<info: Entering event queue @ 2747178166000.  Starting simulation...
<panic: RubyPort::M5Port::recvAtomic() not implemented!
< @ cycle 2747178166500
<[recvAtomic:build/ALPHA/mem/ruby/system/RubyPort.cc, line 125]

this panic occurs probably because that we take checkpoint using Atomic
model first and then use a timing model to restore. I have tried using
timing fs.py to take checkpoint and then timing ruby_fs.py to restore. The
result is this "panic: RubyPort::M5Port::recvAtomic() not implemented!" did
not show up again, and I got a new error:


fatal: Can't unserialize 'system.cpu00:locked'
 @ cycle 6371318229000
[paramIn:build/ALPHA_MESI_CMP_directory/sim/serialize.cc, line 228]


Maybe we can not use ruby_fs.py to restore the checkpoints made by a fs.py
configuration?

Damn it!   The 'm5 checkpoint' command appears to fail forever in
ruby_fs.py !!!!!!

Any DEVELOPER response?
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to