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

[Calvin <calvincv@xxxxxxxxx>]

Hi Niket,

Thanks for your help. I commented out the error message as you
suggested. Now I can get around the assertion problem, but there is
still other error: (I am using the FFT benchmark from Splash2, and
tried to load Ruby alone or with Opal)
-----------------------------------------------------------------------------------------------------------------
Ruby: ruby-opal link established. removing timing_model.
opalinterface: doing notify callback
Opal: opal-ruby link established.
OpalInterface: installation successful.
[0]     PC 0x12f2c      NPC 0x12f30     ctx 0x86
[1]     PC 0x1039948    NPC 0x103994c   ctx 0x0
[cpu0] v:0x0000000000012f5c p:0x0000000039f22f5c  sethi %hi(0x13c00), %g2
patch  PC: 0x103994c 0x1049854
patch  NPC: 0x1039950 0x1049858
patch  PC: 0x12f30 0x12f60
patch  NPC: 0x12f34 0x12f64
patch  NPC: 0xffffffffff3b3aa8 0xff3b3aa8
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:259: *this is [MessageBuffer:
consumer-yes [PrioHeap: [19497, 12, [RefCnt: [L1Msg:
Address=[0x762a040, line 0x762a040] RequestType=GETS ResponseType=
Requestor=L1Cache-0 Sender=Directory--1073753688 Destination=[NetDest
(3) 0 0  - 0 1  - 0 0  - ] MessageSize=Request_Control DataBlk=]
Dirty=0 Time=19493 ]]; ], ]] [Queue from port 1 0 0 to PerfectSwitch]

Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:259: *this is [MessageBuffer:
consumer-yes [PrioHeap: [19497, 12, [RefCnt: [L1Msg:
Address=[0x762a040, line 0x762a040] RequestType=GETS ResponseType=
Requestor=L1Cache-0 Sender=Directory--1073753688 Destination=[NetDest
(3) 0 0  - 0 1  - 0 0  - ] MessageSize=Request_Control DataBlk=]
Dirty=0 Time=19493 ]]; ], ]] [Queue from port 1 0 0 to PerfectSwitch]

Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:260: m_name is [Queue from port 1 0 0
to PerfectSwitch]
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:260: m_name is [Queue from port 1 0 0
to PerfectSwitch]
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:261: current_time is 19494
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:261: current_time is 19494
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:262: delta is 1
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:262: delta is 1
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:263: arrival_time is 19495
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:263: arrival_time is 19495
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:264: m_last_arrival_time is 19497
Warning: in fn void MessageBuffer::enqueue(const MsgPtr&, long long
int) in buffers/MessageBuffer.C:264: m_last_arrival_time is 19497
Fatal Error: in fn void MessageBuffer::enqueue(const MsgPtr&, long
long int) in buffers/MessageBuffer.C:265: FIFO ordering violated
Fatal Error: in fn void MessageBuffer::enqueue(const MsgPtr&, long
long int) in buffers/MessageBuffer.C:265: FIFO ordering violated
***  Simics getting shaky, switching to 'safe' mode.
***  Simics (main thread) received an abort signal, probably an assertion.
-------------------------------------------------------------------------------------------------------------------
Please let me know if you have seen similar problem. I will try other
network topology to see if that works.

--Calvin

On 3/8/07, Niket Agarwal <niketa@xxxxxxxxxxxxx> wrote:
> 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.