Add a dereferenceable attribute
This attribute indicates that the parameter or return pointer is
dereferenceable. Practically speaking, loads from such a pointer within the
associated byte range are safe to speculatively execute. Such pointer
parameters are common in source languages (C++ references, for example).
llvm-svn: 213385
diff --git a/llvm/test/Transforms/InstSimplify/compare.ll b/llvm/test/Transforms/InstSimplify/compare.ll
index 42084c9..94872d3 100644
--- a/llvm/test/Transforms/InstSimplify/compare.ll
+++ b/llvm/test/Transforms/InstSimplify/compare.ll
@@ -874,6 +874,21 @@
; CHECK: ret i1 false
}
+define i1 @nonnull_deref_arg(i32* dereferenceable(4) %i) {
+ %cmp = icmp eq i32* %i, null
+ ret i1 %cmp
+; CHECK-LABEL: @nonnull_deref_arg
+; CHECK: ret i1 false
+}
+
+define i1 @nonnull_deref_as_arg(i32 addrspace(1)* dereferenceable(4) %i) {
+ %cmp = icmp eq i32 addrspace(1)* %i, null
+ ret i1 %cmp
+; CHECK-LABEL: @nonnull_deref_as_arg
+; CHECK: icmp
+; CHECK ret
+}
+
declare nonnull i32* @returns_nonnull_helper()
define i1 @returns_nonnull() {
%call = call nonnull i32* @returns_nonnull_helper()
@@ -883,6 +898,25 @@
; CHECK: ret i1 false
}
+declare dereferenceable(4) i32* @returns_nonnull_deref_helper()
+define i1 @returns_nonnull_deref() {
+ %call = call dereferenceable(4) i32* @returns_nonnull_deref_helper()
+ %cmp = icmp eq i32* %call, null
+ ret i1 %cmp
+; CHECK-LABEL: @returns_nonnull_deref
+; CHECK: ret i1 false
+}
+
+declare dereferenceable(4) i32 addrspace(1)* @returns_nonnull_deref_as_helper()
+define i1 @returns_nonnull_as_deref() {
+ %call = call dereferenceable(4) i32 addrspace(1)* @returns_nonnull_deref_as_helper()
+ %cmp = icmp eq i32 addrspace(1)* %call, null
+ ret i1 %cmp
+; CHECK-LABEL: @returns_nonnull_as_deref
+; CHECK: icmp
+; CHECK: ret
+}
+
; If a bit is known to be zero for A and known to be one for B,
; then A and B cannot be equal.
define i1 @icmp_eq_const(i32 %a) nounwind {
diff --git a/llvm/test/Transforms/LICM/hoist-deref-load.ll b/llvm/test/Transforms/LICM/hoist-deref-load.ll
new file mode 100644
index 0000000..972d75f
--- /dev/null
+++ b/llvm/test/Transforms/LICM/hoist-deref-load.ll
@@ -0,0 +1,86 @@
+; RUN: opt -S -basicaa -licm < %s | FileCheck %s
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; This test represents the following function:
+; void test1(int * __restrict__ a, int * __restrict__ b, int &c, int n) {
+; for (int i = 0; i < n; ++i)
+; if (a[i] > 0)
+; a[i] = c*b[i];
+; }
+; and we want to hoist the load of %c out of the loop. This can be done only
+; because the dereferenceable attribute is on %c.
+
+; CHECK-LABEL: @test1
+; CHECK: load i32* %c, align 4
+; CHECK: for.body:
+
+define void @test1(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly nonnull dereferenceable(4) %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
+ %1 = load i32* %c, 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 @test1, but without the dereferenceable attribute on %c.
+; Without this attribute, we should not hoist the load of %c.
+
+; CHECK-LABEL: @test2
+; CHECK: if.then:
+; CHECK: load i32* %c, align 4
+
+define void @test2(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* nocapture readonly nonnull %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
+ %1 = load i32* %c, 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 }
+