[llvm] r270113 - Recommit r255691 since PR26509 has been fixed.

Wei Mi via llvm-commits llvm-commits at lists.llvm.org
Thu May 19 13:38:04 PDT 2016


Author: wmi
Date: Thu May 19 15:38:03 2016
New Revision: 270113

URL: http://llvm.org/viewvc/llvm-project?rev=270113&view=rev
Log:
Recommit r255691 since PR26509 has been fixed.

Added:
    llvm/trunk/test/Transforms/LoopVectorize/X86/reg-usage.ll
Modified:
    llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
    llvm/trunk/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll

Modified: llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp?rev=270113&r1=270112&r2=270113&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp (original)
+++ llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp Thu May 19 15:38:03 2016
@@ -1518,15 +1518,14 @@ private:
 /// different operations.
 class LoopVectorizationCostModel {
 public:
-  LoopVectorizationCostModel(Loop *L, ScalarEvolution *SE, LoopInfo *LI,
-                             LoopVectorizationLegality *Legal,
+  LoopVectorizationCostModel(Loop *L, PredicatedScalarEvolution &PSE,
+                             LoopInfo *LI, LoopVectorizationLegality *Legal,
                              const TargetTransformInfo &TTI,
                              const TargetLibraryInfo *TLI, DemandedBits *DB,
                              AssumptionCache *AC, const Function *F,
-                             const LoopVectorizeHints *Hints,
-                             SmallPtrSetImpl<const Value *> &ValuesToIgnore)
-      : TheLoop(L), SE(SE), LI(LI), Legal(Legal), TTI(TTI), TLI(TLI), DB(DB),
-        TheFunction(F), Hints(Hints), ValuesToIgnore(ValuesToIgnore) {}
+                             const LoopVectorizeHints *Hints)
+      : TheLoop(L), PSE(PSE), LI(LI), Legal(Legal), TTI(TTI), TLI(TLI), DB(DB),
+        AC(AC), TheFunction(F), Hints(Hints) {}
 
   /// Information about vectorization costs
   struct VectorizationFactor {
@@ -1573,6 +1572,9 @@ public:
   /// given vectorization factors.
   SmallVector<RegisterUsage, 8> calculateRegisterUsage(ArrayRef<unsigned> VFs);
 
+  /// Collect values we want to ignore in the cost model.
+  void collectValuesToIgnore();
+
 private:
   /// The vectorization cost is a combination of the cost itself and a boolean
   /// indicating whether any of the contributing operations will actually
@@ -1617,8 +1619,8 @@ public:
 
   /// The loop that we evaluate.
   Loop *TheLoop;
-  /// Scev analysis.
-  ScalarEvolution *SE;
+  /// Predicated scalar evolution analysis.
+  PredicatedScalarEvolution &PSE;
   /// Loop Info analysis.
   LoopInfo *LI;
   /// Vectorization legality.
@@ -1627,13 +1629,17 @@ public:
   const TargetTransformInfo &TTI;
   /// Target Library Info.
   const TargetLibraryInfo *TLI;
-  /// Demanded bits analysis
+  /// Demanded bits analysis.
   DemandedBits *DB;
+  /// Assumption cache.
+  AssumptionCache *AC;
   const Function *TheFunction;
-  // Loop Vectorize Hint.
+  /// Loop Vectorize Hint.
   const LoopVectorizeHints *Hints;
-  // Values to ignore in the cost model.
-  const SmallPtrSetImpl<const Value *> &ValuesToIgnore;
+  /// Values to ignore in the cost model.
+  SmallPtrSet<const Value *, 16> ValuesToIgnore;
+  /// Values to ignore in the cost model when VF > 1.
+  SmallPtrSet<const Value *, 16> VecValuesToIgnore;
 };
 
 /// \brief This holds vectorization requirements that must be verified late in
@@ -1881,19 +1887,10 @@ struct LoopVectorize : public FunctionPa
       return false;
     }
 
-    // Collect values we want to ignore in the cost model. This includes
-    // type-promoting instructions we identified during reduction detection.
-    SmallPtrSet<const Value *, 32> ValuesToIgnore;
-    CodeMetrics::collectEphemeralValues(L, AC, ValuesToIgnore);
-    for (auto &Reduction : *LVL.getReductionVars()) {
-      RecurrenceDescriptor &RedDes = Reduction.second;
-      SmallPtrSetImpl<Instruction *> &Casts = RedDes.getCastInsts();
-      ValuesToIgnore.insert(Casts.begin(), Casts.end());
-    }
-
     // Use the cost model.
-    LoopVectorizationCostModel CM(L, PSE.getSE(), LI, &LVL, *TTI, TLI, DB, AC,
-                                  F, &Hints, ValuesToIgnore);
+    LoopVectorizationCostModel CM(L, PSE, LI, &LVL, *TTI, TLI, DB, AC, F,
+                                  &Hints);
+    CM.collectValuesToIgnore();
 
     // Check the function attributes to find out if this function should be
     // optimized for size.
@@ -5190,7 +5187,7 @@ LoopVectorizationCostModel::selectVector
   }
 
   // Find the trip count.
-  unsigned TC = SE->getSmallConstantTripCount(TheLoop);
+  unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
   DEBUG(dbgs() << "LV: Found trip count: " << TC << '\n');
 
   MinBWs = computeMinimumValueSizes(TheLoop->getBlocks(), *DB, &TTI);
@@ -5409,7 +5406,7 @@ unsigned LoopVectorizationCostModel::sel
     return 1;
 
   // Do not interleave loops with a relatively small trip count.
-  unsigned TC = SE->getSmallConstantTripCount(TheLoop);
+  unsigned TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
   if (TC > 1 && TC < TinyTripCountInterleaveThreshold)
     return 1;
 
@@ -5639,15 +5636,15 @@ LoopVectorizationCostModel::calculateReg
     if (!Ends.count(I))
       continue;
 
-    // Skip ignored values.
-    if (ValuesToIgnore.count(I))
-      continue;
-
     // Remove all of the instructions that end at this location.
     InstrList &List = TransposeEnds[i];
     for (unsigned int j = 0, e = List.size(); j < e; ++j)
       OpenIntervals.erase(List[j]);
 
+    // Skip ignored values.
+    if (ValuesToIgnore.count(I))
+      continue;
+
     // For each VF find the maximum usage of registers.
     for (unsigned j = 0, e = VFs.size(); j < e; ++j) {
       if (VFs[j] == 1) {
@@ -5657,8 +5654,12 @@ LoopVectorizationCostModel::calculateReg
 
       // Count the number of live intervals.
       unsigned RegUsage = 0;
-      for (auto Inst : OpenIntervals)
+      for (auto Inst : OpenIntervals) {
+        // Skip ignored values for VF > 1.
+        if (VecValuesToIgnore.count(Inst))
+          continue;
         RegUsage += GetRegUsage(Inst->getType(), VFs[j]);
+      }
       MaxUsages[j] = std::max(MaxUsages[j], RegUsage);
     }
 
@@ -5830,6 +5831,7 @@ unsigned LoopVectorizationCostModel::get
   if (VF > 1 && MinBWs.count(I))
     RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
   VectorTy = ToVectorTy(RetTy, VF);
+  auto SE = PSE.getSE();
 
   // TODO: We need to estimate the cost of intrinsic calls.
   switch (I->getOpcode()) {
@@ -6158,6 +6160,79 @@ bool LoopVectorizationCostModel::isConse
   return false;
 }
 
+void LoopVectorizationCostModel::collectValuesToIgnore() {
+  // Ignore ephemeral values.
+  CodeMetrics::collectEphemeralValues(TheLoop, AC, ValuesToIgnore);
+
+  // Ignore type-promoting instructions we identified during reduction
+  // detection.
+  for (auto &Reduction : *Legal->getReductionVars()) {
+    RecurrenceDescriptor &RedDes = Reduction.second;
+    SmallPtrSetImpl<Instruction *> &Casts = RedDes.getCastInsts();
+    VecValuesToIgnore.insert(Casts.begin(), Casts.end());
+  }
+
+  // Ignore induction phis that are only used in either GetElementPtr or ICmp
+  // instruction to exit loop. Induction variables usually have large types and
+  // can have big impact when estimating register usage.
+  // This is for when VF > 1.
+  for (auto &Induction : *Legal->getInductionVars()) {
+    auto *PN = Induction.first;
+    auto *UpdateV = PN->getIncomingValueForBlock(TheLoop->getLoopLatch());
+
+    // Check that the PHI is only used by the induction increment (UpdateV) or
+    // by GEPs. Then check that UpdateV is only used by a compare instruction or
+    // the loop header PHI.
+    // FIXME: Need precise def-use analysis to determine if this instruction
+    // variable will be vectorized.
+    if (std::all_of(PN->user_begin(), PN->user_end(),
+                    [&](const User *U) -> bool {
+                      return U == UpdateV || isa<GetElementPtrInst>(U);
+                    }) &&
+        std::all_of(UpdateV->user_begin(), UpdateV->user_end(),
+                    [&](const User *U) -> bool {
+                      return U == PN || isa<ICmpInst>(U);
+                    })) {
+      VecValuesToIgnore.insert(PN);
+      VecValuesToIgnore.insert(UpdateV);
+    }
+  }
+
+  // Ignore instructions that will not be vectorized.
+  // This is for when VF > 1.
+  for (auto bb = TheLoop->block_begin(), be = TheLoop->block_end(); bb != be;
+       ++bb) {
+    for (auto &Inst : **bb) {
+      switch (Inst.getOpcode())
+      case Instruction::GetElementPtr: {
+        // Ignore GEP if its last operand is an induction variable so that it is
+        // a consecutive load/store and won't be vectorized as scatter/gather
+        // pattern.
+
+        GetElementPtrInst *Gep = cast<GetElementPtrInst>(&Inst);
+        unsigned NumOperands = Gep->getNumOperands();
+        unsigned InductionOperand = getGEPInductionOperand(Gep);
+        bool GepToIgnore = true;
+
+        // Check that all of the gep indices are uniform except for the
+        // induction operand.
+        for (unsigned i = 0; i != NumOperands; ++i) {
+          if (i != InductionOperand &&
+              !PSE.getSE()->isLoopInvariant(PSE.getSCEV(Gep->getOperand(i)),
+                                            TheLoop)) {
+            GepToIgnore = false;
+            break;
+          }
+        }
+
+        if (GepToIgnore)
+          VecValuesToIgnore.insert(&Inst);
+        break;
+      }
+    }
+  }
+}
+
 void InnerLoopUnroller::scalarizeInstruction(Instruction *Instr,
                                              bool IfPredicateStore) {
   assert(!Instr->getType()->isAggregateType() && "Can't handle vectors");

Added: llvm/trunk/test/Transforms/LoopVectorize/X86/reg-usage.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/X86/reg-usage.ll?rev=270113&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/X86/reg-usage.ll (added)
+++ llvm/trunk/test/Transforms/LoopVectorize/X86/reg-usage.ll Thu May 19 15:38:03 2016
@@ -0,0 +1,71 @@
+; RUN: opt < %s -debug-only=loop-vectorize -loop-vectorize -vectorizer-maximize-bandwidth -O2 -S 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+ at a = global [1024 x i8] zeroinitializer, align 16
+ at b = global [1024 x i8] zeroinitializer, align 16
+
+define i32 @foo() {
+; This function has a loop of SAD pattern. Here we check when VF = 16 the
+; register usage doesn't exceed 16.
+;
+; CHECK-LABEL: foo
+; CHECK:      LV(REG): VF = 4
+; CHECK-NEXT: LV(REG): Found max usage: 4
+; CHECK:      LV(REG): VF = 8
+; CHECK-NEXT: LV(REG): Found max usage: 7
+; CHECK:      LV(REG): VF = 16
+; CHECK-NEXT: LV(REG): Found max usage: 13
+
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  %add.lcssa = phi i32 [ %add, %for.body ]
+  ret i32 %add.lcssa
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %s.015 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+  %arrayidx = getelementptr inbounds [1024 x i8], [1024 x i8]* @a, i64 0, i64 %indvars.iv
+  %0 = load i8, i8* %arrayidx, align 1
+  %conv = zext i8 %0 to i32
+  %arrayidx2 = getelementptr inbounds [1024 x i8], [1024 x i8]* @b, i64 0, i64 %indvars.iv
+  %1 = load i8, i8* %arrayidx2, align 1
+  %conv3 = zext i8 %1 to i32
+  %sub = sub nsw i32 %conv, %conv3
+  %ispos = icmp sgt i32 %sub, -1
+  %neg = sub nsw i32 0, %sub
+  %2 = select i1 %ispos, i32 %sub, i32 %neg
+  %add = add nsw i32 %2, %s.015
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 1024
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+}
+
+define i64 @bar(i64* nocapture %a) {
+; CHECK-LABEL: bar
+; CHECK:       LV(REG): VF = 2
+; CHECK:       LV(REG): Found max usage: 4
+;
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  %add2.lcssa = phi i64 [ %add2, %for.body ]
+  ret i64 %add2.lcssa
+
+for.body:
+  %i.012 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+  %s.011 = phi i64 [ 0, %entry ], [ %add2, %for.body ]
+  %arrayidx = getelementptr inbounds i64, i64* %a, i64 %i.012
+  %0 = load i64, i64* %arrayidx, align 8
+  %add = add nsw i64 %0, %i.012
+  store i64 %add, i64* %arrayidx, align 8
+  %add2 = add nsw i64 %add, %s.011
+  %inc = add nuw nsw i64 %i.012, 1
+  %exitcond = icmp eq i64 %inc, 1024
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+}

Modified: llvm/trunk/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll?rev=270113&r1=270112&r2=270113&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll (original)
+++ llvm/trunk/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll Thu May 19 15:38:03 2016
@@ -16,7 +16,7 @@ target triple = "x86_64-unknown-linux-gn
 ; -vectorizer-maximize-bandwidth is indicated.
 ;
 ; CHECK-label: foo
-; CHECK: LV: Selecting VF: 16.
+; CHECK: LV: Selecting VF: 32.
 define void @foo() {
 entry:
   br label %for.body




More information about the llvm-commits mailing list