RFR:8166684:implement intrinsic code with vector instructions for Unsafe.copyMemory()

[Volker Simonis]

Hi Michihiro,

thanks for your contribution and sorry for the late reply.

I have some comments regarding your change:

lxvd2x(tmp_vsr1, 0, R3_ARG1);
stxvd2x(tmp_vsr1, 0, R4_ARG2);


"lxvd2x" the second argument has to be a register not a constant. Your
code works because '0' is implicitly converted to register R0 which in
turn encodes as zero in the instruction. But that's not nice from a
software engineering perspective :)

Please create instead a new version of "lxvd2x" which only takes two
arguments (one vector register and one general purpose register) and
explicitly encodes the zero in the instructions. Please also add an
assertion to the three-argument version of  lxvd2x which asserts that
the second argument is not R0. You can use "ra0mem" for that (just
have a look at the two versions of "ldx" for an example).

The same applies to "stxvd2x". And can you please also fix the other
occurrences of lxvd2x/stxvd2x which you've previously introduced with
change 8158232.

With that change ("8158232: PPC64: improve byte, int and long array
copy stubs by using VSX instructions") you've also introduced
prefetching when using the vector instructions and you aligned the
backbranch target to 32 byte (see "enerate_disjoint_int_copy_core").
Wouldn't that be useful here as well?

And finally, "enerate_disjoint_int_copy_core" tries to achieve 8-byte
alignment if possible. Would that make sense here as well? And what
are the alignement requirements of the vector instruction - can they
cope with 4-byte aligned data?

Thank you and best regards,
Volker




On Fri, Sep 30, 2016 at 3:30 PM, Michihiro Horie <HORIE at jp.ibm.com> wrote:
> Hi Goetz, Martin,
>
> Would you review this? The initialization of tmp1 is now outside the loop.
>
> JIRA: https://bugs.openjdk.java.net/browse/JDK-8166684
> Webrev: http://cr.openjdk.java.net/~horii/8166684/webrev.01/
>
> We created webrev by ourselves, and cced to hotspot-compiler-dev.
>
> Best regards,
> --
> Michihiro,
> IBM Research - Tokyo
>
>
>
> ----- Original message -----
> From: "Lindenmaier, Goetz" <goetz.lindenmaier at sap.com>
> To: "Doerr, Martin" <martin.doerr at sap.com>, Michihiro Horie/Japan/IBM at IBMJP,
> "Simonis, Volker" <volker.simonis at sap.com>,
> "ppc-aix-port-dev at openjdk.java.net" <ppc-aix-port-dev at openjdk.java.net>
> Cc: Hiroshi H Horii/Japan/IBM at IBMJP, Gustavo Romero
> <gromero at linux.vnet.ibm.com>
> Subject: RE: RFR:8166684:implement intrinsic code with vector instructions
> for Unsafe.copyMemory()
> Date: Mon, Sep 26, 2016 10:51 PM
>
> Hi,
>
> please post this RFR also to hotspot-compiler-dev. It must be reviewed
> on one of the official lists before it can be pushed. Ppc-aix-port-dev
> is only for communication about the port, not for reviews.
>
> Also I would appreciate if you could upload your webrevs yourselves.
> We are happy to help out in the beginning, and also with testing,
> reviewing and pushing, but making webrevs is a task I don't see on
> our side in the long term.
>
> Thanks and best regards,
>   Goetz.
>
>> -----Original Message-----
>> From: ppc-aix-port-dev [mailto:ppc-aix-port-dev-
>> bounces at openjdk.java.net] On Behalf Of Doerr, Martin
>> Sent: Montag, 26. September 2016 11:53
>> To: Michihiro Horie <HORIE at jp.ibm.com>; Simonis, Volker
>> <volker.simonis at sap.com>; ppc-aix-port-dev at openjdk.java.net
>> Cc: Hiroshi H Horii <HORII at jp.ibm.com>; Gustavo Romero
>> <gromero at linux.vnet.ibm.com>
>> Subject: RE: RFR:8166684:implement intrinsic code with vector instructions
>> for Unsafe.copyMemory()
>>
>> Hi Michihiro,
>>
>>
>>
>> the initialization of tmp1 should be done outside of the loop. Beside
>> that, the
>> change looks good:
>>
>> http://cr.openjdk.java.net/~mdoerr/8166684_PPC64_unsafe_copymemory/
>> webrev.00/
>> <http://cr.openjdk.java.net/~mdoerr/8166684_PPC64_unsafe_copymemory
>> /webrev.00/>
>>
>>
>>
>> Best regards,
>>
>> Martin
>>
>>
>>
>>
>>
>> From: Michihiro Horie [mailto:HORIE at jp.ibm.com]
>> Sent: Montag, 26. September 2016 09:37
>> To: Doerr, Martin <martin.doerr at sap.com>; Simonis, Volker
>> <volker.simonis at sap.com>; ppc-aix-port-dev at openjdk.java.net
>> Cc: volker.simonis at gmail.com; Gustavo Romero
>> <gromero at linux.vnet.ibm.com>; Hiroshi H Horii <HORII at jp.ibm.com>
>> Subject: RFR:8166684:implement intrinsic code with vector instructions for
>> Unsafe.copyMemory()
>>
>>
>>
>> Dear all,
>>
>> Could I please request reviews for the following change?
>> This change was created for JDK9.
>>
>> I added fixes to the intrinsic code for sun.misc.Unsafe.copyMemory() by
>> using VSX.
>> Since Spark often invokes Unsafe.copyMemory(), it is beneficial to use the
>> vector instructions for these intrinsic code.
>>
>> jira: https://bugs.openjdk.java.net/browse/JDK-8166684
>> <https://bugs.openjdk.java.net/browse/JDK-8166684>
>> diff: (See attached file: unsafe-copymemory-openjdk9.diff)
>>
>> Best regards,
>> --
>> Michihiro Horie,
>> IBM Research - Tokyo
>
>
>
>