<html><body>
<p><font size="2" face="sans-serif">Hi Hal,</font><br>
<br>
<font size="2" face="sans-serif">I am wondering if we should move the FP_EXTEND cases to the PPC-specific combiner:</font><br>
<br>
<font size="2" face="sans-serif">(fadd (fpext (fmul x, y)), z) -> (fma (fpext x), (fpext y), z)</font><br>
<br>
<font size="2" face="sans-serif">We know that for PPC the FPEXT nodes will be removed, but it'll likely not be the case for other architectures. For those, you end up with one FMADD rather than one FMUL and one FADD, but also have two FPEXT nodes rather than one. I would not expect this to take more cycles to run, but there's no way to systematically check that since the cost models are not necessarily accurate.</font><br>
<br>
<font size="2" face="sans-serif">In the end, the "aggressive" flag only ensures that you can combine one FMUL node with many FADD nodes.</font><br>
<br>
<font size="2" face="sans-serif">What do you think?</font><br>
<br>
<font size="2" face="sans-serif">Olivier</font><br>
<br>
<img width="16" height="16" src="cid:1__=0ABBF75BDFF2E0888f9e8a93df938@us.ibm.com" border="0" alt="Inactive hide details for Hal Finkel ---01/08/2015 08:36:56 PM-------- Original Message ----- > From: "Hal Finkel" <hfinkel@anl"><font size="2" color="#424282" face="sans-serif">Hal Finkel ---01/08/2015 08:36:56 PM-------- Original Message ----- > From: "Hal Finkel" <hfinkel@anl.gov></font><br>
<br>
<font size="1" color="#5F5F5F" face="sans-serif">From: </font><font size="1" face="sans-serif">Hal Finkel <hfinkel@anl.gov></font><br>
<font size="1" color="#5F5F5F" face="sans-serif">To: </font><font size="1" face="sans-serif">Owen Anderson <resistor@mac.com></font><br>
<font size="1" color="#5F5F5F" face="sans-serif">Cc: </font><font size="1" face="sans-serif">Olivier H Sallenave/Watson/IBM@IBMUS, <llvm-commits@cs.uiuc.edu></font><br>
<font size="1" color="#5F5F5F" face="sans-serif">Date: </font><font size="1" face="sans-serif">01/08/2015 08:36 PM</font><br>
<font size="1" color="#5F5F5F" face="sans-serif">Subject: </font><font size="1" face="sans-serif">Re: [PATCH] [LLVMdev] More FMA folding opportunities</font><br>
<hr width="100%" size="2" align="left" noshade style="color:#8091A5; "><br>
<br>
<br>
<tt><font size="2">----- Original Message -----<br>
> From: "Hal Finkel" <hfinkel@anl.gov><br>
> To: "Owen Anderson" <resistor@mac.com><br>
> Cc: "Olivier H Sallenave" <ohsallen@us.ibm.com>, llvm-commits@cs.uiuc.edu<br>
> Sent: Thursday, January 8, 2015 6:48:34 PM<br>
> Subject: Re: [PATCH] [LLVMdev] More FMA folding opportunities<br>
> <br>
> ----- Original Message -----<br>
> > From: "Hal Finkel" <hfinkel@anl.gov><br>
> > To: "Owen Anderson" <resistor@mac.com><br>
> > Cc: "Olivier H Sallenave" <ohsallen@us.ibm.com>,<br>
> > llvm-commits@cs.uiuc.edu<br>
> > Sent: Thursday, January 8, 2015 6:19:14 PM<br>
> > Subject: Re: [PATCH] [LLVMdev] More FMA folding opportunities<br>
> > <br>
> > ----- Original Message -----<br>
> > > From: "Owen Anderson" <resistor@mac.com><br>
> > > To: "Hal Finkel" <hfinkel@anl.gov><br>
> > > Cc: "Olivier H Sallenave" <ohsallen@us.ibm.com>,<br>
> > > llvm-commits@cs.uiuc.edu<br>
> > > Sent: Thursday, January 8, 2015 6:16:57 PM<br>
> > > Subject: Re: [PATCH] [LLVMdev] More FMA folding opportunities<br>
> > > <br>
> > > <br>
> > > <br>
> > > <br>
> > > <br>
> > > <br>
> > > On Jan 8, 2015, at 6:06 PM, Hal Finkel < hfinkel@anl.gov > wrote:<br>
> > > <br>
> > > Olivier, Aditya is right. You need to add the FP_EXTEND to the<br>
> > > operands of the resulting FMA as appropriate. Can you please fix<br>
> > > that? We can also move those under the "aggressive" flag for now.<br>
> > > <br>
> > > <br>
> > > Can you fix or revert this ASAP, please? The missing extends are<br>
> > > breaking our branches pretty badly.<br>
> > <br>
> > Yep, will do in a few minutes.<br>
> <br>
> I moved the transformations behind the aggressive flag in r225485 --<br>
> that should unbreak your builds while I fix the extends.<br>
<br>
FP_EXTEND nodes added as of r225492. Thanks for pointing this out!<br>
<br>
-Hal<br>
<br>
> <br>
> -Hal<br>
> <br>
> > <br>
> > -Hal<br>
> > <br>
> > > <br>
> > > <br>
> > > —Owen<br>
> > <br>
> > --<br>
> > Hal Finkel<br>
> > Assistant Computational Scientist<br>
> > Leadership Computing Facility<br>
> > Argonne National Laboratory<br>
> > <br>
> > _______________________________________________<br>
> > llvm-commits mailing list<br>
> > llvm-commits@cs.uiuc.edu<br>
> > </font></tt><tt><font size="2"><a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits">http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits</a></font></tt><tt><font size="2"><br>
> > <br>
> <br>
> --<br>
> Hal Finkel<br>
> Assistant Computational Scientist<br>
> Leadership Computing Facility<br>
> Argonne National Laboratory<br>
> <br>
> _______________________________________________<br>
> llvm-commits mailing list<br>
> llvm-commits@cs.uiuc.edu<br>
> </font></tt><tt><font size="2"><a href="http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits">http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits</a></font></tt><tt><font size="2"><br>
> <br>
<br>
-- <br>
Hal Finkel<br>
Assistant Computational Scientist<br>
Leadership Computing Facility<br>
Argonne National Laboratory<br>
<br>
</font></tt><br>
</body></html>