[PATCH][X86] Lower unsigned vsetcc to psubus in certain cases

[Quentin Colombet]

Hi Adam,

Committed revision 202301.

Thanks,
-Quentin

On Feb 26, 2014, at 10:45 AM, Adam Nemet <anemet at apple.com> wrote:

> 
> On Feb 25, 2014, at 5:07 PM, Quentin Colombet <qcolombet at apple.com> wrote:
> 
>> Hi Adam,
>> 
>> This LGTM with two comments:
> 
> Hi Quentin,
> 
> Thanks very  much for the review.
> 
>> 
>> 1. Could you add a comment on why this is not useful for AVX?
>>  +      if (Subtarget->hasAVX())
>>  +        break;
> 
> Done.
> 
>> 
>> 2. As it is your CHECK-LABEL lines may cause failure on pecoff target, see r201931 on how to fix that.
> 
> Added colon after the label name and -mtriple to the command line.
> 
> New version is attached including the check-in message.  Please apply it for me, thank you.
> 
> Adam
> 
> <vsetcc-psubus-v2.patch>
> 
>> 
>> Thanks,
>> -Quentin
>> 
>> On Feb 24, 2014, at 2:36 PM, Adam Nemet <anemet at apple.com> wrote:
>> 
>>> This is another improvement for SingleSource/Benchmarks/Misc/lowercase.c.
>>> 
>>> The current approach to lower a vsetult is to flip the sign bit of the operands, swap the operands and then use a (signed) pcmpgt.  psubus (unsigned saturating subtract) can be used to emulate a vsetult more efficiently:
>>> 
>>> +    case ISD::SETULT: {
>>> +      // If the comparison is against a constant we can turn this into a
>>> +      // setule.  With psubus, setule does not require a swap.  This is
>>> +      // beneficial because the constant in the register is no longer
>>> +      // destructed as the destination so it can be hoisted out of a loop.
>>> 
>>> I also enable lowering via psubus in a few other cases where it’s clearly beneficial: setule and setuge if minu/maxu cannot be used.  You can see the improvements in the diff to the existing test vec_setcc.ll.
>>> 
>>> I am leaving the other case alone for now because it’s harder to reason about profitability in those cases.
>>> 
>>> Tested on x86_64-apple-darwin.
>>> 
>>> Please apply if it looks good.
>>> 
>>> Adam
>>> 
>>> <rdar://problem/14338765>
>>> 
>>> <vsetcc-psubus-v1.patch>_______________________________________________
>>> llvm-commits mailing list
>>> llvm-commits at cs.uiuc.edu
>>> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
>> 
> 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20140226/25e9aea6/attachment.html>