I have implemented some of the missing cache maintenance instructions for
ARM (although I haven't released a patch), and this one is similar to
those. You should be able to implement them by sending a packet to all
caches with the address to be invalidated - if the line is dirty, write it
back to memory, if not call tags->invalidateBlk() on it.

Alternatively, you could do what is done presently for ARM and simply print
a warning message that the instruction is not implemented. It shouldn't
affect correctness. If this instruction is primarily used to provide
software coherence for the i-cache it won't be of much use because the
i-cache is already coherent in gem5.

-Tony

On Wed, Jun 27, 2012 at 11:45 PM, Paul V. Gratz <[email protected]> wrote:

> Hi All,
> I've been trying to run the Oracle/Sun Java JRE in the X86 ISA model
> and so far the roadblock I'm hitting is a complaint from the java
> runtime that the the CLFLUSH instruction is missing.  Parsing through
> the gem5 code it looks like that instruction has not been implemented.
>  Has anyone gotten past this point in the X86 model?  Before we get
> started working on it, I wanted to make sure there weren't any known
> patches to implement the missing functionality.
> Thanks!
> Paul
>
> --
> -----------------------------------------
> Paul V. Gratz
> Assistant Professor
> ECE Dept, Texas A&M University
> Office: 333D WERC
> Phone: 979-488-4551
> http://www.gratz1.com/pgratz
> _______________________________________________
> gem5-users mailing list
> [email protected]
> http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
>
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to