[Mesa-dev] [PATCH 8/8] R600/SI: replace SI_V_CNDLT with a pattern

[Christian König]

From: Christian König <christian.koenig at amd.com>

It actually fixes quite a bunch of piglit tests.

Signed-off-by: Christian König <christian.koenig at amd.com>
---
 lib/Target/R600/SIISelLowering.cpp |   22 ----------------------
 lib/Target/R600/SIISelLowering.h   |    2 --
 lib/Target/R600/SIInstructions.td  |   12 +++++-------
 3 files changed, 5 insertions(+), 31 deletions(-)

diff --git a/lib/Target/R600/SIISelLowering.cpp b/lib/Target/R600/SIISelLowering.cpp
index 2f304eb..212e3f2 100644
--- a/lib/Target/R600/SIISelLowering.cpp
+++ b/lib/Target/R600/SIISelLowering.cpp
@@ -81,9 +81,6 @@ MachineBasicBlock * SITargetLowering::EmitInstrWithCustomInserter(
   case AMDGPU::SI_WQM:
     LowerSI_WQM(MI, *BB, I, MRI);
     break;
-  case AMDGPU::SI_V_CNDLT:
-    LowerSI_V_CNDLT(MI, *BB, I, MRI);
-    break;
   }
   return BB;
 }
@@ -127,25 +124,6 @@ void SITargetLowering::LowerSI_INTERP(MachineInstr *MI, MachineBasicBlock &BB,
   MI->eraseFromParent();
 }
 
-void SITargetLowering::LowerSI_V_CNDLT(MachineInstr *MI, MachineBasicBlock &BB,
-    MachineBasicBlock::iterator I, MachineRegisterInfo & MRI) const {
-  unsigned VCC = MRI.createVirtualRegister(&AMDGPU::SReg_64RegClass);
-
-  BuildMI(BB, I, BB.findDebugLoc(I),
-          TII->get(AMDGPU::V_CMP_GT_F32_e32),
-          VCC)
-          .addImm(0)
-          .addOperand(MI->getOperand(1));
-
-  BuildMI(BB, I, BB.findDebugLoc(I), TII->get(AMDGPU::V_CNDMASK_B32_e32))
-          .addOperand(MI->getOperand(0))
-          .addOperand(MI->getOperand(3))
-          .addOperand(MI->getOperand(2))
-          .addReg(VCC);
-
-  MI->eraseFromParent();
-}
-
 EVT SITargetLowering::getSetCCResultType(EVT VT) const {
   return MVT::i1;
 }
diff --git a/lib/Target/R600/SIISelLowering.h b/lib/Target/R600/SIISelLowering.h
index a8429b7..5d048f8 100644
--- a/lib/Target/R600/SIISelLowering.h
+++ b/lib/Target/R600/SIISelLowering.h
@@ -29,8 +29,6 @@ class SITargetLowering : public AMDGPUTargetLowering {
               MachineBasicBlock::iterator I, MachineRegisterInfo & MRI) const;
   void LowerSI_WQM(MachineInstr *MI, MachineBasicBlock &BB,
               MachineBasicBlock::iterator I, MachineRegisterInfo & MRI) const;
-  void LowerSI_V_CNDLT(MachineInstr *MI, MachineBasicBlock &BB,
-              MachineBasicBlock::iterator I, MachineRegisterInfo & MRI) const;
 
   SDValue LowerLOAD(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
diff --git a/lib/Target/R600/SIInstructions.td b/lib/Target/R600/SIInstructions.td
index 3b7cc6f..01e7933 100644
--- a/lib/Target/R600/SIInstructions.td
+++ b/lib/Target/R600/SIInstructions.td
@@ -987,13 +987,6 @@ def LOAD_CONST : AMDGPUShaderInst <
 
 let usesCustomInserter = 1 in {
 
-def SI_V_CNDLT : InstSI <
-  (outs VReg_32:$dst),
-  (ins VReg_32:$src0, VReg_32:$src1, VReg_32:$src2),
-  "SI_V_CNDLT $dst, $src0, $src1, $src2",
-  [(set VReg_32:$dst, (int_AMDGPU_cndlt VReg_32:$src0, VReg_32:$src1, VReg_32:$src2))]
->;
-
 def SI_INTERP : InstSI <
   (outs VReg_32:$dst),
   (ins VReg_32:$i, VReg_32:$j, i32imm:$attr_chan, i32imm:$attr, SReg_32:$params),
@@ -1083,6 +1076,11 @@ def SI_KILL : InstSI <
 
 } // end IsCodeGenOnly, isPseudo
 
+def : Pat<
+  (int_AMDGPU_cndlt VReg_32:$src0, VReg_32:$src1, VReg_32:$src2),
+  (V_CNDMASK_B32_e64 VReg_32:$src2, VReg_32:$src1, (V_CMP_GT_F32_e64 0, VReg_32:$src0))
+>;
+
 def : Pat <
   (int_AMDGPU_kilp),
   (SI_KILL (V_MOV_B32_e32 0xbf800000))
-- 
1.7.10.4