linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* Re: arch/86: AVX RAID5 xor checksumming
       [not found] <1334078551-6859-1-git-send-email-james.t.kukunas@linux.intel.com>
@ 2012-04-10 17:37 ` H. Peter Anvin
  2012-04-10 20:14   ` NeilBrown
  0 siblings, 1 reply; 4+ messages in thread
From: H. Peter Anvin @ 2012-04-10 17:37 UTC (permalink / raw)
  To: Jim Kukunas; +Cc: x86, neilb, linux-kernel, mingo, tglx, linux-raid

On 04/10/2012 10:22 AM, Jim Kukunas wrote:
> Hi Folks,
> 
> The following patch adds an AVX implementation of the RAID5 xor checksumming
> functions.
> 
> Based on xor_speed, the AVX implementation appears to be ~32% faster than the
> SSE implementation on my i7 2600:
> 
>         generic_sse: 15088.000 MB/sec
> 	avx: 19936.000 MB/sec
> 
> Thanks.
> 

I think this (and the SSSE3 patches for RAID-6) should go in via the
RAID tree.  Neil, do you agree?

However,

Acked-by: H. Peter Anvin <hpa@zytor.com>

	-hpa

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: arch/86: AVX RAID5 xor checksumming
  2012-04-10 17:37 ` arch/86: AVX RAID5 xor checksumming H. Peter Anvin
@ 2012-04-10 20:14   ` NeilBrown
  2012-04-10 21:20     ` H. Peter Anvin
  0 siblings, 1 reply; 4+ messages in thread
From: NeilBrown @ 2012-04-10 20:14 UTC (permalink / raw)
  To: H. Peter Anvin; +Cc: Jim Kukunas, x86, linux-kernel, mingo, tglx, linux-raid

[-- Attachment #1: Type: text/plain, Size: 975 bytes --]

On Tue, 10 Apr 2012 10:37:00 -0700 "H. Peter Anvin" <hpa@zytor.com> wrote:

> On 04/10/2012 10:22 AM, Jim Kukunas wrote:
> > Hi Folks,
> > 
> > The following patch adds an AVX implementation of the RAID5 xor checksumming
> > functions.
> > 
> > Based on xor_speed, the AVX implementation appears to be ~32% faster than the
> > SSE implementation on my i7 2600:
> > 
> >         generic_sse: 15088.000 MB/sec
> > 	avx: 19936.000 MB/sec
> > 
> > Thanks.
> > 
> 
> I think this (and the SSSE3 patches for RAID-6) should go in via the
> RAID tree.  Neil, do you agree?

I'm happy to take the SSSE3 RAID-6 patches as they only affect lib/raid6, but
I felt that this one - being purely in arch/x86 - should probably go via the
x86 tree.
However I'm flexible and if you (collectively) are happy with these patches
going in through my tree, I'll do that.

Thanks,
NeilBrown

> 
> However,
> 
> Acked-by: H. Peter Anvin <hpa@zytor.com>
> 
> 	-hpa


[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 828 bytes --]

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: arch/86: AVX RAID5 xor checksumming
  2012-04-10 20:14   ` NeilBrown
@ 2012-04-10 21:20     ` H. Peter Anvin
  2012-04-14 12:02       ` Ingo Molnar
  0 siblings, 1 reply; 4+ messages in thread
From: H. Peter Anvin @ 2012-04-10 21:20 UTC (permalink / raw)
  To: NeilBrown; +Cc: Jim Kukunas, x86, linux-kernel, mingo, tglx, linux-raid

On 04/10/2012 01:14 PM, NeilBrown wrote:
>>
>> I think this (and the SSSE3 patches for RAID-6) should go in via the
>> RAID tree.  Neil, do you agree?
> 
> I'm happy to take the SSSE3 RAID-6 patches as they only affect lib/raid6, but
> I felt that this one - being purely in arch/x86 - should probably go via the
> x86 tree.
> However I'm flexible and if you (collectively) are happy with these patches
> going in through my tree, I'll do that.
> 

Go ahead and take them with my Acked-by: -- I think that's easier.

	-hpa

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: arch/86: AVX RAID5 xor checksumming
  2012-04-10 21:20     ` H. Peter Anvin
@ 2012-04-14 12:02       ` Ingo Molnar
  0 siblings, 0 replies; 4+ messages in thread
From: Ingo Molnar @ 2012-04-14 12:02 UTC (permalink / raw)
  To: H. Peter Anvin
  Cc: NeilBrown, Jim Kukunas, x86, linux-kernel, mingo, tglx,
	linux-raid


* H. Peter Anvin <hpa@zytor.com> wrote:

> On 04/10/2012 01:14 PM, NeilBrown wrote:
> >>
> >> I think this (and the SSSE3 patches for RAID-6) should go in via the
> >> RAID tree.  Neil, do you agree?
> > 
> > I'm happy to take the SSSE3 RAID-6 patches as they only affect lib/raid6, but
> > I felt that this one - being purely in arch/x86 - should probably go via the
> > x86 tree.
> > However I'm flexible and if you (collectively) are happy with these patches
> > going in through my tree, I'll do that.
> > 
> 
> Go ahead and take them with my Acked-by: -- I think that's easier.

Yeah - and x86/include/asm/xor*.h should probably be renamed 
raid_xor*.h or so, to make this really obvious to do in the 
future.

Thanks,

	Ingo

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2012-04-14 12:02 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
     [not found] <1334078551-6859-1-git-send-email-james.t.kukunas@linux.intel.com>
2012-04-10 17:37 ` arch/86: AVX RAID5 xor checksumming H. Peter Anvin
2012-04-10 20:14   ` NeilBrown
2012-04-10 21:20     ` H. Peter Anvin
2012-04-14 12:02       ` Ingo Molnar

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).