[PATCH] D59666: AMDGPU: HIP compiler option -finstrument-functions flag
Aakanksha Patil via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Tue May 14 12:42:34 PDT 2019
aakanksha555 updated this revision to Diff 199493.
aakanksha555 marked 5 inline comments as done.
aakanksha555 added a comment.
Return 0 for kernels and non-zero arguments to llvm.returnaddress.
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D59666/new/
https://reviews.llvm.org/D59666
Files:
lib/Target/AMDGPU/SIISelLowering.cpp
lib/Target/AMDGPU/SIISelLowering.h
test/CodeGen/AMDGPU/returnaddress.ll
Index: test/CodeGen/AMDGPU/returnaddress.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/returnaddress.ll
@@ -0,0 +1,33 @@
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefix=GCN %s
+
+; GCN-LABEL: {{^}}func1
+; GCN: v_mov_b32_e32 v0, s30
+; GCN: v_mov_b32_e32 v1, s31
+; GCN: s_setpc_b64 s[30:31]
+define i8* @func1() nounwind {
+entry:
+ %0 = tail call i8* @llvm.returnaddress(i32 0)
+ ret i8* %0
+}
+
+; GCN-LABEL: {{^}}func2
+; GCN: v_mov_b32_e32 v0, 0
+; GCN: v_mov_b32_e32 v1, 0
+; GCN: s_setpc_b64 s[30:31]
+define i8* @func2() nounwind {
+entry:
+ %0 = tail call i8* @llvm.returnaddress(i32 1)
+ ret i8* %0
+}
+
+; GCN-LABEL: {{^}}func3
+; GCN: v_mov_b32_e32 v0, 0
+; GCN: v_mov_b32_e32 v1, v0
+define amdgpu_kernel void @func3(i8** %out) nounwind {
+entry:
+ %tmp = tail call i8* @llvm.returnaddress(i32 0)
+ store i8* %tmp, i8** %out, align 4
+ ret void
+}
+
+declare i8* @llvm.returnaddress(i32) nounwind readnone
Index: lib/Target/AMDGPU/SIISelLowering.h
===================================================================
--- lib/Target/AMDGPU/SIISelLowering.h
+++ lib/Target/AMDGPU/SIISelLowering.h
@@ -89,7 +89,7 @@
SDValue LowerTrig(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerATOMIC_CMP_SWAP(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBRCOND(SDValue Op, SelectionDAG &DAG) const;
-
+ SDValue LowerRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
SDValue adjustLoadValueType(unsigned Opcode, MemSDNode *M,
SelectionDAG &DAG, ArrayRef<SDValue> Ops,
bool IsIntrinsic = false) const;
Index: lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/SIISelLowering.cpp
+++ lib/Target/AMDGPU/SIISelLowering.cpp
@@ -3693,6 +3693,7 @@
switch (Op.getOpcode()) {
default: return AMDGPUTargetLowering::LowerOperation(Op, DAG);
case ISD::BRCOND: return LowerBRCOND(Op, DAG);
+ case ISD::RETURNADDR: return LowerRETURNADDR(Op, DAG);
case ISD::LOAD: {
SDValue Result = LowerLOAD(Op, DAG);
assert((!Result.getNode() ||
@@ -4151,6 +4152,31 @@
return Chain;
}
+SDValue SITargetLowering::LowerRETURNADDR(SDValue Op,
+ SelectionDAG &DAG) const {
+ MVT VT = Op.getSimpleValueType();
+ SDLoc DL(Op);
+ // Checking the depth
+ if (cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue() != 0)
+ return DAG.getConstant(0, DL, VT);
+
+ MachineFunction &MF = DAG.getMachineFunction();
+ const SIMachineFunctionInfo *Info = MF.getInfo<SIMachineFunctionInfo>();
+ // Check for kernel and shader functions
+ if (Info->isEntryFunction())
+ return DAG.getConstant(0, DL, VT);
+
+ MachineFrameInfo &MFI = MF.getFrameInfo();
+ // There is a call to @llvm.returnaddress in this function
+ MFI.setReturnAddressIsTaken(true);
+
+ const SIRegisterInfo *TRI = getSubtarget()->getRegisterInfo();
+ // Get the return address reg and mark it as an implicit live-in
+ unsigned Reg = MF.addLiveIn(TRI->getReturnAddressReg(MF), getRegClassFor(VT));
+
+ return DAG.getCopyFromReg(DAG.getEntryNode(), DL, Reg, VT);
+}
+
SDValue SITargetLowering::getFPExtOrFPTrunc(SelectionDAG &DAG,
SDValue Op,
const SDLoc &DL,
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D59666.199493.patch
Type: text/x-patch
Size: 3433 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190514/8be03772/attachment.bin>
More information about the llvm-commits
mailing list