//===-- AMDGPUInstrInfo.td - AMDGPU DAG nodes --------------*- tablegen -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains DAG node defintions for the AMDGPU target.
//
//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
// AMDGPU DAG Profiles
//===----------------------------------------------------------------------===//

def AMDGPUDTIntTernaryOp : SDTypeProfile<1, 3, [
  SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>, SDTCisInt<0>, SDTCisInt<3>
]>;

//===----------------------------------------------------------------------===//
// AMDGPU DAG Nodes
//

// out = ((a << 32) | b) >> c)
//
// Can be used to optimize rtol:
// rotl(a, b) = bitalign(a, a, 32 - b)
def AMDGPUbitalign : SDNode<"AMDGPUISD::BITALIGN", AMDGPUDTIntTernaryOp>;

// out = a - floor(a)
def AMDGPUfract : SDNode<"AMDGPUISD::FRACT", SDTFPUnaryOp>;

// out = max(a, b) a and b are floats
def AMDGPUfmax : SDNode<"AMDGPUISD::FMAX", SDTFPBinOp,
  [SDNPCommutative, SDNPAssociative]
>;

// out = max(a, b) a and b are signed ints
def AMDGPUsmax : SDNode<"AMDGPUISD::SMAX", SDTIntBinOp,
  [SDNPCommutative, SDNPAssociative]
>;

// out = max(a, b) a and b are unsigned ints
def AMDGPUumax : SDNode<"AMDGPUISD::UMAX", SDTIntBinOp,
  [SDNPCommutative, SDNPAssociative]
>;

// out = min(a, b) a and b are floats
def AMDGPUfmin : SDNode<"AMDGPUISD::FMIN", SDTFPBinOp,
  [SDNPCommutative, SDNPAssociative]
>;

// out = min(a, b) a snd b are signed ints
def AMDGPUsmin : SDNode<"AMDGPUISD::SMIN", SDTIntBinOp,
  [SDNPCommutative, SDNPAssociative]
>;

// out = min(a, b) a and b are unsigned ints
def AMDGPUumin : SDNode<"AMDGPUISD::UMIN", SDTIntBinOp,
  [SDNPCommutative, SDNPAssociative]
>;

// urecip - This operation is a helper for integer division, it returns the
// result of 1 / a as a fractional unsigned integer.
// out = (2^32 / a) + e
// e is rounding error
def AMDGPUurecip : SDNode<"AMDGPUISD::URECIP", SDTIntUnaryOp>;

def fpow : SDNode<"ISD::FPOW", SDTFPBinOp>;