[Mesa-dev] [PATCH 6/8] R600/SI: use patterns for clamp, fabs, fneg

[Christian König]

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

Instead of using custom inserters, it's simpler and
should make DAG folding easier.

Signed-off-by: Christian König <christian.koenig at amd.com>
---
 lib/Target/R600/SIISelLowering.cpp |   36 ------------------------------------
 lib/Target/R600/SIInstructions.td  |   26 ++++++++++++++++++++++----
 2 files changed, 22 insertions(+), 40 deletions(-)

diff --git a/lib/Target/R600/SIISelLowering.cpp b/lib/Target/R600/SIISelLowering.cpp
index 5a468ae..2f304eb 100644
--- a/lib/Target/R600/SIISelLowering.cpp
+++ b/lib/Target/R600/SIISelLowering.cpp
@@ -62,7 +62,6 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) :
 
 MachineBasicBlock * SITargetLowering::EmitInstrWithCustomInserter(
     MachineInstr * MI, MachineBasicBlock * BB) const {
-  const TargetInstrInfo * TII = getTargetMachine().getInstrInfo();
   MachineRegisterInfo & MRI = BB->getParent()->getRegInfo();
   MachineBasicBlock::iterator I = MI;
 
@@ -70,41 +69,6 @@ MachineBasicBlock * SITargetLowering::EmitInstrWithCustomInserter(
   default:
     return AMDGPUTargetLowering::EmitInstrWithCustomInserter(MI, BB);
   case AMDGPU::BRANCH: return BB;
-  case AMDGPU::CLAMP_SI:
-    BuildMI(*BB, I, BB->findDebugLoc(I), TII->get(AMDGPU::V_ADD_F32_e64))
-           .addOperand(MI->getOperand(0))
-           .addOperand(MI->getOperand(1))
-           .addImm(0x80) // SRC1
-           .addImm(0) // ABS
-           .addImm(1) // CLAMP
-           .addImm(0) // OMOD
-           .addImm(0); // NEG
-    MI->eraseFromParent();
-    break;
-
-  case AMDGPU::FABS_SI:
-    BuildMI(*BB, I, BB->findDebugLoc(I), TII->get(AMDGPU::V_ADD_F32_e64))
-                 .addOperand(MI->getOperand(0))
-                 .addOperand(MI->getOperand(1))
-                 .addImm(0x80) // SRC1
-                 .addImm(1) // ABS
-                 .addImm(0) // CLAMP
-                 .addImm(0) // OMOD
-                 .addImm(0); // NEG
-    MI->eraseFromParent();
-    break;
-
-  case AMDGPU::FNEG_SI:
-    BuildMI(*BB, I, BB->findDebugLoc(I), TII->get(AMDGPU::V_ADD_F32_e64))
-                 .addOperand(MI->getOperand(0))
-                 .addOperand(MI->getOperand(1))
-                 .addImm(0x80) // SRC1
-                 .addImm(0) // ABS
-                 .addImm(0) // CLAMP
-                 .addImm(0) // OMOD
-                 .addImm(1); // NEG
-    MI->eraseFromParent();
-    break;
   case AMDGPU::SHADER_TYPE:
     BB->getParent()->getInfo<SIMachineFunctionInfo>()->ShaderType =
                                         MI->getOperand(0).getImm();
diff --git a/lib/Target/R600/SIInstructions.td b/lib/Target/R600/SIInstructions.td
index 700b8f8..71de032 100644
--- a/lib/Target/R600/SIInstructions.td
+++ b/lib/Target/R600/SIInstructions.td
@@ -1184,10 +1184,6 @@ defm : SamplePatterns<VReg_128, v4i32>;
 defm : SamplePatterns<VReg_256, v8i32>;
 defm : SamplePatterns<VReg_512, v16i32>;
 
-def CLAMP_SI : CLAMP<VReg_32>;
-def FABS_SI : FABS<VReg_32>;
-def FNEG_SI : FNEG<VReg_32>;
-
 def : Extract_Element <f32, v4f32, VReg_128, 0, sub0>;
 def : Extract_Element <f32, v4f32, VReg_128, 1, sub1>;
 def : Extract_Element <f32, v4f32, VReg_128, 2, sub2>;
@@ -1211,6 +1207,28 @@ def : BitConvert <i32, f32, VReg_32>;
 def : BitConvert <f32, i32, SReg_32>;
 def : BitConvert <f32, i32, VReg_32>;
 
+/********** =================== **********/
+/********** Src & Dst modifiers **********/
+/********** =================== **********/
+
+def : Pat <
+  (int_AMDIL_clamp VReg_32:$src, (f32 FP_ZERO), (f32 FP_ONE)),
+  (V_ADD_F32_e64 VReg_32:$src, (i32 0x80 /* SRC1 */),
+   0 /* ABS */, 1 /* CLAMP */, 0 /* OMOD */, 0 /* NEG */)
+>;
+
+def : Pat <
+  (fabs VReg_32:$src),
+  (V_ADD_F32_e64 VReg_32:$src, (i32 0x80 /* SRC1 */),
+   1 /* ABS */, 0 /* CLAMP */, 0 /* OMOD */, 0 /* NEG */)
+>;
+
+def : Pat <
+  (fneg VReg_32:$src),
+  (V_ADD_F32_e64 VReg_32:$src, (i32 0x80 /* SRC1 */),
+   0 /* ABS */, 0 /* CLAMP */, 0 /* OMOD */, 1 /* NEG */)
+>;
+
 /********** ================== **********/
 /********** Immediate Patterns **********/
 /********** ================== **********/
-- 
1.7.10.4