<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
