Add constrained intrinsics for some libm-equivalent operations

[andrew.w.kaylor]

Summary

This patch adds constrained versions of some libm-equivalent floating point operations for which non-constrained intrinsics currently exist.

The purpose of the constrained intrinsics is to force the optimizer to respect the restrictions that will be necessary to support things like the STDC FENV_ACCESS ON pragma without interfering with optimizations when these restrictions are not needed. This is a follow-up to D27028.

There are additional libm-equivalent operations which may need to be handled in a future patch. In addition, it will be necessary to update the direct manipulation of libm function calls to prevent unwanted optimizations when FP environment access is enabled.

[andrew.w.kaylor]

Ping.

[craig.topper]

docs/LangRef.rst

12557 ↗

(On Diff #96040)

Probably doesn't matter to the output, but why are there two spaces after metadata on the second line?

include/llvm/CodeGen/ISDOpcodes.h

254 ↗

(On Diff #96040)

Should this say "functions" rather than "operators"?

lib/CodeGen/SelectionDAG/SelectionDAG.cpp

6533 ↗

(On Diff #96040)

LLVM style is to have "case" aligned with "switch"

6534 ↗

(On Diff #96040)

Use llvm_unreachable instead of assert(false). No return required if you use that.

lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp

946 ↗

(On Diff #96040)

Why not just merge this function call into the 'if'?

lib/IR/IntrinsicInst.cpp

149 ↗

(On Diff #96040)

This unreachable shouldn't be necessary with the default in the switch.

lib/IR/Verifier.cpp

4331 ↗

(On Diff #96040)

Don't unary intrinsics only have 3 operands and binary have 4? Is there a hidden one I'm missing?

[andrew.w.kaylor]

docs/LangRef.rst

12557 ↗

(On Diff #96040)

Editing error?

include/llvm/CodeGen/ISDOpcodes.h

254 ↗

(On Diff #96040)

It probably should say 'intrinsics'

lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp

946 ↗

(On Diff #96040)

The original intention was that this value would be used again after the Select() call to decide when we needed to do more work to a selected node. I suspect that's not going to happen here after all so I can probably get rid of this value and the comment below the Select().

lib/IR/IntrinsicInst.cpp

149 ↗

(On Diff #96040)

I agree, but I have a vague memory that I was getting a compiler warning here. I'll look into that.

lib/IR/Verifier.cpp

4331 ↗

(On Diff #96040)

Yeah, I should be using getNumArgOperands() here instead. The extra operand is the function.

[andrew.w.kaylor]

Addressed review comments
Updated to latest source base

[andrew.w.kaylor]

Fixed LangRef spacing issues in more places

[craig.topper]

docs/LangRef.rst

13313 ↗

(On Diff #99810)

environment is misspelled.

13353 ↗

(On Diff #99810)

environment is misspelled

lib/CodeGen/SelectionDAG/SelectionDAG.cpp

6551 ↗

(On Diff #99810)

Lowercase mutate to match the function name?

[andrew.w.kaylor]

Addressed review feedback

[craig.topper]

LGTM

llvm/trunk/docs/LangRef.rst

 Syntax:
 """""""
 
 ::
 
       declare <type> 
       @llvm.experimental.constrained.fadd(<type> <op1>, <type> <op2>,
                                           metadata <rounding mode>,
-                                          metadata  <exception behavior>)
+                                          metadata <exception behavior>)
 
 Overview:
 """""""""
 
 The '``llvm.experimental.constrained.fadd``' intrinsic returns the sum of its
 two operands.
 
 

 Syntax:
 """""""
 
 ::
 
       declare <type> 
       @llvm.experimental.constrained.fsub(<type> <op1>, <type> <op2>,
                                           metadata <rounding mode>,
-                                          metadata  <exception behavior>)
+                                          metadata <exception behavior>)
 
 Overview:
 """""""""
 
 The '``llvm.experimental.constrained.fsub``' intrinsic returns the difference
 of its two operands.
 
 

 Syntax:
 """""""
 
 ::
 
       declare <type> 
       @llvm.experimental.constrained.fmul(<type> <op1>, <type> <op2>,
                                           metadata <rounding mode>,
-                                          metadata  <exception behavior>)
+                                          metadata <exception behavior>)
 
 Overview:
 """""""""
 
 The '``llvm.experimental.constrained.fmul``' intrinsic returns the product of
 its two operands.
 
 

 Syntax:
 """""""
 
 ::
 
       declare <type> 
       @llvm.experimental.constrained.fdiv(<type> <op1>, <type> <op2>,
                                           metadata <rounding mode>,
-                                          metadata  <exception behavior>)
+                                          metadata <exception behavior>)
 
 Overview:
 """""""""
 
 The '``llvm.experimental.constrained.fdiv``' intrinsic returns the quotient of
 its two operands.
 
 

 Syntax:
 """""""
 
 ::
 
       declare <type> 
       @llvm.experimental.constrained.frem(<type> <op1>, <type> <op2>,
                                           metadata <rounding mode>,
-                                          metadata  <exception behavior>)
+                                          metadata <exception behavior>)
 
 Overview:
 """""""""
 
 The '``llvm.experimental.constrained.frem``' intrinsic returns the remainder
 from the division of its two operands.
 
 

 Semantics:
 """"""""""
 
 The value produced is the floating point remainder from the division of the two
 value operands and has the same type as the operands.  The remainder has the
 same sign as the dividend. 
 
 
+Constrained libm-equivalent Intrinsics
+--------------------------------------
+
+In addition to the basic floating point operations for which constrained
+intrinsics are described above, there are constrained versions of various
+operations which provide equivalent behavior to a corresponding libm function.
+These intrinsics allow the precise behavior of these operations with respect to
+rounding mode and exception behavior to be controlled.
+
+As with the basic constrained floating point intrinsics, the rounding mode
+and exception behavior arguments only control the behavior of the optimizer.
+They do not change the runtime floating point environment.
+
+
+'``llvm.experimental.constrained.sqrt``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.sqrt(<type> <op1>,
+                                          metadata <rounding mode>,
+                                          metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.sqrt``' intrinsic returns the square root
+of the specified value, returning the same value as the libm '``sqrt``'
+functions would, but without setting ``errno``.
+
+Arguments:
+""""""""""
+
+The first argument and the return type are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the nonnegative square root of the specified value.
+If the value is less than negative zero, a floating point exception occurs
+and the the return value is architecture specific.
+
+
+'``llvm.experimental.constrained.pow``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.pow(<type> <op1>, <type> <op2>,
+                                         metadata <rounding mode>,
+                                         metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.pow``' intrinsic returns the first operand
+raised to the (positive or negative) power specified by the second operand.
+
+Arguments:
+""""""""""
+
+The first two arguments and the return value are floating point numbers of the
+same type.  The second argument specifies the power to which the first argument
+should be raised.
+
+The third and fourth arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the first value raised to the second power,
+returning the same values as the libm ``pow`` functions would, and
+handles error conditions in the same way.
+
+
+'``llvm.experimental.constrained.powi``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.powi(<type> <op1>, i32 <op2>,
+                                          metadata <rounding mode>,
+                                          metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.powi``' intrinsic returns the first operand
+raised to the (positive or negative) power specified by the second operand. The
+order of evaluation of multiplications is not defined. When a vector of floating
+point type is used, the second argument remains a scalar integer value.
+
+
+Arguments:
+""""""""""
+
+The first argument and the return value are floating point numbers of the same
+type.  The second argument is a 32-bit signed integer specifying the power to
+which the first argument should be raised.
+
+The third and fourth arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the first value raised to the second power with an
+unspecified sequence of rounding operations.
+
+
+'``llvm.experimental.constrained.sin``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.sin(<type> <op1>,
+                                         metadata <rounding mode>,
+                                         metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.sin``' intrinsic returns the sine of the
+first operand.
+
+Arguments:
+""""""""""
+
+The first argument and the return type are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the sine of the specified operand, returning the
+same values as the libm ``sin`` functions would, and handles error
+conditions in the same way.
+
+
+'``llvm.experimental.constrained.cos``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.cos(<type> <op1>,
+                                         metadata <rounding mode>,
+                                         metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.cos``' intrinsic returns the cosine of the
+first operand.
+
+Arguments:
+""""""""""
+
+The first argument and the return type are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the cosine of the specified operand, returning the
+same values as the libm ``cos`` functions would, and handles error
+conditions in the same way.
+
+
+'``llvm.experimental.constrained.exp``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.exp(<type> <op1>,
+                                         metadata <rounding mode>,
+                                         metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.exp``' intrinsic computes the base-e
+exponential of the specified value.
+
+Arguments:
+""""""""""
+
+The first argument and the return value are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the same values as the libm ``exp`` functions
+would, and handles error conditions in the same way.
+
+
+'``llvm.experimental.constrained.exp2``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.exp2(<type> <op1>,
+                                          metadata <rounding mode>,
+                                          metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.exp2``' intrinsic computes the base-2
+exponential of the specified value.
+
+
+Arguments:
+""""""""""
+
+The first argument and the return value are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the same values as the libm ``exp2`` functions
+would, and handles error conditions in the same way.
+
+
+'``llvm.experimental.constrained.log``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.log(<type> <op1>,
+                                         metadata <rounding mode>,
+                                         metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.log``' intrinsic computes the base-e
+logarithm of the specified value.
+
+Arguments:
+""""""""""
+
+The first argument and the return value are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+
+Semantics:
+""""""""""
+
+This function returns the same values as the libm ``log`` functions
+would, and handles error conditions in the same way.
+
+
+'``llvm.experimental.constrained.log10``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.log10(<type> <op1>,
+                                           metadata <rounding mode>,
+                                           metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.log10``' intrinsic computes the base-10
+logarithm of the specified value.
+
+Arguments:
+""""""""""
+
+The first argument and the return value are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the same values as the libm ``log10`` functions
+would, and handles error conditions in the same way.
+
+
+'``llvm.experimental.constrained.log2``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.log2(<type> <op1>,
+                                          metadata <rounding mode>,
+                                          metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.log2``' intrinsic computes the base-2
+logarithm of the specified value.
+
+Arguments:
+""""""""""
+
+The first argument and the return value are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the same values as the libm ``log2`` functions
+would, and handles error conditions in the same way.
+
+
+'``llvm.experimental.constrained.rint``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.rint(<type> <op1>,
+                                          metadata <rounding mode>,
+                                          metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.rint``' intrinsic returns the first
+operand rounded to the nearest integer. It may raise an inexact floating point
+exception if the operand is not an integer.
+
+Arguments:
+""""""""""
+
+The first argument and the return value are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the same values as the libm ``rint`` functions
+would, and handles error conditions in the same way.  The rounding mode is
+described, not determined, by the rounding mode argument.  The actual rounding
+mode is determined by the runtime floating point environment.  The rounding
+mode argument is only intended as information to the compiler.
+
+
+'``llvm.experimental.constrained.nearbyint``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare <type> 
+      @llvm.experimental.constrained.nearbyint(<type> <op1>,
+                                               metadata <rounding mode>,
+                                               metadata <exception behavior>)
+
+Overview:
+"""""""""
+
+The '``llvm.experimental.constrained.nearbyint``' intrinsic returns the first
+operand rounded to the nearest integer. It will not raise an inexact floating
+point exception if the operand is not an integer.
+
+
+Arguments:
+""""""""""
+
+The first argument and the return value are floating point numbers of the same
+type.
+
+The second and third arguments specify the rounding mode and exception
+behavior as described above.
+
+Semantics:
+""""""""""
+
+This function returns the same values as the libm ``nearbyint`` functions
+would, and handles error conditions in the same way.  The rounding mode is
+described, not determined, by the rounding mode argument.  The actual rounding
+mode is determined by the runtime floating point environment.  The rounding
+mode argument is only intended as information to the compiler.
+
+
 General Intrinsics
 ------------------
 
 This class of intrinsics is designed to be generic and has no specific
 purpose.
 
 '``llvm.var.annotation``' Intrinsic
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

llvm/trunk/include/llvm/CodeGen/ISDOpcodes.h

enum NodeType {
     FADD, FSUB, FMUL, FDIV, FREM,
 
     /// Constrained versions of the binary floating point operators.
     /// These will be lowered to the simple operators before final selection.
     /// They are used to limit optimizations while the DAG is being
     /// optimized.
     STRICT_FADD, STRICT_FSUB, STRICT_FMUL, STRICT_FDIV, STRICT_FREM,
 
+    /// Constrained versions of libm-equivalent floating point intrinsics.
+    /// These will be lowered to the equivalent non-constrained pseudo-op
+    /// (or expanded to the equivalent library call) before final selection.
+    /// They are used to limit optimizations while the DAG is being optimized.
+    STRICT_FSQRT, STRICT_FPOW, STRICT_FPOWI, STRICT_FSIN, STRICT_FCOS,
+    STRICT_FEXP, STRICT_FEXP2, STRICT_FLOG, STRICT_FLOG10, STRICT_FLOG2,
+    STRICT_FRINT, STRICT_FNEARBYINT,
+
     /// FMA - Perform a * b + c with no intermediate rounding step.
     FMA,
 
     /// FMAD - Perform a * b + c, while getting the same result as the
     /// separately rounded operations.
     FMAD,
 
     /// FCOPYSIGN(X, Y) - Return the value of X with the sign of Y.  NOTE: This

llvm/trunk/include/llvm/CodeGen/SelectionDAG.h

#endif
   SDNode *SelectNodeTo(SDNode *N, unsigned TargetOpc, SDVTList VTs,
                        ArrayRef<SDValue> Ops);
 
   /// This *mutates* the specified node to have the specified
   /// return type, opcode, and operands.
   SDNode *MorphNodeTo(SDNode *N, unsigned Opc, SDVTList VTs,
                       ArrayRef<SDValue> Ops);
 
+  /// Mutate the specified strict FP node to its non-strict equivalent,
+  /// unlinking the node from its chain and dropping the metadata arguments.
+  /// The node must be a strict FP node.
+  SDNode *mutateStrictFPToFP(SDNode *Node);
+
   /// These are used for target selectors to create a new node
   /// with specified return type(s), MachineInstr opcode, and operands.
   ///
   /// Note that getMachineNode returns the resultant node.  If there is already
   /// a node of the specified opcode and operands, it returns that node instead
   /// of the current one.
   MachineSDNode *getMachineNode(unsigned Opcode, const SDLoc &dl, EVT VT);
   MachineSDNode *getMachineNode(unsigned Opcode, const SDLoc &dl, EVT VT,

llvm/trunk/include/llvm/CodeGen/SelectionDAGNodes.h

public:
   /// MemSDNode. For such nodes, we need some extra state to determine the
   /// proper classof relationship.
   bool isMemIntrinsic() const {
     return (NodeType == ISD::INTRINSIC_W_CHAIN ||
             NodeType == ISD::INTRINSIC_VOID) &&
            SDNodeBits.IsMemIntrinsic;
   }
 
+  /// Test if this node is a strict floating point pseudo-op.
+  bool isStrictFPOpcode() {
+    switch (NodeType) {
+      default: 
+        return false;
+      case ISD::STRICT_FADD:
+      case ISD::STRICT_FSUB:
+      case ISD::STRICT_FMUL:
+      case ISD::STRICT_FDIV:
+      case ISD::STRICT_FREM:
+      case ISD::STRICT_FSQRT:
+      case ISD::STRICT_FPOW:
+      case ISD::STRICT_FPOWI:
+      case ISD::STRICT_FSIN:
+      case ISD::STRICT_FCOS:
+      case ISD::STRICT_FEXP:
+      case ISD::STRICT_FEXP2:
+      case ISD::STRICT_FLOG:
+      case ISD::STRICT_FLOG10:
+      case ISD::STRICT_FLOG2:
+      case ISD::STRICT_FRINT:
+      case ISD::STRICT_FNEARBYINT:
+        return true;
+    }
+  }
+
   /// Test if this node has a post-isel opcode, directly
   /// corresponding to a MachineInstr opcode.
   bool isMachineOpcode() const { return NodeType < 0; }
 
   /// This may only be called if isMachineOpcode returns
   /// true. It returns the MachineInstr opcode value that the node's opcode
   /// corresponds to.
   unsigned getMachineOpcode() const {

llvm/trunk/include/llvm/IR/IntrinsicInst.h

public:
 
     enum ExceptionBehavior {
       ebInvalid,
       ebIgnore,
       ebMayTrap,
       ebStrict
     };
 
+    bool isUnaryOp() const;
     RoundingMode getRoundingMode() const;
     ExceptionBehavior getExceptionBehavior() const;
 
     // Methods for support type inquiry through isa, cast, and dyn_cast:
     static inline bool classof(const IntrinsicInst *I) {
       switch (I->getIntrinsicID()) {
       case Intrinsic::experimental_constrained_fadd:
       case Intrinsic::experimental_constrained_fsub:
       case Intrinsic::experimental_constrained_fmul:
       case Intrinsic::experimental_constrained_fdiv:
       case Intrinsic::experimental_constrained_frem:
+      case Intrinsic::experimental_constrained_sqrt:
+      case Intrinsic::experimental_constrained_pow:
+      case Intrinsic::experimental_constrained_powi:
+      case Intrinsic::experimental_constrained_sin:
+      case Intrinsic::experimental_constrained_cos:
+      case Intrinsic::experimental_constrained_exp:
+      case Intrinsic::experimental_constrained_exp2:
+      case Intrinsic::experimental_constrained_log:
+      case Intrinsic::experimental_constrained_log10:
+      case Intrinsic::experimental_constrained_log2:
+      case Intrinsic::experimental_constrained_rint:
+      case Intrinsic::experimental_constrained_nearbyint:
         return true;
       default: return false;
       }
     }
     static inline bool classof(const Value *V) {
       return isa<IntrinsicInst>(V) && classof(cast<IntrinsicInst>(V));
     }
   };

llvm/trunk/include/llvm/IR/Intrinsics.td

def int_experimental_constrained_fdiv : Intrinsic<[ llvm_anyfloat_ty ],
                                                       LLVMMatchType<0>,
                                                       llvm_metadata_ty,
                                                       llvm_metadata_ty ]>;
   def int_experimental_constrained_frem : Intrinsic<[ llvm_anyfloat_ty ],
                                                     [ LLVMMatchType<0>,
                                                       LLVMMatchType<0>,
                                                       llvm_metadata_ty,
                                                       llvm_metadata_ty ]>;
+
+  // These intrinsics are sensitive to the rounding mode so we need constrained
+  // versions of each of them.  When strict rounding and exception control are
+  // not required the non-constrained versions of these intrinsics should be
+  // used.
+  def int_experimental_constrained_sqrt : Intrinsic<[ llvm_anyfloat_ty ],
+                                                    [ LLVMMatchType<0>,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_powi : Intrinsic<[ llvm_anyfloat_ty ],
+                                                    [ LLVMMatchType<0>,
+                                                      llvm_i32_ty,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_sin  : Intrinsic<[ llvm_anyfloat_ty ],
+                                                    [ LLVMMatchType<0>,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_cos  : Intrinsic<[ llvm_anyfloat_ty ],
+                                                    [ LLVMMatchType<0>,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_pow  : Intrinsic<[ llvm_anyfloat_ty ],
+                                                    [ LLVMMatchType<0>,
+                                                      LLVMMatchType<0>,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_log  : Intrinsic<[ llvm_anyfloat_ty ],
+                                                    [ LLVMMatchType<0>,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_log10: Intrinsic<[ llvm_anyfloat_ty ],
+                                                    [ LLVMMatchType<0>,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_log2 : Intrinsic<[ llvm_anyfloat_ty ],
+                                                    [ LLVMMatchType<0>,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_exp  : Intrinsic<[ llvm_anyfloat_ty ], 
+                                                    [ LLVMMatchType<0>,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_exp2 : Intrinsic<[ llvm_anyfloat_ty ],
+                                                    [ LLVMMatchType<0>,
+                                                      llvm_metadata_ty,
+                                                      llvm_metadata_ty ]>;
+  def int_experimental_constrained_rint  : Intrinsic<[ llvm_anyfloat_ty ],
+                                                     [ LLVMMatchType<0>,
+                                                       llvm_metadata_ty,
+                                                       llvm_metadata_ty ]>;
+  def int_experimental_constrained_nearbyint : Intrinsic<[ llvm_anyfloat_ty ],
+                                                         [ LLVMMatchType<0>,
+                                                           llvm_metadata_ty,
+                                                           llvm_metadata_ty ]>;
 }
-// FIXME: Add intrinsic for fcmp, fptrunc, fpext, fptoui and fptosi.
+// FIXME: Add intrinsics for fcmp, fptrunc, fpext, fptoui and fptosi.
+// FIXME: Add intrinsics for fabs, copysign, floor, ceil, trunc and round?
 
 
 //===------------------------- Expect Intrinsics --------------------------===//
 //
 def int_expect : Intrinsic<[llvm_anyint_ty], [LLVMMatchType<0>,
                                               LLVMMatchType<0>], [IntrNoMem]>;
 
 //===-------------------- Bit Manipulation Intrinsics ---------------------===//

llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp

if (Chain.getNode() != Node) {
     if (UpdatedNodes) {
       UpdatedNodes->insert(Value.getNode());
       UpdatedNodes->insert(Chain.getNode());
     }
     ReplacedNode(Node);
   }
 }
 
+static TargetLowering::LegalizeAction
+getStrictFPOpcodeAction(const TargetLowering &TLI, unsigned Opcode, EVT VT) {
+  unsigned EqOpc;
+  switch (Opcode) {
+    default: llvm_unreachable("Unexpected FP pseudo-opcode");
+    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_FSIN: EqOpc = ISD::FSIN; break;
+    case ISD::STRICT_FCOS: EqOpc = ISD::FCOS; break;
+    case ISD::STRICT_FEXP: EqOpc = ISD::FEXP; break;
+    case ISD::STRICT_FEXP2: EqOpc = ISD::FEXP2; break;
+    case ISD::STRICT_FLOG: EqOpc = ISD::FLOG; break;
+    case ISD::STRICT_FLOG10: EqOpc = ISD::FLOG10; break;
+    case ISD::STRICT_FLOG2: EqOpc = ISD::FLOG2; break;
+    case ISD::STRICT_FRINT: EqOpc = ISD::FRINT; break;
+    case ISD::STRICT_FNEARBYINT: EqOpc = ISD::FNEARBYINT; break;
+  }
+
+  auto Action = TLI.getOperationAction(EqOpc, VT);
+
+  // We don't currently handle Custom or Promote for strict FP pseudo-ops.
+  // For now, we just expand for those cases.
+  if (Action != TargetLowering::Legal)
+    Action = TargetLowering::Expand;
+
+  // ISD::FPOWI returns 'Legal' even though it should be expanded.
+  if (Opcode == ISD::STRICT_FPOWI && Action == TargetLowering::Legal)
+    Action = TargetLowering::Expand;
+
+  return Action;
+}
+
 /// Return a legal replacement for the given operation, with all legal operands.
 void SelectionDAGLegalize::LegalizeOp(SDNode *Node) {
   DEBUG(dbgs() << "\nLegalizing: "; Node->dump(&DAG));
 
   if (Node->getOpcode() == ISD::TargetConstant) // Allow illegal target nodes.
     return;
 
 #ifndef NDEBUG
if (Action == TargetLowering::Expand) {
       SDValue NewVal;
       NewVal = DAG.getNode(ISD::TRAP, SDLoc(Node), Node->getVTList(),
                            Node->getOperand(0));
       ReplaceNode(Node, NewVal.getNode());
       LegalizeOp(NewVal.getNode());
       return;
     }
     break;
+  case ISD::STRICT_FSQRT:
+  case ISD::STRICT_FPOW:
+  case ISD::STRICT_FPOWI:
+  case ISD::STRICT_FSIN:
+  case ISD::STRICT_FCOS:
+  case ISD::STRICT_FEXP:
+  case ISD::STRICT_FEXP2:
+  case ISD::STRICT_FLOG:
+  case ISD::STRICT_FLOG10:
+  case ISD::STRICT_FLOG2:
+  case ISD::STRICT_FRINT:
+  case ISD::STRICT_FNEARBYINT:
+    // These pseudo-ops get legalized as if they were their non-strict
+    // equivalent.  For instance, if ISD::FSQRT is legal then ISD::STRICT_FSQRT
+    // is also legal, but if ISD::FSQRT requires expansion then so does
+    // ISD::STRICT_FSQRT.
+    Action = getStrictFPOpcodeAction(TLI, Node->getOpcode(),
+                                     Node->getValueType(0));
+    break;
 
   default:
     if (Node->getOpcode() >= ISD::BUILTIN_OP_END) {
       Action = TargetLowering::Legal;
     } else {
       Action = TLI.getOperationAction(Node->getOpcode(), Node->getValueType(0));
     }
     break;

 }
 
 SDValue SelectionDAGLegalize::ExpandFPLibCall(SDNode* Node,
                                               RTLIB::Libcall Call_F32,
                                               RTLIB::Libcall Call_F64,
                                               RTLIB::Libcall Call_F80,
                                               RTLIB::Libcall Call_F128,
                                               RTLIB::Libcall Call_PPCF128) {
+  if (Node->isStrictFPOpcode())
+    Node = DAG.mutateStrictFPToFP(Node);
+
   RTLIB::Libcall LC;
   switch (Node->getSimpleValueType(0).SimpleTy) {
   default: llvm_unreachable("Unexpected request for libcall!");
   case MVT::f32: LC = Call_F32; break;
   case MVT::f64: LC = Call_F64; break;
   case MVT::f80: LC = Call_F80; break;
   case MVT::f128: LC = Call_F128; break;
   case MVT::ppcf128: LC = Call_PPCF128; break;
Results.push_back(ExpandFPLibCall(Node, RTLIB::FMIN_F32, RTLIB::FMIN_F64,
                                       RTLIB::FMIN_PPCF128));
     break;
   case ISD::FMAXNUM:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::FMAX_F32, RTLIB::FMAX_F64,
                                       RTLIB::FMAX_F80, RTLIB::FMAX_F128,
                                       RTLIB::FMAX_PPCF128));
     break;
   case ISD::FSQRT:
+  case ISD::STRICT_FSQRT:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::SQRT_F32, RTLIB::SQRT_F64,
                                       RTLIB::SQRT_F80, RTLIB::SQRT_F128,
                                       RTLIB::SQRT_PPCF128));
     break;
   case ISD::FSIN:
+  case ISD::STRICT_FSIN:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::SIN_F32, RTLIB::SIN_F64,
                                       RTLIB::SIN_F80, RTLIB::SIN_F128,
                                       RTLIB::SIN_PPCF128));
     break;
   case ISD::FCOS:
+  case ISD::STRICT_FCOS:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::COS_F32, RTLIB::COS_F64,
                                       RTLIB::COS_F80, RTLIB::COS_F128,
                                       RTLIB::COS_PPCF128));
     break;
   case ISD::FSINCOS:
     // Expand into sincos libcall.
     ExpandSinCosLibCall(Node, Results);
     break;
   case ISD::FLOG:
+  case ISD::STRICT_FLOG:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG_F32, RTLIB::LOG_F64,
                                       RTLIB::LOG_F80, RTLIB::LOG_F128,
                                       RTLIB::LOG_PPCF128));
     break;
   case ISD::FLOG2:
+  case ISD::STRICT_FLOG2:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG2_F32, RTLIB::LOG2_F64,
                                       RTLIB::LOG2_F80, RTLIB::LOG2_F128,
                                       RTLIB::LOG2_PPCF128));
     break;
   case ISD::FLOG10:
+  case ISD::STRICT_FLOG10:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG10_F32, RTLIB::LOG10_F64,
                                       RTLIB::LOG10_F80, RTLIB::LOG10_F128,
                                       RTLIB::LOG10_PPCF128));
     break;
   case ISD::FEXP:
+  case ISD::STRICT_FEXP:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::EXP_F32, RTLIB::EXP_F64,
                                       RTLIB::EXP_F80, RTLIB::EXP_F128,
                                       RTLIB::EXP_PPCF128));
     break;
   case ISD::FEXP2:
+  case ISD::STRICT_FEXP2:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::EXP2_F32, RTLIB::EXP2_F64,
                                       RTLIB::EXP2_F80, RTLIB::EXP2_F128,
                                       RTLIB::EXP2_PPCF128));
     break;
   case ISD::FTRUNC:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::TRUNC_F32, RTLIB::TRUNC_F64,
                                       RTLIB::TRUNC_F80, RTLIB::TRUNC_F128,
                                       RTLIB::TRUNC_PPCF128));
     break;
   case ISD::FFLOOR:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::FLOOR_F32, RTLIB::FLOOR_F64,
                                       RTLIB::FLOOR_F80, RTLIB::FLOOR_F128,
                                       RTLIB::FLOOR_PPCF128));
     break;
   case ISD::FCEIL:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::CEIL_F32, RTLIB::CEIL_F64,
                                       RTLIB::CEIL_F80, RTLIB::CEIL_F128,
                                       RTLIB::CEIL_PPCF128));
     break;
   case ISD::FRINT:
+  case ISD::STRICT_FRINT:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::RINT_F32, RTLIB::RINT_F64,
                                       RTLIB::RINT_F80, RTLIB::RINT_F128,
                                       RTLIB::RINT_PPCF128));
     break;
   case ISD::FNEARBYINT:
+  case ISD::STRICT_FNEARBYINT:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::NEARBYINT_F32,
                                       RTLIB::NEARBYINT_F64,
                                       RTLIB::NEARBYINT_F80,
                                       RTLIB::NEARBYINT_F128,
                                       RTLIB::NEARBYINT_PPCF128));
     break;
   case ISD::FROUND:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::ROUND_F32,
                                       RTLIB::ROUND_F64,
                                       RTLIB::ROUND_F80,
                                       RTLIB::ROUND_F128,
                                       RTLIB::ROUND_PPCF128));
     break;
   case ISD::FPOWI:
+  case ISD::STRICT_FPOWI:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::POWI_F32, RTLIB::POWI_F64,
                                       RTLIB::POWI_F80, RTLIB::POWI_F128,
                                       RTLIB::POWI_PPCF128));
     break;
   case ISD::FPOW:
+  case ISD::STRICT_FPOW:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::POW_F32, RTLIB::POW_F64,
                                       RTLIB::POW_F80, RTLIB::POW_F128,
                                       RTLIB::POW_PPCF128));
     break;
   case ISD::FDIV:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::DIV_F32, RTLIB::DIV_F64,
                                       RTLIB::DIV_F80, RTLIB::DIV_F128,
                                       RTLIB::DIV_PPCF128));

llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAG.cpp

if (!DeadNodeSet.empty()) {
     RemoveDeadNodes(DeadNodes);
   }
 
   if (IP)
     CSEMap.InsertNode(N, IP);   // Memoize the new node.
   return N;
 }
 
+SDNode* SelectionDAG::mutateStrictFPToFP(SDNode *Node) {
+  unsigned OrigOpc = Node->getOpcode();
+  unsigned NewOpc;
+  bool IsUnary = false;
+  switch (OrigOpc) {
+  default: 
+    llvm_unreachable("mutateStrictFPToFP called with unexpected opcode!");
+  case ISD::STRICT_FADD: NewOpc = ISD::FADD; break;
+  case ISD::STRICT_FSUB: NewOpc = ISD::FSUB; break;
+  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_FSQRT: NewOpc = ISD::FSQRT; IsUnary = true; break;
+  case ISD::STRICT_FPOW: NewOpc = ISD::FPOW; break;
+  case ISD::STRICT_FPOWI: NewOpc = ISD::FPOWI; break;
+  case ISD::STRICT_FSIN: NewOpc = ISD::FSIN; IsUnary = true; break;
+  case ISD::STRICT_FCOS: NewOpc = ISD::FCOS; IsUnary = true; break;
+  case ISD::STRICT_FEXP: NewOpc = ISD::FEXP; IsUnary = true; break;
+  case ISD::STRICT_FEXP2: NewOpc = ISD::FEXP2; IsUnary = true; break;
+  case ISD::STRICT_FLOG: NewOpc = ISD::FLOG; IsUnary = true; break;
+  case ISD::STRICT_FLOG10: NewOpc = ISD::FLOG10; IsUnary = true; break;
+  case ISD::STRICT_FLOG2: NewOpc = ISD::FLOG2; IsUnary = true; break;
+  case ISD::STRICT_FRINT: NewOpc = ISD::FRINT; IsUnary = true; break;
+  case ISD::STRICT_FNEARBYINT:
+    NewOpc = ISD::FNEARBYINT;
+    IsUnary = true;
+    break;
+  }
+
+  // We're taking this node out of the chain, so we need to re-link things.
+  SDValue InputChain = Node->getOperand(0);
+  SDValue OutputChain = SDValue(Node, 1);
+  ReplaceAllUsesOfValueWith(OutputChain, InputChain);
+
+  SDVTList VTs = getVTList(Node->getOperand(1).getValueType());
+  SDNode *Res = nullptr;
+  if (IsUnary)
+    Res = MorphNodeTo(Node, NewOpc, VTs, { Node->getOperand(1) });
+  else
+    Res = MorphNodeTo(Node, NewOpc, VTs, { Node->getOperand(1),
+                                           Node->getOperand(2) });
+  
+  // MorphNodeTo can operate in two ways: if an existing node with the
+  // specified operands exists, it can just return it.  Otherwise, it
+  // updates the node in place to have the requested operands.
+  if (Res == Node) {
+    // If we updated the node in place, reset the node ID.  To the isel,
+    // this should be just like a newly allocated machine node.
+    Res->setNodeId(-1);
+  } else {
+    ReplaceAllUsesWith(Node, Res);
+    RemoveDeadNode(Node);
+  }
+
+  return Res; 
+}
+
 
 /// getMachineNode - These are used for target selectors to create a new node
 /// with specified return type(s), MachineInstr opcode, and operands.
 ///
 /// Note that getMachineNode returns the resultant node.  If there is already a
 /// node of the specified opcode and operands, it returns that node instead of
 /// the current one.
 MachineSDNode *SelectionDAG::getMachineNode(unsigned Opcode, const SDLoc &dl,

llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.h

private:
   void visitAtomicLoad(const LoadInst &I);
   void visitAtomicStore(const StoreInst &I);
   void visitLoadFromSwiftError(const LoadInst &I);
   void visitStoreToSwiftError(const StoreInst &I);
 
   void visitInlineAsm(ImmutableCallSite CS);
   const char *visitIntrinsicCall(const CallInst &I, unsigned Intrinsic);
   void visitTargetIntrinsic(const CallInst &I, unsigned Intrinsic);
-  void visitConstrainedFPIntrinsic(const CallInst &I, unsigned Intrinsic);
+  void visitConstrainedFPIntrinsic(const ConstrainedFPIntrinsic &FPI);
 
   void visitVAStart(const CallInst &I);
   void visitVAArg(const VAArgInst &I);
   void visitVAEnd(const CallInst &I);
   void visitVACopy(const CallInst &I);
   void visitStackmap(const CallInst &I);
   void visitPatchpoint(ImmutableCallSite CS,
                        const BasicBlock *EHPadBB = nullptr);

llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

setValue(&I, DAG.getNode(ISD::FMA, sdl,
                              getValue(I.getArgOperand(1)),
                              getValue(I.getArgOperand(2))));
     return nullptr;
   case Intrinsic::experimental_constrained_fadd:
   case Intrinsic::experimental_constrained_fsub:
   case Intrinsic::experimental_constrained_fmul:
   case Intrinsic::experimental_constrained_fdiv:
   case Intrinsic::experimental_constrained_frem:
-    visitConstrainedFPIntrinsic(I, Intrinsic);
+  case Intrinsic::experimental_constrained_sqrt:
+  case Intrinsic::experimental_constrained_pow:
+  case Intrinsic::experimental_constrained_powi:
+  case Intrinsic::experimental_constrained_sin:
+  case Intrinsic::experimental_constrained_cos:
+  case Intrinsic::experimental_constrained_exp:
+  case Intrinsic::experimental_constrained_exp2:
+  case Intrinsic::experimental_constrained_log:
+  case Intrinsic::experimental_constrained_log10:
+  case Intrinsic::experimental_constrained_log2:
+  case Intrinsic::experimental_constrained_rint:
+  case Intrinsic::experimental_constrained_nearbyint:
+    visitConstrainedFPIntrinsic(cast<ConstrainedFPIntrinsic>(I));
     return nullptr;
   case Intrinsic::fmuladd: {
     EVT VT = TLI.getValueType(DAG.getDataLayout(), I.getType());
     if (TM.Options.AllowFPOpFusion != FPOpFusion::Strict &&
         TLI.isFMAFasterThanFMulAndFAdd(VT)) {
       setValue(&I, DAG.getNode(ISD::FMA, sdl,
                                getValue(I.getArgOperand(0)).getValueType(),
                                getValue(I.getArgOperand(0)),
SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I, unsigned Intrinsic) {
   case Intrinsic::experimental_vector_reduce_fmin: {
     visitVectorReduce(I, Intrinsic);
     return nullptr;
   }
 
   }
 }
 
-void SelectionDAGBuilder::visitConstrainedFPIntrinsic(const CallInst &I,
-                                                      unsigned Intrinsic) {
+void SelectionDAGBuilder::visitConstrainedFPIntrinsic(
+    const ConstrainedFPIntrinsic &FPI) {
   SDLoc sdl = getCurSDLoc();
   unsigned Opcode;
-  switch (Intrinsic) {
+  switch (FPI.getIntrinsicID()) {
   default: llvm_unreachable("Impossible intrinsic");  // Can't reach here.
   case Intrinsic::experimental_constrained_fadd:
     Opcode = ISD::STRICT_FADD;
     break;
   case Intrinsic::experimental_constrained_fsub:
     Opcode = ISD::STRICT_FSUB;
     break;
   case Intrinsic::experimental_constrained_fmul:
     Opcode = ISD::STRICT_FMUL;
     break;
   case Intrinsic::experimental_constrained_fdiv:
     Opcode = ISD::STRICT_FDIV;
     break;
   case Intrinsic::experimental_constrained_frem:
     Opcode = ISD::STRICT_FREM;
     break;
+  case Intrinsic::experimental_constrained_sqrt:
+    Opcode = ISD::STRICT_FSQRT;
+    break;
+  case Intrinsic::experimental_constrained_pow:
+    Opcode = ISD::STRICT_FPOW;
+    break;
+  case Intrinsic::experimental_constrained_powi:
+    Opcode = ISD::STRICT_FPOWI;
+    break;
+  case Intrinsic::experimental_constrained_sin:
+    Opcode = ISD::STRICT_FSIN;
+    break;
+  case Intrinsic::experimental_constrained_cos:
+    Opcode = ISD::STRICT_FCOS;
+    break;
+  case Intrinsic::experimental_constrained_exp:
+    Opcode = ISD::STRICT_FEXP;
+    break;
+  case Intrinsic::experimental_constrained_exp2:
+    Opcode = ISD::STRICT_FEXP2;
+    break;
+  case Intrinsic::experimental_constrained_log:
+    Opcode = ISD::STRICT_FLOG;
+    break;
+  case Intrinsic::experimental_constrained_log10:
+    Opcode = ISD::STRICT_FLOG10;
+    break;
+  case Intrinsic::experimental_constrained_log2:
+    Opcode = ISD::STRICT_FLOG2;
+    break;
+  case Intrinsic::experimental_constrained_rint:
+    Opcode = ISD::STRICT_FRINT;
+    break;
+  case Intrinsic::experimental_constrained_nearbyint:
+    Opcode = ISD::STRICT_FNEARBYINT;
+    break;
   }
   const TargetLowering &TLI = DAG.getTargetLoweringInfo();
   SDValue Chain = getRoot();
-  SDValue Ops[3] = { Chain, getValue(I.getArgOperand(0)),
-                     getValue(I.getArgOperand(1)) };
   SmallVector<EVT, 4> ValueVTs;
-  ComputeValueVTs(TLI, DAG.getDataLayout(), I.getType(), ValueVTs);
+  ComputeValueVTs(TLI, DAG.getDataLayout(), FPI.getType(), ValueVTs);
   ValueVTs.push_back(MVT::Other); // Out chain
 
   SDVTList VTs = DAG.getVTList(ValueVTs);
-  SDValue Result = DAG.getNode(Opcode, sdl, VTs, Ops);
+  SDValue Result;
+  if (FPI.isUnaryOp())
+    Result = DAG.getNode(Opcode, sdl, VTs, 
+                         { Chain, getValue(FPI.getArgOperand(0)) });
+  else
+    Result = DAG.getNode(Opcode, sdl, VTs, 
+                         { Chain, getValue(FPI.getArgOperand(0)),
+                           getValue(FPI.getArgOperand(1))  });
 
   assert(Result.getNode()->getNumValues() == 2);
   SDValue OutChain = Result.getValue(1);
   DAG.setRoot(OutChain);
   SDValue FPResult = Result.getValue(0);
-  setValue(&I, FPResult);
+  setValue(&FPI, FPResult);
 }
 
 std::pair<SDValue, SDValue>
 SelectionDAGBuilder::lowerInvokable(TargetLowering::CallLoweringInfo &CLI,
                                     const BasicBlock *EHPadBB) {
   MachineFunction &MF = DAG.getMachineFunction();
   MachineModuleInfo &MMI = MF.getMMI();
   MCSymbol *BeginLabel = nullptr;

llvm/trunk/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp

public:
   void NodeDeleted(SDNode *N, SDNode *E) override {
     if (ISelPosition == SelectionDAG::allnodes_iterator(N))
       ++ISelPosition;
   }
 };
 
 } // end anonymous namespace
 
-static bool isStrictFPOp(SDNode *Node, unsigned &NewOpc) {
-  unsigned OrigOpc = Node->getOpcode();
-  switch (OrigOpc) {
-    case ISD::STRICT_FADD: NewOpc = ISD::FADD; return true;
-    case ISD::STRICT_FSUB: NewOpc = ISD::FSUB; return true;
-    case ISD::STRICT_FMUL: NewOpc = ISD::FMUL; return true;
-    case ISD::STRICT_FDIV: NewOpc = ISD::FDIV; return true;
-    case ISD::STRICT_FREM: NewOpc = ISD::FREM; return true;
-    default: return false;
-  }
-}
-
-SDNode* SelectionDAGISel::MutateStrictFPToFP(SDNode *Node, unsigned NewOpc) {
-  assert(((Node->getOpcode() == ISD::STRICT_FADD && NewOpc == ISD::FADD) ||
-          (Node->getOpcode() == ISD::STRICT_FSUB && NewOpc == ISD::FSUB) ||
-          (Node->getOpcode() == ISD::STRICT_FMUL && NewOpc == ISD::FMUL) ||
-          (Node->getOpcode() == ISD::STRICT_FDIV && NewOpc == ISD::FDIV) ||
-          (Node->getOpcode() == ISD::STRICT_FREM && NewOpc == ISD::FREM)) &&
-          "Unexpected StrictFP opcode!");
-
-  // We're taking this node out of the chain, so we need to re-link things.
-  SDValue InputChain = Node->getOperand(0);
-  SDValue OutputChain = SDValue(Node, 1);
-  CurDAG->ReplaceAllUsesOfValueWith(OutputChain, InputChain);
-
-  SDVTList VTs = CurDAG->getVTList(Node->getOperand(1).getValueType());
-  SDValue Ops[2] = { Node->getOperand(1), Node->getOperand(2) };
-  SDNode *Res = CurDAG->MorphNodeTo(Node, NewOpc, VTs, Ops);
-  
-  // MorphNodeTo can operate in two ways: if an existing node with the
-  // specified operands exists, it can just return it.  Otherwise, it
-  // updates the node in place to have the requested operands.
-  if (Res == Node) {
-    // If we updated the node in place, reset the node ID.  To the isel,
-    // this should be just like a newly allocated machine node.
-    Res->setNodeId(-1);
-  } else {
-    CurDAG->ReplaceAllUsesWith(Node, Res);
-    CurDAG->RemoveDeadNode(Node);
-  }
-
-  return Res; 
-}
-
 void SelectionDAGISel::DoInstructionSelection() {
   DEBUG(dbgs() << "===== Instruction selection begins: BB#"
         << FuncInfo->MBB->getNumber()
         << " '" << FuncInfo->MBB->getName() << "'\n");
 
   PreprocessISelDAG();
 
   // Select target instructions for the DAG.
while (ISelPosition != CurDAG->allnodes_begin()) {
       // When we are using non-default rounding modes or FP exception behavior
       // FP operations are represented by StrictFP pseudo-operations.  They
       // need to be simplified here so that the target-specific instruction
       // selectors know how to handle them.
       //
       // If the current node is a strict FP pseudo-op, the isStrictFPOp()
       // function will provide the corresponding normal FP opcode to which the
       // node should be mutated.
-      unsigned NormalFPOpc = ISD::UNDEF;
-      bool IsStrictFPOp = isStrictFPOp(Node, NormalFPOpc);
-      if (IsStrictFPOp)
-        Node = MutateStrictFPToFP(Node, NormalFPOpc);
+      //
+      // FIXME: The backends need a way to handle FP constraints.
+      if (Node->isStrictFPOpcode())
+        Node = CurDAG->mutateStrictFPToFP(Node);
 
       Select(Node);
-
-      // FIXME: Add code here to attach an implicit def and use of
-      // target-specific FP environment registers.
     }
 
     CurDAG->setRoot(Dummy.getValue());
   }
 
   DEBUG(dbgs() << "===== Instruction selection ends:\n");
 
   PostprocessISelDAG();

llvm/trunk/lib/IR/IntrinsicInst.cpp

Value *InstrProfIncrementInst::getStep() const {
   }
   const Module *M = getModule();
   LLVMContext &Context = M->getContext();
   return ConstantInt::get(Type::getInt64Ty(Context), 1);
 }
 
 ConstrainedFPIntrinsic::RoundingMode
 ConstrainedFPIntrinsic::getRoundingMode() const {
-  Metadata *MD = dyn_cast<MetadataAsValue>(getOperand(2))->getMetadata();
+  unsigned NumOperands = getNumArgOperands();
+  Metadata *MD = 
+      dyn_cast<MetadataAsValue>(getArgOperand(NumOperands - 2))->getMetadata();
   if (!MD || !isa<MDString>(MD))
     return rmInvalid;
   StringRef RoundingArg = cast<MDString>(MD)->getString();
 
   // For dynamic rounding mode, we use round to nearest but we will set the
   // 'exact' SDNodeFlag so that the value will not be rounded.
   return StringSwitch<RoundingMode>(RoundingArg)
     .Case("round.dynamic",    rmDynamic)
     .Case("round.tonearest",  rmToNearest)
     .Case("round.downward",   rmDownward)
     .Case("round.upward",     rmUpward)
     .Case("round.towardzero", rmTowardZero)
     .Default(rmInvalid);
 }
 
 ConstrainedFPIntrinsic::ExceptionBehavior
 ConstrainedFPIntrinsic::getExceptionBehavior() const {
-  Metadata *MD = dyn_cast<MetadataAsValue>(getOperand(3))->getMetadata();
+  unsigned NumOperands = getNumArgOperands();
+  Metadata *MD = 
+      dyn_cast<MetadataAsValue>(getArgOperand(NumOperands - 1))->getMetadata();
   if (!MD || !isa<MDString>(MD))
     return ebInvalid;
   StringRef ExceptionArg = cast<MDString>(MD)->getString();
   return StringSwitch<ExceptionBehavior>(ExceptionArg)
     .Case("fpexcept.ignore",  ebIgnore)
     .Case("fpexcept.maytrap", ebMayTrap)
     .Case("fpexcept.strict",  ebStrict)
     .Default(ebInvalid);
 }
+
+bool ConstrainedFPIntrinsic::isUnaryOp() const {
+  switch (getIntrinsicID()) {
+    default: 
+      return false;
+    case Intrinsic::experimental_constrained_sqrt:
+    case Intrinsic::experimental_constrained_sin:
+    case Intrinsic::experimental_constrained_cos:
+    case Intrinsic::experimental_constrained_exp:
+    case Intrinsic::experimental_constrained_exp2:
+    case Intrinsic::experimental_constrained_log:
+    case Intrinsic::experimental_constrained_log10:
+    case Intrinsic::experimental_constrained_log2:
+    case Intrinsic::experimental_constrained_rint:
+    case Intrinsic::experimental_constrained_nearbyint:
+      return true;
+  }
+}

llvm/trunk/lib/IR/Verifier.cpp

Assert(isa<ConstantInt>(CS.getArgOperand(1)),
            "constant int",
            CS);
     break;
   case Intrinsic::experimental_constrained_fadd:
   case Intrinsic::experimental_constrained_fsub:
   case Intrinsic::experimental_constrained_fmul:
   case Intrinsic::experimental_constrained_fdiv:
   case Intrinsic::experimental_constrained_frem:
+  case Intrinsic::experimental_constrained_sqrt:
+  case Intrinsic::experimental_constrained_pow:
+  case Intrinsic::experimental_constrained_powi:
+  case Intrinsic::experimental_constrained_sin:
+  case Intrinsic::experimental_constrained_cos:
+  case Intrinsic::experimental_constrained_exp:
+  case Intrinsic::experimental_constrained_exp2:
+  case Intrinsic::experimental_constrained_log:
+  case Intrinsic::experimental_constrained_log10:
+  case Intrinsic::experimental_constrained_log2:
+  case Intrinsic::experimental_constrained_rint:
+  case Intrinsic::experimental_constrained_nearbyint:
     visitConstrainedFPIntrinsic(
         cast<ConstrainedFPIntrinsic>(*CS.getInstruction()));
     break;
   case Intrinsic::dbg_declare: // llvm.dbg.declare
     Assert(isa<MetadataAsValue>(CS.getArgOperand(0)),
            "invalid llvm.dbg.declare intrinsic call 1", CS);
     visitDbgIntrinsic("declare", cast<DbgDeclareInst>(*CS.getInstruction()));
     break;
if (auto *LB = dyn_cast<DILexicalBlockBase>(LocalScope))
     return getSubprogram(LB->getRawScope());
 
   // Just return null; broken scope chains are checked elsewhere.
   assert(!isa<DILocalScope>(LocalScope) && "Unknown type of local scope");
   return nullptr;
 }
 
 void Verifier::visitConstrainedFPIntrinsic(ConstrainedFPIntrinsic &FPI) {
-  Assert(isa<MetadataAsValue>(FPI.getOperand(2)),
+  unsigned NumOperands = FPI.getNumArgOperands();
+  Assert(((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)),
          "invalid rounding mode argument", &FPI);
   Assert(FPI.getRoundingMode() != ConstrainedFPIntrinsic::rmInvalid,
          "invalid rounding mode argument", &FPI);
   Assert(FPI.getExceptionBehavior() != ConstrainedFPIntrinsic::ebInvalid,
          "invalid exception behavior argument", &FPI);
 }
 
 template <class DbgIntrinsicTy>

llvm/trunk/test/CodeGen/X86/fp-intrinsics.ll

%add = call double @llvm.experimental.constrained.fadd.f64(
                                                metadata !"fpexcept.strict")
   br label %if.end
 
 if.end:
   %a.0 = phi double [%add, %if.then], [ %a, %entry ]
   ret double %a.0
 }
 
+; Verify that sqrt(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f5
+; CHECK:  sqrtsd
+define double @f5() {
+entry:
+  %result = call double @llvm.experimental.constrained.sqrt.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that pow(42.1, 3.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f6
+; CHECK:  pow
+define double @f6() {
+entry:
+  %result = call double @llvm.experimental.constrained.pow.f64(double 42.1,
+                                               double 3.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that powi(42.1, 3) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f7
+; CHECK:  powi
+define double @f7() {
+entry:
+  %result = call double @llvm.experimental.constrained.powi.f64(double 42.1,
+                                               i32 3,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that sin(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f8
+; CHECK:  sin
+define double @f8() {
+entry:
+  %result = call double @llvm.experimental.constrained.sin.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that cos(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f9
+; CHECK:  cos
+define double @f9() {
+entry:
+  %result = call double @llvm.experimental.constrained.cos.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that exp(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f10
+; CHECK:  exp
+define double @f10() {
+entry:
+  %result = call double @llvm.experimental.constrained.exp.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that exp2(42.1) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f11
+; CHECK:  exp2
+define double @f11() {
+entry:
+  %result = call double @llvm.experimental.constrained.exp2.f64(double 42.1,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that log(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f12
+; CHECK:  log
+define double @f12() {
+entry:
+  %result = call double @llvm.experimental.constrained.log.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that log10(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f13
+; CHECK:  log10
+define double @f13() {
+entry:
+  %result = call double @llvm.experimental.constrained.log10.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that log2(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f14
+; CHECK:  log2
+define double @f14() {
+entry:
+  %result = call double @llvm.experimental.constrained.log2.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that rint(42.1) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f15
+; CHECK:  rint
+define double @f15() {
+entry:
+  %result = call double @llvm.experimental.constrained.rint.f64(double 42.1,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that nearbyint(42.1) isn't simplified when the rounding mode is
+; unknown.
+; CHECK-LABEL: f16
+; CHECK:  nearbyint
+define double @f16() {
+entry:
+  %result = call double @llvm.experimental.constrained.nearbyint.f64(
+                                               double 42.1,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
 
 @llvm.fp.env = thread_local global i8 zeroinitializer, section "llvm.metadata"
 declare double @llvm.experimental.constrained.fdiv.f64(double, double, metadata, metadata)
 declare double @llvm.experimental.constrained.fmul.f64(double, double, metadata, metadata)
 declare double @llvm.experimental.constrained.fadd.f64(double, double, metadata, metadata)
 declare double @llvm.experimental.constrained.fsub.f64(double, double, metadata, metadata)
+declare double @llvm.experimental.constrained.sqrt.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.pow.f64(double, double, metadata, metadata)
+declare double @llvm.experimental.constrained.powi.f64(double, i32, metadata, metadata)
+declare double @llvm.experimental.constrained.sin.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.cos.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.exp.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.exp2.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.log.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.log10.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.log2.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.rint.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.nearbyint.f64(double, metadata, metadata)

llvm/trunk/test/Feature/fp-intrinsics.ll

if.then:
   br label %if.end
 
 if.end:
   %a.0 = phi double [%add, %if.then], [ %a, %entry ]
   ret double %a.0
 }
 
 
+; Verify that sqrt(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f5
+; CHECK: call double @llvm.experimental.constrained.sqrt
+define double @f5() {
+entry:
+  %result = call double @llvm.experimental.constrained.sqrt.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that pow(42.1, 3.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f6
+; CHECK: call double @llvm.experimental.constrained.pow
+define double @f6() {
+entry:
+  %result = call double @llvm.experimental.constrained.pow.f64(double 42.1,
+                                               double 3.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that powi(42.1, 3) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f7
+; CHECK: call double @llvm.experimental.constrained.powi
+define double @f7() {
+entry:
+  %result = call double @llvm.experimental.constrained.powi.f64(double 42.1,
+                                               i32 3,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that sin(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f8
+; CHECK: call double @llvm.experimental.constrained.sin
+define double @f8() {
+entry:
+  %result = call double @llvm.experimental.constrained.sin.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that cos(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f9
+; CHECK: call double @llvm.experimental.constrained.cos
+define double @f9() {
+entry:
+  %result = call double @llvm.experimental.constrained.cos.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that exp(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f10
+; CHECK: call double @llvm.experimental.constrained.exp
+define double @f10() {
+entry:
+  %result = call double @llvm.experimental.constrained.exp.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that exp2(42.1) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f11
+; CHECK: call double @llvm.experimental.constrained.exp2
+define double @f11() {
+entry:
+  %result = call double @llvm.experimental.constrained.exp2.f64(double 42.1,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that log(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f12
+; CHECK: call double @llvm.experimental.constrained.log
+define double @f12() {
+entry:
+  %result = call double @llvm.experimental.constrained.log.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that log10(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f13
+; CHECK: call double @llvm.experimental.constrained.log10
+define double @f13() {
+entry:
+  %result = call double @llvm.experimental.constrained.log10.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that log2(42.0) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f14
+; CHECK: call double @llvm.experimental.constrained.log2
+define double @f14() {
+entry:
+  %result = call double @llvm.experimental.constrained.log2.f64(double 42.0,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that rint(42.1) isn't simplified when the rounding mode is unknown.
+; CHECK-LABEL: f15
+; CHECK: call double @llvm.experimental.constrained.rint
+define double @f15() {
+entry:
+  %result = call double @llvm.experimental.constrained.rint.f64(double 42.1,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
+; Verify that nearbyint(42.1) isn't simplified when the rounding mode is
+; unknown.
+; CHECK-LABEL: f16
+; CHECK: call double @llvm.experimental.constrained.nearbyint
+define double @f16() {
+entry:
+  %result = call double @llvm.experimental.constrained.nearbyint.f64(
+                                               double 42.1,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %result
+}
+
 @llvm.fp.env = thread_local global i8 zeroinitializer, section "llvm.metadata"
 declare double @llvm.experimental.constrained.fdiv.f64(double, double, metadata, metadata)
 declare double @llvm.experimental.constrained.fmul.f64(double, double, metadata, metadata)
 declare double @llvm.experimental.constrained.fadd.f64(double, double, metadata, metadata)
 declare double @llvm.experimental.constrained.fsub.f64(double, double, metadata, metadata)
+declare double @llvm.experimental.constrained.sqrt.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.pow.f64(double, double, metadata, metadata)
+declare double @llvm.experimental.constrained.powi.f64(double, i32, metadata, metadata)
+declare double @llvm.experimental.constrained.sin.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.cos.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.exp.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.exp2.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.log.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.log10.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.log2.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.rint.f64(double, metadata, metadata)
+declare double @llvm.experimental.constrained.nearbyint.f64(double, metadata, metadata)

llvm/trunk/test/Verifier/fp-intrinsics.ll

 ; RUN: opt -verify -S < %s 2>&1 | FileCheck --check-prefix=CHECK1 %s
 ; RUN: sed -e s/.T2:// %s | not opt -verify -disable-output 2>&1 | FileCheck --check-prefix=CHECK2 %s
 ; RUN: sed -e s/.T3:// %s | not opt -verify -disable-output 2>&1 | FileCheck --check-prefix=CHECK3 %s
+; RUN: sed -e s/.T4:// %s | not opt -verify -disable-output 2>&1 | FileCheck --check-prefix=CHECK4 %s
+; RUN: sed -e s/.T5:// %s | not opt -verify -disable-output 2>&1 | FileCheck --check-prefix=CHECK5 %s
 
-; Common declaration used for all runs.
+; Common declarations used for all runs.
 declare double @llvm.experimental.constrained.fadd.f64(double, double, metadata, metadata)
+declare double @llvm.experimental.constrained.sqrt.f64(double, metadata, metadata)
 
 ; Test that the verifier accepts legal code, and that the correct attributes are
 ; attached to the FP intrinsic.
 ; CHECK1: declare double @llvm.experimental.constrained.fadd.f64(double, double, metadata, metadata) #[[ATTR:[0-9]+]]
+; CHECK1: declare double @llvm.experimental.constrained.sqrt.f64(double, metadata, metadata) #[[ATTR]]
 ; CHECK1: attributes #[[ATTR]] = { inaccessiblememonly nounwind }
 ; Note: FP exceptions aren't usually caught through normal unwind mechanisms,
 ;       but we may want to revisit this for asynchronous exception handling.
 define double @f1(double %a, double %b) {
 entry:
   %fadd = call double @llvm.experimental.constrained.fadd.f64(
                                                double %a, double %b,
                                                metadata !"round.dynamic",
                                                metadata !"fpexcept.strict")
   ret double %fadd
 }
 
+define double @f1u(double %a) {
+entry:
+  %fsqrt = call double @llvm.experimental.constrained.sqrt.f64(
+                                               double %a,
+                                               metadata !"round.dynamic",
+                                               metadata !"fpexcept.strict")
+  ret double %fsqrt
+}
+
 ; Test an illegal value for the rounding mode argument.
 ; CHECK2: invalid rounding mode argument
 ;T2: define double @f2(double %a, double %b) {
 ;T2: entry:
 ;T2:   %fadd = call double @llvm.experimental.constrained.fadd.f64(
 ;T2:                                           double %a, double %b,
 ;T2:                                           metadata !"round.dynomite",
 ;T2:                                           metadata !"fpexcept.strict")
 ;T2:   ret double %fadd
 ;T2: }
 
 ; Test an illegal value for the exception behavior argument.
 ; CHECK3: invalid exception behavior argument
-;T3: define double @f2(double %a, double %b) {
+;T3: define double @f3(double %a, double %b) {
 ;T3: entry:
 ;T3:   %fadd = call double @llvm.experimental.constrained.fadd.f64(
 ;T3:                                         double %a, double %b,
 ;T3:                                         metadata !"round.dynamic",
 ;T3:                                         metadata !"fpexcept.restrict")
 ;T3:   ret double %fadd
 ;T3: }
+
+; Test an illegal value for the rounding mode argument.
+; CHECK4: invalid rounding mode argument
+;T4: define double @f4(double %a) {
+;T4: entry:
+;T4:   %fadd = call double @llvm.experimental.constrained.sqrt.f64(
+;T4:                                           double %a,
+;T4:                                           metadata !"round.dynomite",
+;T4:                                           metadata !"fpexcept.strict")
+;T4:   ret double %fadd
+;T4: }
+
+; Test an illegal value for the exception behavior argument.
+; CHECK5: invalid exception behavior argument
+;T5: define double @f5(double %a) {
+;T5: entry:
+;T5:   %fadd = call double @llvm.experimental.constrained.sqrt.f64(
+;T5:                                         double %a,
+;T5:                                         metadata !"round.dynamic",
+;T5:                                         metadata !"fpexcept.restrict")
+;T5:   ret double %fadd
+;T5: }