Any help with this Nilay ?
I believe that the code seems illogical because the value of "delayedResponse"
will always return true due to passing true to the timing parameter in
translate" function
Regards
From: mostafa.m.has...@hotmail.com
To: gem5-users@gem5.org; ni...@cs.wisc.edu
Date: Tue, 8 Jan 2013 03:51:42 +0200
Subject: Re: [gem5-users] Running benchmark on FS X86 : Assertion
`!delayedResponse' failed.
I traced this error and suspectthe behavior of this peice in recvPacket
function (lines 604-609 in
"build/X86_MESI_CMP_directory/arch/x86/pagetable_walker.cc")
bool delayedResponse;
Fault fault = walker->tlb->translate(req, tc, NULL, mode,
delayedResponse, true);
assert(!delayedResponse);
// Let the CPU continue.
translation->finish(fault, req, tc, mode);
When I checked the "translate" function in 298-303 "":
Fault fault = walker->star
t(tc, translation, req, mode);
if (timing || fault != NoFault) {
// This gets ignored in atomic mode.
delayedResponse = true;
return fault;
}
I can see that we have already passed true to "timing" which will cause
"delayedResponse" to change to true irrespective of the value of "fault", which
in turn cause the assertion in recvPacket function to fail constantly
Could you help me with this pease
Regards
_______________________________________________
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
_______________________________________________
gem5-users mailing list
gem5-users@gem5.org
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users
