Re: [PATCHv2] powerpc: P9 vector load instruction change in memcpy and memmove

[Carlos O'Donell <carlos at redhat dot com>]

On 10/19/2017 01:19 PM, Adhemerval Zanella wrote:
> 
> 
> On 19/10/2017 16:48, Tulio Magno Quites Machado Filho wrote:
>> Adhemerval Zanella <adhemerval.zanella@linaro.org> writes:
>>
>>> On 19/10/2017 16:20, Tulio Magno Quites Machado Filho wrote:
>>>> From: Rajalakshmi Srinivasaraghavan <raji@linux.vnet.ibm.com>
>>>>
>>>> Adhemerval Zanella <adhemerval.zanella@linaro.org> writes:
>>>>
>>>>> According to "POWER8 Processor User’s Manual for the Single-Chip Module"
>>>>> (it is buried on a sign wall at [1]), both lxv2dx/lvx and stxvd2x/stvx
>>>>> uses the same pipeline, have the same latency and same throughput.  The
>>>>> only difference is lxv2dx/stxv2x have microcode handling for unaligned
>>>>> case and for 4k crossing or 32-byte cross L1 miss (which should not
>>>>> occur in the with aligned address).
>>>>>
>>>>> Why not change POWER7 implementation instead of dropping another one
>>>>> which is exactly the same for POWER9?
>>>>
>>>> We're trying to limit the impact of this requirement on other processors so
>>>> that newer P7 or P8 optimizations can still benefit from lxv2dx and stxvd2x.
>>>>
>>>> However, we could avoid source code duplication with the macros LVX and STVX
>>>> I propose here in version 2.
>>>> That way, we will postpone the copy to when/if a P7 optimization is
>>>> contributed.
>>>
>>> And which benefit will be exactly? For this specific case current code 
>>> already only does aligned accesses, so it does not really matter whether 
>>> you use VSX or VMX instruction. If I recall correctly, both lxv2dx/lvx 
>>> and stxvd2x/stvx shows the same latency and throughput also for POWER7.  
>>>
>>> I see no gain on using this POWER9 specific case where you could adjust
>>> POWER7 one.
>>
>> There are no gains now.  The problem arises when contributing a new
>> optimization, e.g. a memcpy optimization for POWER8 using lxv2dx or stxvd2x.
>>
>> If POWER9 doesn't have its own implementation, this problem will appear again.
>>
> 
> I think if eventually a POWER8 optimization could not be used as is for POWER9,
> then a new ifunc variant would make sense.  But I still think we current
> variant, a much simpler solutions (in code sense and maintainability) would be
> to just adapt POWER7 variant to use VMX instructions.
 
We are arguing about taste and style here. About duplication versus functionality.
I would leave it up the machine maintainer to decide how best to move forward.

Tulio knows, and may not be able to say, if there are future optimizations coming
down the line. So we lack a clear picture for deciding on this issue of duplication.

My opinion is that I would *rather* see a POWER7 version that is just for POWER7,
and a POWER8 or POWER9 version that is *just* for POWER8 or POWER9.

The separation of the files allows for simpler incremental distro testing of the
changes without needing to revalidate the POWER7 code again.

-- 
Cheers,
Carlos.