> On 2011-05-26 23:29:05, Gabe Black wrote: > > What does Self.all do? What is it for? You have one use in the change so I > > have a basic idea, but it would be helpful to know the specifics. > > Ali Saidi wrote: > It's similar to Parent.any in that it traverses the object hierarchy and > finds all (as opposed to one) objects that are of a certain type. As you > see from the memories example, the system object can have a pointer to all > PhysicalMemory objects that belong to that system. The reason to add > something like this, is to have a generic way to prevent speculation from > touching I/O. It's possible for a speculative instruction fetch to sneak out > of the CPU if the wrong 10 things all happen an once and with this another > change can prevent that (will post soon). It's not as simple as just not > fetching from non-cacheable memory, since most architectures start their > processors in some kind of caches disabled, tlb should only issue > non-cachable transaction state.
So if the real machine is using speculative execution in this cache-disable mode, how does it avoid touching I/O locations? - Steve ----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: http://reviews.m5sim.org/r/720/#review1262 ----------------------------------------------------------- On 2011-05-26 19:17:18, Ali Saidi wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > http://reviews.m5sim.org/r/720/ > ----------------------------------------------------------- > > (Updated 2011-05-26 19:17:18) > > > Review request for Default, Ali Saidi, Gabe Black, Steve Reinhardt, and > Nathan Binkert. > > > Summary > ------- > > Config: Add support for a Self.all proxy object > > > Diffs > ----- > > src/python/m5/SimObject.py 3f37cc5d25bc > src/python/m5/params.py 3f37cc5d25bc > src/python/m5/proxy.py 3f37cc5d25bc > src/sim/System.py 3f37cc5d25bc > > Diff: http://reviews.m5sim.org/r/720/diff > > > Testing > ------- > > > Thanks, > > Ali > > _______________________________________________ gem5-dev mailing list gem5-dev@m5sim.org http://m5sim.org/mailman/listinfo/gem5-dev