This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH 5/6] vfprintf: Introduce printf_positional function
- From: "Carlos O'Donell" <carlos at redhat dot com>
- To: Florian Weimer <fweimer at redhat dot com>
- Cc: libc-alpha at sourceware dot org
- Date: Fri, 06 Mar 2015 10:43:43 -0500
- Subject: Re: [PATCH 5/6] vfprintf: Introduce printf_positional function
- Authentication-results: sourceware.org; auth=none
- References: <cover dot 1425246936 dot git dot fweimer at redhat dot com> <06448920c54ddf7d92cce8a2311a0daf470436aa dot 1425246936 dot git dot fweimer at redhat dot com> <54F9A453 dot 5060506 at redhat dot com>
On 03/06/2015 07:57 AM, Florian Weimer wrote:
> On 03/01/2015 10:16 PM, Florian Weimer wrote:
>> This splits a considerable chunk of code from the main vfprintf
>> function. This will make it easier to remove the use of extend_alloca
>> from the positional argument handling code.
>
> Inspection of the generated assembly on x86_64 shows that splitting the
> two functions helps GCC 4.9 with register allocation; there are fewer
> spills.
Awesome.
> I used the following totally made-up benchmark to see if there is a
> performance regression.
Made up or not, it's a microbenchmark you used to test the changes.
Could you please post this as a separate patch for inclusion into
benchtests/ as a positional printf microbenchmark? That way we have
a record of what was used, and can look at changes to printf as we
adjust this code?
Cheers,
Carlos.