<div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote">On Sun, Aug 16, 2015 at 9:15 PM, deadal nix <span dir="ltr"><<a href="mailto:deadalnix@gmail.com" target="_blank">deadalnix@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div>I understand these objections. They ends up being a problem at the limit (ie the example of the 64k store or 1Mb+ aggregate). These probably require their own fix or probably just shouldn't be supported.<br><br></div>That being said, there is a vast space between what is done now and aggregate so big that it causes real hard problems like the ones you mention. reducing that gap seems like a win to me. Additionally, there is vast bag of trick that can be deployed to mitigate the problem (for instance, load to store forwarding can be changed into memcpy). Things is, one got to start somewhere.<br><br></div><div>More generally, it doesn't seems right to me to reject something because it doesn't cover all bases. The fact that it covers more bases than what exists now should be enough (unless it create some kind of bad precedent).<br></div></div></blockquote><div><br></div><div>I would argue that a fix in the wrong direction is worse than the status quo.</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div></div><div><br></div><div><div>The argument that target are relying on InstCombine to mitigate IR requiring legalization seems dubious to me. First, because both aggregate and large scalar require legalization, so, if not ideal, the proposed change does not makes things any worse than they already are. In fact, as far as legalization is concerned, theses are pretty much the same. It should also be noted that InstCombine is not guaranteed to run before the target, so it seems like a bad idea to me to rely on it in the backend.<br></div></div></div></blockquote><div><br></div><div>InstCombine is not guaranteed to run before IR hits the backend but the result of legalizing the machinations of InstCombine's output during SelectionDAG is worse than generating illegal IR in the first place.</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div></div><div><br>As for the big integral thing, I really don't care. I can change it to
create multiple loads/stores respecting data layout, I have the code for
that and could adapt it for this PR without too much trouble. If this
is the only thing that is blocking this PR, then we can proceed. But I'd
like some notion that we are making progress. Would you be willing to accept a solution based on creating a serie of load/store respecting the datalayout ?<br></div></div></div></blockquote><div><br></div><div>Splitting the memory operation into smaller operations is not semantics preserving from an IR-theoretic perspective. For example, splitting a volatile memory operation into several volatile memory operations is not OK. Same goes with atomics. Some targets provide atomic memory operations at the granularity of a cache line and splitting at legal integer granularity would be observably different.</div><div><br></div><div>With the above in mind, I don't see it as unreasonable for frontends to generate IR that LLVM is comfortable with. We seem fine telling frontend authors that they should strive to avoid large aggregate memory operations in our performance tips guide <<a href="http://llvm.org/docs/Frontend/PerformanceTips.html#avoid-loads-and-stores-of-large-aggregate-type">http://llvm.org/docs/Frontend/PerformanceTips.html#avoid-loads-and-stores-of-large-aggregate-type</a>>. Implementation experience with Clang hasn't shown this to be particularly odious to follow and none of the LLVM-side solutions seem satisfactory.</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div><br></div></div></div><div class="HOEnZb"><div class="h5"><div class="gmail_extra"><br><div class="gmail_quote">2015-08-16 20:01 GMT-07:00 David Majnemer <span dir="ltr"><<a href="mailto:david.majnemer@gmail.com" target="_blank">david.majnemer@gmail.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote"><div><div>On Sun, Aug 16, 2015 at 7:05 PM, deadal nix via llvm-dev <span dir="ltr"><<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><div><div>Hi all,<br><br></div>As most of you may now, LLVM is completely unable to do anything reasonable with aggregate load/stores, beside just legalize them into something in the backend.<br><br></div>This is not a good state of affair. Aggregate are part of LLVM IR, and as such, LLVM should do something about them.<br><br></div>That is a bit of a chicken and egg issue: front end just implement their own tricks to avoid aggregate or plain don't care about the resulting executable as long as it works. As such, pretty much everybody that care about this already implemented something in the front end.<br><br><div>Which is honestly rather stupid. Everybody is doing the same work again and again because LLVM is not doing it.<br><br></div><div>That being said, I now know why LLVM is not doing it. Any attempt at making things move on that front result in someone finding the solution not good enough and stalling the process.<br><br></div><div>Things is, pretty much anything is better than nothing. Comparing any current solution to an hypothetical nonexistant perfect solution is not constructive. And at this stage, this is close to being disrespectful. I have <a href="http://reviews.llvm.org/D9766" target="_blank">http://reviews.llvm.org/D9766</a> (from may) and no actionable item on it. It was done as per feedback on previous discussion on the subject. There is no proposal to improve the code, no proposal to do it another way, no nothing. FROM MAY !<br><br></div><div>I'd like to get things moving here. If you guys don't give a s*** about it because clang already have a work around, then fine. The good thing is that it won't affect clang, for the very same reason: it is not using it. But there are numerous front end out there, that do not have the manpower backing clang, and all have to jump through hoops to handle aggregate for LLVM not to mess up. So please be considerate for the smaller guys in town.<br></div></div></blockquote><div><br></div></div></div><div>Hello,</div><div><br></div><div>I see things a little differently and I'll do my best to explain my position.</div><div><br></div><div>First of all, LLVM's backend doesn't handle large aggregates very well and there appears no desire from the greater community to fix this. Last year I tried to fix PR21513 which involved a fairly large store of aggregate type totaling around 64 KB. It turns out that the backend's representation requires having a node with > 64,000 operands. I submitted a patch to fix this, <a href="http://reviews.llvm.org/D6164" target="_blank">http://reviews.llvm.org/D6164</a>, but others in the community reasoned that the cure was worse than the disease as it results in all SDNodes becoming a little larger.</div><div><br></div><div>Second of all, turning large aggregates memory operations into large scalar memory operations, via the integer types, doesn't work for memory operations beyond 1 MB because the largest integer type is (2**23)-1 bits. I think it would be quite costly to make the scalarization scale significantly beyond this. Beyond that, InstCombine is not supposed to generate type which aren't considered legal by datalayout. Targets out there rely on InstCombine to respect this to mitigate the creation of IR which doesn't map well to the hardware.</div><div><br></div><div>What I tried, but perhaps failed, to intimate was that today's status quo is considered to be a reasonable engineering compromise. LLVM doesn't provide a *completely* abstract and normalized interface to computation but we try our best in the face of the constraints we are faced with. This is why clang's technique is, to me, reasonable.</div><div><br></div><div>I hope this explains where I am coming from.</div><div><br></div><div>Thanks,</div><div>David Majnemer</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr"><div><br></div></div>
<br>_______________________________________________<br>
LLVM Developers mailing list<br>
<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a> <a href="http://llvm.cs.uiuc.edu" rel="noreferrer" target="_blank">http://llvm.cs.uiuc.edu</a><br>
<a href="http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev" rel="noreferrer" target="_blank">http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev</a><br>
<br></blockquote></div><br></div></div>
</blockquote></div><br></div>
</div></div></blockquote></div><br></div></div>