<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40">
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:#0563C1;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:#954F72;
text-decoration:underline;}
span.EmailStyle17
{mso-style-type:personal;
font-family:"Calibri",sans-serif;
color:windowtext;}
span.EmailStyle18
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:#1F497D;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang="EN-US" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal">Hello llvm-dev,<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">I would appreciate your feedback on the following problem. We’re trying to determine whether this is a bug in LLVM or not.<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">In the IR snippet below, we have two pointers<span style="color:#1F497D">
</span>(p and q) which initially point to two completely non-overlapping locations. Then, on every iteration of a loop, we swap the pointers and load<span style="color:#1F497D">
</span>from the first, followed by a store to the second.<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">1) AA says the two pointers are NoAlias, even though they do point to the same<span style="color:#1F497D">
</span>location if we consider them in distinct loop iterations. Is this right?<o:p></o:p></p>
<p class="MsoNormal">2) Dependence Analysis says there is no dependence between the load and the store. Is this right?<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">define float @f() {<o:p></o:p></p>
<p class="MsoNormal">entry:<o:p></o:p></p>
<p class="MsoNormal"> %g = alloca float, align 4<o:p></o:p></p>
<p class="MsoNormal"> %h = alloca float, align 4<o:p></o:p></p>
<p class="MsoNormal"> br label %for.body<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">for.cond.cleanup: <o:p></o:p></p>
<p class="MsoNormal"> ret float undef<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">for.body:<o:p></o:p></p>
<p class="MsoNormal"> %p = phi float* [ %g, %entry ], [ %q, %for.body ]<o:p></o:p></p>
<p class="MsoNormal"> %q = phi float* [ %h, %entry ], [ %p, %for.body ]<o:p></o:p></p>
<p class="MsoNormal"> %0 = load float, float* %p, align 4<o:p></o:p></p>
<p class="MsoNormal"> store float undef, float* %q, align 4<o:p></o:p></p>
<p class="MsoNormal"> br i1 undef, label %for.cond.cleanup, label %for.body<o:p></o:p></p>
<p class="MsoNormal">}<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">AliasSet[0x872d800, 1] must alias, Ref Pointers: (float* %p, LocationSize::precise(4))<o:p></o:p></p>
<p class="MsoNormal">AliasSet[0x872d8b0, 1] must alias, Mod Pointers: (float* %q, LocationSize::precise(4))<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">da analyze - <o:p></o:p></p>
<p class="MsoNormal"> %0 = load float, float* %p, align 4 ; I added these two debug statements, DA doesn’t print the values it is looking at…<o:p></o:p></p>
<p class="MsoNormal"> store float undef, float* %q, align 4<o:p></o:p></p>
<p class="MsoNormal">none!<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">--<o:p></o:p></p>
<p class="MsoNormal">Felipe<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
</body>
</html>