harmony-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Wenlong Li" <wenl...@gmail.com>
Subject Re: Anyone plans to enable interpreter + jit in client mode?
Date Wed, 12 Nov 2008 07:24:10 GMT
Sorry, Alexei, it is my typo. The result in my side shows RI (Sun's
1.5.0_15) is 2x  faster than Harmony in client mode for SPECJVM2008
startup benchmarks.

btw, I tried your delayed recompilation patch, and found it doesn't
bring performance benefit for my test case. After checking the code,
it sounds like the recompilation doesn't happen as the profiling
result doesn't exceed the threshold. So recompilation is not time
consuming in VM creation.

Thx,
Wenlong


On Wed, Nov 12, 2008 at 3:01 PM, Alexei Fedotov
<alexei.fedotov@gmail.com> wrote:
> Wenlong, I'm sorry. You wrote:
>> Results show RI is around 2x faster than Sun's 1.5.0_15.
>
> What is RI?
>
> Thanks, Alexei
>
> On Wed, Nov 12, 2008 at 9:28 AM, Wenlong Li <wenlong@gmail.com> wrote:
>> Aleksey,
>>
>> I am trying your delayed recompilation patch, and will let you know the result.
>>
>> As for interpreter vs. jet or client, I measured the VM creation time
>> of Harmony, and found interpreter takes the least time to create
>> Harmony VM, e.g., 94 ms, while jet takes 121 ms, and client takes 140
>> ms (all these time are for Harmony). At the same time, I compared
>> Harmony with RI in client mode for JVM2008 startup benchmarks. Results
>> show RI is around 2x faster than Sun's 1.5.0_15.
>>
>> Any thought or comment?
>>
>> Thx,
>> Wenlong
>>
>> On Wed, Nov 12, 2008 at 2:09 PM, Aleksey Shipilev
>> <aleksey.shipilev@gmail.com> wrote:
>>> Harmony's way to "interpret bytecode" is to compile it with JET. Last
>>> time I measured JET overhead, it was relatively small, like 5% of
>>> overall execution time on Eclipse startup. On another hand, if you
>>> compare performance on JET-compiled code of Harmony (-Xem:jet) with
>>> performance of code interpreted by any  RI, you will see JET rocks. My
>>> other measurements shows JET-compiled code is like 3x times faster
>>> than Sun's 1.5.0_10 interpretation ;)
>>>
>>> Have you any data supporting your proposal?
>>>
>>> Thanks,
>>> Aleksey.
>>>
>>> On Wed, Nov 12, 2008 at 6:52 AM, Wenlong Li <wenlong@gmail.com> wrote:
>>>> Hello, all,
>>>>
>>>> Harmony now uses jet+jit in client mode, does anybody know why? Seems
>>>> RI uses interpreter + jit or jit only to compile target program. Does
>>>> anybody have done or plan to support the interpreter + jit in client
>>>> mode? I am asking this question because RI has good startup
>>>> performance, but Harmony has not good startup performance (one of the
>>>> problems is compilation overhead).
>>>>
>>>> Thx,
>>>> Wenlong
>>>>
>>>
>>
>
>
>
> --
> С уважением,
> Алексей Федотов,
> Телеком Экспресс
>
Mime
View raw message