Revert "AMDGPU: Fix handling of alignment padding in DAG argument lowering"
This reverts commit r337021.
WARNING: MemorySanitizer: use-of-uninitialized-value
#0 0x1415cd65 in void write_signed<long>(llvm::raw_ostream&, long, unsigned long, llvm::IntegerStyle) /code/llvm-project/llvm/lib/Support/NativeFormatting.cpp:95:7
#1 0x1415c900 in llvm::write_integer(llvm::raw_ostream&, long, unsigned long, llvm::IntegerStyle) /code/llvm-project/llvm/lib/Support/NativeFormatting.cpp:121:3
#2 0x1472357f in llvm::raw_ostream::operator<<(long) /code/llvm-project/llvm/lib/Support/raw_ostream.cpp:117:3
#3 0x13bb9d4 in llvm::raw_ostream::operator<<(int) /code/llvm-project/llvm/include/llvm/Support/raw_ostream.h:210:18
#4 0x3c2bc18 in void printField<unsigned int, &(amd_kernel_code_s::amd_kernel_code_version_major)>(llvm::StringRef, amd_kernel_code_s const&, llvm::raw_ostream&) /code/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp:78:23
#5 0x3c250ba in llvm::printAmdKernelCodeField(amd_kernel_code_s const&, int, llvm::raw_ostream&) /code/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp:104:5
#6 0x3c27ca3 in llvm::dumpAmdKernelCode(amd_kernel_code_s const*, llvm::raw_ostream&, char const*) /code/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp:113:5
#7 0x3a46e6c in llvm::AMDGPUTargetAsmStreamer::EmitAMDKernelCodeT(amd_kernel_code_s const&) /code/llvm-project/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp:161:3
#8 0xd371e4 in llvm::AMDGPUAsmPrinter::EmitFunctionBodyStart() /code/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp:204:26
[...]
Uninitialized value was created by an allocation of 'KernelCode' in the stack frame of function '_ZN4llvm16AMDGPUAsmPrinter21EmitFunctionBodyStartEv'
#0 0xd36650 in llvm::AMDGPUAsmPrinter::EmitFunctionBodyStart() /code/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp:192
llvm-svn: 337079
diff --git a/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp b/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp
index 113d624..4110e6a 100644
--- a/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/R600ISelLowering.cpp
@@ -50,6 +50,18 @@
using namespace llvm;
+static bool allocateKernArg(unsigned ValNo, MVT ValVT, MVT LocVT,
+ CCValAssign::LocInfo LocInfo,
+ ISD::ArgFlagsTy ArgFlags, CCState &State) {
+ MachineFunction &MF = State.getMachineFunction();
+ AMDGPUMachineFunction *MFI = MF.getInfo<AMDGPUMachineFunction>();
+
+ uint64_t Offset = MFI->allocateKernArg(LocVT.getStoreSize(),
+ ArgFlags.getOrigAlign());
+ State.addLoc(CCValAssign::getCustomMem(ValNo, ValVT, Offset, LocVT, LocInfo));
+ return true;
+}
+
#include "R600GenCallingConv.inc"
R600TargetLowering::R600TargetLowering(const TargetMachine &TM,
@@ -222,7 +234,7 @@
setOperationAction(ISD::FMA, MVT::f32, Expand);
setOperationAction(ISD::FMA, MVT::f64, Expand);
}
-
+
// FIXME: This was moved from AMDGPUTargetLowering, I'm not sure if we
// need it for R600.
if (!Subtarget->hasFP32Denormals())
@@ -1571,7 +1583,7 @@
case CallingConv::C:
case CallingConv::Fast:
case CallingConv::Cold:
- llvm_unreachable("kernels should not be handled here");
+ return CC_R600_Kernel;
case CallingConv::AMDGPU_VS:
case CallingConv::AMDGPU_GS:
case CallingConv::AMDGPU_PS:
@@ -1646,12 +1658,13 @@
unsigned ValBase = ArgLocs[In.getOrigArgIndex()].getLocMemOffset();
unsigned PartOffset = VA.getLocMemOffset();
+ unsigned Offset = Subtarget->getExplicitKernelArgOffset(MF.getFunction()) +
+ VA.getLocMemOffset();
MachinePointerInfo PtrInfo(UndefValue::get(PtrTy), PartOffset - ValBase);
SDValue Arg = DAG.getLoad(
ISD::UNINDEXED, Ext, VT, DL, Chain,
- DAG.getConstant(PartOffset, DL, MVT::i32), DAG.getUNDEF(MVT::i32),
- PtrInfo,
+ DAG.getConstant(Offset, DL, MVT::i32), DAG.getUNDEF(MVT::i32), PtrInfo,
MemVT, /* Alignment = */ 4, MachineMemOperand::MONonTemporal |
MachineMemOperand::MODereferenceable |
MachineMemOperand::MOInvariant);