[IR] NFC: Remove 'experimental' from partial.reduce.add intrinsic (#158637)

The partial reduction intrinsics are no longer experimental, because
they've been used in production for a while and are unlikely to change.

Author: sdesmalen-arm

llvm/docs/LangRef.rst

@@ -20562,7 +20562,7 @@ Note that it has the following implications:
 -  If ``%cnt`` is non-zero, the return value is non-zero as well.
 -  If ``%cnt`` is less than or equal to ``%max_lanes``, the return value is equal to ``%cnt``.
 
-'``llvm.experimental.vector.partial.reduce.add.*``' Intrinsic
+'``llvm.vector.partial.reduce.add.*``' Intrinsic
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Syntax:
@@ -20571,15 +20571,15 @@ This is an overloaded intrinsic.
 
 ::
 
-      declare <4 x i32> @llvm.experimental.vector.partial.reduce.add.v4i32.v4i32.v8i32(<4 x i32> %a, <8 x i32> %b)
-      declare <4 x i32> @llvm.experimental.vector.partial.reduce.add.v4i32.v4i32.v16i32(<4 x i32> %a, <16 x i32> %b)
-      declare <vscale x 4 x i32> @llvm.experimental.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv8i32(<vscale x 4 x i32> %a, <vscale x 8 x i32> %b)
-      declare <vscale x 4 x i32> @llvm.experimental.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv16i32(<vscale x 4 x i32> %a, <vscale x 16 x i32> %b)
+      declare <4 x i32> @llvm.vector.partial.reduce.add.v4i32.v4i32.v8i32(<4 x i32> %a, <8 x i32> %b)
+      declare <4 x i32> @llvm.vector.partial.reduce.add.v4i32.v4i32.v16i32(<4 x i32> %a, <16 x i32> %b)
+      declare <vscale x 4 x i32> @llvm.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv8i32(<vscale x 4 x i32> %a, <vscale x 8 x i32> %b)
+      declare <vscale x 4 x i32> @llvm.vector.partial.reduce.add.nxv4i32.nxv4i32.nxv16i32(<vscale x 4 x i32> %a, <vscale x 16 x i32> %b)
 
 Overview:
 """""""""
 
-The '``llvm.vector.experimental.partial.reduce.add.*``' intrinsics reduce the
+The '``llvm.vector.partial.reduce.add.*``' intrinsics reduce the
 concatenation of the two vector arguments down to the number of elements of the
 result vector type.
 

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -1328,7 +1328,7 @@ class TargetTransformInfo {
 
   /// \return The cost of a partial reduction, which is a reduction from a
   /// vector to another vector with fewer elements of larger size. They are
-  /// represented by the llvm.experimental.partial.reduce.add intrinsic, which
+  /// represented by the llvm.vector.partial.reduce.add intrinsic, which
   /// takes an accumulator of type \p AccumType and a second vector operand to
   /// be accumulated, whose element count is specified by \p VF. The type of
   /// reduction is specified by \p Opcode. The second operand passed to the

llvm/include/llvm/CodeGen/TargetLowering.h

@@ -480,7 +480,7 @@ class LLVM_ABI TargetLoweringBase {
     return true;
   }
 
-  /// Return true if the @llvm.experimental.vector.partial.reduce.* intrinsic
+  /// Return true if the @llvm.vector.partial.reduce.* intrinsic
   /// should be expanded using generic code in SelectionDAGBuilder.
   virtual bool
   shouldExpandPartialReductionIntrinsic(const IntrinsicInst *I) const {

llvm/include/llvm/IR/Intrinsics.td

@@ -2797,9 +2797,9 @@ foreach n = 2...8 in {
 
 //===-------------- Intrinsics to perform partial reduction ---------------===//
 
-def int_experimental_vector_partial_reduce_add : DefaultAttrsIntrinsic<[LLVMMatchType<0>],
-                                                                       [llvm_anyvector_ty, llvm_anyvector_ty],
-                                                                       [IntrNoMem]>;
+def int_vector_partial_reduce_add : DefaultAttrsIntrinsic<[LLVMMatchType<0>],
+                                                          [llvm_anyvector_ty, llvm_anyvector_ty],
+                                                          [IntrNoMem]>;
 
 //===----------------- Pointer Authentication Intrinsics ------------------===//
 //

llvm/lib/CodeGen/ComplexDeinterleavingPass.cpp

@@ -1022,8 +1022,7 @@ ComplexDeinterleavingGraph::identifyDotProduct(Value *V) {
 
   CompositeNode *ANode = nullptr;
 
-  const Intrinsic::ID PartialReduceInt =
-      Intrinsic::experimental_vector_partial_reduce_add;
+  const Intrinsic::ID PartialReduceInt = Intrinsic::vector_partial_reduce_add;
 
   Value *AReal = nullptr;
   Value *AImag = nullptr;
@@ -1139,8 +1138,7 @@ ComplexDeinterleavingGraph::identifyPartialReduction(Value *R, Value *I) {
     return nullptr;
 
   auto *IInst = dyn_cast<IntrinsicInst>(*CommonUser);
-  if (!IInst || IInst->getIntrinsicID() !=
-                    Intrinsic::experimental_vector_partial_reduce_add)
+  if (!IInst || IInst->getIntrinsicID() != Intrinsic::vector_partial_reduce_add)
     return nullptr;
 
   if (CompositeNode *CN = identifyDotProduct(IInst))

llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

@@ -8102,7 +8102,7 @@ void SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I,
     setValue(&I, Trunc);
     return;
   }
-  case Intrinsic::experimental_vector_partial_reduce_add: {
+  case Intrinsic::vector_partial_reduce_add: {
     if (!TLI.shouldExpandPartialReductionIntrinsic(cast<IntrinsicInst>(&I))) {
       visitTargetIntrinsic(I, Intrinsic);
       return;

llvm/lib/IR/AutoUpgrade.cpp

@@ -1259,6 +1259,8 @@ static bool upgradeIntrinsicFunction1(Function *F, Function *&NewFn,
               .StartsWith("reverse.", Intrinsic::vector_reverse)
               .StartsWith("interleave2.", Intrinsic::vector_interleave2)
               .StartsWith("deinterleave2.", Intrinsic::vector_deinterleave2)
+              .StartsWith("partial.reduce.add",
+                          Intrinsic::vector_partial_reduce_add)
               .Default(Intrinsic::not_intrinsic);
       if (ID != Intrinsic::not_intrinsic) {
         const auto *FT = F->getFunctionType();
@@ -1269,7 +1271,8 @@ static bool upgradeIntrinsicFunction1(Function *F, Function *&NewFn,
           Tys.push_back(FT->getReturnType());
         if (ID != Intrinsic::vector_interleave2)
           Tys.push_back(FT->getParamType(0));
-        if (ID == Intrinsic::vector_insert)
+        if (ID == Intrinsic::vector_insert ||
+            ID == Intrinsic::vector_partial_reduce_add)
           // Inserting overloads the inserted type.
           Tys.push_back(FT->getParamType(1));
         rename(F);

llvm/lib/IR/Verifier.cpp

@@ -6530,7 +6530,7 @@ void Verifier::visitIntrinsicCall(Intrinsic::ID ID, CallBase &Call) {
     }
     break;
   }
-  case Intrinsic::experimental_vector_partial_reduce_add: {
+  case Intrinsic::vector_partial_reduce_add: {
     VectorType *AccTy = cast<VectorType>(Call.getArgOperand(0)->getType());
     VectorType *VecTy = cast<VectorType>(Call.getArgOperand(1)->getType());
 

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -2184,8 +2184,7 @@ bool AArch64TargetLowering::shouldExpandGetActiveLaneMask(EVT ResVT,
 
 bool AArch64TargetLowering::shouldExpandPartialReductionIntrinsic(
     const IntrinsicInst *I) const {
-  assert(I->getIntrinsicID() ==
-             Intrinsic::experimental_vector_partial_reduce_add &&
+  assert(I->getIntrinsicID() == Intrinsic::vector_partial_reduce_add &&
          "Unexpected intrinsic!");
   return true;
 }
@@ -17474,8 +17473,7 @@ bool AArch64TargetLowering::optimizeExtendOrTruncateConversion(
             if (match(SingleUser, m_c_Mul(m_Specific(I), m_SExt(m_Value()))))
               return true;
             if (match(SingleUser,
-                      m_Intrinsic<
-                          Intrinsic::experimental_vector_partial_reduce_add>(
+                      m_Intrinsic<Intrinsic::vector_partial_reduce_add>(
                           m_Value(), m_Specific(I))))
               return true;
             return false;
@@ -22522,8 +22520,7 @@ SDValue tryLowerPartialReductionToDot(SDNode *N,
                                       SelectionDAG &DAG) {
 
   assert(N->getOpcode() == ISD::INTRINSIC_WO_CHAIN &&
-         getIntrinsicID(N) ==
-             Intrinsic::experimental_vector_partial_reduce_add &&
+         getIntrinsicID(N) == Intrinsic::vector_partial_reduce_add &&
          "Expected a partial reduction node");
 
   bool Scalable = N->getValueType(0).isScalableVector();
@@ -22617,8 +22614,7 @@ SDValue tryLowerPartialReductionToWideAdd(SDNode *N,
                                           SelectionDAG &DAG) {
 
   assert(N->getOpcode() == ISD::INTRINSIC_WO_CHAIN &&
-         getIntrinsicID(N) ==
-             Intrinsic::experimental_vector_partial_reduce_add &&
+         getIntrinsicID(N) == Intrinsic::vector_partial_reduce_add &&
          "Expected a partial reduction node");
 
   if (!Subtarget->hasSVE2() && !Subtarget->isStreamingSVEAvailable())
@@ -22683,7 +22679,7 @@ static SDValue performIntrinsicCombine(SDNode *N,
   switch (IID) {
   default:
     break;
-  case Intrinsic::experimental_vector_partial_reduce_add: {
+  case Intrinsic::vector_partial_reduce_add: {
     if (SDValue Dot = tryLowerPartialReductionToDot(N, Subtarget, DAG))
       return Dot;
     if (SDValue WideAdd = tryLowerPartialReductionToWideAdd(N, Subtarget, DAG))

llvm/lib/Target/WebAssembly/WebAssemblyISelLowering.cpp

@@ -418,7 +418,7 @@ MVT WebAssemblyTargetLowering::getPointerMemTy(const DataLayout &DL,
 
 bool WebAssemblyTargetLowering::shouldExpandPartialReductionIntrinsic(
     const IntrinsicInst *I) const {
-  if (I->getIntrinsicID() != Intrinsic::experimental_vector_partial_reduce_add)
+  if (I->getIntrinsicID() != Intrinsic::vector_partial_reduce_add)
     return true;
 
   EVT VT = EVT::getEVT(I->getType());
@@ -2117,8 +2117,7 @@ SDValue WebAssemblyTargetLowering::LowerVASTART(SDValue Op,
 // extmul and adds.
 SDValue performLowerPartialReduction(SDNode *N, SelectionDAG &DAG) {
   assert(N->getOpcode() == ISD::INTRINSIC_WO_CHAIN);
-  if (N->getConstantOperandVal(0) !=
-      Intrinsic::experimental_vector_partial_reduce_add)
+  if (N->getConstantOperandVal(0) != Intrinsic::vector_partial_reduce_add)
     return SDValue();
 
   assert(N->getValueType(0) == MVT::v4i32 && "can only support v4i32");