<div dir="ltr">See attached some quick slides (backup from the dev meeting talk) about the pass pipeline.<div><br></div><div><br></div><div><br></div><div>-- </div><div>Mehdi</div></div><br><div class="gmail_quote"><div dir="ltr">Le mer. 11 avr. 2018 à 12:18, Mehdi AMINI <<a href="mailto:joker.eph@gmail.com">joker.eph@gmail.com</a>> a écrit :<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><br><br><div class="gmail_quote"><div dir="ltr">Le mer. 11 avr. 2018 à 11:20, <<a href="mailto:katya.romanova@sony.com" target="_blank">katya.romanova@sony.com</a>> a écrit :<br></div><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 class="m_-4189846966886113444m_3310699647359420469WordSection1">
<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"><u></u> <u></u></span></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif">From:</span></b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"> Mehdi AMINI <<a href="mailto:joker.eph@gmail.com" target="_blank">joker.eph@gmail.com</a>>
<br>
<b>Sent:</b> Tuesday, April 10, 2018 11:53 PM<br>
<b>To:</b> Romanova, Katya <<a href="mailto:katya.romanova@sony.com" target="_blank">katya.romanova@sony.com</a>><br>
<b>Cc:</b> David Blaikie <<a href="mailto:dblaikie@gmail.com" target="_blank">dblaikie@gmail.com</a>>; Teresa Johnson <<a href="mailto:tejohnson@google.com" target="_blank">tejohnson@google.com</a>>; llvm-dev <<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>><br>
<b>Subject:</b> Re: [llvm-dev] exploring possibilities for unifying ThinLTO and FullLTO frontend + initial optimization pipeline<u></u><u></u></span></p>
<p class="MsoNormal"><u></u> <u></u></p>
<div>
<p class="MsoNormal" style="margin-bottom:12.0pt"><u></u> <u></u></p>
<div>
<div>
<p class="MsoNormal">Le mar. 10 avr. 2018 à 23:18, <<a href="mailto:katya.romanova@sony.com" target="_blank">katya.romanova@sony.com</a>> a écrit :<u></u><u></u></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">
<div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">Hi Mehdi,</span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">Awesome! It’s a very clear design. The only question left is which pipeline to choose for unified compile-phase
optimization pipeline. </span><u></u><u></u></p>
<p class="m_-4189846966886113444m_3310699647359420469gmail-m-2135444533988741634msolistparagraph"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">-</span><span style="font-size:7.0pt;color:#1f497d">
</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">ThinLTO compile-phase pipeline? It might very negatively affect compile-time and the memory footprint for FullLTO link-phase. That was the reason why so many optimization were
moved from the link-phase to the parallel compile-phase for FullLTO in the first place.</span><u></u><u></u></p>
</div>
</div>
</blockquote>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Just to clarify: "optimizations" were not "moved from the link-phase to the parallel compile-phase for FullLTO", they have never been in the link phase for FullLTO. It has always been this way.<u></u><u></u></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-family:"Calibri",sans-serif;color:#0070c0">I see. What I meant was the following comment from the phabricator review about defining the ThinLTO pipeline, but I didn’t remember its exact wording.
<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;color:#0070c0"><a href="https://reviews.llvm.org/D17115" target="_blank"><span style="color:#0070c0">https://reviews.llvm.org/D17115</span></a><u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;color:#0070c0">“On the contrary to Full LTO, ThinLTO can afford to shift compile time from the frontend to the linker: both phases are parallel”.<u></u><u></u></span></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">I think that the ThinLTO compile-phase pipeline will only affect FullLTO in the sense that we need to add more passes during the link phase, is this what you meant?<u></u><u></u></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-family:"Calibri",sans-serif;color:#0070c0">Yes, that’s exactly what I meant.<u></u><u></u></span></p>
</div>
<div>
<p class="MsoNormal"> <span style="color:#1f497d">
</span><u></u><u></u></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">
<div>
<div>
<p class="m_-4189846966886113444m_3310699647359420469gmail-m-2135444533988741634msolistparagraph"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">-</span><span style="font-size:7.0pt;color:#1f497d">
</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">FullLTO compile-phase pipeline? More optimization passes at compile-phase will obviously increase compile time for ThinLTO, though I suspect it will be tolerable. It is not
very clear how this choice will affect the overall runtime performance for ThinLTO. Assuming we keep well-tuned link-phase/backend optimization pipeline “as is” for ThinLTO and FullLTO, we will repeat some optimization passes for ThinLTO at compile-phase and
later at link-phase which potentially could improve the performance… or it could make it worse, because we might perform an optimization early at compile-time, potentially preventing more aggressive optimization at link-phase when we see a larger scope. Any
prediction on what would happen to the ThinLTO runtime performance at run-time?</span><u></u><u></u></p>
</div>
</div>
</blockquote>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Note: repeating optimization is not supposed to improve performance, at least this isn't the goal of the pipeline. <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">The pipeline for ThinLTO has been modeled on O3, good or bad we felt there was no reason to really deviate and any improvement to one could (should!) reflect on the other.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">The rational behind the ThinLTO pipeline is not only compile time: it split the O3 pipeline at the point where we stop the "function simplification" / inliner loop and before we get into unrolling/vectorization.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">I remember even trying to stop the compile-phase without inlining but the generated IR was too big: the inliner CGSCC visit actually reduces the size of the IR considerably in some cases.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><span style="color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;color:#0070c0">Thank you for sharing! It’s a very helpful.<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;color:#0070c0"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;color:#0070c0">Mehdi, It seems that you have spent a significant time experimenting with ThinLTO pipeline and determining where exactly the compile-phase should end and link-phase should start.
How do you envision unified ThinLTO/FullLTO compile-phase pipeline? We might tune/improve this pipeline it in the future, but having a good starting point is very important too.</span></p></div></div></div></div></div></blockquote><div><br></div><div>I don't know: it is all about tradeoffs :)</div><div>I was in favor of using a single pipeline based on ~O3, the reason being mainly that it is easier to maintain/validate/evolve: when folks improve the O3 pipeline you get the benefit immediately in the ThinLTO optimization phase, in contrary with FullLTO. The tradeoff is about compile-time: it can become really long for FullLTO in some extreme cases. I suggested in the past that such cases could be handled by running the FullLTO linker optimization phase with O1 to reduce the amount of optimization.</div><div><br></div><div><br></div><div> </div><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 class="m_-4189846966886113444m_3310699647359420469WordSection1"><div><div><div><p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;color:#0070c0"><u></u><u></u></span></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></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">
<div>
<div>
<p class="m_-4189846966886113444m_3310699647359420469gmail-m-2135444533988741634msolistparagraph"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">-</span><span style="font-size:7.0pt;color:#1f497d">
</span><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">New “unified” compile-phase pipeline?</span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">I guess, there is not a definitive answer and we have to experiment, measure compile-time/run-time
performance and potentially make some adjustments to the pipeline and to the thresholds. We have a few proprietary tests in Sony that we could use for the performance measurements, but it will be nicer if there are some open source benchmarks that we could
use. What did you use in Google/Apple for ThinLTO/FullLTO measurements? Have you used some proprietary benchmarks also? It’s important to make sure we won’t have run-time/compile-time performance degradation, but it will be nicer if anyone can run previously
used ThinLTO/FullLTO benchmarks oneself, while making changes to the optimization pipeline and heuristics.</span><u></u><u></u></p>
</div>
</div>
</blockquote>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">We benchmarked multiple variants of the pipeline two years ago. There were some regressions when adoption the ThinLTO pipeline in FullLTO (and some improvements), but when investigated we didn't find any real regressions that couldn't be
solved by fixing the optimizer. <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><span style="color:#0070c0"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;color:#0070c0">When referring to ThinLTO and FullLTO pipelines here do you mean compile-phase pipeline, link-phase pipeline or full pipeline (i.e., compile-phase + link-phase)? The terminology
is slightly confusing here.</span></p></div></div></div></div></div></blockquote><div><br></div><div><br></div><div>Here I meant everything: trying to use the exact same pipeline in both phases.</div><div><br></div><div> </div><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 class="m_-4189846966886113444m_3310699647359420469WordSection1"><div><div><div><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"><u></u> <u></u></span></p>
<p class="MsoNormal">I.e. these are cases where FullLTO gets it right "by luck" and not by principle, and fixing such cases helps the non-LTO O3 (for example this test case <a href="https://bugs.llvm.org/show_bug.cgi?id=27395" target="_blank">https://bugs.llvm.org/show_bug.cgi?id=27395</a>
)<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></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">
<div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal">>> # No flag: use the compile-phase preference, perform ThinLTO on a.o and FullLTO on b.o/c.o, but allow ThinLTO import between the LTO group and the ThinLTO >> objects<u></u><u></u></p>
<p class="MsoNormal">>> $ clang a.o b.o c.o<u></u><u></u></p>
<p class="MsoNormal"> <u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">If I understood you correctly, while doing ThinLTO on a.o, we could import from b.o and c.o (this is
possible since the summaries are available), while we won’t see a.o when doing FullLTO for b.o/c.o. (i.e., the previous non-permeable barrier between ThinLTO and FullLTO groups will become permeable in one direction).</span><u></u><u></u></p>
</div>
</div>
</blockquote>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">It could be permeable in both direction: b.o+c.o become "like a single ThinLTO object" after they get merged.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><span style="color:#1f497d"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;color:#0070c0">I see…<u></u><u></u></span></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">
<div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">However, do you think by doing this, we will achieve a better performance than doing ThinLTO backend
for all of the files (a.o, b.o, c.o)?</span><u></u><u></u></p>
</div>
</div>
</blockquote>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">Performance is always very much use-case dependent.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">One may know that a group of files performs better when they get merged together with FullLTO while the rest of the app does not?<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"><u></u> <u></u></p>
</div>
<div>
<p class="MsoNormal">I don't know but this all needs to be carefully looked at from a user-interface point of view I think (will it be intuitive for the users? Will it fit in every (most) scenarios? etc.).<u></u><u></u></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"><u></u> <u></u></span></p>
<p class="MsoNormal"><span style="color:#0070c0">>> # No flag: use the compile-phase preference, perform ThinLTO on a.o and FullLTO on b.o/c.o, but allow ThinLTO import between the LTO group and the ThinLTO >> objects<u></u><u></u></span></p>
<p class="MsoNormal"><span style="color:#0070c0">>> $ clang a.o b.o c.o<u></u><u></u></span></p>
<p class="MsoNormal"><span style="font-family:"Calibri",sans-serif;color:#0070c0">I wonder if we have a use-case for the “mix and match compile-phase preference” situation that you described above? Maybe the linker should simply report an error in this case?
Or do we have to accept this because of backwards compatibility?</span></p></div></div></div></div></div></blockquote><div><br></div><div>I don't know :)</div><div>We need to consider the cases of "old" bitcode that wouldn't have summaries (maybe they could get merged in the LTO partition but not participate in cross-module optimizations?)</div><div>We should hear from Apple folks as well.</div><div><br></div><div>-- </div><div>Mehdi</div><div><br></div><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 class="m_-4189846966886113444m_3310699647359420469WordSection1"><div><div><div><p class="MsoNormal"><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>
<blockquote style="border:none;border-left:solid #cccccc 1.0pt;padding:0in 0in 0in 6.0pt;margin-left:4.8pt;margin-right:0in">
<div>
<div>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">Thank you!</span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">Katya.</span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-size:11.0pt;font-family:"Calibri",sans-serif;color:#1f497d">
</span><u></u><u></u></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif">From:</span></b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"> Mehdi AMINI <<a href="mailto:joker.eph@gmail.com" target="_blank">joker.eph@gmail.com</a>>
<br>
<b>Sent:</b> Tuesday, April 10, 2018 5:25 PM<br>
<b>To:</b> Romanova, Katya <<a href="mailto:katya.romanova@sony.com" target="_blank">katya.romanova@sony.com</a>><br>
<b>Cc:</b> David Blaikie <<a href="mailto:dblaikie@gmail.com" target="_blank">dblaikie@gmail.com</a>>; Teresa Johnson <<a href="mailto:tejohnson@google.com" target="_blank">tejohnson@google.com</a>>; llvm-dev <<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>><br>
<b>Subject:</b> Re: [llvm-dev] exploring possibilities for unifying ThinLTO and FullLTO frontend + initial optimization pipeline</span><u></u><u></u></p>
<p class="MsoNormal"> <u></u><u></u></p>
<div>
<p class="MsoNormal">Hi,<u></u><u></u></p>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">It is non trivial to recompute summaries (which is why we have summaries in the bitcode in the first place by the way), because bitcode is expensive to load.<u></u><u></u></p>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<div>
<p class="MsoNormal">I think shipping two different variant of the bitcode, one with and one without summaries isn't providing much benefit while complicating the flow. We could achieve what you're
looking for by revisiting the flow a little.<u></u><u></u></p>
</div>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">I would try to consider if we can:<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">1) always generate summaries.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">2) Use the same compile-phase optimization pipeline for ThinLTO and LTO.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">3) Decide at link time if you want to do FullLTO or ThinLTO.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">We haven't got this route 2 years ago because during the bringup we didn't want to affect FullLTO in any way, but it may make sense now to have `clang -flto=thin` and `clang -flto=full`
be identical and change the linker plugins to operate either in full-LTO mode or in ThinLTO mode but not differentiate based on the availability of the summaries.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">A possible behavior could be:<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"># The -flto flag in the compile phase does not change the produced bitcode but for a flag that record the preference in the bitcode (FullLTO vs ThinLTO)<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">$ clang -c -flto=thin a.cpp<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">$ clang -c -flto=full b.cpp<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">$ clang -c -flto=full c.cpp<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"># At link time the behavior depends on the -flto flag passed in.<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"># No flag: use the compile-phase preference, perform ThinLTO on a.o and FullLTO on b.o/c.o, but allow ThinLTO import between the LTO group and the ThinLTO objects<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">$ clang a.o b.o c.o<u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"># Forces full LTO, merges all the objects, no cross module importing will happen.<u></u><u></u></p>
</div>
<div>
<div>
<p class="MsoNormal">clang a.o b.o c.o -flto=full<u></u><u></u></p>
</div>
</div>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal"># Forces ThinLTO for all objects, FullLTO won't happen, no objects will be merged.<u></u><u></u></p>
</div>
<div>
<div>
<p class="MsoNormal">clang a.o b.o c.o -flto=thin<u></u><u></u></p>
</div>
</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"> <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">-- <u></u><u></u></p>
</div>
<div>
<p class="MsoNormal">Mehdi<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>
<div>
<p class="MsoNormal"> <u></u><u></u></p>
</div>
</div>
</div>
<p class="MsoNormal"> <u></u><u></u></p>
<div>
<div>
<p class="MsoNormal">Le mar. 10 avr. 2018 à 15:51, via llvm-dev <<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>> a écrit :<u></u><u></u></p>
</div>
<blockquote style="border:none;border-left:solid #cccccc 1.0pt;padding:0in 0in 0in 6.0pt;margin-left:4.8pt;margin-top:5.0pt;margin-right:0in;margin-bottom:5.0pt">
<div>
<div>
<p class="MsoNormal">Hi David,<u></u><u></u></p>
<p class="MsoNormal">Thank you so much for your reply!<u></u><u></u></p>
<p class="MsoNormal"> <u></u><u></u></p>
<p class="MsoNormal">>> You're dealing with a situation where you are shipped BC files offline and then do one, or multiple builds with these BC files?<br>
<span style="font-family:"Arial",sans-serif;color:black">Yes, that’s exactly the case.</span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal">>> If the scenario was more like a naive build: Multiple BC files generated on a single (multi-core/threaded) machine (but some Thin, some
<u></u><u></u></p>
<p class="MsoNormal">>> Full) & then fed to the linker, I would wonder if it'd be relatively cheap for the LTO step to support this by computing summaries for
<u></u><u></u></p>
<p class="MsoNormal">>> FullLTO files on the fly (without a separate tool/writing the summary to disk, etc).<u></u><u></u></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif;color:black">I think so. My understanding that for FullLTO files, it’s possible to perform name anonymous globals pass and compute summaries
on the fly, which should allow to perform ThinLTO at link phase. </span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif;color:black"> </span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif;color:black">Katya.</span><u></u><u></u></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif;color:#1f497d"> </span><u></u><u></u></p>
<p class="MsoNormal"><b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif">From:</span></b><span style="font-size:11.0pt;font-family:"Calibri",sans-serif"> David Blaikie <<a href="mailto:dblaikie@gmail.com" target="_blank">dblaikie@gmail.com</a>>
<br>
<b>Sent:</b> Tuesday, April 10, 2018 7:38 AM<br>
<b>To:</b> Romanova, Katya <<a href="mailto:katya.romanova@sony.com" target="_blank">katya.romanova@sony.com</a>>; Teresa Johnson <<a href="mailto:tejohnson@google.com" target="_blank">tejohnson@google.com</a>><br>
<b>Cc:</b> <a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a><br>
<b>Subject:</b> Re: [llvm-dev] exploring possibilities for unifying ThinLTO and FullLTO frontend + initial optimization pipeline</span><u></u><u></u></p>
<p class="MsoNormal"> <u></u><u></u></p>
<div>
<p class="MsoNormal" style="margin-bottom:12.0pt">Hi Katya,<br>
<br>
[+Teresa since this is about ThinLTO & she's the owner there]<br>
<br>
I'm not sure how other folks feel, but terminologically I'm not sure I think of these as different formats (for example you mention the idea of stripping the summaries from ThinLTO BC files to then feed them in as FullLTO files - I would imagine it'd be reasonable
to modify/fix/improve the linker integration to have it (perhaps optionally) /ignore/ the summaries, or use the summaries but in a non-siloed way (so that there's not that optimization boundary between ThinLTO and FullLTO))<br>
<br>
You're dealing with a situation where you are shipped BC files offline and then do one, or multiple builds with these BC files?<br>
<br>
If the scenario was more like a naive build: Multiple BC files generated on a single (multi-core/threaded) machine (but some Thin, some Full) & then fed to the linker, I would wonder if it'd be relatively cheap for the LTO step to support this by computing
summaries for FullLTO files on the fly (without a separate tool/writing the summary to disk, etc). Though I suppose that'd produce a pretty wildly different behavior in the link when just a single ThinLTO BC file was added to an otherwise FullLTO build.<br>
<br>
Anyway - just some (admittedly fairly uninformed) thoughts. I'm sure Teresa has more informed ideas about how this might all look.<u></u><u></u></p>
<div>
<div>
<p class="MsoNormal">On Mon, Apr 9, 2018 at 12:20 PM via llvm-dev <<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>> wrote:<u></u><u></u></p>
</div>
<blockquote style="border:none;border-left:solid #cccccc 1.0pt;padding:0in 0in 0in 6.0pt;margin-left:4.8pt;margin-top:5.0pt;margin-right:0in;margin-bottom:5.0pt">
<div>
<div>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">Hello,</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">I am exploring the possibility of unifying the BC file generation phase for ThinLTO and FullLTO. Our third party library providers prefer to give us only one version of the BC archives, rather than test and ship both Thin and Full
LTO BC archives. We want to find a way to allow our users to pick either Thin or Full LTO, while having only one “unified” version of the BC archive.</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">Note, I am not necessarily proposing to do this work in the upstream compiler. If there is no interest from other companies, we might have to keep this as a private patch for Sony.</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">One of the ideas (not my preference) is to mix and match files in the Thin and Full BC formats. I'm not sure how well the "mix and match" scenario works in general. I was wondering if Apple or Google are doing this for production?</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">I wrote a toy example, compiled one group of files with ThinLTO and the rest with FullLTO, linked them with gold. I saw that irrespective of whether the Thin or Full LTO option was used at the link step, files are optimized within
the Thin group and within the Full group separately, but they don't know about the files in the other group (which makes sense). Basically, the border between Thin and Full LTO bitcode files created an artificial "barrier" which prevented cross-border optimization.</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">Obviously, I am not too fond of this idea. Even if mixing and matching ThinLTO and FullLTO bitcode files will work “as is”, I suspect we will see a non-trivial runtime performance degradation because of the "ThinLTO"/"FullLTO" border.
Are you aware of any potential problems with this solution, other than performance?</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black"> </span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">Another, hopefully, better idea is to introduce a "unified" BC format, which could either be FullLTO, ThinLTO, or neither (e.g., something in between).</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">If the user chooses FullLTO at the link step, but some of the files are in the Thin BC format – the linker will call a special LTO API to convert these files to the Full LTO BC format (i.e., stripping the module summary section + potentially
do some additional optimizations from the FullLTO pass manager pipeline).</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">If the user chooses ThinLTO at the link step, but some of the files are in the Full BC format – the linker will call an LTO API to convert these files to the Thin LTO bitcode format (by regenerating the module summary section dynamically
for the Full LTO bitcode files). </span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">I think the most reasonable idea for the unification of the Thin and Full LTO compilation pipelines is to use Full LTO as the “unified” BC format. If the user requests FullLTO – no additional work is needed, the linker will perform
FullLTO as usual. If the user request ThinLTO, the linker will call an API to regenerate the module summary section for all the files in the FullLTO format and perform ThinLTO as usual.
</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">In reality I suspect things will be much more complicated. The pipelines for the Thin and Full LTO compilation phases are quite different. ThinLTO can afford to do much more optimization in the linking phase (since it has parallel
backends & smaller IR compared to FullLTO), while for FullLTO we are forced to move some optimizations from linking to the compilation phase.</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">So, if we pick FullLTO as our unified format, we would increase the build time for ThinLTO (we will be doing the FullLTO initial optimization pipeline in the compile phase, which is more than what ThinLTO is currently doing, but the
pipeline of the optimizations in the backend will stay the same). It’s not clear what will happen with the runtime performance: we might improve it (because we repeat some of the optimizations several times), or we might make it worse (because we might do
an optimization in the early compilation phase, potentially preventing more aggressive optimization later). What are your expectations? Will this approach work in general? If so, what do you think will happen with the runtime performance?</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">I also noticed that the pass manager pipeline is different for ThinLTO+Sample PGO (use profile case). This might create some additional complications for unification of Thin and FullLTO BC generation phase too, but it’s too small detail
to worry about right now. I’m more interested in choosing a right general direction for solving this problem now.</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">Please share your thoughts!</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">Thank you!</span><u></u><u></u></p>
<p class="MsoNormal" style="margin-bottom:8.0pt;line-height:105%">
<span style="color:black">Katya.</span><u></u><u></u></p>
<p class="MsoNormal"> <u></u><u></u></p>
<p class="MsoNormal"><span style="font-family:"Arial",sans-serif"> </span><u></u><u></u></p>
</div>
</div>
<p class="MsoNormal">_______________________________________________<br>
LLVM Developers mailing list<br>
<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a><br>
<a href="http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev" target="_blank">http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev</a><u></u><u></u></p>
</blockquote>
</div>
</div>
</div>
</div>
<p class="MsoNormal">_______________________________________________<br>
LLVM Developers mailing list<br>
<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a><br>
<a href="http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev" target="_blank">http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev</a></p></blockquote></div></div></div></blockquote></div></div></div></div></blockquote><div> </div></div></div></blockquote></div>