RFR (XL): 8152664 - Support non-continuous CodeBlobs in HotSpot
Andrew Dinn
adinn at redhat.com
Fri Apr 8 13:59:25 UTC 2016
On 07/04/16 18:28, Christian Thalinger wrote:
>
>> On Apr 7, 2016, at 2:25 AM, Andrew Dinn <adinn at redhat.com> wrote:
>> Why do 'we want to be able to have pieces of compiled code and
>> metadata that are not located in one continuous piece of memory'?
>> Is there a motive for making this change?
>
> Yes, there are two reasons:
>
> 1) We would like to separate metadata from code in the CodeCache so
> that we (potentially) get better CPU cache utilization:
>
> https://bugs.openjdk.java.net/browse/JDK-7072317
>
> 2) As described in my last year’s JVMLS talk our AOT solution uses
> shared libraries as a container format and as you know code and data
> need to be separate.
Thanks for the explanation, Christian. Perhaps it might be a good idea
to add a link to indicate that 7072317 relates to (or even is a
dependency of?) 8152664?
> If you haven’t been at JVMLS here is the recording of my talk and the
> section about the container format:
>
> https://youtu.be/Xybzyv8qbOc?t=10m41s
I did watch this just after the summit -- great talk, by the way -- but,
needless to say, failed to retain the relevant detail from that long ago.
regards,
Andrew Dinn
-----------
More information about the hotspot-dev
mailing list