summaryrefslogtreecommitdiffstats
path: root/llvm/test/Transforms
diff options
context:
space:
mode:
authorIgor Laevsky <igmyrj@gmail.com>2015-11-10 14:10:31 +0000
committerIgor Laevsky <igmyrj@gmail.com>2015-11-10 14:10:31 +0000
commit01c3692a105d04b87173ce8e875c484fb294ee52 (patch)
tree2922e99024dc190b6c0b8e3dfceb8f1383e4d3a8 /llvm/test/Transforms
parent21aa762226a2a92097a1a35640a07dcf6d162894 (diff)
downloadbcm5719-llvm-01c3692a105d04b87173ce8e875c484fb294ee52.tar.gz
bcm5719-llvm-01c3692a105d04b87173ce8e875c484fb294ee52.zip
Strip metadata when speculatively hoisting instructions
This is fix for PR24059. When we are hoisting instruction above some condition it may turn out that metadata on this instruction was control dependant on the condition. This metadata becomes invalid and we need to drop it. This patch should cover most obvious places of speculative execution (which I have found by greping isSafeToSpeculativelyExecute). I think there are more cases but at least this change covers the severe ones. Differential Revision: http://reviews.llvm.org/D14398 llvm-svn: 252604
Diffstat (limited to 'llvm/test/Transforms')
-rw-r--r--llvm/test/Transforms/LICM/hoist-deref-load.ll44
-rw-r--r--llvm/test/Transforms/SimplifyCFG/SpeculativeExec.ll26
2 files changed, 70 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LICM/hoist-deref-load.ll b/llvm/test/Transforms/LICM/hoist-deref-load.ll
index c384a858d1e..fd10c5d7503 100644
--- a/llvm/test/Transforms/LICM/hoist-deref-load.ll
+++ b/llvm/test/Transforms/LICM/hoist-deref-load.ll
@@ -388,5 +388,49 @@ for.end: ; preds = %for.inc, %entry
ret void
}
+; In this test we should be able to only hoist load from %cptr. We can't hoist
+; load from %c because it's dereferenceability can depend on %cmp1 condition.
+; By moving it out of the loop we break this dependency and can not rely
+; on the dereferenceability anymore.
+; In other words this test checks that we strip dereferenceability metadata
+; after hoisting an instruction.
+
+; CHECK-LABEL: @test10
+; CHECK: %c = load i32*, i32** %cptr
+; CHECK-NOT: dereferenceable
+; CHECK: if.then:
+; CHECK: load i32, i32* %c, align 4
+
+define void @test10(i32* noalias %a, i32* %b, i32** dereferenceable(8) %cptr, 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, i32* %a, i64 %indvars.iv
+ %0 = load i32, i32* %arrayidx, align 4
+ %cmp1 = icmp sgt i32 %0, 0
+ br i1 %cmp1, label %if.then, label %for.inc
+
+if.then: ; preds = %for.body
+ %c = load i32*, i32** %cptr, !dereferenceable !0
+ %1 = load i32, i32* %c, align 4
+ %arrayidx3 = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
+ %2 = load i32, 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 }
!0 = !{i64 4}
diff --git a/llvm/test/Transforms/SimplifyCFG/SpeculativeExec.ll b/llvm/test/Transforms/SimplifyCFG/SpeculativeExec.ll
index c23a96df52e..73f9a0f88ac 100644
--- a/llvm/test/Transforms/SimplifyCFG/SpeculativeExec.ll
+++ b/llvm/test/Transforms/SimplifyCFG/SpeculativeExec.ll
@@ -69,3 +69,29 @@ end:
ret i8* %x10
}
+
+define i32* @test5(i32 %a, i32 %b, i32 %c, i32* dereferenceable(10) %ptr1,
+ i32* dereferenceable(10) %ptr2, i32** dereferenceable(10) %ptr3) nounwind {
+; CHECK-LABEL: @test5(
+entry:
+ %tmp1 = icmp eq i32 %b, 0
+ br i1 %tmp1, label %bb1, label %bb3
+
+bb1: ; preds = %entry
+ %tmp2 = icmp sgt i32 %c, 1
+ br i1 %tmp2, label %bb2, label %bb3
+; CHECK: bb1:
+; CHECK-NEXT: icmp sgt i32 %c, 1
+; CHECK-NEXT: load i32*, i32** %ptr3
+; CHECK-NOT: dereferenceable
+; CHECK-NEXT: select i1 %tmp2, i32* %tmp3, i32* %ptr2
+; CHECK-NEXT: ret i32* %tmp3.ptr2
+
+bb2: ; preds = bb1
+ %tmp3 = load i32*, i32** %ptr3, !dereferenceable !{i64 10}
+ br label %bb3
+
+bb3: ; preds = %bb2, %entry
+ %tmp4 = phi i32* [ %ptr1, %entry ], [ %ptr2, %bb1 ], [ %tmp3, %bb2 ]
+ ret i32* %tmp4
+}
OpenPOWER on IntegriCloud