This is the mail archive of the
mailing list for the glibc project.
Re: GNU Tools Cauldron 2013 - 2nd Call for Abstracts
I will attend and do not know exactly what I will talk about then.
On Wed, Feb 13, 2013 at 01:03:24PM -0500, Carlos O'Donell wrote:
> On Mon, Feb 4, 2013 at 12:36 AM, Siddhesh Poyarekar <firstname.lastname@example.org> wrote:
> > On Mon, Jan 21, 2013 at 03:13:46PM -0500, Diego Novillo wrote:
> >> This time we will meet at Google Headquarters in Mountain View,
> >> California from 12/Jul/2013 to 14/Jul/2013.
> > <snip>
> >> - BoFs: coordination meetings with other developers.
> > This should be close enough to planning for 2.19, so it might be a
> > good time to have a glibc BoF.
> A GNU C Library BOF has been proposed and accepted for GNU Cauldron 2013.
> The GNU C Library is used as the C library in the GNU systems
> and most systems with the Linux kernel. The library is
> primarily designed to be a portable and high performance C
> library.It follows all relevant standards including ISO C11
> and POSIX.1-2008. It is also internationalized and has one of
> the most complete internationalization interfaces known.
> This BOF aims to bring together developers of other components
> that have dependencies on glibc and glibc developers to talk
> about the following topics:
> * Planning for glibc 2.19 and what work needs to be done
> between the August -> December 2013 timeframe (2.19 development
> * Performance?
> - The project calls itself a "high performance C library", but
> we've never had a standard performance regression testsuite
> - How do we measure performance?
> - How do we track it?
> - What criteria do we use to evaluate patches based on performance?
> - Starting with libm e.g. accuracy vs. runtime performance.
I will talk about these as situation develops. I have several plans on my
todo list. One is adding performance counters to my framework.
> * libm
> - Offer three libraries?
> - Slow high performance, middle of the road, high performance low precision.
How do you choose this with finer granularity? I have no good idea how yet.
> * Tuning the C library?
> - What do we expose?
> - Why?
> - Hardware lock elision examples.
> - Runtime tuning.
> - Environment variables.
One project in my todo list is post link time optimizer. Expaining needs
> * POSIX conformance
> - The usual.
> * ISO C11, and C++11
> - What's left?
> * IPv4 and IPv6
> - getaddrinfo mess.
> As always we will report back to the community about the things
> discussed at the BOF.
> The BOF is simply a good time to meet face-to-face and get to know eachother :-)
> As I mentioned before I will likely be unable to attend the BOF in
> person but will be there virtually.