> On Sept. 21, 2012, 9:24 a.m., Nilay Vaish wrote: > > Just for my understanding, can you present what was happening earlier, what > > will happen > > with this patch in the clock example that you have provided?
AttributeError, cannot unproxy clock in Root, and the reason is that it tries to get Parent.clock from the system instead of the actual clock object it has, and then the Root doesn't have a clock and things blow up. Try it out :) - Andreas ----------------------------------------------------------- This is an automatically generated e-mail. To reply, visit: http://reviews.gem5.org/r/1432/#review3510 ----------------------------------------------------------- On Sept. 21, 2012, 9:05 a.m., Andreas Hansson wrote: > > ----------------------------------------------------------- > This is an automatically generated e-mail. To reply, visit: > http://reviews.gem5.org/r/1432/ > ----------------------------------------------------------- > > (Updated Sept. 21, 2012, 9:05 a.m.) > > > Review request for Default. > > > Description > ------- > > This patch modifies how proxies are traversed and unproxied to allow > chained proxies. The issue that is solved manifested itself when a > proxy during its evaluation ended up being hitting another proxy, and > the second one got evaluated using the object that was originally used > for the first proxy. > > For a more tangible example, see the following patch on making the > default clock being inherited from the parent. In this patch, the CPU > clock is a proxy Parent.clock, which is overridden in the system to be > an actual value. This all works fine, but the AlphaLinuxSystem has a > boot_cpu_frequency parameter that is Self.cpu[0].clock.frequency. When > the latter is evaluated, it all happens relative to the current object > of the proxy, i.e. the system. Thus the cpu.clock is evaluated as > Parent.clock, but using the system rather than the cpu as the object > to enquire. > > > Diffs > ----- > > src/python/m5/proxy.py 7d506c3ef13d > > Diff: http://reviews.gem5.org/r/1432/diff/ > > > Testing > ------- > > util/regress all passing (disregarding t1000 and eio) > > > Thanks, > > Andreas Hansson > > _______________________________________________ gem5-dev mailing list [email protected] http://m5sim.org/mailman/listinfo/gem5-dev
