[aarch64-port-dev ] aarch64 and arm64 jdk benchmarks result sharing
Zhongwei Yao
zhongwei.yao at linaro.org
Tue Apr 11 02:00:31 UTC 2017
I see. And I would share the Partner A's information by offlist discussion.
On 10 April 2017 at 22:37, Bob Vandette <bob.vandette at oracle.com> wrote:
> Thanks for pointing that out. The bottom tabs was offscreen when I popped
> up the spreadsheet
> on my laptop.
>
> I assume Partner A has implemented some of the Large System Extensions on
> the system your
> are testing on?
>
> Bob.
>
> On Apr 9, 2017, at 10:17 PM, Zhongwei Yao <zhongwei.yao at linaro.org> wrote:
>
> Hi, Bob,
> There are specJBB2015 and Hadoop TeraSort in our benchmarks results
> already. Please check the other tabs in our benchmarks result in the
> spreadsheet. Thanks!
>
> On 8 April 2017 at 03:37, Bob Vandette <bob.vandette at oracle.com> wrote:
>
>> Zongwei,
>>
>> Thanks for running these benchmarks.
>>
>> Have you had the chance to try any server workload type of benchmarks?
>>
>> Just wondering if you had any results running things like specJBB or
>> Hadoop TeraSort.
>>
>> Bob.
>>
>>
>> > On Mar 29, 2017, at 9:43 PM, Zhongwei Yao <zhongwei.yao at linaro.org>
>> wrote:
>> >
>> > Hi,
>> > We have been running some Java benchmarks on AArch64 servers with
>> different
>> > OpenJDK ports: aarch64 and arm64. You can find the results at [1].
>> > And our JDK version:
>> > - aarch64 OpenJDK: build from latest JDK9 source with config:
>> > "--with-jvm-variants=server --with-debug-level=release"
>> >
>> > - arm64 OpenJDK: build from latest JDK9 source with config:
>> > "--with-jvm-variants=server --with-debug-level=release --wi
>> > th-cpu-port=arm64"
>> >
>> > And from the data, aarch64 OpenJDK is better than arm64 OpenJDK
>> > generally, but with some exceptions. So we think it is worth to take a
>> look
>> > at following cases for aarch64 OpenJDK:
>> > - Dacapo's sunflow, tradebeans and xalan
>> > - SPECjvm2008's scimark.lu.large
>> >
>> > And we also find arm64 is better than aarch64 for byte/short data type
>> > vectorization in our JMH cases ([2]), which we are investigating.
>> >
>> > Feedbacks are welcome. Thanks!
>> >
>> > [1]:
>> > https://docs.google.com/spreadsheets/d/18iklOrbaL67i46XHsPTr
>> dTObWqUJJK8EO4-k0eqdLKM/edit?usp=sharing
>> > [2]: https://git.linaro.org/leg/openjdk/jmh-linaro-org.git/
>> >
>> > --
>> > Best regards,
>> > Zhongwei
>>
>>
>
>
> --
> Best regards,
> Zhongwei
>
>
>
--
Best regards,
Zhongwei
More information about the aarch64-port-dev
mailing list