<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=Windows-1252">
<meta name="Generator" content="Microsoft Word 12 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:Wingdings;
panose-1:5 0 0 0 0 0 0 0 0 0;}
@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:Tahoma;
panose-1:2 11 6 4 3 5 4 4 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman","serif";}
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.MsoAcetate, li.MsoAcetate, div.MsoAcetate
{mso-style-priority:99;
mso-style-link:"Balloon Text Char";
margin:0in;
margin-bottom:.0001pt;
font-size:8.0pt;
font-family:"Tahoma","sans-serif";}
p.MsoListParagraph, li.MsoListParagraph, div.MsoListParagraph
{mso-style-priority:34;
margin-top:0in;
margin-right:0in;
margin-bottom:0in;
margin-left:.5in;
margin-bottom:.0001pt;
font-size:12.0pt;
font-family:"Times New Roman","serif";}
span.hoenzb
{mso-style-name:hoenzb;}
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-reply;
font-family:"Calibri","sans-serif";
color:#1F497D;}
.MsoChpDefault
{mso-style-type:export-only;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
/* List Definitions */
@list l0
{mso-list-id:1706522901;
mso-list-type:hybrid;
mso-list-template-ids:-233682420 1565300604 67698691 67698693 67698689 67698691 67698693 67698689 67698691 67698693;}
@list l0:level1
{mso-level-number-format:bullet;
mso-level-text:\F0D8;
mso-level-tab-stop:none;
mso-level-number-position:left;
text-indent:-.25in;
font-family:Wingdings;
mso-fareast-font-family:Calibri;
mso-bidi-font-family:Arial;}
ol
{margin-bottom:0in;}
ul
{margin-bottom:0in;}
--></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="blue" vlink="purple">
<div class="WordSection1">
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">I checked my optimization on codegen level against –O2 optimization. This is the code for comparison:<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">IR before –O2:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> %c = extractelement <8 x i32> %a, i32 1<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> %d = insertelement <8 x i32> %b, i32 %c, i32 7<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">The code:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> vunpcklps %ymm0, %ymm0, %ymm0 ## ymm0 = ymm0[0,0,1,1,4,4,5,5]<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> vperm2f128 $0, %ymm0, %ymm0, %ymm0 ## ymm0 = ymm0[0,1,0,1]<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> vblendps $128, %ymm0, %ymm1, %ymm0<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">After –O2:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> %d = shufflevector <8 x i32> %b, <8 x i32> %a, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 9><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>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">The code:<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> vextractf128 $1, %ymm1, %xmm2<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> vshufps $33, %xmm2, %xmm0, %xmm0 ## xmm0 = xmm0[1,0],xmm2[2,0]<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> vshufps $36, %xmm0, %xmm2, %xmm0 ## xmm0 = xmm2[0,1],xmm0[2,0]<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> vinsertf128 $1, %xmm0, %ymm1, %ymm0<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>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">IR before –O2:<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"> %c = extractelement <4 x i64> %a, i32 3<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> %d = insertelement <4 x i64> %b, i64 %c, i32 2<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">vunpckhpd %ymm0, %ymm0, %ymm0 ## ymm0 = ymm0[1,1,3,3]<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">vblendpd $4, %ymm0, %ymm1, %ymm0<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">IR after –O2<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"> %d = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 1, i32 7, i32 3><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">vextractf128 $1, %ymm1, %xmm2<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">vextractf128 $1, %ymm0, %xmm0<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">vpunpckhqdq %xmm2, %xmm0, %xmm0 ## xmm0 = xmm0[1],xmm2[1]<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">vinsertf128 $1, %xmm0, %ymm1, %ymm0<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">I have to say that the code, as I generated now in my own branch requires more changes in X86ISelLowering. I plan to send the patches one-by-one.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">And answering on your question<o:p></o:p></span></p>
<p class="MsoListParagraph" style="text-indent:-.25in;mso-list:l0 level1 lfo1"><![if !supportLists]><span style="font-family:Wingdings"><span style="mso-list:Ignore">Ø<span style="font:7.0pt "Times New Roman"">
</span></span></span><![endif]><span dir="LTR"></span>Or is this a pattern that parts of the backend will produce internally where the IR optimizers couldn't see it?<o:p></o:p></p>
<p class="MsoListParagraph"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D">Right, the optimizer does not see this pattern, our backend generates it later.<o:p></o:p></span></p>
<p class="MsoNormal"><b><i><span style="color:teal"><o:p> </o:p></span></i></b></p>
<p class="MsoNormal"><b><i><span style="color:teal"><o:p> </o:p></span></i></b></p>
<p class="MsoNormal"><b><i><span style="color:teal">- Elena</span></i></b><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1F497D"><o:p></o:p></span></p>
<div style="border:none;border-top:solid #B5C4DF 1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span style="font-size:10.0pt;font-family:"Tahoma","sans-serif"">From:</span></b><span style="font-size:10.0pt;font-family:"Tahoma","sans-serif""> Nick Lewycky [mailto:nlewycky@google.com]
<br>
<b>Sent:</b> Friday, July 13, 2012 21:43<br>
<b>To:</b> Demikhovsky, Elena<br>
<b>Cc:</b> Nick Lewycky; Commit Messages and Patches for LLVM<br>
<b>Subject:</b> Re: [llvm-commits] Please Review: AVX code optimization<o:p></o:p></span></p>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<p class="MsoNormal">On 11 July 2012 03:34, Demikhovsky, Elena <<a href="mailto:elena.demikhovsky@intel.com" target="_blank">elena.demikhovsky@intel.com</a>> wrote:<o:p></o:p></p>
<p class="MsoNormal">I'm not sure that all architectures will see performance gain.<br>
While building shuffles, I know that each shuffle will be replaced with one machine instruction.<br>
I also know that shuffle is cheaper (1 cycle) than extract (3 cycles) and insert (2 cycles).<br>
I know that blend is better than other shuffle. And this information is specific for X86 and written in IA optimization guide.<o:p></o:p></p>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">The IR-level optimizers already do transform your testcases into shufflevector instructions. Here's the result after opt -O2:<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<div>
<p class="MsoNormal">define <8 x i32> @test20(<8 x i32> %a, <8 x i32> %b) nounwind readnone {<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"> %d = shufflevector <8 x i32> %b, <8 x i32> %a, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 9><o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"> ret <8 x i32> %d<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">}<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">define <8 x i32> @test21(<8 x i32> %a, <8 x i32> %b) nounwind readnone {<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"> %d = shufflevector <8 x i32> %b, <8 x i32> %a, <8 x i32> <i32 0, i32 1, i32 9, i32 3, i32 4, i32 5, i32 6, i32 7><o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"> ret <8 x i32> %d<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">}<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">define <4 x i64> @test22(<4 x i64> %a, <4 x i64> %b) nounwind readnone {<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"> %d = shufflevector <4 x i64> %b, <4 x i64> %a, <4 x i32> <i32 0, i32 1, i32 7, i32 3><o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"> ret <4 x i64> %d<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">}<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">define <4 x i64> @test23(<4 x i64> %a, <4 x i64> %b) nounwind readnone {<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"> %d = shufflevector <4 x i64> %b, <4 x i64> %a, <4 x i32> <i32 0, i32 1, i32 7, i32 3><o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"> ret <4 x i64> %d<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal">}<o:p></o:p></p>
</div>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">In what case does the patch you sent in improve generated code? Running the optimizing code generator on unoptimized IR? Or is this a pattern that parts of the backend will produce internally where the IR optimizers couldn't see it?<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">Nick<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<blockquote style="border:none;border-left:solid #CCCCCC 1.0pt;padding:0in 0in 0in 6.0pt;margin-left:4.8pt;margin-right:0in">
<p class="MsoNormal"><span style="color:#888888"><br>
<span class="hoenzb">- Elena</span></span><o:p></o:p></p>
<div>
<p class="MsoNormal">-----Original Message-----<br>
From: Nick Lewycky [mailto:<a href="mailto:nicholas@mxc.ca">nicholas@mxc.ca</a>]<br>
Sent: Wednesday, July 11, 2012 11:47<br>
To: Demikhovsky, Elena<br>
Cc: Commit Messages and Patches for LLVM<br>
Subject: Re: [llvm-commits] Please Review: AVX code optimization<br>
<br>
Demikhovsky, Elena wrote:<br>
> I wrote an optimization for extractelement - insertelement sequences.<br>
> Please review.<br>
<br>
It looks like this is a dagcombine to turn insertelement+extractelement pairs into vector shuffles. Perhaps I'm missing a good reason, but why not do this as an IR optimization?<br>
<br>
Nick<o:p></o:p></p>
</div>
<div>
<p class="MsoNormal" style="margin-bottom:12.0pt">---------------------------------------------------------------------<br>
Intel Israel (74) Limited<br>
<br>
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.<br>
<br>
<o:p></o:p></p>
</div>
<div>
<div>
<p class="MsoNormal">_______________________________________________<br>
llvm-commits mailing list<br>
<a href="mailto:llvm-commits@cs.uiuc.edu">llvm-commits@cs.uiuc.edu</a><br>
<a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits" target="_blank">http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits</a><o:p></o:p></p>
</div>
</div>
</blockquote>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<font face="monospace">---------------------------------------------------------------------<br>
Intel Israel (74) Limited<br>
<br>
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.</font></body>
</html>