In the standard library the X86 Board currently doesn’t support memory sizes 
>3GB. The reason for this is due to restrictions in how we setup the memory 
ranges of the system.

If you  look at the code here: 
https://github.com/gem5/gem5/blob/55cecfc3e8fb2bdddfd96a850b0fdaca9bcdd0b3/src/python/gem5/components/boards/x86_board.py#L281,
 you can see that we hardcode the I/O memory range to start at 0xC0000000, with 
the memory range immediately prior. Memory sizes >3GB will mean it overlaps the 
I/O memory range.

We have been meaning to make this more flexible, allowing for higher memory 
ranges, but this has yet to be implemented.

If you’re feeling confident, and understand X86 memory ranges, you could hack 
this code to create a system >3GB.

--
Dr. Bobby R. Bruce
Room 3050,
Kemper Hall, UC Davis
Davis,
CA, 95616
 
web: https://www.bobbybruce.net

> On Jun 15, 2023, at 6:56 AM, Vincent Abraham via gem5-users 
> <gem5-users@gem5.org> wrote:
> 
> The error has been resolved. Turns out I didn't specify the partition on the 
> disk image. But I'm still wondering if there's any code for running the 
> benchmark with a system with >3GB main memory.
> 
> On Wed, Jun 14, 2023 at 4:20 PM Vincent Abraham <vincent....@gmail.com 
> <mailto:vincent....@gmail.com>> wrote:
>> Also, I'm getting the following error on running the command: 
>> build/X86/gem5.opt configs/example/gem5_library/x86-parsec-benchmarks.py 
>> --benchmark vips --size simsmall
>> 
>> Kernel panic - not syncing: VFS: Unable to mount root fs on 
>> unknown-block(3,0)
>> CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.19.83 #1
>> Hardware name:  , BIOS  06/08/2008
>> Call Trace:
>>  dump_stack+0x5d/0x79
>>  panic+0xe2/0x236
>>  mount_block_root+0x2b0/0x2e4
>>  ? set_debug_rodata+0xc/0xc
>>  prepare_namespace+0x15b/0x191
>>  kernel_init_freeable+0x23c/0x24c
>>  ? rest_init+0xa0/0xa0
>>  kernel_init+0x5/0xf0
>>  ret_from_fork+0x35/0x40
>> Kernel Offset: disabled
>> ---[ end Kernel panic - not syncing: VFS: Unable to mount root fs on 
>> unknown-block(3,0) ]---
>> 
>> Any help with how to resolve this would be appreciated. I used 
>> gem5-resources to build the disk image for the benchmark and followed the 
>> steps mentioned in 
>> https://gem5.googlesource.com/public/gem5-resources/+/refs/heads/stable/src/parsec/.
>>  I only changed the vm_memory to 16384 and cores to 8 in parsec.json.
>> 
>> On Wed, Jun 14, 2023 at 11:57 AM Vincent Abraham <vincent....@gmail.com 
>> <mailto:vincent....@gmail.com>> wrote:
>>> Hi everyone,
>>> Is it possible in any way to run the provided x86-parsec-benchmarks.py 
>>> script for a system with >3GB of memory? Is there any other way around this 
>>> like running the fs.py script for parsec benchmarks?
>>> 
>>> Thanks,
>>> Vincent
> _______________________________________________
> gem5-users mailing list -- gem5-users@gem5.org
> To unsubscribe send an email to gem5-users-le...@gem5.org

_______________________________________________
gem5-users mailing list -- gem5-users@gem5.org
To unsubscribe send an email to gem5-users-le...@gem5.org

Reply via email to