[VP] llvm.vp.fneg intrinsic and LangRef

Reviewed By: frasercrmck

Differential Revision: https://reviews.llvm.org/D119262

llvm/docs/LangRef.rst

@@ -18599,7 +18599,7 @@ operation.
 Semantics:
 """"""""""
 
-The '``llvm.vp.fadd``' intrinsic performs floating-point addition (:ref:`add <i_fadd>`)
+The '``llvm.vp.fadd``' intrinsic performs floating-point addition (:ref:`fadd <i_fadd>`)
 of the first and second vector operand on each enabled lane.  The result on
 disabled lanes is undefined.  The operation is performed in the default
 floating-point environment.
@@ -18648,7 +18648,7 @@ operation.
 Semantics:
 """"""""""
 
-The '``llvm.vp.fsub``' intrinsic performs floating-point subtraction (:ref:`add <i_fsub>`)
+The '``llvm.vp.fsub``' intrinsic performs floating-point subtraction (:ref:`fsub <i_fsub>`)
 of the first and second vector operand on each enabled lane.  The result on
 disabled lanes is undefined.  The operation is performed in the default
 floating-point environment.
@@ -18697,7 +18697,7 @@ operation.
 Semantics:
 """"""""""
 
-The '``llvm.vp.fmul``' intrinsic performs floating-point multiplication (:ref:`add <i_fmul>`)
+The '``llvm.vp.fmul``' intrinsic performs floating-point multiplication (:ref:`fmul <i_fmul>`)
 of the first and second vector operand on each enabled lane.  The result on
 disabled lanes is undefined.  The operation is performed in the default
 floating-point environment.
@@ -18746,7 +18746,7 @@ operation.
 Semantics:
 """"""""""
 
-The '``llvm.vp.fdiv``' intrinsic performs floating-point division (:ref:`add <i_fdiv>`)
+The '``llvm.vp.fdiv``' intrinsic performs floating-point division (:ref:`fdiv <i_fdiv>`)
 of the first and second vector operand on each enabled lane.  The result on
 disabled lanes is undefined.  The operation is performed in the default
 floating-point environment.
@@ -18795,7 +18795,7 @@ operation.
 Semantics:
 """"""""""
 
-The '``llvm.vp.frem``' intrinsic performs floating-point remainder (:ref:`add <i_frem>`)
+The '``llvm.vp.frem``' intrinsic performs floating-point remainder (:ref:`frem <i_frem>`)
 of the first and second vector operand on each enabled lane.  The result on
 disabled lanes is undefined.  The operation is performed in the default
 floating-point environment.
@@ -18812,6 +18812,54 @@ Examples:
       %also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> undef
 
 
+.. _int_vp_fneg:
+
+'``llvm.vp.fneg.*``' Intrinsics
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+This is an overloaded intrinsic.
+
+::
+
+      declare <16 x float>  @llvm.vp.fneg.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
+      declare <vscale x 4 x float>  @llvm.vp.fneg.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
+      declare <256 x double>  @llvm.vp.fneg.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
+
+Overview:
+"""""""""
+
+Predicated floating-point negation of a vector of floating-point values.
+
+
+Arguments:
+""""""""""
+
+The first operand and the result have the same vector of floating-point type.
+The second operand is the vector mask and has the same number of elements as the
+result vector type. The third operand is the explicit vector length of the
+operation.
+
+Semantics:
+""""""""""
+
+The '``llvm.vp.fneg``' intrinsic performs floating-point negation (:ref:`fneg <i_fneg>`)
+of the first vector operand on each enabled lane.  The result on disabled lanes
+is undefined.
+
+Examples:
+"""""""""
+
+.. code-block:: llvm
+
+      %r = call <4 x float> @llvm.vp.fneg.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
+      ;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
+
+      %t = fneg <4 x float> %a
+      %also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> undef
+
+
 .. _int_vp_fma:
 
 '``llvm.vp.fma.*``' Intrinsics

llvm/include/llvm/IR/Intrinsics.td

@@ -1505,6 +1505,11 @@ let IntrProperties =
                                 LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
                                 llvm_i32_ty]>;
 
+  def int_vp_fneg : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
+                              [ LLVMMatchType<0>,
+                                LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>,
+                                llvm_i32_ty]>;
+
   def int_vp_fma : DefaultAttrsIntrinsic<[ llvm_anyvector_ty ],
                               [ LLVMMatchType<0>,
                                 LLVMMatchType<0>,

llvm/include/llvm/IR/VPIntrinsics.def

@@ -211,6 +211,11 @@ HELPER_REGISTER_BINARY_FP_VP(frem, VP_FREM, FRem)
 
 #undef HELPER_REGISTER_BINARY_FP_VP
 
+// llvm.vp.fneg(x,mask,vlen)
+BEGIN_REGISTER_VP(vp_fneg, 1, 2, VP_FNEG, -1)
+VP_PROPERTY_FUNCTIONAL_OPC(FNeg)
+END_REGISTER_VP(vp_fneg, VP_FNEG)
+
 // llvm.vp.fma(x,y,z,mask,vlen)
 BEGIN_REGISTER_VP(vp_fma, 3, 4, VP_FMA, -1)
 VP_PROPERTY_CONSTRAINEDFP(1, 1, experimental_constrained_fma)

llvm/unittests/IR/VPIntrinsicTest.cpp

@@ -51,8 +51,10 @@ protected:
       Str << " declare <8 x float> @llvm.vp." << BinaryFPOpcode
           << ".v8f32(<8 x float>, <8 x float>, <8 x i1>, i32) ";
 
+    Str << " declare <8 x float> @llvm.vp.fneg.v8f32(<8 x float>, <8 x i1>, "
+           "i32)";
     Str << " declare <8 x float> @llvm.vp.fma.v8f32(<8 x float>, <8 x float>, "
-                 "<8 x float>, <8 x i1>, i32) ";
+           "<8 x float>, <8 x i1>, i32) ";
 
     Str << " declare void @llvm.vp.store.v8i32.p0v8i32(<8 x i32>, <8 x i32>*, "
            "<8 x i1>, i32) ";