This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [ARM] Don't give SETs a base cost of COSTS_N_INSNS (4)
- From: Richard Earnshaw <rearnsha at arm dot com>
- To: gcc-patches at gcc dot gnu dot org, richard dot sandiford at linaro dot org
- Date: Thu, 18 Aug 2011 14:18:50 +0100
- Subject: Re: [ARM] Don't give SETs a base cost of COSTS_N_INSNS (4)
- References: <m3aab6rhw0.fsf@richards-thinkpad.stglab.manchester.uk.ibm.com>
On 18/08/11 14:03, Richard Sandiford wrote:
> Following on from:
>
> http://gcc.gnu.org/ml/gcc/2011-08/msg00306.html
>
> this patch stops the ARM and Thumb-2 rtx costs from giving SETs a base
> cost of COSTS_N_INSNS (4). In current trunk, the main effect is to stop
> ivopts from being excessively conservative in the number of ivopts that
> it creates.
>
> I measured the effect on an embedded benchmark, which showed some nice
> improvements. (Results sent to Ramana privately.)
>
> Tested on arm-linux-gnueabi. OK to install?
>
> Richard
>
>
> gcc/
> * config/arm/arm.c (arm_rtx_costs_1): Don't modify the costs of SET.
> (arm_size_rtx_costs): Likewise.
Erm... Cough!
Ok.
R.