<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=utf-8">
<meta name="Generator" content="Microsoft Word 15 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:Helvetica;
panose-1:2 11 6 4 2 2 2 2 2 4;}
@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;}
@font-face
{font-family:Consolas;
panose-1:2 11 6 9 2 2 4 3 2 4;}
@font-face
{font-family:"Lucida Sans Unicode";
panose-1:2 11 6 2 3 5 4 2 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman",serif;
color:black;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
p
{mso-style-priority:99;
mso-margin-top-alt:auto;
margin-right:0cm;
mso-margin-bottom-alt:auto;
margin-left:0cm;
font-size:12.0pt;
font-family:"Times New Roman",serif;
color:black;}
pre
{mso-style-priority:99;
mso-style-link:"HTML Preformatted Char";
margin:0cm;
margin-bottom:.0001pt;
font-size:10.0pt;
font-family:"Courier New";
color:black;}
span.apple-converted-space
{mso-style-name:apple-converted-space;}
span.HTMLPreformattedChar
{mso-style-name:"HTML Preformatted Char";
mso-style-priority:99;
mso-style-link:"HTML Preformatted";
font-family:Consolas;
color:black;}
span.EmailStyle21
{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:612.0pt 792.0pt;
margin:72.0pt 90.0pt 72.0pt 90.0pt;}
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 bgcolor="white" lang="EN-US" link="blue" vlink="purple">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">+1 for “</span>just rerun the vectorizer<span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">” on the scalar remainder loop, as the
proposed decision process is broken down into “first determine best VF for main loop, then determine best next EpilogVF for remainder loop” anyhow:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"> const LoopVectorizationCostModel::VectorizationFactor EpilogVF =<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"> CM.identifyNextProfitableVF(VF.Width);<o:p></o:p></span></p>
<p class="MsoNormal"><a name="_MailEndCompose"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></a></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">Raising some aspects:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">o The unroll factor may also affect the best EpilogVF. For instance, if UF=1 then EpilogVF < VF, as the patch currently enforces. But if UF is larger the next
profitable EpilogVF could be equal to VF.<br>
<br>
<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">o The scalar loop serves two purposes, as determined by its two pre-headers: either as a default in case runtime dependence checks fail, or as a remainder loop
in which case it is known to be vectorizable with trip count less-than VF*UF (or equal-to it*). Would be good to keep this in mind when rerunning.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">(*) Note that if original loop requiresScalarEpilogue(), the trip count of the remainder loop may be equal to VF*UF, and/or the vectorized remainder loop may
too require a scalar epilogue.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">o It should be interesting to see how a single masked iteration that uses the original VF, say for UF=1, works. LV should hopefully already support most of what’s
needed.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">o The original Trip Count clearly affects the profitability of vectorizing the remainder loop. Would be good to leverage any information that can be derived about
TC either statically or based on profiling, when determining EpilogVF. Potential speedups and overheads/slowdowns could possibly be demonstrated using extreme cases; what would the best and worst cases be? Perhaps TinyTripCountVectorThreshold is also affected?<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">o Finally, VPlan is currently modeling how to vectorize the loop body according to the potentially profitable VF’s. It’s modelling could be used to generate vector
code for both body and remainder, and to consider their combined, overall cost.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D">Ayal.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1F497D"><o:p> </o:p></span></p>
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm">
<p class="MsoNormal"><a name="_____replyseparator"></a><b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:windowtext">From:</span></b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:windowtext"> llvm-dev [mailto:llvm-dev-bounces@lists.llvm.org]
<b>On Behalf Of </b>Hal Finkel via llvm-dev<br>
<b>Sent:</b> Friday, February 24, 2017 00:14<br>
<b>To:</b> Adam Nemet <anemet@apple.com>; Nema, Ashutosh <Ashutosh.Nema@amd.com><br>
<b>Cc:</b> llvm-dev <llvm-dev@lists.llvm.org><br>
<b>Subject:</b> Re: [llvm-dev] [Proposal][RFC] Epilog loop vectorization<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<p><o:p> </o:p></p>
<div>
<p class="MsoNormal">On 02/22/2017 11:52 AM, Adam Nemet via llvm-dev wrote:<o:p></o:p></p>
</div>
<blockquote style="margin-top:5.0pt;margin-bottom:5.0pt">
<div>
<p class="MsoNormal">Hi Ashutosh,<o:p></o:p></p>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<blockquote style="margin-top:5.0pt;margin-bottom:5.0pt">
<div>
<p class="MsoNormal">On Feb 22, 2017, at 1:57 AM, Nema, Ashutosh via llvm-dev <<a href="mailto:llvm-dev@lists.llvm.org">llvm-dev@lists.llvm.org</a>> wrote:<o:p></o:p></p>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Hi,</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">This is a proposal about epilog loop vectorization.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Currently Loop Vectorizer inserts an epilogue loop for handling loops that don’t have known iteration counts.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">The Loop Vectorizer supports loops with an unknown trip count, unknown trip count may not be a multiple of the vector width, and the vectorizer
has to execute the last few iterations as scalar code. It keeps a scalar copy of the loop for the remaining iterations.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Loop with the large width has a high possibility of executing many scalar iterations.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">i.e. i8 data type with 256bits target register can vectorize with vector width 32, with that maximum trip count possibility for scalar(epilog)
loop is 31, which is significant & worth vectorizing.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Large vector factor has following challenges:</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div style="margin-left:36.0pt">
<p class="MsoNormal" style="text-indent:-18.0pt"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif">1)</span><span style="font-size:7.0pt"> <span class="apple-converted-space"> </span></span><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Possibility
of remainder iteration is substantial.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div style="margin-left:36.0pt">
<p class="MsoNormal" style="text-indent:-18.0pt"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif">2)</span><span style="font-size:7.0pt"> <span class="apple-converted-space"> </span></span><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Actual
trip count at runtime is substantial but not meeting minimum trip count to execute vector loop.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">These challenges can be addressed by mask instructions, but these instructions are limited and may not be available to all targets.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">By epilog vectorization our aim to vectorize epilog loop where original loop is vectorized with large vector factor and has a high possibility
of executing scalar iterations.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">This require following changes:</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div style="margin-left:36.0pt">
<p class="MsoNormal" style="text-indent:-18.0pt"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif">1)</span><span style="font-size:7.0pt"> <span class="apple-converted-space"> </span></span><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Costing:
Preserve all profitable vector factor.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div style="margin-left:36.0pt">
<p class="MsoNormal" style="text-indent:-18.0pt"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif">2)</span><span style="font-size:7.0pt"> <span class="apple-converted-space"> </span></span><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Transform:
Create an additional vector loop with next profitable vector factor.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
</div>
</blockquote>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">Is this something that you propose to be on by default for wide VPU architectures without masking support? I.e. how widely is this applicable? If not then perhaps a better strategy would be to just annotate the remainder loop with some
metadata to limit the vectorization factor and just rerun the vectorizer.<o:p></o:p></p>
</div>
</div>
</blockquote>
<p class="MsoNormal"><br>
Why would this solution (annotating the remainder loop to limit vectorization and rerunning the vectorization process) not be preferred regardless?<br>
<br>
One issue that might be relevant here are runtime aliasing checks, which are probably going to be redundant, or partially redundant, between the different vectorized versions. Will we be able to do any necessary cleanup after the fact? Moreover, we often don't
hoist (unswitch) these checks out of inner loops (perhaps because they're inside the trip-count checks?); I wonder if the proposed block structure will make this situation better or worse (or have no overall effect).<br>
<br>
Thanks again,<br>
Hal<br>
<br>
<br>
<o:p></o:p></p>
<blockquote style="margin-top:5.0pt;margin-bottom:5.0pt">
<div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">Adam<o:p></o:p></p>
</div>
<p class="MsoNormal"><br>
<br>
<o:p></o:p></p>
<blockquote style="margin-top:5.0pt;margin-bottom:5.0pt">
<div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Please refer attached file (BlockLayout.png) for the details about transformed block layout.</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Patch is available at:<span class="apple-converted-space"> </span><a href="https://reviews.llvm.org/D30247"><span style="color:#954F72">https://reviews.llvm.org/D30247</span></a></span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white"> </span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Regards,</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Lucida Sans Unicode",sans-serif;background:white">Ashutosh</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"><o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"> <o:p></o:p></span></p>
</div>
<p class="MsoNormal"><BlockLayout.png><span style="font-size:9.0pt;font-family:"Helvetica",sans-serif">_______________________________________________<br>
LLVM Developers mailing list<br>
</span><a href="mailto:llvm-dev@lists.llvm.org"><span style="font-size:9.0pt;font-family:"Helvetica",sans-serif;color:#954F72">llvm-dev@lists.llvm.org</span></a><span style="font-size:9.0pt;font-family:"Helvetica",sans-serif"><br>
</span><a href="http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev"><span style="font-size:9.0pt;font-family:"Helvetica",sans-serif;color:#954F72">http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev</span></a><o:p></o:p></p>
</div>
</blockquote>
</div>
<p class="MsoNormal"><br>
<br>
<br>
<br>
<o:p></o:p></p>
<pre>_______________________________________________<o:p></o:p></pre>
<pre>LLVM Developers mailing list<o:p></o:p></pre>
<pre><a href="mailto:llvm-dev@lists.llvm.org">llvm-dev@lists.llvm.org</a><o:p></o:p></pre>
<pre><a href="http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev">http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev</a><o:p></o:p></pre>
</blockquote>
<p class="MsoNormal"><br>
<br>
<o:p></o:p></p>
<pre>-- <o:p></o:p></pre>
<pre>Hal Finkel<o:p></o:p></pre>
<pre>Lead, Compiler Technology and Programming Languages<o:p></o:p></pre>
<pre>Leadership Computing Facility<o:p></o:p></pre>
<pre>Argonne National Laboratory<o:p></o:p></pre>
</div>
<p>---------------------------------------------------------------------<br>
Intel Israel (74) Limited</p>
<p>This e-mail and any attachments may contain confidential material for<br>
the sole use of the intended recipient(s). Any review or distribution<br>
by others is strictly prohibited. If you are not the intended<br>
recipient, please contact the sender and delete all copies.</p></body>
</html>