Recommit "[VP,Integer,#2] ExpandVectorPredication pass"

This reverts the revert 02c5ba8

Fix:

Pass was registered as DUMMY_FUNCTION_PASS causing the newpm-pass
functions to be doubly defined. Triggered in -DLLVM_ENABLE_MODULE=1
builds.

Original commit:

This patch implements expansion of llvm.vp.* intrinsics
(https://llvm.org/docs/LangRef.html#vector-predication-intrinsics).

VP expansion is required for targets that do not implement VP code
generation. Since expansion is controllable with TTI, targets can switch
on the VP intrinsics they do support in their backend offering a smooth
transition strategy for VP code generation (VE, RISC-V V, ARM SVE,
AVX512, ..).

Reviewed By: rogfer01

Differential Revision: https://reviews.llvm.org/D78203

Author: Simon Moll

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -61,6 +61,7 @@ class TargetLibraryInfo;
 class Type;
 class User;
 class Value;
+class VPIntrinsic;
 struct KnownBits;
 template <typename T> class Optional;
 
@@ -1379,6 +1380,38 @@ class TargetTransformInfo {
   /// Intrinsics") Use of %evl is discouraged when that is not the case.
   bool hasActiveVectorLength() const;
 
+  struct VPLegalization {
+    enum VPTransform {
+      // keep the predicating parameter
+      Legal = 0,
+      // where legal, discard the predicate parameter
+      Discard = 1,
+      // transform into something else that is also predicating
+      Convert = 2
+    };
+
+    // How to transform the EVL parameter.
+    // Legal:   keep the EVL parameter as it is.
+    // Discard: Ignore the EVL parameter where it is safe to do so.
+    // Convert: Fold the EVL into the mask parameter.
+    VPTransform EVLParamStrategy;
+
+    // How to transform the operator.
+    // Legal:   The target supports this operator.
+    // Convert: Convert this to a non-VP operation.
+    // The 'Discard' strategy is invalid.
+    VPTransform OpStrategy;
+
+    bool shouldDoNothing() const {
+      return (EVLParamStrategy == Legal) && (OpStrategy == Legal);
+    }
+    VPLegalization(VPTransform EVLParamStrategy, VPTransform OpStrategy)
+        : EVLParamStrategy(EVLParamStrategy), OpStrategy(OpStrategy) {}
+  };
+
+  /// \returns How the target needs this vector-predicated operation to be
+  /// transformed.
+  VPLegalization getVPLegalizationStrategy(const VPIntrinsic &PI) const;
   /// @}
 
   /// @}
@@ -1688,6 +1721,8 @@ class TargetTransformInfo::Concept {
   virtual bool supportsScalableVectors() const = 0;
   virtual bool hasActiveVectorLength() const = 0;
   virtual InstructionCost getInstructionLatency(const Instruction *I) = 0;
+  virtual VPLegalization
+  getVPLegalizationStrategy(const VPIntrinsic &PI) const = 0;
 };
 
 template <typename T>
@@ -2259,6 +2294,11 @@ class TargetTransformInfo::Model final : public TargetTransformInfo::Concept {
   InstructionCost getInstructionLatency(const Instruction *I) override {
     return Impl.getInstructionLatency(I);
   }
+
+  VPLegalization
+  getVPLegalizationStrategy(const VPIntrinsic &PI) const override {
+    return Impl.getVPLegalizationStrategy(PI);
+  }
 };
 
 template <typename T>

llvm/include/llvm/Analysis/TargetTransformInfoImpl.h

@@ -750,6 +750,13 @@ class TargetTransformInfoImplBase {
 
   bool hasActiveVectorLength() const { return false; }
 
+  TargetTransformInfo::VPLegalization
+  getVPLegalizationStrategy(const VPIntrinsic &PI) const {
+    return TargetTransformInfo::VPLegalization(
+        /* EVLParamStrategy */ TargetTransformInfo::VPLegalization::Discard,
+        /* OperatorStrategy */ TargetTransformInfo::VPLegalization::Convert);
+  }
+
 protected:
   // Obtain the minimum required size to hold the value (without the sign)
   // In case of a vector it returns the min required size for one element.

llvm/include/llvm/CodeGen/ExpandVectorPredication.h

@@ -0,0 +1,23 @@
+//===-- ExpandVectorPredication.h - Expand vector predication ---*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CODEGEN_EXPANDVECTORPREDICATION_H
+#define LLVM_CODEGEN_EXPANDVECTORPREDICATION_H
+
+#include "llvm/IR/PassManager.h"
+
+namespace llvm {
+
+class ExpandVectorPredicationPass
+    : public PassInfoMixin<ExpandVectorPredicationPass> {
+public:
+  PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM);
+};
+} // end namespace llvm
+
+#endif // LLVM_CODEGEN_EXPANDVECTORPREDICATION_H

llvm/include/llvm/CodeGen/MachinePassRegistry.def

@@ -44,6 +44,7 @@ FUNCTION_PASS("partially-inline-libcalls", PartiallyInlineLibCallsPass, ())
 FUNCTION_PASS("ee-instrument", EntryExitInstrumenterPass, (false))
 FUNCTION_PASS("post-inline-ee-instrument", EntryExitInstrumenterPass, (true))
 FUNCTION_PASS("expand-reductions", ExpandReductionsPass, ())
+FUNCTION_PASS("expandvp", ExpandVectorPredicationPass, ())
 FUNCTION_PASS("lowerinvoke", LowerInvokePass, ())
 FUNCTION_PASS("scalarize-masked-mem-intrin", ScalarizeMaskedMemIntrinPass, ())
 FUNCTION_PASS("verify", VerifierPass, ())

llvm/include/llvm/CodeGen/Passes.h

@@ -453,6 +453,11 @@ namespace llvm {
   // the corresponding function in a vector library (e.g., SVML, libmvec).
   FunctionPass *createReplaceWithVeclibLegacyPass();
 
+  /// This pass expands the vector predication intrinsics into unpredicated
+  /// instructions with selects or just the explicit vector length into the
+  /// predicate mask.
+  FunctionPass *createExpandVectorPredicationPass();
+
   // This pass expands memcmp() to load/stores.
   FunctionPass *createExpandMemCmpPass();
 

llvm/include/llvm/IR/IntrinsicInst.h

@@ -395,9 +395,11 @@ class VPIntrinsic : public IntrinsicInst {
 
   /// \return the mask parameter or nullptr.
   Value *getMaskParam() const;
+  void setMaskParam(Value *);
 
   /// \return the vector length parameter or nullptr.
   Value *getVectorLengthParam() const;
+  void setVectorLengthParam(Value *);
 
   /// \return whether the vector length param can be ignored.
   bool canIgnoreVectorLengthParam() const;

llvm/include/llvm/InitializePasses.h

@@ -154,6 +154,7 @@ void initializeEntryExitInstrumenterPass(PassRegistry&);
 void initializeExpandMemCmpPassPass(PassRegistry&);
 void initializeExpandPostRAPass(PassRegistry&);
 void initializeExpandReductionsPass(PassRegistry&);
+void initializeExpandVectorPredicationPass(PassRegistry &);
 void initializeMakeGuardsExplicitLegacyPassPass(PassRegistry&);
 void initializeExternalAAWrapperPassPass(PassRegistry&);
 void initializeFEntryInserterPass(PassRegistry&);

llvm/include/llvm/LinkAllPasses.h

@@ -197,6 +197,7 @@ namespace {
       (void) llvm::createMergeFunctionsPass();
       (void) llvm::createMergeICmpsLegacyPass();
       (void) llvm::createExpandMemCmpPass();
+      (void) llvm::createExpandVectorPredicationPass();
       std::string buf;
       llvm::raw_string_ostream os(buf);
       (void) llvm::createPrintModulePass(os);

llvm/lib/Analysis/TargetTransformInfo.cpp

@@ -1026,6 +1026,11 @@ bool TargetTransformInfo::preferPredicatedReductionSelect(
   return TTIImpl->preferPredicatedReductionSelect(Opcode, Ty, Flags);
 }
 
+TargetTransformInfo::VPLegalization
+TargetTransformInfo::getVPLegalizationStrategy(const VPIntrinsic &VPI) const {
+  return TTIImpl->getVPLegalizationStrategy(VPI);
+}
+
 bool TargetTransformInfo::shouldExpandReduction(const IntrinsicInst *II) const {
   return TTIImpl->shouldExpandReduction(II);
 }

llvm/lib/CodeGen/CMakeLists.txt

@@ -29,6 +29,7 @@ add_llvm_component_library(LLVMCodeGen
   ExpandMemCmp.cpp
   ExpandPostRAPseudos.cpp
   ExpandReductions.cpp
+  ExpandVectorPredication.cpp
   FaultMaps.cpp
   FEntryInserter.cpp
   FinalizeISel.cpp