Hi Brad,
I have applied the previous comments. This version also passes
10,000,000 ruby tests and the MOESI_hammer regression test (quick).
I have a question about Flush requests. In the current version, flush
requests return data (similar to loads) for testing purposes. I think it
should not return data, but it still should notify the Sequencer when it
is done (using flushCallback and hitCallback). As ruby requests are
either load or store, the Sequencer sets data properly in the
hitCallback. However, for flush requests, I was thinking to add another
hitCallback function that does not deal with data, what do you think?
Also, should I keep my changes in Check.cc (e.g., initiateFlush)? if a
flush request does not return data, then we can not issue and test it in
this way.
Thanks,
Somayeh
On 03/13/2011 09:50 PM, Somayeh Sardashti wrote:
This is an automatically generated e-mail. To reply, visit:
http://reviews.m5sim.org/r/552/
Review request for Default and Brad Beckmann.
By Somayeh Sardashti.
/Updated 2011-03-13 19:50:32.384965/
Description
my initial implementation of cache flushing
Testing (updated)
This implementation has passed 10,000,000 ruby test cases, and the MOESI_hammer
regression tests.
Diffs (updated)
* src/cpu/testers/rubytest/Check.hh (baf4b5f6782e)
* src/cpu/testers/rubytest/Check.cc (baf4b5f6782e)
* src/mem/packet.hh (baf4b5f6782e)
* src/mem/packet.cc (baf4b5f6782e)
* src/mem/protocol/MOESI_hammer-cache.sm (baf4b5f6782e)
* src/mem/protocol/MOESI_hammer-dir.sm (baf4b5f6782e)
* src/mem/protocol/MOESI_hammer-msg.sm (baf4b5f6782e)
* src/mem/protocol/RubySlicc_Exports.sm (baf4b5f6782e)
* src/mem/protocol/RubySlicc_Types.sm (baf4b5f6782e)
* src/mem/ruby/slicc_interface/RubyRequest.hh (baf4b5f6782e)
* src/mem/ruby/slicc_interface/RubyRequest.cc (baf4b5f6782e)
* src/mem/ruby/system/DMASequencer.cc (baf4b5f6782e)
* src/mem/ruby/system/RubyPort.cc (baf4b5f6782e)
* src/mem/ruby/system/Sequencer.hh (baf4b5f6782e)
* src/mem/ruby/system/Sequencer.cc (baf4b5f6782e)
View Diff <http://reviews.m5sim.org/r/552/diff/>
_______________________________________________
m5-dev mailing list
m5-dev@m5sim.org
http://m5sim.org/mailman/listinfo/m5-dev
