[PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-13 Thread linkw
From: Kewen Lin Previous version link for background: https://gcc.gnu.org/ml/gcc-patches/2019-04/msg00912.html Firstly, it's to call predict_doloop_p hook to check this loop will be transformed to doloop or not, if yes, find the expected comp iv use and its dependent original iv, set the iv cand

Re: [PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-14 Thread Richard Biener
On Tue, May 14, 2019 at 5:10 AM wrote: > > From: Kewen Lin > > Previous version link for background: > https://gcc.gnu.org/ml/gcc-patches/2019-04/msg00912.html > > Firstly, it's to call predict_doloop_p hook to check this > loop will be transformed to doloop or not, if yes, find > the expected co

Re: [PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-14 Thread Kewen.Lin
on 2019/5/14 下午3:26, Richard Biener wrote: > On Tue, May 14, 2019 at 5:10 AM wrote: >> >> From: Kewen Lin >> >> Previous version link for background: >> https://gcc.gnu.org/ml/gcc-patches/2019-04/msg00912.html >> >> Firstly, it's to call predict_doloop_p hook to check this >> loop will be transfo

Re: [PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-15 Thread Richard Biener
On Wed, 15 May 2019, Kewen.Lin wrote: > on 2019/5/14 下午3:26, Richard Biener wrote: > > On Tue, May 14, 2019 at 5:10 AM wrote: > >> > >> From: Kewen Lin > >> > >> Previous version link for background: > >> https://gcc.gnu.org/ml/gcc-patches/2019-04/msg00912.html > >> > >> Firstly, it's to call pr

Re: [PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-15 Thread Segher Boessenkool
On Wed, May 15, 2019 at 10:47:31AM +0200, Richard Biener wrote: > Ah, so the key issue is that the doloop IV is "free"? That > is, it doesn't consume a general register and whatnot? That > is allocating this IV doesn't really interfere with other IVs? That is one half of it, yes. > But can othe

Re: [PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-15 Thread Kewen.Lin
on 2019/5/15 下午4:47, Richard Biener wrote: > On Wed, 15 May 2019, Kewen.Lin wrote: > >> on 2019/5/14 下午3:26, Richard Biener wrote: >>> On Tue, May 14, 2019 at 5:10 AM wrote: From: Kewen Lin Previous version link for background: https://gcc.gnu.org/ml/gcc-patches/2019-04/

Re: [PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-16 Thread Richard Biener
On Wed, 15 May 2019, Segher Boessenkool wrote: > On Wed, May 15, 2019 at 10:47:31AM +0200, Richard Biener wrote: > > Ah, so the key issue is that the doloop IV is "free"? That > > is, it doesn't consume a general register and whatnot? That > > is allocating this IV doesn't really interfere with

Re: [PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-16 Thread Segher Boessenkool
On Thu, May 16, 2019 at 09:25:49AM +0200, Richard Biener wrote: > On Wed, 15 May 2019, Segher Boessenkool wrote: > > > Otherwise I understand that IVOPTs doesn't properly cost > > > the doloop IV update and conditional branch. > > > > Currently it doesn't even *know* something is or isn't a doloop

Re: [PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-16 Thread Jeff Law
On 5/15/19 2:47 AM, Richard Biener wrote: > On Wed, 15 May 2019, Kewen.Lin wrote: > >> on 2019/5/14 下午3:26, Richard Biener wrote: >>> On Tue, May 14, 2019 at 5:10 AM wrote: From: Kewen Lin Previous version link for background: https://gcc.gnu.org/ml/gcc-patches/2019-04/m

Re: [PATCH v2 3/3] Consider doloop cmp use in ivopts

2019-05-16 Thread Segher Boessenkool
Hi Jeff, On Thu, May 16, 2019 at 12:41:16PM -0600, Jeff Law wrote: > For architectures like PPC, we probably don't want to use the loop count > for anything else as it's likely expensive to get data in/out of the the > loop count register. That is part of it. Another part is that it costs extra