mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-14 20:57:01 +00:00
f95b162188
The SelectionDAGBuilder was promoting vector kernel arguments to legal types, but this won't work for R600 and SI since kernel arguments are stored in memory and can't be promoted. In order to handle vector arguments correctly we need to look at the original types from the LLVM IR function. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193215 91177308-0d34-0410-b5e6-96231b3b80d8
62 lines
2.3 KiB
TableGen
62 lines
2.3 KiB
TableGen
//===---- 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] , CCAssignToReg<[
|
|
SGPR0, SGPR1, SGPR2, SGPR3, SGPR4, SGPR5, SGPR6, SGPR7,
|
|
SGPR8, SGPR9, SGPR10, SGPR11, SGPR12, SGPR13, SGPR14, SGPR15,
|
|
SGPR16
|
|
]>>>,
|
|
|
|
CCIfInReg<CCIfType<[i64] , CCAssignToRegWithShadow<
|
|
[ SGPR0, SGPR2, SGPR4, SGPR6, SGPR8, SGPR10, SGPR12, SGPR14 ],
|
|
[ SGPR1, SGPR3, SGPR5, SGPR7, SGPR9, SGPR11, SGPR13, SGPR15 ]
|
|
>>>,
|
|
|
|
CCIfNotInReg<CCIfType<[f32, i32] , 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
|
|
]>>>,
|
|
|
|
CCIfByVal<CCIfType<[i64] , CCAssignToRegWithShadow<
|
|
[ SGPR0, SGPR2, SGPR4, SGPR6, SGPR8, SGPR10, SGPR12, SGPR14 ],
|
|
[ SGPR1, SGPR3, SGPR5, SGPR7, SGPR9, SGPR11, SGPR13, SGPR15 ]
|
|
>>>
|
|
|
|
]>;
|
|
|
|
// Calling convention for compute kernels
|
|
def CC_AMDGPU_Kernel : CallingConv<[
|
|
CCCustom<"allocateStack">
|
|
]>;
|
|
|
|
def CC_AMDGPU : CallingConv<[
|
|
CCIf<"State.getTarget().getSubtarget<AMDGPUSubtarget>().getGeneration() == "
|
|
"AMDGPUSubtarget::SOUTHERN_ISLANDS && "
|
|
"State.getMachineFunction().getInfo<SIMachineFunctionInfo>()->"#
|
|
"ShaderType == ShaderType::COMPUTE", CCDelegateTo<CC_AMDGPU_Kernel>>,
|
|
CCIf<"State.getTarget().getSubtarget<AMDGPUSubtarget>().getGeneration() < "
|
|
"AMDGPUSubtarget::SOUTHERN_ISLANDS && "
|
|
"State.getMachineFunction().getInfo<R600MachineFunctionInfo>()->"
|
|
"ShaderType == ShaderType::COMPUTE", CCDelegateTo<CC_AMDGPU_Kernel>>,
|
|
CCIf<"State.getTarget().getSubtarget<AMDGPUSubtarget>()"#
|
|
".getGeneration() == AMDGPUSubtarget::SOUTHERN_ISLANDS", CCDelegateTo<CC_SI>>
|
|
]>;
|