llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td

//===---- AMDCallingConv.td - Calling Conventions for Radeon GPUs ---------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This describes the calling conventions for the AMD Radeon GPUs.
//
//===----------------------------------------------------------------------===//

// Inversion of CCIfInReg
class CCIfNotInReg<CCAction A> : CCIf<"!ArgFlags.isInReg()", A> {}

// Calling convention for SI
def CC_SI : CallingConv<[

  CCIfInReg<CCIfType<[f32, i32, f16] , CCAssignToReg<[
    SGPR0, SGPR1, SGPR2, SGPR3, SGPR4, SGPR5, SGPR6, SGPR7,
    SGPR8, SGPR9, SGPR10, SGPR11, SGPR12, SGPR13, SGPR14, SGPR15,
    SGPR16, SGPR17, SGPR18, SGPR19, SGPR20, SGPR21, SGPR22, SGPR23,
    SGPR24, SGPR25, SGPR26, SGPR27, SGPR28, SGPR29, SGPR30, SGPR31,
    SGPR32, SGPR33, SGPR34, SGPR35, SGPR36, SGPR37, SGPR38, SGPR39
  ]>>>,

  CCIfInReg<CCIfType<[i64] , CCAssignToRegWithShadow<
    [ SGPR0, SGPR2, SGPR4, SGPR6, SGPR8, SGPR10, SGPR12, SGPR14,
      SGPR16, SGPR18, SGPR20, SGPR22, SGPR24, SGPR26, SGPR28, SGPR30,
      SGPR32, SGPR34, SGPR36, SGPR38 ],
    [ SGPR1, SGPR3, SGPR5, SGPR7, SGPR9, SGPR11, SGPR13, SGPR15,
      SGPR17, SGPR19, SGPR21, SGPR23, SGPR25, SGPR27, SGPR29, SGPR31,
      SGPR33, SGPR35, SGPR37, SGPR39 ]
  >>>,

  // 32*4 + 4 is the minimum for a fetch shader consumer with 32 inputs.
  CCIfNotInReg<CCIfType<[f32, i32, f16] , CCAssignToReg<[
    VGPR0, VGPR1, VGPR2, VGPR3, VGPR4, VGPR5, VGPR6, VGPR7,
    VGPR8, VGPR9, VGPR10, VGPR11, VGPR12, VGPR13, VGPR14, VGPR15,
    VGPR16, VGPR17, VGPR18, VGPR19, VGPR20, VGPR21, VGPR22, VGPR23,
    VGPR24, VGPR25, VGPR26, VGPR27, VGPR28, VGPR29, VGPR30, VGPR31,
    VGPR32, VGPR33, VGPR34, VGPR35, VGPR36, VGPR37, VGPR38, VGPR39,
    VGPR40, VGPR41, VGPR42, VGPR43, VGPR44, VGPR45, VGPR46, VGPR47,
    VGPR48, VGPR49, VGPR50, VGPR51, VGPR52, VGPR53, VGPR54, VGPR55,
    VGPR56, VGPR57, VGPR58, VGPR59, VGPR60, VGPR61, VGPR62, VGPR63,
    VGPR64, VGPR65, VGPR66, VGPR67, VGPR68, VGPR69, VGPR70, VGPR71,
    VGPR72, VGPR73, VGPR74, VGPR75, VGPR76, VGPR77, VGPR78, VGPR79,
    VGPR80, VGPR81, VGPR82, VGPR83, VGPR84, VGPR85, VGPR86, VGPR87,
    VGPR88, VGPR89, VGPR90, VGPR91, VGPR92, VGPR93, VGPR94, VGPR95,
    VGPR96, VGPR97, VGPR98, VGPR99, VGPR100, VGPR101, VGPR102, VGPR103,
    VGPR104, VGPR105, VGPR106, VGPR107, VGPR108, VGPR109, VGPR110, VGPR111,
    VGPR112, VGPR113, VGPR114, VGPR115, VGPR116, VGPR117, VGPR118, VGPR119,
    VGPR120, VGPR121, VGPR122, VGPR123, VGPR124, VGPR125, VGPR126, VGPR127,
    VGPR128, VGPR129, VGPR130, VGPR131, VGPR132, VGPR133, VGPR134, VGPR135
  ]>>>,

  CCIfByVal<CCIfType<[i64] , CCAssignToRegWithShadow<
    [ SGPR0, SGPR2, SGPR4, SGPR6, SGPR8, SGPR10, SGPR12, SGPR14,
      SGPR16, SGPR18, SGPR20, SGPR22, SGPR24, SGPR26, SGPR28, SGPR30,
      SGPR32, SGPR34, SGPR36, SGPR38 ],
    [ SGPR1, SGPR3, SGPR5, SGPR7, SGPR9, SGPR11, SGPR13, SGPR15,
      SGPR17, SGPR19, SGPR21, SGPR23, SGPR25, SGPR27, SGPR29, SGPR31,
      SGPR33, SGPR35, SGPR37, SGPR39 ]
  >>>

]>;

def RetCC_SI : CallingConv<[
  CCIfType<[i32] , CCAssignToReg<[
    SGPR0, SGPR1, SGPR2, SGPR3, SGPR4, SGPR5, SGPR6, SGPR7,
    SGPR8, SGPR9, SGPR10, SGPR11, SGPR12, SGPR13, SGPR14, SGPR15,
    SGPR16, SGPR17, SGPR18, SGPR19, SGPR20, SGPR21, SGPR22, SGPR23,
    SGPR24, SGPR25, SGPR26, SGPR27, SGPR28, SGPR29, SGPR30, SGPR31,
    SGPR32, SGPR33, SGPR34, SGPR35, SGPR36, SGPR37, SGPR38, SGPR39
  ]>>,

  // 32*4 + 4 is the minimum for a fetch shader with 32 outputs.
  CCIfType<[f32, f16] , CCAssignToReg<[
    VGPR0, VGPR1, VGPR2, VGPR3, VGPR4, VGPR5, VGPR6, VGPR7,
    VGPR8, VGPR9, VGPR10, VGPR11, VGPR12, VGPR13, VGPR14, VGPR15,
    VGPR16, VGPR17, VGPR18, VGPR19, VGPR20, VGPR21, VGPR22, VGPR23,
    VGPR24, VGPR25, VGPR26, VGPR27, VGPR28, VGPR29, VGPR30, VGPR31,
    VGPR32, VGPR33, VGPR34, VGPR35, VGPR36, VGPR37, VGPR38, VGPR39,
    VGPR40, VGPR41, VGPR42, VGPR43, VGPR44, VGPR45, VGPR46, VGPR47,
    VGPR48, VGPR49, VGPR50, VGPR51, VGPR52, VGPR53, VGPR54, VGPR55,
    VGPR56, VGPR57, VGPR58, VGPR59, VGPR60, VGPR61, VGPR62, VGPR63,
    VGPR64, VGPR65, VGPR66, VGPR67, VGPR68, VGPR69, VGPR70, VGPR71,
    VGPR72, VGPR73, VGPR74, VGPR75, VGPR76, VGPR77, VGPR78, VGPR79,
    VGPR80, VGPR81, VGPR82, VGPR83, VGPR84, VGPR85, VGPR86, VGPR87,
    VGPR88, VGPR89, VGPR90, VGPR91, VGPR92, VGPR93, VGPR94, VGPR95,
    VGPR96, VGPR97, VGPR98, VGPR99, VGPR100, VGPR101, VGPR102, VGPR103,
    VGPR104, VGPR105, VGPR106, VGPR107, VGPR108, VGPR109, VGPR110, VGPR111,
    VGPR112, VGPR113, VGPR114, VGPR115, VGPR116, VGPR117, VGPR118, VGPR119,
    VGPR120, VGPR121, VGPR122, VGPR123, VGPR124, VGPR125, VGPR126, VGPR127,
    VGPR128, VGPR129, VGPR130, VGPR131, VGPR132, VGPR133, VGPR134, VGPR135
  ]>>
]>;

// Calling convention for R600
def CC_R600 : CallingConv<[
  CCIfInReg<CCIfType<[v4f32, v4i32] , CCAssignToReg<[
    T0_XYZW, T1_XYZW, T2_XYZW, T3_XYZW, T4_XYZW, T5_XYZW, T6_XYZW, T7_XYZW,
    T8_XYZW, T9_XYZW, T10_XYZW, T11_XYZW, T12_XYZW, T13_XYZW, T14_XYZW, T15_XYZW,
    T16_XYZW, T17_XYZW, T18_XYZW, T19_XYZW, T20_XYZW, T21_XYZW, T22_XYZW,
    T23_XYZW, T24_XYZW, T25_XYZW, T26_XYZW, T27_XYZW, T28_XYZW, T29_XYZW,
    T30_XYZW, T31_XYZW, T32_XYZW
  ]>>>
]>;

// Calling convention for compute kernels
def CC_AMDGPU_Kernel : CallingConv<[
  CCCustom<"allocateKernArg">
]>;

def CC_AMDGPU : CallingConv<[
  CCIf<"static_cast<const AMDGPUSubtarget&>"
        "(State.getMachineFunction().getSubtarget()).getGeneration() >="
          "AMDGPUSubtarget::SOUTHERN_ISLANDS && "
        "!AMDGPU::isShader(State.getCallingConv())",
       CCDelegateTo<CC_AMDGPU_Kernel>>,
  CCIf<"static_cast<const AMDGPUSubtarget&>"
        "(State.getMachineFunction().getSubtarget()).getGeneration() < "
          "AMDGPUSubtarget::SOUTHERN_ISLANDS && "
         "!AMDGPU::isShader(State.getCallingConv())",
        CCDelegateTo<CC_AMDGPU_Kernel>>,
   CCIf<"static_cast<const AMDGPUSubtarget&>"
         "(State.getMachineFunction().getSubtarget()).getGeneration() >= "
           "AMDGPUSubtarget::SOUTHERN_ISLANDS",
        CCDelegateTo<CC_SI>>,
   CCIf<"static_cast<const AMDGPUSubtarget&>"
          "(State.getMachineFunction().getSubtarget()).getGeneration() < "
            "AMDGPUSubtarget::SOUTHERN_ISLANDS",
        CCDelegateTo<CC_R600>>
]>;