This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [PATCHv2] new target hook for loop unrolling adjustment
- From: Gerald Pfeifer <gerald at pfeifer dot com>
- To: Christian Borntraeger <borntraeger at de dot ibm dot com>
- Cc: Richard Guenther <richard dot guenther at gmail dot com>, Andreas Krebbel <krebbel at linux dot vnet dot ibm dot com>, gcc-patches at gcc dot gnu dot org, Wolfgang Gellerich <gellerich at de dot ibm dot com>
- Date: Sat, 1 Jan 2011 14:30:22 +0100 (CET)
- Subject: Re: [PATCHv2] new target hook for loop unrolling adjustment
- References: <201001271427.29150.borntraeger@de.ibm.com> <84fc9c001001270832n6c267b43wfd6eefedaa8da001@mail.gmail.com> <201002011520.59815.borntraeger@de.ibm.com>
On Mon, 1 Feb 2010, Christian Borntraeger wrote:
> +@deftypefn {Target Hook} unsigned TARGET_LOOP_UNROLL_ADJUST (unsigned @var{nunroll}, struct loop *@var{loop})
> +This target hook returns a new value for the number of times @var{loop}
> +should be unrolled. The parameter @var{nunroll} is the number of times
> +the loop is to be unrolled. The parameter @var{loop} is a pointer to
> +the loop, which is going to be checked for unrolling. This target hook
> +is required only when the target has special constraints like maximum
> +number of memory accesses.
I am struggling a bit reading this description. Perhaps something like
"...adjusts the number of times... @var{unroll} is the original number
of times..." or something along these lines?
(Yes, this stuck in my outbox for nearly a year. :-( )
Gerald