RFR(S): 8194740: Fix for: UseSubwordForMaxVector causes performance regression

[Vladimir Kozlov]

http://cr.openjdk.java.net/~vdeshpande/SubwordFix/webrev.01/

Good. Now we have to wait performance results.

Thanks,
Vladimir

On 6/11/18 11:48 AM, Deshpande, Vivek R wrote:
> Hi Vladimir
> 
> I have updated the webrev with suggested {} for if().
> 
> Regards,
> Vivek
> 
> -----Original Message-----
> From: hotspot-compiler-dev [mailto:hotspot-compiler-dev-bounces at openjdk.java.net] On Behalf Of Deshpande, Vivek R
> Sent: Friday, June 8, 2018 4:42 PM
> To: Vladimir Kozlov <vladimir.kozlov at oracle.com>; hotspot-compiler-dev at openjdk.java.net compiler <hotspot-compiler-dev at openjdk.java.net>
> Subject: RE: RFR(S): 8194740: Fix for: UseSubwordForMaxVector causes performance regression
> 
> Thanks Vladimir
> 
> I will take do that and resend the updated webrev.
> Thanks Tobias for making the runs.
> 
> Regards,
> Vivek
> 
> -----Original Message-----
> From: Vladimir Kozlov [mailto:vladimir.kozlov at oracle.com]
> Sent: Friday, June 8, 2018 4:34 PM
> To: Deshpande, Vivek R <vivek.r.deshpande at intel.com>; hotspot-compiler-dev at openjdk.java.net compiler <hotspot-compiler-dev at openjdk.java.net>
> Subject: Re: RFR(S): 8194740: Fix for: UseSubwordForMaxVector causes performance regression
> 
> Hi Vivek,
> 
> Changes look good to me. Only add {} for condition in loopTransform.cpp.
> I asked Tobias to rerun performance testing to verify the fix.
> 
> Thanks,
> Vladimir
> 
> On 6/7/18 3:24 PM, Deshpande, Vivek R wrote:
>> Hi All
>>
>> I have a fix for the regression caused by Subword Analysis. I tested
>> the fix with SPECjvm2008.MPEG and I don't observe the slowdown.
>>
>> Could you please review the patch and sponsor it.
>>
>> Bug ID:
>>
>> https://bugs.openjdk.java.net/browse/JDK-8194740
>>
>> Webrev:
>> http://cr.openjdk.java.net/~vdeshpande/SubwordFix/webrev.00/
>>
>> Regards,
>>
>> Vivek
>>