Date: Tue, 18 Jun 2024 15:31:12 -0600 From: Warner Losh <imp@bsdimp.com> To: Jason Bacon <bacon4000@gmail.com> Cc: Robert Clausecker <fuz@freebsd.org>, "freebsd-hackers@freebsd.org" <hackers@freebsd.org>, kargl@freebsd.org Subject: Re: Opportunities for numerical work on FreeBSD? Message-ID: <CANCZdfp1pOp0aQDg_7RQW2KsCmKbU38Uuy3wxep-ZsUrmiBVeg@mail.gmail.com> In-Reply-To: <06f93359-b284-494c-b8b1-dc3dba1e1264@gmail.com> References: <ZnHEVbKEh8gF-Aje@fuz.su> <06f93359-b284-494c-b8b1-dc3dba1e1264@gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
[-- Attachment #1 --] On Tue, Jun 18, 2024, 3:27 PM Jason Bacon <bacon4000@gmail.com> wrote: > On 6/18/24 12:31, Robert Clausecker wrote: > > Greetings, > > > > I have here a talented maths student looking for a place to > > complete her mandatory (unpaid) industry internship. > > > > She has a knack for numerical analysis, differential equations, > > and writing floating point code. I suggested that there might > > be need for some improvement to the math code currently shipped > > with FreeBSD as the old msun code, while very precise, is not > > writted to take advantage of modern SIMD FPUs with FMA support > > and could be improved considerably. > > > > Is there an interest for such or other numerical work on the > > FreeBSD code base? Would anybody be interested in supervising > > such work? If yes, I would try to connect the two of you. > > > > Yours, > > Robert Clausecker > > > > Coincidentally, I just came across a recent benchmark that might provide > some hints about where to focus the efforts: > > https://www.phoronix.com/review/bsd-linux-threadripper-7980x But stress-ng isn't a benchmark. It says so in it's docs. Also there are several ifdef linux in the source to make it faster on linux. I wouldn't waste my time on that garbage. Warner > > -- > Life is a game. Play hard. Play fair. Have fun. > > > [-- Attachment #2 --] <div dir="auto"><div><br><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Tue, Jun 18, 2024, 3:27 PM Jason Bacon <<a href="mailto:bacon4000@gmail.com">bacon4000@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On 6/18/24 12:31, Robert Clausecker wrote:<br> > Greetings,<br> > <br> > I have here a talented maths student looking for a place to<br> > complete her mandatory (unpaid) industry internship.<br> > <br> > She has a knack for numerical analysis, differential equations,<br> > and writing floating point code. I suggested that there might<br> > be need for some improvement to the math code currently shipped<br> > with FreeBSD as the old msun code, while very precise, is not<br> > writted to take advantage of modern SIMD FPUs with FMA support<br> > and could be improved considerably.<br> > <br> > Is there an interest for such or other numerical work on the<br> > FreeBSD code base? Would anybody be interested in supervising<br> > such work? If yes, I would try to connect the two of you.<br> > <br> > Yours,<br> > Robert Clausecker<br> > <br> <br> Coincidentally, I just came across a recent benchmark that might provide <br> some hints about where to focus the efforts:<br> <br> <a href="https://www.phoronix.com/review/bsd-linux-threadripper-7980x" rel="noreferrer noreferrer" target="_blank">https://www.phoronix.com/review/bsd-linux-threadripper-7980x</a></blockquote></div></div><div dir="auto"><br></div><div dir="auto"><br></div><div dir="auto">But stress-ng isn't a benchmark. It says so in it's docs. Also there are several ifdef linux in the source to make it faster on linux.</div><div dir="auto"><br></div><div dir="auto">I wouldn't waste my time on that garbage.</div><div dir="auto"><br></div><div dir="auto">Warner</div><div dir="auto"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><br> -- <br> Life is a game. Play hard. Play fair. Have fun.<br> <br> <br> </blockquote></div></div></div>
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CANCZdfp1pOp0aQDg_7RQW2KsCmKbU38Uuy3wxep-ZsUrmiBVeg>