpp_combine.mir
index b58b2ee0edbff7413c7db153da6d1afed3401148..e0e3c352fd20f51bf36cd611ab9f774df6fc1f7c 100644 (file)
--- a/test/CodeGen/AMDGPU/dpp_combine.mir
+++ b/test/CodeGen/AMDGPU/dpp_combine.mir
@@ -575,6 +575,30 @@ body: |
     %2:vgpr_32 = V_CEIL_F32_e32 $vgpr0, implicit $exec
 ...
 
+# Do not combine a dpp mov which reads a physreg.
+# GCN-LABEL: name: phys_dpp_mov_old_src
+# GCN: %0:vgpr_32 = V_MOV_B32_dpp undef $vgpr0, undef %1:vgpr_32, 1, 15, 15, 1, implicit $exec
+# GCN: %2:vgpr_32 = V_CEIL_F32_e32 %0, implicit $exec
+name: phys_dpp_mov_old_src
+tracksRegLiveness: true
+body: |
+  bb.0:
+    %1:vgpr_32 = V_MOV_B32_dpp undef $vgpr0, undef %0:vgpr_32, 1, 15, 15, 1, implicit $exec
+    %2:vgpr_32 = V_CEIL_F32_e32 %1, implicit $exec
+...
+
+# Do not combine a dpp mov which reads a physreg.
+# GCN-LABEL: name: phys_dpp_mov_src
+# GCN: %0:vgpr_32 = V_MOV_B32_dpp undef %1:vgpr_32, undef $vgpr0, 1, 15, 15, 1, implicit $exec
+# GCN: %2:vgpr_32 = V_CEIL_F32_e32 %0, implicit $exec
+name: phys_dpp_mov_src
+tracksRegLiveness: true
+body: |
+  bb.0:
+    %1:vgpr_32 = V_MOV_B32_dpp undef %0:vgpr_32, undef $vgpr0, 1, 15, 15, 1, implicit $exec
+    %2:vgpr_32 = V_CEIL_F32_e32 %1, implicit $exec
+...
+
 # GCN-LABEL: name: dpp_reg_sequence_both_combined
 # GCN: %0:vreg_64 = COPY $vgpr0_vgpr1
 # GCN: %1:vreg_64 = COPY $vgpr2_vgpr3