Add ‘llvm.experimental.constrained.fma‘ Intrinsic.
Differential Revision: http://reviews.llvm.org/D36335
llvm-svn: 311629
diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
index 7a208cb..e0825e8 100644
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
@@ -907,6 +907,7 @@
case ISD::STRICT_FSQRT: EqOpc = ISD::FSQRT; break;
case ISD::STRICT_FPOW: EqOpc = ISD::FPOW; break;
case ISD::STRICT_FPOWI: EqOpc = ISD::FPOWI; break;
+ case ISD::STRICT_FMA: EqOpc = ISD::FMA; break;
case ISD::STRICT_FSIN: EqOpc = ISD::FSIN; break;
case ISD::STRICT_FCOS: EqOpc = ISD::FCOS; break;
case ISD::STRICT_FEXP: EqOpc = ISD::FEXP; break;
@@ -1072,6 +1073,7 @@
}
break;
case ISD::STRICT_FSQRT:
+ case ISD::STRICT_FMA:
case ISD::STRICT_FPOW:
case ISD::STRICT_FPOWI:
case ISD::STRICT_FSIN:
@@ -1240,7 +1242,7 @@
// If the index is dependent on the store we will introduce a cycle when
// creating the load (the load uses the index, and by replacing the chain
// we will make the index dependent on the load). Also, the store might be
- // dependent on the extractelement and introduce a cycle when creating
+ // dependent on the extractelement and introduce a cycle when creating
// the load.
if (SDNode::hasPredecessorHelper(ST, Visited, Worklist) ||
ST->hasPredecessor(Op.getNode()))
@@ -4065,6 +4067,10 @@
Results.push_back(ExpandFPLibCall(Node, RTLIB::FMA_F32, RTLIB::FMA_F64,
RTLIB::FMA_F80, RTLIB::FMA_F128,
RTLIB::FMA_PPCF128));
+ case ISD::STRICT_FMA:
+ Results.push_back(ExpandFPLibCall(Node, RTLIB::FMA_F32, RTLIB::FMA_F64,
+ RTLIB::FMA_F80, RTLIB::FMA_F128,
+ RTLIB::FMA_PPCF128));
break;
case ISD::FADD:
Results.push_back(ExpandFPLibCall(Node, RTLIB::ADD_F32, RTLIB::ADD_F64,
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index b415421..d00ecaf 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -6695,6 +6695,7 @@
unsigned OrigOpc = Node->getOpcode();
unsigned NewOpc;
bool IsUnary = false;
+ bool IsTernary = false;
switch (OrigOpc) {
default:
llvm_unreachable("mutateStrictFPToFP called with unexpected opcode!");
@@ -6703,6 +6704,7 @@
case ISD::STRICT_FMUL: NewOpc = ISD::FMUL; break;
case ISD::STRICT_FDIV: NewOpc = ISD::FDIV; break;
case ISD::STRICT_FREM: NewOpc = ISD::FREM; break;
+ case ISD::STRICT_FMA: NewOpc = ISD::FMA; IsTernary = true; break;
case ISD::STRICT_FSQRT: NewOpc = ISD::FSQRT; IsUnary = true; break;
case ISD::STRICT_FPOW: NewOpc = ISD::FPOW; break;
case ISD::STRICT_FPOWI: NewOpc = ISD::FPOWI; break;
@@ -6729,6 +6731,10 @@
SDNode *Res = nullptr;
if (IsUnary)
Res = MorphNodeTo(Node, NewOpc, VTs, { Node->getOperand(1) });
+ else if (IsTernary)
+ Res = MorphNodeTo(Node, NewOpc, VTs, { Node->getOperand(1),
+ Node->getOperand(2),
+ Node->getOperand(3)});
else
Res = MorphNodeTo(Node, NewOpc, VTs, { Node->getOperand(1),
Node->getOperand(2) });
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index fc441b8..1371f52 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -5432,6 +5432,7 @@
case Intrinsic::experimental_constrained_fmul:
case Intrinsic::experimental_constrained_fdiv:
case Intrinsic::experimental_constrained_frem:
+ case Intrinsic::experimental_constrained_fma:
case Intrinsic::experimental_constrained_sqrt:
case Intrinsic::experimental_constrained_pow:
case Intrinsic::experimental_constrained_powi:
@@ -5963,6 +5964,9 @@
case Intrinsic::experimental_constrained_frem:
Opcode = ISD::STRICT_FREM;
break;
+ case Intrinsic::experimental_constrained_fma:
+ Opcode = ISD::STRICT_FMA;
+ break;
case Intrinsic::experimental_constrained_sqrt:
Opcode = ISD::STRICT_FSQRT;
break;
@@ -6009,10 +6013,15 @@
SDVTList VTs = DAG.getVTList(ValueVTs);
SDValue Result;
if (FPI.isUnaryOp())
- Result = DAG.getNode(Opcode, sdl, VTs,
+ Result = DAG.getNode(Opcode, sdl, VTs,
{ Chain, getValue(FPI.getArgOperand(0)) });
+ else if (FPI.isTernaryOp())
+ Result = DAG.getNode(Opcode, sdl, VTs,
+ { Chain, getValue(FPI.getArgOperand(0)),
+ getValue(FPI.getArgOperand(1)),
+ getValue(FPI.getArgOperand(2)) });
else
- Result = DAG.getNode(Opcode, sdl, VTs,
+ Result = DAG.getNode(Opcode, sdl, VTs,
{ Chain, getValue(FPI.getArgOperand(0)),
getValue(FPI.getArgOperand(1)) });
diff --git a/llvm/lib/IR/IntrinsicInst.cpp b/llvm/lib/IR/IntrinsicInst.cpp
index 8b12c55..67bd5b6 100644
--- a/llvm/lib/IR/IntrinsicInst.cpp
+++ b/llvm/lib/IR/IntrinsicInst.cpp
@@ -14,10 +14,10 @@
// are all subclasses of the CallInst class. Note that none of these classes
// has state or virtual methods, which is an important part of this gross/neat
// hack working.
-//
+//
// In some cases, arguments to intrinsics need to be generic and are defined as
// type pointer to empty struct { }*. To access the real item of interest the
-// cast instruction needs to be stripped away.
+// cast instruction needs to be stripped away.
//
//===----------------------------------------------------------------------===//
@@ -98,7 +98,7 @@
ConstrainedFPIntrinsic::RoundingMode
ConstrainedFPIntrinsic::getRoundingMode() const {
unsigned NumOperands = getNumArgOperands();
- Metadata *MD =
+ Metadata *MD =
dyn_cast<MetadataAsValue>(getArgOperand(NumOperands - 2))->getMetadata();
if (!MD || !isa<MDString>(MD))
return rmInvalid;
@@ -118,7 +118,7 @@
ConstrainedFPIntrinsic::ExceptionBehavior
ConstrainedFPIntrinsic::getExceptionBehavior() const {
unsigned NumOperands = getNumArgOperands();
- Metadata *MD =
+ Metadata *MD =
dyn_cast<MetadataAsValue>(getArgOperand(NumOperands - 1))->getMetadata();
if (!MD || !isa<MDString>(MD))
return ebInvalid;
@@ -132,7 +132,7 @@
bool ConstrainedFPIntrinsic::isUnaryOp() const {
switch (getIntrinsicID()) {
- default:
+ default:
return false;
case Intrinsic::experimental_constrained_sqrt:
case Intrinsic::experimental_constrained_sin:
@@ -147,3 +147,13 @@
return true;
}
}
+
+bool ConstrainedFPIntrinsic::isTernaryOp() const {
+ switch (getIntrinsicID()) {
+ default:
+ return false;
+ case Intrinsic::experimental_constrained_fma:
+ return true;
+ }
+}
+
diff --git a/llvm/lib/IR/Verifier.cpp b/llvm/lib/IR/Verifier.cpp
index c5cee49..0cd6dbb 100644
--- a/llvm/lib/IR/Verifier.cpp
+++ b/llvm/lib/IR/Verifier.cpp
@@ -3973,6 +3973,7 @@
case Intrinsic::experimental_constrained_fmul:
case Intrinsic::experimental_constrained_fdiv:
case Intrinsic::experimental_constrained_frem:
+ case Intrinsic::experimental_constrained_fma:
case Intrinsic::experimental_constrained_sqrt:
case Intrinsic::experimental_constrained_pow:
case Intrinsic::experimental_constrained_powi:
@@ -4433,8 +4434,9 @@
void Verifier::visitConstrainedFPIntrinsic(ConstrainedFPIntrinsic &FPI) {
unsigned NumOperands = FPI.getNumArgOperands();
- Assert(((NumOperands == 3 && FPI.isUnaryOp()) || (NumOperands == 4)),
- "invalid arguments for constrained FP intrinsic", &FPI);
+ Assert(((NumOperands == 5 && FPI.isTernaryOp()) ||
+ (NumOperands == 3 && FPI.isUnaryOp()) || (NumOperands == 4)),
+ "invalid arguments for constrained FP intrinsic", &FPI);
Assert(isa<MetadataAsValue>(FPI.getArgOperand(NumOperands-1)),
"invalid exception behavior argument", &FPI);
Assert(isa<MetadataAsValue>(FPI.getArgOperand(NumOperands-2)),