radeon/llvm: Add intrinsic for enabling whole quad mode in SI pixel shaders.

Signed-off-by: Michel Dänzer <[email protected]>
Reviewed-by: Tom Stellard <[email protected]>

4 files changed, 23 insertions, 0 deletions

diff --git a/src/gallium/drivers/radeon/SIISelLowering.cpp b/src/gallium/drivers/radeon/SIISelLowering.cpp
index 2c8167382c7..ebe9514a2b9 100644
--- a/src/gallium/drivers/radeon/SIISelLowering.cpp
+++ b/src/gallium/drivers/radeon/SIISelLowering.cpp
@@ -132,6 +132,9 @@ MachineBasicBlock * SITargetLowering::EmitInstrWithCustomInserter(
   case AMDGPU::SI_KIL:
     LowerSI_KIL(MI, *BB, I, MRI);
     break;
+  case AMDGPU::SI_WQM:
+    LowerSI_WQM(MI, *BB, I, MRI);
+    break;
   case AMDGPU::SI_V_CNDLT:
     LowerSI_V_CNDLT(MI, *BB, I, MRI);
     break;
@@ -146,6 +149,16 @@ void SITargetLowering::AppendS_WAITCNT(MachineInstr *MI, MachineBasicBlock &BB,
           .addImm(0);
 }
 
+
+void SITargetLowering::LowerSI_WQM(MachineInstr *MI, MachineBasicBlock &BB,
+    MachineBasicBlock::iterator I, MachineRegisterInfo & MRI) const
+{
+  BuildMI(BB, I, BB.findDebugLoc(I), TII->get(AMDGPU::S_WQM_B64), AMDGPU::EXEC)
+          .addReg(AMDGPU::EXEC);
+
+  MI->eraseFromParent();
+}
+
 void SITargetLowering::LowerSI_INTERP(MachineInstr *MI, MachineBasicBlock &BB,
     MachineBasicBlock::iterator I, MachineRegisterInfo & MRI) const
 {
diff --git a/src/gallium/drivers/radeon/SIISelLowering.h b/src/gallium/drivers/radeon/SIISelLowering.h
index 80c7f4bb86c..4407bf04667 100644
--- a/src/gallium/drivers/radeon/SIISelLowering.h
+++ b/src/gallium/drivers/radeon/SIISelLowering.h
@@ -37,6 +37,8 @@ class SITargetLowering : public AMDGPUTargetLowering
               MachineBasicBlock::iterator I, MachineRegisterInfo &MRI) const;
   void LowerSI_KIL(MachineInstr *MI, MachineBasicBlock &BB,
               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;
 
diff --git a/src/gallium/drivers/radeon/SIInstructions.td b/src/gallium/drivers/radeon/SIInstructions.td
index 20d4c003aa1..286819638a8 100644
--- a/src/gallium/drivers/radeon/SIInstructions.td
+++ b/src/gallium/drivers/radeon/SIInstructions.td
@@ -986,6 +986,13 @@ def SI_KIL : InstSI <
 	[(int_AMDGPU_kill VReg_32:$src)]
 >;
 
+def SI_WQM : InstSI <
+	(outs),
+	(ins),
+	"SI_WQM",
+	[(int_SI_wqm)]
+>;
+
 } // end usesCustomInserter 
 
 // SI Psuedo branch instructions.  These are used by the CFG structurizer pass
diff --git a/src/gallium/drivers/radeon/SIIntrinsics.td b/src/gallium/drivers/radeon/SIIntrinsics.td
index 401325bf5b1..fbb8dc90fbe 100644
--- a/src/gallium/drivers/radeon/SIIntrinsics.td
+++ b/src/gallium/drivers/radeon/SIIntrinsics.td
@@ -20,6 +20,7 @@ let TargetPrefix = "SI", isTarget = 1 in {
   def int_SI_load_const : Intrinsic <[llvm_float_ty], [llvm_i64_ty, llvm_i32_ty], []>;
   def int_SI_vs_load_buffer_index : Intrinsic <[llvm_i32_ty], [], [IntrNoMem]>;
   def int_SI_vs_load_input : Intrinsic <[llvm_v4f32_ty], [llvm_v4i32_ty, llvm_i16_ty, llvm_i32_ty], []> ;
+  def int_SI_wqm : Intrinsic <[], [], []>;
 
   def int_SI_sample : Intrinsic <[llvm_v4f32_ty], [llvm_i32_ty, llvm_v4f32_ty, llvm_v8i32_ty, llvm_v4i32_ty]>;