Make Value::isDereferenceablePointer handle offsets to pointer types with dereference...

When we have a parameter (or call site return) with a dereferenceable
attribute, it can specify the size of an array pointed to by that parameter. If
we have a value for which we can accumulate a constant offset to such a
parameter, then we can use that offset in a direct comparison with the size
specified by the dereferenceable attribute.

This enables us to handle cases like this:

  int foo(int a[static 3]) {
    return a[2]; /* this is always dereferenceable */
  }

llvm-svn: 213447

diff --git a/llvm/lib/IR/Value.cpp b/llvm/lib/IR/Value.cpp
index efdd6a7..94f979a 100644 (file)
--- a/llvm/lib/IR/Value.cpp
+++ b/llvm/lib/IR/Value.cpp
@@ -574,6 +574,27 @@ static bool isDereferenceablePointer(const Value *V, const DataLayout *DL,
 /// isDereferenceablePointer - Test if this value is always a pointer to
 /// allocated and suitably aligned memory for a simple load or store.
 bool Value::isDereferenceablePointer(const DataLayout *DL) const {
+  // When dereferenceability information is provided by a dereferenceable
+  // attribute, we know exactly how many bytes are dereferenceable. If we can
+  // determine the exact offset to the attributed variable, we can use that
+  // information here.
+  Type *Ty = getType()->getPointerElementType();
+  if (Ty->isSized() && DL) {
+    APInt Offset(DL->getTypeStoreSizeInBits(getType()), 0);
+    const Value *BV = stripAndAccumulateInBoundsConstantOffsets(*DL, Offset);
+
+    APInt DerefBytes(Offset.getBitWidth(), 0);
+    if (const Argument *A = dyn_cast<Argument>(BV))
+      DerefBytes = A->getDereferenceableBytes();
+    else if (ImmutableCallSite CS = BV)
+      DerefBytes = CS.getDereferenceableBytes(0);
+
+    if (DerefBytes.getBoolValue() && Offset.isNonNegative()) {
+      if (DerefBytes.uge(Offset + DL->getTypeStoreSize(Ty)))
+        return true;
+    }
+  }
+
   SmallPtrSet<const Value *, 32> Visited;
   return ::isDereferenceablePointer(this, DL, Visited);
 }

diff --git a/llvm/test/Transforms/LICM/hoist-deref-load.ll b/llvm/test/Transforms/LICM/hoist-deref-load.ll
index 972d75f..c230d1d 100644 (file)
--- a/llvm/test/Transforms/LICM/hoist-deref-load.ll
+++ b/llvm/test/Transforms/LICM/hoist-deref-load.ll
@@ -82,5 +82,87 @@ for.end:                                          ; preds = %for.inc, %entry
   ret void
 }
 
+; This test represents the following function:
+; void test3(int * restrict a, int * restrict b, int c[static 3], int n) {
+;   for (int i = 0; i < n; ++i)
+;     if (a[i] > 0)
+;       a[i] = c[2]*b[i];
+; }
+; and we want to hoist the load of c[2] out of the loop. This can be done only
+; because the dereferenceable attribute is on %c.
+
+; CHECK-LABEL: @test3
+; CHECK: load i32* %c2, align 4
+; CHECK: for.body:
+
+define void @test3(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly dereferenceable(12) %c, i32 %n) #0 {
+entry:
+  %cmp11 = icmp sgt i32 %n, 0
+  br i1 %cmp11, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.inc
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %cmp1 = icmp sgt i32 %0, 0
+  br i1 %cmp1, label %if.then, label %for.inc
+
+if.then:                                          ; preds = %for.body
+  %c2 = getelementptr inbounds i32* %c, i64 2
+  %1 = load i32* %c2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i64 %indvars.iv
+  %2 = load i32* %arrayidx3, align 4
+  %mul = mul nsw i32 %2, %1
+  store i32 %mul, i32* %arrayidx, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body, %if.then
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.inc, %entry
+  ret void
+}
+
+; This is the same as @test3, but with a dereferenceable attribute on %c with a
+; size too small to cover c[2] (and so we should not hoist it).
+
+; CHECK-LABEL: @test4
+; CHECK: if.then:
+; CHECK: load i32* %c2, align 4
+
+define void @test4(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly dereferenceable(11) %c, i32 %n) #0 {
+entry:
+  %cmp11 = icmp sgt i32 %n, 0
+  br i1 %cmp11, label %for.body, label %for.end
+
+for.body:                                         ; preds = %entry, %for.inc
+  %indvars.iv = phi i64 [ %indvars.iv.next, %for.inc ], [ 0, %entry ]
+  %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %0 = load i32* %arrayidx, align 4
+  %cmp1 = icmp sgt i32 %0, 0
+  br i1 %cmp1, label %if.then, label %for.inc
+
+if.then:                                          ; preds = %for.body
+  %c2 = getelementptr inbounds i32* %c, i64 2
+  %1 = load i32* %c2, align 4
+  %arrayidx3 = getelementptr inbounds i32* %b, i64 %indvars.iv
+  %2 = load i32* %arrayidx3, align 4
+  %mul = mul nsw i32 %2, %1
+  store i32 %mul, i32* %arrayidx, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %for.body, %if.then
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, %n
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.inc, %entry
+  ret void
+}
+
 attributes #0 = { nounwind uwtable }