Hi,
So I've written a fancy deadlock-detection algorithm hoping that it would
detect deadlocks caused the l2-bus trying to access a private cache while that
same private cache tried to access the l2-bus, so that I could roll back one
of the calls. However I found an additional problem. It
On Mar 6, 2010, at 5:41 PM, Stijn Souffriau wrote:
Hi,
So I've written a fancy deadlock-detection algorithm hoping that it
would
detect deadlocks caused the l2-bus trying to access a private cache
while that
same private cache tried to access the l2-bus, so that I could roll
back
On Saturday 06 March 2010 11:53:55 pm Ali wrote:
If you provide us with a back trace of the call we could tell you for
sure, but I imagine it's either a response coming back from the cache,
or it could be one of the status change messages (I think the only one
we support is the range change)
Hi Stijn,
They are just snoop requests from the access filtering through the
system. You might be able to stop them by having the CPU return
snoop=false to getDeviceAddressRanges(), but I'm not sure that the
caches have code to do that implemented (Steve?). In any case, it's
certainly OK