Mailing-List: contact dev-help@harmony.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@harmony.apache.org
Received-SPF: neutral (athena.apache.org: local policy)
Message-ID: <48215343.2090701@anu.edu.au>
Date: Wed, 07 May 2008 16:59:15 +1000
From: Robin Garner <robin.garner@anu.edu.au>
User-Agent: Thunderbird 2.0.0.12 (X11/20080227)
MIME-Version: 1.0
To: dev@harmony.apache.org
Subject: Re: [drlvm][gc]benchmark
References: <482026A7.2080604@gmail.com>
 <9623c9a50805060244s154b1e0cj9c96186df8ba7ba@mail.gmail.com>
 <4bebff790805060407k43908e9fs61a9c59036586327@mail.gmail.com>
In-Reply-To: <4bebff790805060407k43908e9fs61a9c59036586327@mail.gmail.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit

The DaCapo benchmarks were designed specifically with GC in mind, and 
are (in my opinion at least) more representative of current GC workloads 
than the SPEC benchmarks.

http://dacapobench.org/

cheers

Aleksey Shipilev wrote:
> Hi Lyon,
>
> You might consider use the microbenchmark that specifically stresses
> GC. This little one [1] I wrote for my GC performance tuning [2].
>
> Thanks,
> Aleksey.
>
> [1] https://issues.apache.org/jira/secure/attachment/12368829/GCTest.java
> [2] https://issues.apache.org/jira/browse/HARMONY-5058
>
> On Tue, May 6, 2008 at 1:44 PM, Xiao-Feng Li <xiaofeng.li@gmail.com> wrote:
>   
>> We usually just use SPEC benchmarks. You can try DaCapo from UMass.
>>
>>  Thanks,
>>  xiaofeng
>>
>>
>>
>>  On Tue, May 6, 2008 at 5:36 PM, lyon <ustcliao@gmail.com> wrote:
>>  > hi all
>>  >  I intend to test the performance of my implement on the gc,and I try to
>>  >  compare with
>>  >  performance of original algorithm that is based on the SPECjbb.But I
>>  >  found that the SPECjbb is not free,
>>  >  what other benchmarks are available?
>>  >  thanks
>>  >
>>
>>
>>
>>  --
>>  http://xiao-feng.blogspot.com
>>
>>