This is the mail archive of the gcc@gcc.gnu.org mailing list for the GCC project.

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]
Other format:	[Raw text]

Re: ARM compiler rewriting code to be longer and slower

From: Steven Bosscher <stevenb dot gcc at gmail dot com>
To: Ramana Radhakrishnan <ramana dot radhakrishnan at arm dot com>
Cc: Adam Nemet <anemet at caviumnetworks dot com>, Ramana Radhakrishnan <ramana dot r at gmail dot com>, zoltan at bendor dot com dot au, gcc at gcc dot gnu dot org
Date: Mon, 16 Mar 2009 17:28:43 +0100
Subject: Re: ARM compiler rewriting code to be longer and slower
References: <Pine.LNX.4.31.0903131358550.5688-100000@susu.bendor.com.au> <67ea2eb0903151519j5e9a7f0dr6cb1ce59057b5f92@mail.gmail.com> <571f6b510903151642j4a1f32a2g5c4b6397126034f3@mail.gmail.com> <o7fxhe9lr8.fsf@ropi.home> <6022141616936800448@unknownmsgid>

On Mon, Mar 16, 2009 at 2:52 PM, Ramana Radhakrishnan
<ramana.radhakrishnan@arm.com> wrote:
> Wouldn't doing this in CSE only solve the problem within an extended basic
> block and not necessarily across the program ? Surely you'd want to do it
> globally or am I missing something very basic here ?

Why so serious^Wsurely?

I think doing this optimization over extended basic blocks would catch
90% of the cases.  The loop-carried form is covered by auto-increment
generation (and yes I know that pass also needs to be improved ;-)

Ciao!
Steven

References:
- ARM compiler rewriting code to be longer and slower
  - From: zoltan
- Re: ARM compiler rewriting code to be longer and slower
  - From: Ramana Radhakrishnan
- Re: ARM compiler rewriting code to be longer and slower
  - From: Steven Bosscher
- Re: ARM compiler rewriting code to be longer and slower
  - From: Adam Nemet

Index Nav:	[Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav:	[Date Prev] [Date Next]	[Thread Prev] [Thread Next]