Hi Aditya,

The first issue (with 4096 MB) is probably due to the memory map of the system, 
with a chunk of memory available before the device addresses, and then 
additional space above the devices. When you set the memory to 4096 MB I 
suspect it is getting into the device range, and it seems there is no check 
(besides the bus being unhappy). I tend to recall Nilay did some modifications 
here, so perhaps all you need to do is update to the latest gem5 trunk.

The second issue is that you are using the abstract class SimpleDRAM. You have 
to use one of the derived classes, e.g. DDR3_1600_x64. I am surprised this was 
not caught in the script (as it checks for abstract classes in MemConfig.py). 
I’ll give it a spin and see how it behaves.

Andreas

From: Aditya Deshpande 
<[email protected]<mailto:[email protected]>>
Reply-To: gem5 users mailing list 
<[email protected]<mailto:[email protected]>>
Date: Tuesday, 8 April 2014 00:54
To: "[email protected]<mailto:[email protected]>" 
<[email protected]<mailto:[email protected]>>
Subject: [gem5-users] Problems with Running X86 FS simulation

Hello All,

I am trying to run X86 in FS mode using following command line

./build/X86_MESI_Two_Level/gem5.opt configs/example/fs.py 
--disk-image=/nfs/div1/adeshpan/arch/x86_disks/disks/x86root-parsec_ad.img 
--kernel=/nfs/div1/adeshpan/arch/x86_disks/binaries/x86_64-vmlinux-2.6.22.9 
--caches --l1d_size=64kB --l1i_size=64kB --l2cache --l2_size=512kB 
--cacheline_size=64 --num-cpus=1 --cpu-type=TimingSimpleCPU --mem-size=4096MB
...
Global frequency set at 1000000000000 ticks per second
info: kernel located at: 
/nfs/div1/adeshpan/arch/x86_disks/binaries/x86_64-vmlinux-2.6.22.9
      0: rtc: Real-time clock set to Sun Jan  1 00:00:00 2012
Listening for com_1 connection on port 3456
warn: Reading current count from inactive timer.
fatal: system.membus has two ports with same range:
        system.mem_ctrls.port
        system.bridge.slave
 @ cycle 0
[recvRangeChange:build/X86_MESI_Two_Level/mem/bus.cc, line 421]
Memory Usage: 4505484 KBytes

When I remove the last option of --mem-size=4096MB, the simulation executes. I 
want to set memory size. Is there any other way of doing this with 
/config/example/fs.py?


Another thing when I use mem-type=SimpleDRAM. I get following error:

./build/X86_MESI_Two_Level/gem5.opt configs/example/fs.py 
--disk-image=/nfs/div1/adeshpan/arch/x86_disks/disks/x86root-parsec_ad.img 
--kernel=/nfs/div1/adeshpan/arch/x86_disks/binaries/x86_64-vmlinux-2.6.22.9 
--caches --l1d_size=64kB --l1i_size=64kB --l2cache --l2_size=512kB --num-cpus=1 
--cpu-type=TimingSimpleCPU --mem-type=SimpleDRAM --mem-size=4096MB
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/nfs/div1/adeshpan/arch/gem5/src/python/m5/main.py", line 388, in main
    exec filecode in scope
  File "configs/example/fs.py", line 177, in <module>
    MemConfig.config_mem(options, test_sys)
  File "/nfs/div1/adeshpan/arch/gem5/configs/common/MemConfig.py", line 175, in 
config_mem
    rowbuffer_size = ctrl.device_rowbuffer_size.value * \
  File "/nfs/div1/adeshpan/arch/gem5/src/python/m5/SimObject.py", line 734, in 
__getattr__
    raise AttributeError, err_string
AttributeError: object 'SimpleDRAM' has no attribute 'device_rowbuffer_size'
  (C++ object is not yet constructed, so wrapped C++ methods are unavailable.)

Any idea how to fix this?
Any help is appreciated.

Regards,
Aditya

-- IMPORTANT NOTICE: The contents of this email and any attachments are 
confidential and may also be privileged. If you are not the intended recipient, 
please notify the sender immediately and do not disclose the contents to any 
other person, use it for any purpose, or store or copy the information in any 
medium. Thank you.

ARM Limited, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, Registered 
in England & Wales, Company No: 2557590
ARM Holdings plc, Registered office 110 Fulbourn Road, Cambridge CB1 9NJ, 
Registered in England & Wales, Company No: 2548782
_______________________________________________
gem5-users mailing list
[email protected]
http://m5sim.org/cgi-bin/mailman/listinfo/gem5-users

Reply via email to