RFR (S) : 8014362 : Need to expose some processor features via Unsafe interface
vladimir.kozlov at oracle.com
Wed May 15 15:19:04 PDT 2013
Sorry, I am late to this discussion.
I think, sun.zip.clmulSupported approach is only temporary solution. As
Christian told we would need more CPU information for Graal.
We should start discussing (new RFE) about new JVM - JAVA API to pass
information about hybrid hw environment (GPU+CPU+etc) JVM is running on.
An other solution for current problem could be resurrection of
sun.cpu.isalist property (bug 6340855).
On 5/15/13 2:49 PM, Christian Thalinger wrote:
> On May 15, 2013, at 2:26 PM, David Chase <david.r.chase at oracle.com> wrote:
>> We probably should, but I'd like to limit the scope of this work (the companion patch is 1500 lines long,
>> includes obscure bit-fiddling, and assembly language). I'm totally happy to file a bug against the established
>> naming convention.
> Sure, I'm fine with that. I figured if you are already touching that code in the JDK we could do it now.
> -- Chris
>> On 2013-05-15, at 4:31 PM, Christian Thalinger <christian.thalinger at oracle.com> wrote:
>>> On May 15, 2013, at 7:34 AM, David Chase <david.r.chase at oracle.com> wrote:
>>>> Plan B, pass the information through a property "sun.zip.clmulSupported", to be removed on the JDK side.
>>> Shouldn't we use some kind of HotSpot related namespace and remove all properties in that namespace? That would make future additions easier. Maybe: com.oracle.jvm.hotspot.*
>>> -- Chris
More information about the hotspot-compiler-dev