This is the mail archive of the
mailing list for the GCC project.
Re: [PATCH ARM]Handle REG addressing mode in output_move_neon explicitly
- From: Ramana Radhakrishnan <ramana dot gcc at googlemail dot com>
- To: "bin.cheng" <bin dot cheng at arm dot com>
- Cc: Richard Earnshaw <Richard dot Earnshaw at arm dot com>, gcc-patches <gcc-patches at gcc dot gnu dot org>
- Date: Wed, 2 Jul 2014 07:48:44 +0100
- Subject: Re: [PATCH ARM]Handle REG addressing mode in output_move_neon explicitly
- Authentication-results: sourceware.org; auth=none
- References: <002f01cf6357$854c7a00$8fe56e00$ at arm dot com> <5362542B dot 6060609 at arm dot com> <004301cf6832$aee35020$0ca9f060$ at arm dot com>
- Reply-to: ramrad01 at arm dot com
On Mon, May 5, 2014 at 8:21 AM, bin.cheng <email@example.com> wrote:
>> -----Original Message-----
>> From: Richard Earnshaw
>> Sent: Thursday, May 01, 2014 10:03 PM
>> To: Bin Cheng
>> Cc: firstname.lastname@example.org
>> Subject: Re: [PATCH ARM]Handle REG addressing mode in
>> output_move_neon explicitly
>> On 29/04/14 04:02, bin.cheng wrote:
>> > Hi,
>> > Function output_move_neon now generates vld1.64 for memory ref like
>> > "dx <- [r1:SI]", this is bogus because it requires at least 64-bit
>> > alignment for 32-bit aligned memory ref. It works now because GCC
>> > doesn't generate such insns in the first place, but things are going
>> > to change if memset/memcpy calls are inlined by using neon instructions.
>> V[LD/ST]1.64 only need to be 64-bit aligned if strict alignment is
> enabled. We
>> normally assume that not to be the case. The exception to this is when an
> theoretically, this doesn't make the problem go away, right?
>> explicit alignment check is used in the address expression (the :64
>> which causes the address to be checked for strict alignment at all times.
>> Do you have a testcase?
> I can't provide a test case without the memset inlining patch.
Are the tests in the memset inlining patch now sufficient to expose
the problem or do we need another test ?