[BasicAA] Make better use of zext and sign information

Two related things:

 1. Fixes a bug when calculating the offset in GetLinearExpression. The code
    previously used zext to extend the offset, so negative offsets were converted
    to large positive ones.

 2. Enhance aliasGEP to deduce that, if the difference between two GEP
    allocations is positive and all the variables that govern the offset are also
    positive (i.e. the offset is strictly after the higher base pointer), then
    locations that fit in the gap between the two base pointers are NoAlias.

Patch by Nick White!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218714 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Analysis/BasicAliasAnalysis.cpp b/lib/Analysis/BasicAliasAnalysis.cpp
index 9cfd02c02186886a3b2cc23c1eba90fe19162767..f4052b9dbabf1c6dd17217b738d79e0a8dab1f0f 100644 (file)
--- a/lib/Analysis/BasicAliasAnalysis.cpp
+++ b/lib/Analysis/BasicAliasAnalysis.cpp
@@ -254,7 +254,10 @@ static Value *GetLinearExpression(Value *V, APInt &Scale, APInt &Offset,
     Value *Result = GetLinearExpression(CastOp, Scale, Offset, Extension,
                                         DL, Depth+1, AT, DT);
     Scale = Scale.zext(OldWidth);
-    Offset = Offset.zext(OldWidth);
+
+    // We have to sign-extend even if Extension == EK_ZeroExt as we can't
+    // decompose a sign extension (i.e. zext(x - 1) != zext(x) - zext(-1)).
+    Offset = Offset.sext(OldWidth);
 
     return Result;
   }
@@ -1055,8 +1058,26 @@ BasicAliasAnalysis::aliasGEP(const GEPOperator *GEP1, uint64_t V1Size,
   // Grab the least significant bit set in any of the scales.
   if (!GEP1VariableIndices.empty()) {
     uint64_t Modulo = 0;
-    for (unsigned i = 0, e = GEP1VariableIndices.size(); i != e; ++i)
+    bool AllPositive = true;
+    for (unsigned i = 0, e = GEP1VariableIndices.size(); i != e; ++i) {
+      const Value *V = GEP1VariableIndices[i].V;
       Modulo |= (uint64_t)GEP1VariableIndices[i].Scale;
+
+      // If the variable's been zero-extended or begins with a zero then
+      //  we know it's positive. regardless of whether the value is signed
+      // or unsigned.
+      bool SignKnownZero, SignKnownOne;
+      ComputeSignBit(
+        const_cast<Value *>(V),
+        SignKnownZero, SignKnownOne,
+        DL, 0, AT, nullptr, DT);
+      bool IsZExt = GEP1VariableIndices[i].Extension == EK_ZeroExt;
+      AllPositive &= IsZExt || SignKnownZero;
+
+      // If the Value is currently positive but could change in a cycle,
+      // then we can't guarantee it'll always br positive.
+      AllPositive &= isValueEqualInPotentialCycles(V, V);
+    }
     Modulo = Modulo ^ (Modulo & (Modulo - 1));
 
     // We can compute the difference between the two addresses
@@ -1066,6 +1087,12 @@ BasicAliasAnalysis::aliasGEP(const GEPOperator *GEP1, uint64_t V1Size,
     if (V1Size != UnknownSize && V2Size != UnknownSize &&
         ModOffset >= V2Size && V1Size <= Modulo - ModOffset)
       return NoAlias;
+
+    // If we know all the variables are positive, then GEP1 >= GEP1BasePtr.
+    // If GEP1BasePtr > V2 (GEP1BaseOffset > 0) then we know the pointers
+    // don't alias if V2Size can fit in the gap between V2 and GEP1BasePtr.
+    if (AllPositive && GEP1BaseOffset > 0 && V2Size <= (uint64_t) GEP1BaseOffset)
+      return NoAlias;
   }
 
   // Statically, we can see that the base objects are the same, but the

diff --git a/test/Analysis/BasicAA/phi-aa.ll b/test/Analysis/BasicAA/phi-aa.ll
index 74279e1c4c93769c1e81db4fc1295e1176ebdf83..c1100f1d36fc73eb4ad8472b5be963949faf1ef0 100644 (file)
--- a/test/Analysis/BasicAA/phi-aa.ll
+++ b/test/Analysis/BasicAA/phi-aa.ll
@@ -39,6 +39,7 @@ return:
 
 ; CHECK-LABEL: pr18068
 ; CHECK: MayAlias: i32* %0, i32* %arrayidx5
+; CHECK: NoAlias: i32* %arrayidx13, i32* %arrayidx5
 
 define i32 @pr18068(i32* %jj7, i32* %j) {
 entry:

diff --git a/test/Analysis/BasicAA/zext.ll b/test/Analysis/BasicAA/zext.ll
new file mode 100644 (file)
index 0000000..07912d5
--- /dev/null
+++ b/test/Analysis/BasicAA/zext.ll
@@ -0,0 +1,65 @@
+; RUN: opt < %s -basicaa -aa-eval -print-all-alias-modref-info -disable-output 2>&1 | FileCheck %s
+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"
+
+; CHECK-LABEL: test_with_zext
+; CHECK:  NoAlias: i8* %a, i8* %b
+
+define void @test_with_zext() {
+  %1 = tail call i8* @malloc(i64 120)
+  %a = getelementptr inbounds i8* %1, i64 8
+  %2 = getelementptr inbounds i8* %1, i64 16
+  %3 = zext i32 3 to i64
+  %b = getelementptr inbounds i8* %2, i64 %3
+  ret void
+}
+
+; CHECK-LABEL: test_with_lshr
+; CHECK:  NoAlias: i8* %a, i8* %b
+
+define void @test_with_lshr(i64 %i) {
+  %1 = tail call i8* @malloc(i64 120)
+  %a = getelementptr inbounds i8* %1, i64 8
+  %2 = getelementptr inbounds i8* %1, i64 16
+  %3 = lshr i64 %i, 2
+  %b = getelementptr inbounds i8* %2, i64 %3
+  ret void
+}
+
+; CHECK-LABEL: test_with_a_loop
+; CHECK:  NoAlias: i8* %a, i8* %b
+
+define void @test_with_a_loop() {
+  %1 = tail call i8* @malloc(i64 120)
+  %a = getelementptr inbounds i8* %1, i64 8
+  %2 = getelementptr inbounds i8* %1, i64 16
+  br label %for.loop
+
+for.loop:
+  %i = phi i32 [ 0, %0 ], [ %i.next, %for.loop ]
+  %3 = zext i32 %i to i64
+  %b = getelementptr inbounds i8* %2, i64 %3
+  %i.next = add nuw nsw i32 %i, 1
+  %4 = icmp eq i32 %i.next, 10
+  br i1 %4, label %for.loop.exit, label %for.loop
+
+for.loop.exit:
+  ret void
+}
+
+; CHECK-LABEL: test_sign_extension
+; CHECK:  PartialAlias: i64* %b.i64, i8* %a
+
+define void @test_sign_extension(i32 %p) {
+  %1 = tail call i8* @malloc(i64 120)
+  %p.64 = zext i32 %p to i64
+  %a = getelementptr inbounds i8* %1, i64 %p.64
+  %p.minus1 = add i32 %p, -1
+  %p.minus1.64 = zext i32 %p.minus1 to i64
+  %b.i8 = getelementptr inbounds i8* %1, i64 %p.minus1.64
+  %b.i64 = bitcast i8* %b.i8 to i64*
+  ret void
+}
+
+; Function Attrs: nounwind
+declare noalias i8* @malloc(i64)