<html><head><style type='text/css'>p { margin: 0; }</style></head><body><div style='font-family: arial,helvetica,sans-serif; font-size: 10pt; color: #000000'><br><hr id="zwchr"><blockquote style="border-left: 2px solid rgb(16, 16, 255); margin-left: 5px; padding-left: 5px; color: rgb(0, 0, 0); font-weight: normal; font-style: normal; text-decoration: none; font-family: Helvetica,Arial,sans-serif; font-size: 12pt;"><b>From: </b>"Chandler Carruth via llvm-dev" <llvm-dev@lists.llvm.org><br><b>To: </b>"James Molloy" <james@jamesmolloy.co.uk>, "Stephen Canon" <scanon@apple.com><br><b>Cc: </b>"LLVM Dev" <llvm-dev@lists.llvm.org><br><b>Sent: </b>Monday, April 4, 2016 1:41:05 PM<br><b>Subject: </b>Re: [llvm-dev] RFC: Constant folding math functions for long double<br><br><div dir="ltr">My two cents:<div><br></div><div id="DWT20385">1) While I'm sympathetic to Steve's point about this not always being desirable, the fact than *many* other compilers do this will ensure that code is written assuming it. I think we need to have support for this in order to have even remotely performance portable library code.</div></div></blockquote><br>+1<br><br><blockquote style="border-left: 2px solid rgb(16, 16, 255); margin-left: 5px; padding-left: 5px; color: rgb(0, 0, 0); font-weight: normal; font-style: normal; text-decoration: none; font-family: Helvetica,Arial,sans-serif; font-size: 12pt;"><div dir="ltr"><div></div><div><br></div><div id="DWT20386">2) I strongly dislike an optional dependency on MPFR. We shouldn't have critical functionality tied to system libraries IMO. I understand that it is a *lot* of work, but I think we need to produce or get contributed a reasonable implementation of these routines under the LLVM license. As an added benefit, we might be able to (eventually) share the code for them with a runtime library that provides portable implementations for systems where hardware support is lacking.</div></div></blockquote><br>+1<br><br>The prospect of having Clang compiled with MPFR available produce different code, even on otherwise identical base systems, than Clang compiled without it seems highly undesirable (especially since we might have only small numerical differences as observable effects). Plus, there are licensing considerations in environments where we need to statically link LLVM (in JITs and such) that I don't think we want to impose on downstream developers/distributors.<br><br>However, the good news is that developing our own APFloat versions of these functions is relatively easy -- not easy in an absolute sense, but: 1) Unlike the libc implementations, we're not worried about raw performance on native types, 2) we can use large floats with a lot of extra precision easily, and 3) we don't need to use algorithms designed to be efficient for really-large bit counts (like MPFR does).<br><br>In this regard, it might also be helpful to look at: https://github.com/JuliaLang/openlibm (which seems to be very-permissively licensed and has reference implementations for all of the relevant algorithms in C).<br><br> -Hal<br><br><blockquote style="border-left: 2px solid rgb(16, 16, 255); margin-left: 5px; padding-left: 5px; color: rgb(0, 0, 0); font-weight: normal; font-style: normal; text-decoration: none; font-family: Helvetica,Arial,sans-serif; font-size: 12pt;"><div dir="ltr"><div></div><div><br></div><div>-Chandler</div></div><br><div class="gmail_quote"><div dir="ltr">On Mon, Apr 4, 2016 at 11:31 AM James Molloy via llvm-dev <<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><div dir="ltr">Hi,<div><br></div><div>If you're interested, include/bits/random.tcc:3312 (std::generate_canonical()). I wish I could just point people at libc++, but that's outside of my control. As for fixing the library, that horse bolted some time ago.</div><div><br></div><div>Cheers,</div><div><br></div><div>James</div></div><br><div class="gmail_quote"><div dir="ltr">On Mon, 4 Apr 2016 at 18:50 Stephen Canon <<a href="mailto:scanon@apple.com" target="_blank">scanon@apple.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><div style="word-wrap: break-word;"><div>That sounds like a library issue that qualifies as “somewhat strange”. Why does this require a log at all?</div><div><br></div><div>– Steve</div></div><div style="word-wrap: break-word;"><br><div><blockquote><div>On Apr 4, 2016, at 10:46 AM, James Molloy via llvm-dev <<a href="mailto:llvm-dev@lists.llvm.org" target="_blank">llvm-dev@lists.llvm.org</a>> wrote:</div><br><div><div dir="ltr">Hi Joerg,<div><br></div><div>> <span style="line-height: 1.5;">IMO if constant folding of transcendental functions makes a significant</span></div>difference for your program, you likely are doing something strange<br>already.<div><br></div><div>Alas it's not as simple as that. Currently, if you declare:</div><div><br></div><div>std::uniform_real_distribution<float> x;</div><div><br></div><div>LLVM emits two calls to logl() with constant arguments, a fdiv and a fptoui.</div><div><br></div><div>Libc++'s implementation is consumed and folded much more nicely by LLVM, but at the moment anyone comparing LLVM and GCC will think that GCC is around 40% better for some workloads.</div><div><br></div><div>James</div></div><br><div class="gmail_quote"><div dir="ltr">On Mon, 4 Apr 2016 at 17:49 Reid Kleckner <<a href="mailto:rnk@google.com" target="_blank">rnk@google.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><div dir="ltr">My feeling is that we shouldn't be relying on host long double routines. We're already skating on thin ice by relying on host double and float routines. This is a great way to make the compilation result vary depending on the host, which is something we try to avoid.<div><br></div><div>An optional MPFR dependency would also be pretty painful. I expect it will frequently be missing and will not be exercised by most buildbots.</div></div><div class="gmail_extra"><br><div class="gmail_quote"></div></div><div class="gmail_extra"><div class="gmail_quote">On Mon, Apr 4, 2016 at 6:59 AM, James Molloy 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></div></div><div class="gmail_extra"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;"><div dir="ltr"><span style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;">Hi,</span><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"><br></div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;">Clang is currently unable to constant fold calls to math.h functions such as logl(), expl() etc.</div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"><br></div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;">The problem is that APFloat doesn't have these functions, so Clang is forced to rely on the host math library. Because long double isn't portable, we only ever query the host math library for double or float results.</div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"><br></div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;">I can see three methods for allowing constant folding for types that are larger than double, some more expensive than others:</div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"><br></div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"> 1. Introduce a dependency on libMPFR, as GCC does. The dependency could be hard or soft, with a fallback to the current behaviour if it doesn't exist.</div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"> 2. Write the trancendental functions ourselves in APFloat (yuck!)</div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"> 3. If the long double format on the compiler host is the same as the target, use the host library.</div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"><br></div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;">(2) is the hardest. (3) is the easiest, but only works in a subset of cases and I really don't like the idea of better output when compiling on one platform compared to another (with equivalent targets).</div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"><br></div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;">What do people think about (1)? Or is this completely out of the question?</div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"><br></div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;">Cheers,</div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;"><br></div><div style="color: rgb(33, 33, 33); font-size: 13px; line-height: 19.5px;">James</div></div>
<br></blockquote></div></div><div class="gmail_extra"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">_______________________________________________<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" rel="noreferrer" target="_blank">http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev</a><br>
<br></blockquote></div></div></blockquote></div>
_______________________________________________<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><br></div></blockquote></div><br></div></blockquote></div>
_______________________________________________<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" rel="noreferrer" target="_blank">http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev</a><br>
</blockquote></div>
<br>_______________________________________________<br>LLVM Developers mailing list<br>llvm-dev@lists.llvm.org<br>http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev<br></blockquote><br><br><br>-- <br><div><span name="x"></span>Hal Finkel<br>Assistant Computational Scientist<br>Leadership Computing Facility<br>Argonne National Laboratory<span name="x"></span><br></div></div></body></html>