[AArch64] Add target hook for preferPredicateOverEpilogue

This patch adds the AArch64 hook for preferPredicateOverEpilogue,
which currently returns true if SVE is enabled and one of the
following conditions (non-exhaustive) is met:

1. The "sve-tail-folding" option is set to "all", or
2. The "sve-tail-folding" option is set to "all+noreductions"
and the loop does not contain reductions,
3. The "sve-tail-folding" option is set to "all+norecurrences"
and the loop has no first-order recurrences.

Currently the default option is "disabled", but this will be
changed in a later patch.

I've added new tests to show the options behave as expected here:

  Transforms/LoopVectorize/AArch64/sve-tail-folding-option.ll

Differential Revision: https://reviews.llvm.org/D129560

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -52,6 +52,7 @@ class LoadInst;
 class LoopAccessInfo;
 class Loop;
 class LoopInfo;
+class LoopVectorizationLegality;
 class ProfileSummaryInfo;
 class RecurrenceDescriptor;
 class SCEV;
@@ -530,7 +531,7 @@ class TargetTransformInfo {
   bool preferPredicateOverEpilogue(Loop *L, LoopInfo *LI, ScalarEvolution &SE,
                                    AssumptionCache &AC, TargetLibraryInfo *TLI,
                                    DominatorTree *DT,
-                                   const LoopAccessInfo *LAI) const;
+                                   LoopVectorizationLegality *LVL) const;
 
   /// Query the target whether lowering of the llvm.get.active.lane.mask
   /// intrinsic is supported and how the mask should be used. A return value
@@ -1555,10 +1556,12 @@ class TargetTransformInfo::Concept {
                                         AssumptionCache &AC,
                                         TargetLibraryInfo *LibInfo,
                                         HardwareLoopInfo &HWLoopInfo) = 0;
-  virtual bool
-  preferPredicateOverEpilogue(Loop *L, LoopInfo *LI, ScalarEvolution &SE,
-                              AssumptionCache &AC, TargetLibraryInfo *TLI,
-                              DominatorTree *DT, const LoopAccessInfo *LAI) = 0;
+  virtual bool preferPredicateOverEpilogue(Loop *L, LoopInfo *LI,
+                                           ScalarEvolution &SE,
+                                           AssumptionCache &AC,
+                                           TargetLibraryInfo *TLI,
+                                           DominatorTree *DT,
+                                           LoopVectorizationLegality *LVL) = 0;
   virtual PredicationStyle emitGetActiveLaneMask() = 0;
   virtual Optional<Instruction *> instCombineIntrinsic(InstCombiner &IC,
                                                        IntrinsicInst &II) = 0;
@@ -1935,8 +1938,8 @@ class TargetTransformInfo::Model final : public TargetTransformInfo::Concept {
   bool preferPredicateOverEpilogue(Loop *L, LoopInfo *LI, ScalarEvolution &SE,
                                    AssumptionCache &AC, TargetLibraryInfo *TLI,
                                    DominatorTree *DT,
-                                   const LoopAccessInfo *LAI) override {
-    return Impl.preferPredicateOverEpilogue(L, LI, SE, AC, TLI, DT, LAI);
+                                   LoopVectorizationLegality *LVL) override {
+    return Impl.preferPredicateOverEpilogue(L, LI, SE, AC, TLI, DT, LVL);
   }
   PredicationStyle emitGetActiveLaneMask() override {
     return Impl.emitGetActiveLaneMask();

llvm/include/llvm/Analysis/TargetTransformInfoImpl.h

@@ -163,7 +163,7 @@ class TargetTransformInfoImplBase {
   bool preferPredicateOverEpilogue(Loop *L, LoopInfo *LI, ScalarEvolution &SE,
                                    AssumptionCache &AC, TargetLibraryInfo *TLI,
                                    DominatorTree *DT,
-                                   const LoopAccessInfo *LAI) const {
+                                   LoopVectorizationLegality *LVL) const {
     return false;
   }
 

llvm/include/llvm/CodeGen/BasicTTIImpl.h

@@ -603,8 +603,8 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
   bool preferPredicateOverEpilogue(Loop *L, LoopInfo *LI, ScalarEvolution &SE,
                                    AssumptionCache &AC, TargetLibraryInfo *TLI,
                                    DominatorTree *DT,
-                                   const LoopAccessInfo *LAI) {
-    return BaseT::preferPredicateOverEpilogue(L, LI, SE, AC, TLI, DT, LAI);
+                                   LoopVectorizationLegality *LVL) {
+    return BaseT::preferPredicateOverEpilogue(L, LI, SE, AC, TLI, DT, LVL);
   }
 
   PredicationStyle emitGetActiveLaneMask() {

llvm/lib/Analysis/TargetTransformInfo.cpp

@@ -294,8 +294,8 @@ bool TargetTransformInfo::isHardwareLoopProfitable(
 bool TargetTransformInfo::preferPredicateOverEpilogue(
     Loop *L, LoopInfo *LI, ScalarEvolution &SE, AssumptionCache &AC,
     TargetLibraryInfo *TLI, DominatorTree *DT,
-    const LoopAccessInfo *LAI) const {
-  return TTIImpl->preferPredicateOverEpilogue(L, LI, SE, AC, TLI, DT, LAI);
+    LoopVectorizationLegality *LVL) const {
+  return TTIImpl->preferPredicateOverEpilogue(L, LI, SE, AC, TLI, DT, LVL);
 }
 
 PredicationStyle TargetTransformInfo::emitGetActiveLaneMask() const {

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -22,6 +22,7 @@
 #include "llvm/IR/PatternMatch.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Transforms/InstCombine/InstCombiner.h"
+#include "llvm/Transforms/Vectorize/LoopVectorizationLegality.h"
 #include <algorithm>
 using namespace llvm;
 using namespace llvm::PatternMatch;
@@ -37,6 +38,74 @@ static cl::opt<unsigned> SVEGatherOverhead("sve-gather-overhead", cl::init(10),
 static cl::opt<unsigned> SVEScatterOverhead("sve-scatter-overhead",
                                             cl::init(10), cl::Hidden);
 
+class TailFoldingKind {
+private:
+  uint8_t Bits = 0; // Currently defaults to disabled.
+
+public:
+  enum TailFoldingOpts {
+    TFDisabled = 0x0,
+    TFReductions = 0x01,
+    TFRecurrences = 0x02,
+    TFSimple = 0x80,
+    TFAll = TFReductions | TFRecurrences | TFSimple
+  };
+
+  void operator=(const std::string &Val) {
+    if (Val.empty())
+      return;
+    SmallVector<StringRef, 6> TailFoldTypes;
+    StringRef(Val).split(TailFoldTypes, '+', -1, false);
+    for (auto TailFoldType : TailFoldTypes) {
+      if (TailFoldType == "disabled")
+        Bits = 0;
+      else if (TailFoldType == "all")
+        Bits = TFAll;
+      else if (TailFoldType == "default")
+        Bits = 0; // Currently defaults to never tail-folding.
+      else if (TailFoldType == "simple")
+        add(TFSimple);
+      else if (TailFoldType == "reductions")
+        add(TFReductions);
+      else if (TailFoldType == "recurrences")
+        add(TFRecurrences);
+      else if (TailFoldType == "noreductions")
+        remove(TFReductions);
+      else if (TailFoldType == "norecurrences")
+        remove(TFRecurrences);
+      else {
+        errs()
+            << "invalid argument " << TailFoldType.str()
+            << " to -sve-tail-folding=; each element must be one of: disabled, "
+               "all, default, simple, reductions, noreductions, recurrences, "
+               "norecurrences\n";
+      }
+    }
+  }
+
+  operator uint8_t() const { return Bits; }
+
+  void add(uint8_t Flag) { Bits |= Flag; }
+  void remove(uint8_t Flag) { Bits &= ~Flag; }
+};
+
+TailFoldingKind TailFoldingKindLoc;
+
+cl::opt<TailFoldingKind, true, cl::parser<std::string>> SVETailFolding(
+    "sve-tail-folding",
+    cl::desc(
+        "Control the use of vectorisation using tail-folding for SVE:"
+        "\ndisabled    No loop types will vectorize using tail-folding"
+        "\ndefault     Uses the default tail-folding settings for the target "
+        "CPU"
+        "\nall         All legal loop types will vectorize using tail-folding"
+        "\nsimple      Use tail-folding for simple loops (not reductions or "
+        "recurrences)"
+        "\nreductions  Use tail-folding for loops containing reductions"
+        "\nrecurrences Use tail-folding for loops containing first order "
+        "recurrences"),
+    cl::location(TailFoldingKindLoc));
+
 bool AArch64TTIImpl::areInlineCompatible(const Function *Caller,
                                          const Function *Callee) const {
   const TargetMachine &TM = getTLI()->getTargetMachine();
@@ -2955,3 +3024,20 @@ InstructionCost AArch64TTIImpl::getShuffleCost(TTI::ShuffleKind Kind,
 
   return BaseT::getShuffleCost(Kind, Tp, Mask, Index, SubTp);
 }
+
+bool AArch64TTIImpl::preferPredicateOverEpilogue(
+    Loop *L, LoopInfo *LI, ScalarEvolution &SE, AssumptionCache &AC,
+    TargetLibraryInfo *TLI, DominatorTree *DT, LoopVectorizationLegality *LVL) {
+  if (!ST->hasSVE() || TailFoldingKindLoc == TailFoldingKind::TFDisabled)
+    return false;
+
+  TailFoldingKind Required; // Defaults to 0.
+  if (LVL->getReductionVars().size())
+    Required.add(TailFoldingKind::TFReductions);
+  if (LVL->getFirstOrderRecurrences().size())
+    Required.add(TailFoldingKind::TFRecurrences);
+  if (!Required)
+    Required.add(TailFoldingKind::TFSimple);
+
+  return (TailFoldingKindLoc & Required) == Required;
+}

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h

@@ -340,6 +340,11 @@ class AArch64TTIImpl : public BasicTTIImplBase<AArch64TTIImpl> {
     return PredicationStyle::None;
   }
 
+  bool preferPredicateOverEpilogue(Loop *L, LoopInfo *LI, ScalarEvolution &SE,
+                                   AssumptionCache &AC, TargetLibraryInfo *TLI,
+                                   DominatorTree *DT,
+                                   LoopVectorizationLegality *LVL);
+
   bool supportsScalableVectors() const { return ST->hasSVE(); }
 
   bool enableScalableVectorization() const { return ST->hasSVE(); }

llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp

@@ -20,8 +20,8 @@
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
-#include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/IntrinsicInst.h"
+#include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/IntrinsicsARM.h"
 #include "llvm/IR/PatternMatch.h"
 #include "llvm/IR/Type.h"
@@ -33,6 +33,7 @@
 #include "llvm/Transforms/InstCombine/InstCombiner.h"
 #include "llvm/Transforms/Utils/Local.h"
 #include "llvm/Transforms/Utils/LoopUtils.h"
+#include "llvm/Transforms/Vectorize/LoopVectorizationLegality.h"
 #include <algorithm>
 #include <cassert>
 #include <cstdint>
@@ -2197,12 +2198,9 @@ static bool canTailPredicateLoop(Loop *L, LoopInfo *LI, ScalarEvolution &SE,
   return true;
 }
 
-bool ARMTTIImpl::preferPredicateOverEpilogue(Loop *L, LoopInfo *LI,
-                                             ScalarEvolution &SE,
-                                             AssumptionCache &AC,
-                                             TargetLibraryInfo *TLI,
-                                             DominatorTree *DT,
-                                             const LoopAccessInfo *LAI) {
+bool ARMTTIImpl::preferPredicateOverEpilogue(
+    Loop *L, LoopInfo *LI, ScalarEvolution &SE, AssumptionCache &AC,
+    TargetLibraryInfo *TLI, DominatorTree *DT, LoopVectorizationLegality *LVL) {
   if (!EnableTailPredication) {
     LLVM_DEBUG(dbgs() << "Tail-predication not enabled.\n");
     return false;
@@ -2244,7 +2242,7 @@ bool ARMTTIImpl::preferPredicateOverEpilogue(Loop *L, LoopInfo *LI,
     return false;
   }
 
-  return canTailPredicateLoop(L, LI, SE, DL, LAI);
+  return canTailPredicateLoop(L, LI, SE, DL, LVL->getLAI());
 }
 
 PredicationStyle ARMTTIImpl::emitGetActiveLaneMask() const {

llvm/lib/Target/ARM/ARMTargetTransformInfo.h

@@ -288,12 +288,10 @@ class ARMTTIImpl : public BasicTTIImplBase<ARMTTIImpl> {
                                 AssumptionCache &AC,
                                 TargetLibraryInfo *LibInfo,
                                 HardwareLoopInfo &HWLoopInfo);
-  bool preferPredicateOverEpilogue(Loop *L, LoopInfo *LI,
-                                   ScalarEvolution &SE,
-                                   AssumptionCache &AC,
-                                   TargetLibraryInfo *TLI,
+  bool preferPredicateOverEpilogue(Loop *L, LoopInfo *LI, ScalarEvolution &SE,
+                                   AssumptionCache &AC, TargetLibraryInfo *TLI,
                                    DominatorTree *DT,
-                                   const LoopAccessInfo *LAI);
+                                   LoopVectorizationLegality *LVL);
   void getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                TTI::UnrollingPreferences &UP,
                                OptimizationRemarkEmitter *ORE);

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -9745,8 +9745,7 @@ static ScalarEpilogueLowering getScalarEpilogueLowering(
   };
 
   // 4) if the TTI hook indicates this is profitable, request predication.
-  if (TTI->preferPredicateOverEpilogue(L, LI, *SE, *AC, TLI, DT,
-                                       LVL.getLAI()))
+  if (TTI->preferPredicateOverEpilogue(L, LI, *SE, *AC, TLI, DT, &LVL))
     return CM_ScalarEpilogueNotNeededUsePredicate;
 
   return CM_ScalarEpilogueAllowed;