Hi Elena,<div><br></div><div>You might want to check with Craig about the X86 specifics, since I'm not very familiar with the X86 FMA work, but the DAG combines look good.</div><div><br></div><div>One minor style note:</div>
<div><br></div><div><div>+ // Negative multiplication when NegA xor NegB </div><div>+ bool NegMul = (NegA || NegB) && !(NegA && NegB); </div></div><div><br></div><div>This could be expressed as </div><div>
<br></div><div>bool NegMul = NegA ^ NegB;</div><div>or</div><div>bool NegMul = NegA != NegB;</div><div><br></div><div>Otherwise it looks good to me.</div><div><br></div><div>Cheers,</div><div>Lang.</div><div><br><div class="gmail_quote">
On Wed, Jul 25, 2012 at 2:36 AM, Demikhovsky, Elena <span dir="ltr"><<a href="mailto:elena.demikhovsky@intel.com" target="_blank">elena.demikhovsky@intel.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div lang="EN-US" link="blue" vlink="purple">
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">I’d like to commit this patch.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">Hi Craig,<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">Any objections?<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">Thanks<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><u></u> <u></u></span></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"><u></u><u></u></span></p>
<div>
<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""> Demikhovsky, Elena
<br>
<b>Sent:</b> Tuesday, July 24, 2012 09:51<br>
<b>To:</b> 'Lang Hames'<br>
<b>Subject:</b> RE: [llvm-commits] Please review: FMA implementation for X86 architecture<u></u><u></u></span></p>
</div>
</div><div class="im">
<p class="MsoNormal"><u></u> <u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">Hi Lang,<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">You are right. The expression x--(y*z) was converted to x+(y*z) before it reaches Combine().<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">I removed the code bellow.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">May I commit?
<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d">Thanks<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri","sans-serif";color:#1f497d"><u></u> <u></u></span></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"><u></u><u></u></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""> Lang Hames [<a href="mailto:lhames@gmail.com" target="_blank">mailto:lhames@gmail.com</a>]
<br>
<b>Sent:</b> Tuesday, July 24, 2012 00:19<br>
<b>To:</b> Demikhovsky, Elena<br>
<b>Cc:</b> Commit Messages and Patches for LLVM<br>
<b>Subject:</b> Re: [llvm-commits] Please review: FMA implementation for X86 architecture<u></u><u></u></span></p>
</div>
<p class="MsoNormal"><u></u> <u></u></p>
</div><p class="MsoNormal">Hi Elena,<u></u><u></u></p><div><div class="h5">
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">The second DAG combine looks a bit off:<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<div>
<p class="MsoNormal">+ // fold (fsub x, -(fmul, y, z)) -> (fma (fneg y), z, x)<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">That implies:<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">x - -(y * z) ==> -y * z + a<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Which isn't a valid transformation. You probably don't want the negate on 'y'.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">+ if (N1.getOpcode() == ISD::FNEG && <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">+ N1.getOperand(0).getOpcode() == ISD::FMUL &&<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">+ N1->hasOneUse() && N1.getOperand(0).hasOneUse()) {<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">+ SDValue N10 = N1.getOperand(0).getOperand(0);<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">+ SDValue N11 = N1.getOperand(0).getOperand(1);<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">+ return DAG.getNode(ISD::FMA, dl, VT,<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">+ DAG.getNode(ISD::FNEG, N1->getDebugLoc(), VT, N10),<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">+ N11, N1);<u></u><u></u></p>
</div>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Given the observation above, I think the ISD::FNEG should go away here. Also N1 is being used as the RHS addend. I think that should be N0?<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Otherwise it looks good to me.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Cheers,<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">Lang.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
<div>
<p class="MsoNormal">On Mon, Jul 23, 2012 at 8:43 AM, Demikhovsky, Elena <<a href="mailto:elena.demikhovsky@intel.com" target="_blank">elena.demikhovsky@intel.com</a>> wrote:<u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:12.0pt"><br>
I added code generation for FMA patterns on AVX2 architecture.<br>
<br>
- Elena<br>
<br>
<br>
---------------------------------------------------------------------<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>
_______________________________________________<br>
llvm-commits mailing list<br>
<a href="mailto:llvm-commits@cs.uiuc.edu" target="_blank">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><u></u><u></u></p>
</div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
</div></div></div><div><div class="h5">
<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></div></div></div>
</blockquote></div><br></div>