This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
Re: [RFC] [Patch X86_64]: Pass to split FMA to MUL and ADD
- From: Marc Glisse <marc dot glisse at inria dot fr>
- To: "Kumar, Venkataramanan" <Venkataramanan dot Kumar at amd dot com>
- Cc: "gcc-patches at gcc dot gnu dot org" <gcc-patches at gcc dot gnu dot org>, "Dharmakan, Rohit arul raj" <Rohitarulraj dot Dharmakan at amd dot com>, "Jan Hubicka (hubicka at ucw dot cz)" <hubicka at ucw dot cz>, Uros Bizjak <ubizjak at gmail dot com>
- Date: Tue, 7 Nov 2017 08:21:54 +0100 (CET)
- Subject: Re: [RFC] [Patch X86_64]: Pass to split FMA to MUL and ADD
- Authentication-results: sourceware.org; auth=none
- References: <CY4PR12MB173625509B98E82B0133B39C8F510@CY4PR12MB1736.namprd12.prod.outlook.com>
- Reply-to: gcc-patches at gcc dot gnu dot org
On Tue, 7 Nov 2017, Kumar, Venkataramanan wrote:
The attached patch implements an RTL pass which splits generated FMA instruction into MUL/ADD sequence.
That seems wrong if the user explicitly asked for FMA in his program,
unless you have a way to recognize which FMA instructions come from user
calls to fma and which were invented by gcc. Why not disable the gimple
transformation that creates FMA instead ?
* doc/invoke.texi (SPARC Options): Document -msplit-fma.
Sparc really?
--
Marc Glisse