This is the mail archive of the gcc-patches@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: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.

From: Marc Glisse <marc dot glisse at inria dot fr>
To: Cong Hou <congh at google dot com>
Cc: Richard Biener <rguenther at suse dot de>, GCC Patches <gcc-patches at gcc dot gnu dot org>
Date: Fri, 22 Nov 2013 01:39:23 +0100 (CET)
Subject: Re: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
Authentication-results: sourceware.org; auth=none
References: <CAK=A3=0jwnwHsyoOnPq1yDwSC=KJHfXwgpyMwvOaCLtqCTo_5g at mail dot gmail dot com> <alpine dot LNX dot 2 dot 00 dot 1311150945290 dot 4261 at zhemvz dot fhfr dot qr> <CAK=A3=3TAJNrivikE-NFAOYsyn49PxqkhYMfs0TzFtDqci2f1Q at mail dot gmail dot com> <alpine dot LNX dot 2 dot 00 dot 1311191034550 dot 4261 at zhemvz dot fhfr dot qr> <CAK=A3=1d3mOmC-cGNiGDjfyZOQ5NWzVQmzeSOwYSF7JoBHJWew at mail dot gmail dot com> <alpine dot LNX dot 2 dot 00 dot 1311200951200 dot 4261 at zhemvz dot fhfr dot qr> <CAK=A3=1Puwf0tkqMuuvRXxHk66a9+kkfL9x+-aqPvP=PdQOicw at mail dot gmail dot com> <CAK=A3=3_9_i_xPNPDxOHVc-+r4cnCu4tBSFPou0YYD=QNoBULQ at mail dot gmail dot com>
Reply-to: gcc-patches at gcc dot gnu dot org

On Thu, 21 Nov 2013, Cong Hou wrote:

While I added the new define_insn_and_split for vec_merge, a bug is
exposed: in config/i386/sse.md, [ define_expand "xop_vmfrcz<mode>2" ]
only takes one input, but the corresponding builtin functions have two
inputs, which are shown in i386.c:

 { OPTION_MASK_ISA_XOP, CODE_FOR_xop_vmfrczv4sf2,
"__builtin_ia32_vfrczss",     IX86_BUILTIN_VFRCZSS,     UNKNOWN,
(int)MULTI_ARG_2_SF },
 { OPTION_MASK_ISA_XOP, CODE_FOR_xop_vmfrczv2df2,
"__builtin_ia32_vfrczsd",     IX86_BUILTIN_VFRCZSD,     UNKNOWN,
(int)MULTI_ARG_2_DF },

In consequence, the ix86_expand_multi_arg_builtin() function tries to
check two args but based on the define_expand of xop_vmfrcz<mode>2,
the content of insn_data[CODE_FOR_xop_vmfrczv4sf2].operand[2] may be
incorrect (because it only needs one input).

The patch below fixed this issue.

Bootstrapped and tested on ax x86-64 machine. Note that this patch
should be applied before the one I sent earlier (sorry for sending
them in wrong order).


This is PR 56788. Your patch seems strange to me and I don't think it
fixes the real issue, but I'll let more knowledgeable people answer.

--
Marc Glisse

Follow-Ups:
- Re: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
  - From: Cong Hou

References:
- [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
  - From: Cong Hou
- Re: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
  - From: Richard Biener
- Re: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
  - From: Cong Hou
- Re: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
  - From: Richard Biener
- Re: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
  - From: Cong Hou
- Re: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
  - From: Richard Biener
- Re: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
  - From: Cong Hou
- Re: [PATCH] Support addsub/subadd as non-isomorphic operations for SLP vectorizer.
  - From: Cong Hou

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