Re: [Gems-users] Flow of an IFetch

[Hemayet Hossain <hossain@xxxxxxxxxxxxxxxx>]

Hi Mike,
Thanks for the prompt reply.

> The original request message will sit in the
> mandatory queue until this is done.
How is it determined that the IFetch can't be processed when the it has 
already issued PUTS (block is already deallocated from L1D)? Any poniter?
Thanks.
------
Hemayet

> > Hi Everybody,
> > I was looking over the MSI_MOSI_SMP_directory proctocol. In *-L1Cache.sm
> > file for an IFetch, if the block is in L1D then an event L1_WriteBack is
> > triggered which deallocates the copy from L1D, allocates space and copy
> > data in TBE, and issues PUTS. The original cache message is kept in the
> > mandatory queue. I could not confidently trace what happend after that.
> >
> > Can any body tell me the flow of this (I mean upto loading the the
> > instruction to L1I) considering timing steps? May be it's a long answer,
> > but any answer will be appreciated.
> >
> > Thanks.
> > --
> > Hemayet Hossain