[AMDGPU] Fixed dpp combine of VOP1

If original instruction did not have source modifiers they were
not added to the new DPP instruction as well, even if needed.

Differential Revision: https://reviews.llvm.org/D68729

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@374241 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/GCNDPPCombine.cpp b/lib/Target/AMDGPU/GCNDPPCombine.cpp
index e1845e2e8e879d2f9f4d35363f4cc76480d61e0e..954058592d659b7d2fd990c5a2df0ce1b2363c4a 100644 (file)
--- a/lib/Target/AMDGPU/GCNDPPCombine.cpp
+++ b/lib/Target/AMDGPU/GCNDPPCombine.cpp
@@ -195,6 +195,10 @@ MachineInstr *GCNDPPCombine::createDPPInst(MachineInstr &OrigMI,
       assert(0LL == (Mod0->getImm() & ~(SISrcMods::ABS | SISrcMods::NEG)));
       DPPInst.addImm(Mod0->getImm());
       ++NumOperands;
+    } else if (AMDGPU::getNamedOperandIdx(DPPOp,
+                   AMDGPU::OpName::src0_modifiers) != -1) {
+      DPPInst.addImm(0);
+      ++NumOperands;
     }
     auto *Src0 = TII->getNamedOperand(MovMI, AMDGPU::OpName::src0);
     assert(Src0);
@@ -214,6 +218,10 @@ MachineInstr *GCNDPPCombine::createDPPInst(MachineInstr &OrigMI,
       assert(0LL == (Mod1->getImm() & ~(SISrcMods::ABS | SISrcMods::NEG)));
       DPPInst.addImm(Mod1->getImm());
       ++NumOperands;
+    } else if (AMDGPU::getNamedOperandIdx(DPPOp,
+                   AMDGPU::OpName::src1_modifiers) != -1) {
+      DPPInst.addImm(0);
+      ++NumOperands;
     }
     if (auto *Src1 = TII->getNamedOperand(OrigMI, AMDGPU::OpName::src1)) {
       if (!TII->isOperandLegal(*DPPInst.getInstr(), NumOperands, Src1)) {

diff --git a/test/CodeGen/AMDGPU/dpp_combine.mir b/test/CodeGen/AMDGPU/dpp_combine.mir
index c43fb037d074ffdcbd99195512f1d5d36da7aa93..76a2082cfc2678b34b5a911fc8f3fb6d75f166dc 100644 (file)
--- a/test/CodeGen/AMDGPU/dpp_combine.mir
+++ b/test/CodeGen/AMDGPU/dpp_combine.mir
@@ -526,3 +526,26 @@ body: |
     %3:vreg_64 = REG_SEQUENCE %2, %subreg.sub0 ; %3.sub1 is undef
     %4:vgpr_32 = V_MOV_B32_dpp %3.sub1, %1, 1, 15, 15, 1, implicit $exec
     %5:vgpr_32 = V_ADD_U32_e32 %4, %0.sub1, implicit $exec
+...
+
+# Test instruction which does not have modifiers in VOP1 form but does in DPP form.
+# CHECK-LABEL: name: dpp_vop1
+# CHECK: %3:vgpr_32 = V_CEIL_F32_dpp %1:vgpr_32, 0, undef %2:vgpr_32, 1, 15, 15, 1, implicit $exec
+name: dpp_vop1
+tracksRegLiveness: true
+body: |
+  bb.0:
+    %2:vgpr_32 = V_MOV_B32_dpp undef %1:vgpr_32, undef %0:vgpr_32, 1, 15, 15, 1, implicit $exec
+    %3:vgpr_32 = V_CEIL_F32_e32 %2, implicit $exec
+...
+
+# Test instruction which does not have modifiers in VOP2 form but does in DPP form.
+# CHECK-LABEL: name: dpp_min
+# CHECK: %3:vgpr_32 = V_MIN_F32_dpp %1:vgpr_32, 0, undef %2:vgpr_32, 0, undef %4:vgpr_32, 1, 15, 15, 1, implicit $exec
+name: dpp_min
+tracksRegLiveness: true
+body: |
+  bb.0:
+    %2:vgpr_32 = V_MOV_B32_dpp undef %1:vgpr_32, undef %0:vgpr_32, 1, 15, 15, 1, implicit $exec
+    %4:vgpr_32 = V_MIN_F32_e32 %2, undef %3:vgpr_32, implicit $exec
+...