[8u-dev] RFR for non-clean backport of 8154156: PPC64: improve array copy stubs by using vector instructions

[Doerr, Martin]

> Do you mean to create a patch after picking a set of code from one of 
> original changesets, then create another one after picking up from another 
> changeset, etc.?
Yes, that would be helpful.

Best regards,
Martin


-----Original Message-----
From: Kazunori Ogata <OGATAK at jp.ibm.com> 
Sent: Montag, 1. April 2019 12:56
To: Doerr, Martin <martin.doerr at sap.com>
Cc: jdk8u-dev at openjdk.java.net
Subject: RE: [8u-dev] RFR for non-clean backport of 8154156: PPC64: improve array copy stubs by using vector instructions

Hi Martin,

Thank you for reviewing.

> I think it will be helpful to get an incremental webrev if you do such 
> changes again in the future. That would make it much easier to see what 
you've done.

Do you mean to create a patch after picking a set of code from one of 
original changesets, then create another one after picking up from another 
changeset, etc.?  I'll do it in the future cherry picking from multiple 
change set.  Thank you for your suggestion.


Regards,
Ogata


"Doerr, Martin" <martin.doerr at sap.com> wrote on 2019/04/01 19:27:27:

> From: "Doerr, Martin" <martin.doerr at sap.com>
> To: Kazunori Ogata <OGATAK at jp.ibm.com>, "jdk8u-dev at openjdk.java.net" 
> <jdk8u-dev at openjdk.java.net>
> Date: 2019/04/01 19:31
> Subject: RE: [8u-dev] RFR for non-clean backport of 8154156: PPC64: 
> improve array copy stubs by using vector instructions
> 
> Hi Ogata,
> 
> I haven't seen any manual adaptations. You only had to pick parts of 
> different changes if I didn't miss anything. I think the selection makes 
sense.
> Looks good to me.
> 
> I think it will be helpful to get an incremental webrev if you do such 
> changes again in the future. That would make it much easier to see what 
you've done.
> 
> Best regards,
> Martin
> 
> 
> -----Original Message-----
> From: jdk8u-dev <jdk8u-dev-bounces at openjdk.java.net> On Behalf Of 
Kazunori Ogata
> Sent: Donnerstag, 28. März 2019 13:56
> To: jdk8u-dev at openjdk.java.net
> Subject: [8u-dev] RFR for non-clean backport of 8154156: PPC64: improve 
> array copy stubs by using vector instructions
> 
> Hi,
> 
> May I get review for non-clean backport of 8154156: PPC64: improve array 

> copy stubs by using vector instructions?
> 
> This is the same change as I posted in January [1], but I updated the 
> patch based on the latest jdk8u-dev tree.  As we've had ppc-expert 
> reviewers in jdk8u-dev community, I'd like to request for review.
> 
> Original patch: https://urldefense.proofpoint.com/v2/url?
> 
u=http-3A__hg.openjdk.java.net_jdk_jdk_rev_c9d756fa846e&d=DwIFAw&c=jf_iaSHvJObTbx-
> siA1ZOg&r=p-
> 
FJcrbNvnCOLkbIdmQ2tigCrcpdU77tlI2EIdaEcJw&m=kByIA1iAKsgJMD6pdYyw1l-5xcMR5UypOklN7bgdBqM&s=_EJfiOe4f_0Of-
> lvi1RbSMBdvPWsNqvQr5fRnoifzug&e=
> Weberv: https://urldefense.proofpoint.com/v2/url?
> u=http-3A__cr.openjdk.java.net_-7Ehorii_jdk8u-5Faes-5Fbe_8154156_webrev.
> 02_&d=DwIFAw&c=jf_iaSHvJObTbx-siA1ZOg&r=p-
> 
FJcrbNvnCOLkbIdmQ2tigCrcpdU77tlI2EIdaEcJw&m=kByIA1iAKsgJMD6pdYyw1l-5xcMR5UypOklN7bgdBqM&s=Tqj6-
> lI1D6uSHJn7I8ULG2nPE2Dns-8EXZ30v2CTSl0&e=
> 
> I confirmed it was buildable for both release and fastdebug builds, and 
> JTREG caused no degradation.
> 
> Refs: 
> [1] 
> https://urldefense.proofpoint.com/v2/url?
> 
u=https-3A__mail.openjdk.java.net_pipermail_jdk8u-2Ddev_2019-2DJanuary_008372.html&d=DwIFAw&c=jf_iaSHvJObTbx-
> siA1ZOg&r=p-
> 
FJcrbNvnCOLkbIdmQ2tigCrcpdU77tlI2EIdaEcJw&m=kByIA1iAKsgJMD6pdYyw1l-5xcMR5UypOklN7bgdBqM&s=os4yIaDEEo_KjCCNEz66kbGPDkZnCa0BcyWxq1fRNi8&e=
> 
> 
> Regards,
> Ogata
> 
> 
> 
>