[ValueTracking] An improvement to IR ValueTracking on Non-negative Integers

    
Since this change is known to cause performance degradations in some cases it's commited under a temporary flag which is turned off by default.

Patch by Li Huang

Differential Revision: https://reviews.llvm.org/D18777

llvm-svn: 284022

2 files changed, 48 insertions, 5 deletions

diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
index 6a4aaf1727a..69702db9ef5 100644
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -51,6 +51,12 @@ const unsigned MaxDepth = 6;
 static cl::opt<unsigned> DomConditionsMaxUses("dom-conditions-max-uses",
                                               cl::Hidden, cl::init(20));
 
+// This optimization is known to cause performance regressions is some cases,
+// keep it under a temporary flag for now.
+static cl::opt<bool>
+DontImproveNonNegativePhiBits("dont-improve-non-negative-phi-bits",
+                              cl::Hidden, cl::init(true));
+
 /// Returns the bitwidth of the given scalar or pointer type (if unknown returns
 /// 0). For vector types, returns the element type's bitwidth.
 static unsigned getBitWidth(Type *Ty, const DataLayout &DL) {
@@ -1300,9 +1306,46 @@ static void computeKnownBitsFromOperator(const Operator *I, APInt &KnownZero,
           APInt KnownZero3(KnownZero), KnownOne3(KnownOne);
           computeKnownBits(L, KnownZero3, KnownOne3, Depth + 1, Q);
 
-          KnownZero = APInt::getLowBitsSet(BitWidth,
-                                           std::min(KnownZero2.countTrailingOnes(),
-                                                    KnownZero3.countTrailingOnes()));
+          KnownZero = APInt::getLowBitsSet(
+              BitWidth, std::min(KnownZero2.countTrailingOnes(),
+                                 KnownZero3.countTrailingOnes()));
+
+          if (DontImproveNonNegativePhiBits)
+            break;
+
+          auto *OverflowOp = dyn_cast<OverflowingBinaryOperator>(LU);
+          if (OverflowOp && OverflowOp->hasNoSignedWrap()) {
+            // If initial value of recurrence is nonnegative, and we are adding
+            // a nonnegative number with nsw, the result can only be nonnegative
+            // or poison value regardless of the number of times we execute the
+            // add in phi recurrence. If initial value is negative and we are
+            // adding a negative number with nsw, the result can only be
+            // negative or poison value. Similar arguments apply to sub and mul.
+            //
+            // (add non-negative, non-negative) --> non-negative
+            // (add negative, negative) --> negative
+            if (Opcode == Instruction::Add) {
+              if (KnownZero2.isNegative() && KnownZero3.isNegative())
+                KnownZero.setBit(BitWidth - 1);
+              else if (KnownOne2.isNegative() && KnownOne3.isNegative())
+                KnownOne.setBit(BitWidth - 1);
+            }
+
+            // (sub nsw non-negative, negative) --> non-negative
+            // (sub nsw negative, non-negative) --> negative
+            else if (Opcode == Instruction::Sub && LL == I) {
+              if (KnownZero2.isNegative() && KnownOne3.isNegative())
+                KnownZero.setBit(BitWidth - 1);
+              else if (KnownOne2.isNegative() && KnownZero3.isNegative())
+                KnownOne.setBit(BitWidth - 1);
+            }
+
+            // (mul nsw non-negative, non-negative) --> non-negative
+            else if (Opcode == Instruction::Mul && KnownZero2.isNegative() &&
+                     KnownZero3.isNegative())
+              KnownZero.setBit(BitWidth - 1);
+          }
+
           break;
         }
       }
diff --git a/llvm/test/Transforms/BBVectorize/loop1.ll b/llvm/test/Transforms/BBVectorize/loop1.ll
index 70a5def4222..0a0a6629897 100644
--- a/llvm/test/Transforms/BBVectorize/loop1.ll
+++ b/llvm/test/Transforms/BBVectorize/loop1.ll
@@ -1,7 +1,7 @@
 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"
 ; RUN: opt < %s -bb-vectorize -bb-vectorize-req-chain-depth=3 -bb-vectorize-ignore-target-info -instcombine -gvn -S | FileCheck %s
-; RUN: opt < %s -basicaa -loop-unroll -unroll-threshold=45 -unroll-allow-partial -bb-vectorize -bb-vectorize-req-chain-depth=3 -bb-vectorize-ignore-target-info -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-UNRL
+; RUN: opt < %s -dont-improve-non-negative-phi-bits=false -basicaa -loop-unroll -unroll-threshold=45 -unroll-allow-partial -bb-vectorize -bb-vectorize-req-chain-depth=3 -bb-vectorize-ignore-target-info -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-UNRL
 ; The second check covers the use of alias analysis (with loop unrolling).
 
 define void @test1(double* noalias %out, double* noalias %in1, double* noalias %in2) nounwind uwtable {
@@ -83,7 +83,7 @@ for.body:                                         ; preds = %for.body, %entry
 ; CHECK-UNRL: %add12 = fadd <2 x double> %add7, %mul11
 ; CHECK-UNRL: %4 = bitcast double* %arrayidx14 to <2 x double>*
 ; CHECK-UNRL: store <2 x double> %add12, <2 x double>* %4, align 8
-; CHECK-UNRL: %indvars.iv.next.1 = add nsw i64 %indvars.iv, 2
+; CHECK-UNRL: %indvars.iv.next.1 = add nuw nsw i64 %indvars.iv, 2
 ; CHECK-UNRL: %lftr.wideiv.1 = trunc i64 %indvars.iv.next.1 to i32
 ; CHECK-UNRL: %exitcond.1 = icmp eq i32 %lftr.wideiv.1, 10
 ; CHECK-UNRL: br i1 %exitcond.1, label %for.end, label %for.body