<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 14 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
{font-family:Tahoma;
panose-1:2 11 6 4 3 5 4 4 2 4;}
@font-face
{font-family:"Book Antiqua";
panose-1:2 4 6 2 5 3 5 3 3 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0cm;
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;}
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";}
p.MsoAcetate, li.MsoAcetate, div.MsoAcetate
{mso-style-priority:99;
mso-style-link:"Balloon Text Char";
margin:0cm;
margin-bottom:.0001pt;
font-size:8.0pt;
font-family:"Tahoma","sans-serif";}
span.BalloonTextChar
{mso-style-name:"Balloon Text Char";
mso-style-priority:99;
mso-style-link:"Balloon Text";
font-family:"Tahoma","sans-serif";}
span.EmailStyle20
{mso-style-type:personal;
font-family:"Book Antiqua","serif";
color:windowtext;
font-weight:normal;
font-style:normal;
text-decoration:none none;}
span.EmailStyle21
{mso-style-type:personal;
font-family:"Calibri","sans-serif";
color:#1F497D;}
span.EmailStyle22
{mso-style-type:personal;
font-family:"Calibri","sans-serif";
color:#1F497D;}
span.EmailStyle23
{mso-style-type:personal;
font-family:"Book Antiqua","serif";
color:#943634;
font-weight:normal;
font-style:normal;
text-decoration:none none;}
span.EmailStyle24
{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 72.0pt 72.0pt 72.0pt;}
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 lang="EN-GB" link="#0563C1" vlink="#954F72">
<div class="WordSection1">
<p class="MsoNormal"><span style="color:#1F497D">Hi Martin,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">As far as I understand, you need Clang builtin that would be mapped to LLVM select instruction with vector types?<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">It seems fairly generic and just as it works in OpenCL indeed. Unfortunately, we don’t have support for this in Clang yet.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">Cheers,<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">Anastasia<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p> </o:p></span></p>
<div>
<div style="border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0cm 0cm 0cm">
<p class="MsoNormal"><b><span lang="EN-US" style="font-size:10.0pt;font-family:"Tahoma","sans-serif"">From:</span></b><span lang="EN-US" style="font-size:10.0pt;font-family:"Tahoma","sans-serif""> Martin J. O'Riordan [mailto:martin.oriordan@movidius.com]
<br>
<b>Sent:</b> 13 June 2016 21:38<br>
<b>To:</b> Anastasia Stulova; 'Demikhovsky, Elena'; cfe-dev@lists.llvm.org<br>
<b>Cc:</b> nd<br>
<b>Subject:</b> RE: [cfe-dev] OpenCL 'select' as a builtin?<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">Hi Anastasia,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">My own thoughts on this were to mirror the structure of ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">__builtin_shufflevector</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’,
only with true/false instead of element indices. I just chose OpenCL’s ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">select</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’,
because it is the closest construct already supported by CLang/LLVM that came close to what I want, and there was just a possibility this already had some built-in form that I had not discovered (my code search answered my question anyway - thanks also to
Elana for your response).<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">For example, given an OpenCL ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">select</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’
of:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal" style="margin-left:36.0pt"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">float4 f1, f2;<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:36.0pt"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">int4 sel = { 0, -1, -1, 0 };<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:36.0pt"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">float4 res = select(f1, f2, sel);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">This might be represented by a built-in something like:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal" style="margin-left:36.0pt"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">float4 res = __builtin_select(f1, f2, false, true, true, false);<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">And as with ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">__builtin_shufflevector</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’
the IR normalisation/canonicalization could analogously transform code as expressed in many different ways to a single canonical form using ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">__builtin_select</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’.
Also, as with the ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">__builtin_shufflevector</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’,
the selectors for ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">__builtin_select</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’
would be restricted to constants just as the indices are for ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">__builtin_shufflevector</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’
and so not as flexible as OpenCL’s actual ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">select</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’
which can accept a variable selector. This doesn’t really bring in any OpenCL versus C/C++ vs other language issues, as the ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">__builtin_select</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’
would be language agnostic.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">The reason that I wondered about this built-in in the first place, was that I wanted to use lane-predication for some
operations. For example, let’s say I have:<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal" style="margin-left:36.0pt"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">int4 selectiveMultiply(int4 values, int4 selector, int multiplier) {<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:36.0pt"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US"> return [OpenCL]select(values, values * multiplier /* splat */, selector);<o:p></o:p></span></p>
<p class="MsoNormal" style="margin-left:36.0pt"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">}<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">If the ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">selector</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’
is the set ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">{false, true, true, false}</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’
then the code generated for the above is pretty convoluted, even when that set if known at compile-time via inlining. But if I could reduce this to a ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">__builtin_select</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’,
my custom lowering implementation could lower this to a single lane-predicated multiply instruction.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">Of course, this I can discover these patterns using exhaustive DAG-to-DAG analysis in a target specific fashion, but
if the idea was raised to a more abstract idiom within LLVM, then the analysis could be shared by all targets (as is shuffle), and only the target specific lowering really cares, and it can always ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New";color:black;mso-fareast-language:EN-US">expand</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US">’
if it can’t do anything special anyway - back to the generic status quo.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"> MartinO<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif";color:#943634;mso-fareast-language:EN-US"><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"><b><span lang="EN-US">From:</span></b><span lang="EN-US"> Anastasia Stulova [<a href="mailto:Anastasia.Stulova@arm.com">mailto:Anastasia.Stulova@arm.com</a>]
<br>
<b>Sent:</b> 13 June 2016 18:47<br>
<b>To:</b> Demikhovsky, Elena <<a href="mailto:elena.demikhovsky@intel.com">elena.demikhovsky@intel.com</a>>;
<a href="mailto:Martin.ORiordan@Movidius.com">Martin.ORiordan@Movidius.com</a>; 'cfe-dev@lists.llvm.org' (<a href="mailto:cfe-dev@lists.llvm.org">cfe-dev@lists.llvm.org</a>) <<a href="mailto:cfe-dev@lists.llvm.org">cfe-dev@lists.llvm.org</a>><br>
<b>Cc:</b> nd <<a href="mailto:nd@arm.com">nd@arm.com</a>><br>
<b>Subject:</b> RE: [cfe-dev] OpenCL 'select' as a builtin?<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><span lang="EN-IE"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">Wondering if it would make sense to share __builtin_select among languages, assuming it has the same format…<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D">Anastasia<o:p></o:p></span></p>
<p class="MsoNormal"><span style="color:#1F497D"><o:p> </o:p></span></p>
<div>
<div style="border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0cm 0cm 0cm">
<p class="MsoNormal"><b><span lang="EN-US" style="font-size:10.0pt;font-family:"Tahoma","sans-serif"">From:</span></b><span lang="EN-US" style="font-size:10.0pt;font-family:"Tahoma","sans-serif""> cfe-dev [<a href="mailto:cfe-dev-bounces@lists.llvm.org">mailto:cfe-dev-bounces@lists.llvm.org</a>]
<b>On Behalf Of </b>Demikhovsky, Elena via cfe-dev<br>
<b>Sent:</b> 13 June 2016 12:25<br>
<b>To:</b> <a href="mailto:Martin.ORiordan@Movidius.com">Martin.ORiordan@Movidius.com</a><br>
<b>Cc:</b> cfe-dev<br>
<b>Subject:</b> Re: [cfe-dev] OpenCL 'select' as a builtin?<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><a name="_MailEndCompose"><span lang="EN-US" style="color:#1F497D">No, there is no such intrinsic yet. We also need it for AVX-512 masked intrinsics.</span></a><span lang="EN-US" style="color:#1F497D"><o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="color:#1F497D">So it is worth to add.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="color:#1F497D">We use __builtin_ia32_select[b|w|d..]* meanwhile, which are not polymorphic.
<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="color:#1F497D">See </span><span lang="EN-US"><a href="http://reviews.llvm.org/D21060">http://reviews.llvm.org/D21060</a><span style="color:#1F497D">.<o:p></o:p></span></span></p>
<p class="MsoNormal"><span lang="EN-US" style="color:#1F497D"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-US" style="color:#1F497D"><o:p> </o:p></span></p>
<div>
<p class="MsoNormal" style="margin-left:36.0pt;text-indent:-18.0pt"><span lang="EN-US" style="font-size:12.0pt;color:#2F5496">-</span><span lang="EN-US" style="font-size:7.0pt;font-family:"Times New Roman","serif";color:#2F5496">
</span><b><i><span lang="EN-US" style="font-size:12.0pt;font-family:"Times New Roman","serif";color:#2F5496"> Elena<o:p></o:p></span></i></b></p>
</div>
<p class="MsoNormal"><span lang="EN-US" style="color:#1F497D"><o:p> </o:p></span></p>
<div style="border:none;border-left:solid blue 1.5pt;padding:0cm 0cm 0cm 4.0pt">
<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 lang="EN-US">From:</span></b><span lang="EN-US"> cfe-dev [<a href="mailto:cfe-dev-bounces@lists.llvm.org">mailto:cfe-dev-bounces@lists.llvm.org</a>]
<b>On Behalf Of </b>Martin J. O'Riordan via cfe-dev<br>
<b>Sent:</b> Saturday, June 11, 2016 08:05<br>
<b>To:</b> 'Clang Dev' <<a href="mailto:cfe-dev@lists.llvm.org">cfe-dev@lists.llvm.org</a>><br>
<b>Subject:</b> [cfe-dev] OpenCL 'select' as a builtin?<o:p></o:p></span></p>
</div>
</div>
<p class="MsoNormal"><span lang="EN-US"><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif"">Is there a builtin for CLang that implements the same semantics as OpenCL’s “select” function, but which can be used from C and C++?<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif""><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif"">I tried the obvious name ‘</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Courier New"">__builtin_select</span><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif"">’
but that doesn’t exist, and a trawl through the online docs didn’t reveal anything either.<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif""><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif"">Thanks,<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif""><o:p> </o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif""> MartinO<o:p></o:p></span></p>
<p class="MsoNormal"><span lang="EN-IE" style="font-size:12.0pt;font-family:"Book Antiqua","serif""><o:p> </o:p></span></p>
</div>
<p><span lang="EN-US">---------------------------------------------------------------------<br>
Intel Israel (74) Limited<o:p></o:p></span></p>
<p><span lang="EN-US">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.<o:p></o:p></span></p>
</div>
</body>
</html>