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;
.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
{
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;
[(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
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]>;