Re: [Gems-users] : How to set up the network file for MESI_SCMP_tiledL2bank_directory protocol

[Mike Marty <mikem@xxxxxxxxxxx>]

Yes, that is true.  I guess I have a bad habit of not filling in Message
fields with default values when they aren't used.  You would only see
these errors when looking at debugging output.  And yes, I usually have
the assert commented out.  However I comment this assert out in the SLICC
generator instead so that I don't have to re-edit the machine-generated
file.

I'll add this to my TODO list for bug-fixes

--Mike


> Hi Calvin,
> I was also trying to run Gems for a CMP setup. I have tried out MOESI_CMP_directory protocol and it works fine.
>
> I also got the same problem with MESI_SCMP_tiledL2bank_directory protocol.
> I looked at the gems-users archive and found out that a similar error was faced by someone for invalid range for type "MachineType".
> Mike had replied that the solution was to goto MachineType.C in the /generated/<protocol>
>  directory and comment out the line that was giving the error.
>
> I tried and it worked.
>
> The reason I think is that, all Coherence type messages for this protocol are not defined.
>
> Mike might throw some light onto this.
>
> Hope this helps..
>
> Cheers,
> Niket.
>
>
>
>
> ______________________________________________________________________
> Hi all,
>
> I am using GEMS to simulate a single-chip CMP system. I tried to use
> the MESI_SCMP_tiledL2bank_directory protocol, but I don't quite
> understand how to set up the network file to support different
> configurations (e.g., with 2 cores, 4 cores, etc.).
>
> GEMS 1.4 release only includes one file:
> TILED_Procs-16_ProcsPerChip-16_L2Banks-16_Memories-16.txt
> I tried to modify it for a simple two-core system:
> ---------------------------------------------------------------------------------------
> processors:2
> procs_per_chip:2
> L2banks:2
> memories:2
>
> ext_node:L1Cache:0 int_node:0 link_latency:1 bw_multiplier:72
> ext_node:L2Cache:0 int_node:0 link_latency:1 bw_multiplier:72
> ext_node:L1Cache:1 int_node:1 link_latency:1 bw_multiplier:72
> ext_node:L2Cache:1 int_node:1 link_latency:1 bw_multiplier:72
> ext_node:Directory:0 int_node:0 link_latency:1 bw_multiplier:80
> ext_node:Directory:1 int_node:1 link_latency:1 bw_multiplier:80
>
> int_node:0 int_node:1 link_latency:2 bw_multiplier:64
> -------------------------------------------------------------------------------------------
>
> but GEMS got error like the following:
> -------------------------------------------------------------------------------------------
> Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
> int) in Gems/Install_MESI_SCMP/ruby/buffers/MessageBuffer.C:259: *this
> is [MessageBuffer:  consumer-yes [PrioHeap: [88380, 13, [RefCnt:
> [L1Msg: Address=[0x762a040, line 0x762a040] RequestType=GETS
> ResponseType=Fatal Error: in fn std::string
> CoherenceResponseType_to_string(const CoherenceResponseType&) in
> Gems/Install_MESI_SCMP/ruby/generated/MESI_SCMP_tiledL2bank_directory/CoherenceResponseType.C:35:
> Invalid range for type CoherenceResponseType
> Fatal Error: in fn std::string CoherenceResponseType_to_string(const
> CoherenceResponseType&) in
> Gems/Install_MESI_SCMP/ruby/generated/MESI_SCMP_tiledL2bank_directory/CoherenceResponseType.C:35:
> Invalid range for type CoherenceResponseType
> ***  Simics getting shaky, switching to 'safe' mode.
> ***  Simics (main thread) received an abort signal, probably an assertion.
> -------------------------------------------------------------------------------------------
>
> Could you help clarify how to set up the network file or provide the
> correct configuration? Is it possible to use other network topology
> like PT_TO_PT?  I couldn't find detailed document on this.
>
> Also, is there any other protocol available for simulating single-chip
> CMP? It seems the only one available now is
> MESI_SCMP_tiledL2bank_directory.
>
> Thanks for your help,
> Calvin
>
> _______________________________________________
> Gems-users mailing list
> Gems-users@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/gems-users
> Use Google to search the GEMS Users mailing list by adding "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
>