Move several vector intrinsics out of experimental namespace (llvm#88748)

This patch is moving out following intrinsics:
* vector.interleave2/deinterleave2
* vector.reverse
* vector.splice

from the experimental namespace.

All these intrinsics exist in LLVM for more than a year now, and are
widely used, so should not be considered as experimental.

Author: mgabka

clang/lib/CodeGen/CGExprScalar.cpp

@@ -2330,7 +2330,7 @@ Value *ScalarExprEmitter::VisitCastExpr(CastExpr *CE) {
     }
 
     // Perform VLAT <-> VLST bitcast through memory.
-    // TODO: since the llvm.experimental.vector.{insert,extract} intrinsics
+    // TODO: since the llvm.vector.{insert,extract} intrinsics
     //       require the element types of the vectors to be the same, we
     //       need to keep this around for bitcasts between VLAT <-> VLST where
     //       the element types of the vectors are not the same, until we figure

llvm/docs/LangRef.rst

@@ -18805,7 +18805,7 @@ runtime, then the result vector is a :ref:`poison value <poisonvalues>`. The
 ``idx`` parameter must be a vector index constant type (for most targets this
 will be an integer pointer type).
 
-'``llvm.experimental.vector.reverse``' Intrinsic
+'``llvm.vector.reverse``' Intrinsic
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Syntax:
@@ -18814,25 +18814,26 @@ This is an overloaded intrinsic.
 
 ::
 
-      declare <2 x i8> @llvm.experimental.vector.reverse.v2i8(<2 x i8> %a)
-      declare <vscale x 4 x i32> @llvm.experimental.vector.reverse.nxv4i32(<vscale x 4 x i32> %a)
+      declare <2 x i8> @llvm.vector.reverse.v2i8(<2 x i8> %a)
+      declare <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> %a)
 
 Overview:
 """""""""
 
-The '``llvm.experimental.vector.reverse.*``' intrinsics reverse a vector.
+The '``llvm.vector.reverse.*``' intrinsics reverse a vector.
 The intrinsic takes a single vector and returns a vector of matching type but
 with the original lane order reversed. These intrinsics work for both fixed
-and scalable vectors. While this intrinsic is marked as experimental the
-recommended way to express reverse operations for fixed-width vectors is still
-to use a shufflevector, as that may allow for more optimization opportunities.
+and scalable vectors. While this intrinsic supports all vector types
+the recommended way to express this operation for fixed-width vectors is
+still to use a shufflevector, as that may allow for more optimization
+opportunities.
 
 Arguments:
 """"""""""
 
 The argument to this intrinsic must be a vector.
 
-'``llvm.experimental.vector.deinterleave2``' Intrinsic
+'``llvm.vector.deinterleave2``' Intrinsic
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Syntax:
@@ -18841,13 +18842,13 @@ This is an overloaded intrinsic.
 
 ::
 
-      declare {<2 x double>, <2 x double>} @llvm.experimental.vector.deinterleave2.v4f64(<4 x double> %vec1)
-      declare {<vscale x 4 x i32>, <vscale x 4 x i32>}  @llvm.experimental.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %vec1)
+      declare {<2 x double>, <2 x double>} @llvm.vector.deinterleave2.v4f64(<4 x double> %vec1)
+      declare {<vscale x 4 x i32>, <vscale x 4 x i32>}  @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %vec1)
 
 Overview:
 """""""""
 
-The '``llvm.experimental.vector.deinterleave2``' intrinsic constructs two
+The '``llvm.vector.deinterleave2``' intrinsic constructs two
 vectors by deinterleaving the even and odd lanes of the input vector.
 
 This intrinsic works for both fixed and scalable vectors. While this intrinsic
@@ -18859,15 +18860,15 @@ For example:
 
 .. code-block:: text
 
-  {<2 x i64>, <2 x i64>} llvm.experimental.vector.deinterleave2.v4i64(<4 x i64> <i64 0, i64 1, i64 2, i64 3>); ==> {<2 x i64> <i64 0, i64 2>, <2 x i64> <i64 1, i64 3>}
+  {<2 x i64>, <2 x i64>} llvm.vector.deinterleave2.v4i64(<4 x i64> <i64 0, i64 1, i64 2, i64 3>); ==> {<2 x i64> <i64 0, i64 2>, <2 x i64> <i64 1, i64 3>}
 
 Arguments:
 """"""""""
 
 The argument is a vector whose type corresponds to the logical concatenation of
 the two result types.
 
-'``llvm.experimental.vector.interleave2``' Intrinsic
+'``llvm.vector.interleave2``' Intrinsic
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Syntax:
@@ -18876,13 +18877,13 @@ This is an overloaded intrinsic.
 
 ::
 
-      declare <4 x double> @llvm.experimental.vector.interleave2.v4f64(<2 x double> %vec1, <2 x double> %vec2)
-      declare <vscale x 8 x i32> @llvm.experimental.vector.interleave2.nxv8i32(<vscale x 4 x i32> %vec1, <vscale x 4 x i32> %vec2)
+      declare <4 x double> @llvm.vector.interleave2.v4f64(<2 x double> %vec1, <2 x double> %vec2)
+      declare <vscale x 8 x i32> @llvm.vector.interleave2.nxv8i32(<vscale x 4 x i32> %vec1, <vscale x 4 x i32> %vec2)
 
 Overview:
 """""""""
 
-The '``llvm.experimental.vector.interleave2``' intrinsic constructs a vector
+The '``llvm.vector.interleave2``' intrinsic constructs a vector
 by interleaving two input vectors.
 
 This intrinsic works for both fixed and scalable vectors. While this intrinsic
@@ -18894,7 +18895,7 @@ For example:
 
 .. code-block:: text
 
-   <4 x i64> llvm.experimental.vector.interleave2.v4i64(<2 x i64> <i64 0, i64 2>, <2 x i64> <i64 1, i64 3>); ==> <4 x i64> <i64 0, i64 1, i64 2, i64 3>
+   <4 x i64> llvm.vector.interleave2.v4i64(<2 x i64> <i64 0, i64 2>, <2 x i64> <i64 1, i64 3>); ==> <4 x i64> <i64 0, i64 1, i64 2, i64 3>
 
 Arguments:
 """"""""""
@@ -18940,7 +18941,7 @@ The '``llvm.experimental.cttz.elts``' intrinsic counts the trailing (least
 significant) zero elements in a vector. If ``src == 0`` the result is the
 number of elements in the input vector.
 
-'``llvm.experimental.vector.splice``' Intrinsic
+'``llvm.vector.splice``' Intrinsic
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 Syntax:
@@ -18949,13 +18950,13 @@ This is an overloaded intrinsic.
 
 ::
 
-      declare <2 x double> @llvm.experimental.vector.splice.v2f64(<2 x double> %vec1, <2 x double> %vec2, i32 %imm)
-      declare <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> %vec1, <vscale x 4 x i32> %vec2, i32 %imm)
+      declare <2 x double> @llvm.vector.splice.v2f64(<2 x double> %vec1, <2 x double> %vec2, i32 %imm)
+      declare <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> %vec1, <vscale x 4 x i32> %vec2, i32 %imm)
 
 Overview:
 """""""""
 
-The '``llvm.experimental.vector.splice.*``' intrinsics construct a vector by
+The '``llvm.vector.splice.*``' intrinsics construct a vector by
 concatenating elements from the first input vector with elements of the second
 input vector, returning a vector of the same type as the input vectors. The
 signed immediate, modulo the number of elements in the vector, is the index
@@ -18966,16 +18967,16 @@ immediate, it extracts ``-imm`` trailing elements from the first vector, and
 the remaining elements from ``%vec2``.
 
 These intrinsics work for both fixed and scalable vectors. While this intrinsic
-is marked as experimental, the recommended way to express this operation for
+supports all vector types the recommended way to express this operation for
 fixed-width vectors is still to use a shufflevector, as that may allow for more
 optimization opportunities.
 
 For example:
 
 .. code-block:: text
 
- llvm.experimental.vector.splice(<A,B,C,D>, <E,F,G,H>, 1);  ==> <B, C, D, E> index
- llvm.experimental.vector.splice(<A,B,C,D>, <E,F,G,H>, -3); ==> <B, C, D, E> trailing elements
+ llvm.vector.splice(<A,B,C,D>, <E,F,G,H>, 1);  ==> <B, C, D, E> index
+ llvm.vector.splice(<A,B,C,D>, <E,F,G,H>, -3); ==> <B, C, D, E> trailing elements
 
 
 Arguments:
@@ -22198,7 +22199,7 @@ Overview:
 """""""""
 
 The '``llvm.experimental.vp.splice.*``' intrinsic is the vector length
-predicated version of the '``llvm.experimental.vector.splice.*``' intrinsic.
+predicated version of the '``llvm.vector.splice.*``' intrinsic.
 
 Arguments:
 """"""""""
@@ -22257,7 +22258,7 @@ Overview:
 """""""""
 
 The '``llvm.experimental.vp.reverse.*``' intrinsic is the vector length
-predicated version of the '``llvm.experimental.vector.reverse.*``' intrinsic.
+predicated version of the '``llvm.vector.reverse.*``' intrinsic.
 
 Arguments:
 """"""""""

llvm/docs/ReleaseNotes.rst

@@ -50,7 +50,11 @@ Update on required toolchains to build LLVM
 Changes to the LLVM IR
 ----------------------
 
-- Added Memory Model Relaxation Annotations (MMRAs).
+* Added Memory Model Relaxation Annotations (MMRAs).
+* Renamed ``llvm.experimental.vector.reverse`` intrinsic to ``llvm.vector.reverse``.
+* Renamed ``llvm.experimental.vector.splice`` intrinsic to ``llvm.vector.splice``.
+* Renamed ``llvm.experimental.vector.interleave2`` intrinsic to ``llvm.vector.interleave2``.
+* Renamed ``llvm.experimental.vector.deinterleave2`` intrinsic to ``llvm.vector.deinterleave2``.
 
 Changes to LLVM infrastructure
 ------------------------------

llvm/include/llvm/CodeGen/BasicTTIImpl.h

@@ -1662,12 +1662,12 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
           TTI::SK_InsertSubvector, cast<VectorType>(Args[0]->getType()),
           std::nullopt, CostKind, Index, cast<VectorType>(Args[1]->getType()));
     }
-    case Intrinsic::experimental_vector_reverse: {
+    case Intrinsic::vector_reverse: {
       return thisT()->getShuffleCost(
           TTI::SK_Reverse, cast<VectorType>(Args[0]->getType()), std::nullopt,
           CostKind, 0, cast<VectorType>(RetTy));
     }
-    case Intrinsic::experimental_vector_splice: {
+    case Intrinsic::vector_splice: {
       unsigned Index = cast<ConstantInt>(Args[2])->getZExtValue();
       return thisT()->getShuffleCost(
           TTI::SK_Splice, cast<VectorType>(Args[0]->getType()), std::nullopt,

llvm/include/llvm/CodeGen/GlobalISel/IRTranslator.h

@@ -247,8 +247,8 @@ class IRTranslator : public MachineFunctionPass {
   bool translateTrap(const CallInst &U, MachineIRBuilder &MIRBuilder,
                      unsigned Opcode);
 
-  // Translate @llvm.experimental.vector.interleave2 and
-  // @llvm.experimental.vector.deinterleave2 intrinsics for fixed-width vector
+  // Translate @llvm.vector.interleave2 and
+  // @llvm.vector.deinterleave2 intrinsics for fixed-width vector
   // types into vector shuffles.
   bool translateVectorInterleave2Intrinsic(const CallInst &CI,
                                            MachineIRBuilder &MIRBuilder);

llvm/include/llvm/CodeGen/TargetLowering.h

@@ -3146,7 +3146,7 @@ class TargetLoweringBase {
 
   /// Lower a deinterleave intrinsic to a target specific load intrinsic.
   /// Return true on success. Currently only supports
-  /// llvm.experimental.vector.deinterleave2
+  /// llvm.vector.deinterleave2
   ///
   /// \p DI is the deinterleave intrinsic.
   /// \p LI is the accompanying load instruction
@@ -3157,7 +3157,7 @@ class TargetLoweringBase {
 
   /// Lower an interleave intrinsic to a target specific store intrinsic.
   /// Return true on success. Currently only supports
-  /// llvm.experimental.vector.interleave2
+  /// llvm.vector.interleave2
   ///
   /// \p II is the interleave intrinsic.
   /// \p SI is the accompanying store instruction

llvm/include/llvm/IR/Intrinsics.td

@@ -2577,15 +2577,15 @@ def int_preserve_static_offset : DefaultAttrsIntrinsic<[llvm_ptr_ty],
 
 //===------------ Intrinsics to perform common vector shuffles ------------===//
 
-def int_experimental_vector_reverse : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
-                                                            [LLVMMatchType<0>],
-                                                            [IntrNoMem]>;
+def int_vector_reverse : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
+                                               [LLVMMatchType<0>],
+                                               [IntrNoMem]>;
 
-def int_experimental_vector_splice : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
-                                                           [LLVMMatchType<0>,
-                                                            LLVMMatchType<0>,
-                                                            llvm_i32_ty],
-                                                           [IntrNoMem, ImmArg<ArgIndex<2>>]>;
+def int_vector_splice : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
+                                              [LLVMMatchType<0>,
+                                               LLVMMatchType<0>,
+                                               llvm_i32_ty],
+                                              [IntrNoMem, ImmArg<ArgIndex<2>>]>;
 
 //===---------- Intrinsics to query properties of scalable vectors --------===//
 def int_vscale : DefaultAttrsIntrinsic<[llvm_anyint_ty], [], [IntrNoMem]>;
@@ -2600,15 +2600,15 @@ def int_vector_extract : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
                                                [IntrNoMem, IntrSpeculatable, ImmArg<ArgIndex<1>>]>;
 
 
-def int_experimental_vector_interleave2   : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
-                                                                  [LLVMHalfElementsVectorType<0>,
-                                                                   LLVMHalfElementsVectorType<0>],
-                                                                  [IntrNoMem]>;
+def int_vector_interleave2   : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
+                                                     [LLVMHalfElementsVectorType<0>,
+                                                      LLVMHalfElementsVectorType<0>],
+                                                     [IntrNoMem]>;
 
-def int_experimental_vector_deinterleave2 : DefaultAttrsIntrinsic<[LLVMHalfElementsVectorType<0>,
-                                                                   LLVMHalfElementsVectorType<0>],
-                                                                  [llvm_anyvector_ty],
-                                                                  [IntrNoMem]>;
+def int_vector_deinterleave2 : DefaultAttrsIntrinsic<[LLVMHalfElementsVectorType<0>,
+                                                      LLVMHalfElementsVectorType<0>],
+                                                     [llvm_anyvector_ty],
+                                                     [IntrNoMem]>;
 
 //===----------------- Pointer Authentication Intrinsics ------------------===//
 //

llvm/include/llvm/IR/PatternMatch.h

@@ -2513,7 +2513,7 @@ inline typename m_Intrinsic_Ty<Opnd0, Opnd1>::Ty m_CopySign(const Opnd0 &Op0,
 
 template <typename Opnd0>
 inline typename m_Intrinsic_Ty<Opnd0>::Ty m_VecReverse(const Opnd0 &Op0) {
-  return m_Intrinsic<Intrinsic::experimental_vector_reverse>(Op0);
+  return m_Intrinsic<Intrinsic::vector_reverse>(Op0);
 }
 
 //===----------------------------------------------------------------------===//

llvm/lib/Analysis/InstructionSimplify.cpp

@@ -6281,11 +6281,11 @@ static Value *simplifyUnaryIntrinsic(Function *F, Value *Op0,
                m_Intrinsic<Intrinsic::pow>(m_SpecificFP(10.0), m_Value(X)))))
       return X;
     break;
-  case Intrinsic::experimental_vector_reverse:
-    // experimental.vector.reverse(experimental.vector.reverse(x)) -> x
+  case Intrinsic::vector_reverse:
+    // vector.reverse(vector.reverse(x)) -> x
     if (match(Op0, m_VecReverse(m_Value(X))))
       return X;
-    // experimental.vector.reverse(splat(X)) -> splat(X)
+    // vector.reverse(splat(X)) -> splat(X)
     if (isSplatValue(Op0))
       return Op0;
     break;

llvm/lib/CodeGen/ComplexDeinterleavingPass.cpp

@@ -1639,8 +1639,7 @@ bool ComplexDeinterleavingGraph::checkNodes() {
 ComplexDeinterleavingGraph::NodePtr
 ComplexDeinterleavingGraph::identifyRoot(Instruction *RootI) {
   if (auto *Intrinsic = dyn_cast<IntrinsicInst>(RootI)) {
-    if (Intrinsic->getIntrinsicID() !=
-        Intrinsic::experimental_vector_interleave2)
+    if (Intrinsic->getIntrinsicID() != Intrinsic::vector_interleave2)
       return nullptr;
 
     auto *Real = dyn_cast<Instruction>(Intrinsic->getOperand(0));
@@ -1675,7 +1674,7 @@ ComplexDeinterleavingGraph::identifyDeinterleave(Instruction *Real,
   Value *FinalValue = nullptr;
   if (match(Real, m_ExtractValue<0>(m_Instruction(I))) &&
       match(Imag, m_ExtractValue<1>(m_Specific(I))) &&
-      match(I, m_Intrinsic<Intrinsic::experimental_vector_deinterleave2>(
+      match(I, m_Intrinsic<Intrinsic::vector_deinterleave2>(
                    m_Value(FinalValue)))) {
     NodePtr PlaceholderNode = prepareCompositeNode(
         llvm::ComplexDeinterleavingOperation::Deinterleave, Real, Imag);
@@ -1960,13 +1959,11 @@ Value *ComplexDeinterleavingGraph::replaceNode(IRBuilderBase &Builder,
       // Splats that are not constant are interleaved where they are located
       Instruction *InsertPoint = (I->comesBefore(R) ? R : I)->getNextNode();
       IRBuilder<> IRB(InsertPoint);
-      ReplacementNode =
-          IRB.CreateIntrinsic(Intrinsic::experimental_vector_interleave2, NewTy,
-                              {Node->Real, Node->Imag});
+      ReplacementNode = IRB.CreateIntrinsic(Intrinsic::vector_interleave2,
+                                            NewTy, {Node->Real, Node->Imag});
     } else {
-      ReplacementNode =
-          Builder.CreateIntrinsic(Intrinsic::experimental_vector_interleave2,
-                                  NewTy, {Node->Real, Node->Imag});
+      ReplacementNode = Builder.CreateIntrinsic(
+          Intrinsic::vector_interleave2, NewTy, {Node->Real, Node->Imag});
     }
     break;
   }
@@ -1991,9 +1988,8 @@ Value *ComplexDeinterleavingGraph::replaceNode(IRBuilderBase &Builder,
     auto *B = replaceNode(Builder, Node->Operands[1]);
     auto *NewMaskTy = VectorType::getDoubleElementsVectorType(
         cast<VectorType>(MaskReal->getType()));
-    auto *NewMask =
-        Builder.CreateIntrinsic(Intrinsic::experimental_vector_interleave2,
-                                NewMaskTy, {MaskReal, MaskImag});
+    auto *NewMask = Builder.CreateIntrinsic(Intrinsic::vector_interleave2,
+                                            NewMaskTy, {MaskReal, MaskImag});
     ReplacementNode = Builder.CreateSelect(NewMask, A, B);
     break;
   }
@@ -2021,8 +2017,8 @@ void ComplexDeinterleavingGraph::processReductionOperation(
   Value *InitImag = OldPHIImag->getIncomingValueForBlock(Incoming);
 
   IRBuilder<> Builder(Incoming->getTerminator());
-  auto *NewInit = Builder.CreateIntrinsic(
-      Intrinsic::experimental_vector_interleave2, NewVTy, {InitReal, InitImag});
+  auto *NewInit = Builder.CreateIntrinsic(Intrinsic::vector_interleave2, NewVTy,
+                                          {InitReal, InitImag});
 
   NewPHI->addIncoming(NewInit, Incoming);
   NewPHI->addIncoming(OperationReplacement, BackEdge);
@@ -2034,9 +2030,9 @@ void ComplexDeinterleavingGraph::processReductionOperation(
 
   Builder.SetInsertPoint(
       &*FinalReductionReal->getParent()->getFirstInsertionPt());
-  auto *Deinterleave = Builder.CreateIntrinsic(
-      Intrinsic::experimental_vector_deinterleave2,
-      OperationReplacement->getType(), OperationReplacement);
+  auto *Deinterleave = Builder.CreateIntrinsic(Intrinsic::vector_deinterleave2,
+                                               OperationReplacement->getType(),
+                                               OperationReplacement);
 
   auto *NewReal = Builder.CreateExtractValue(Deinterleave, (uint64_t)0);
   FinalReductionReal->replaceUsesOfWith(Real, NewReal);