Why is your application calling sys_clone at that point? It can't find any
more thread contexts because you have already used them all.
If you application is using pthread_create() you probably don't need to
execute 4 instances of it.
Jason
On Tue, Oct 25, 2016 at 5:54 PM anoir nechi wrote:
>
*Hi again*
*I've tried what you told me about the multi-threaded workload like this:*
for i in xrange(np):
p = LiveProcess()
p.cmd = ['/home/anoir/m5threads/lock_test/test_lock']
system.cpu[i].workload = p
system.cpu[i].createThreads()
*but i get this error message:*Beginning si
Thank you Jason
On Wed, Oct 12, 2016 at 4:39 PM, Jason Lowe-Power
wrote:
> This should work.
>
> Attached is a diff for the simple.py script in
> configs/learning_gem5/part1/ that has 4 CPUs and runs hello 4 times.
> Hopefully this helps.
>
> For a multithreaded application, I believe you'll use
This should work.
Attached is a diff for the simple.py script in configs/learning_gem5/part1/
that has 4 CPUs and runs hello 4 times. Hopefully this helps.
For a multithreaded application, I believe you'll use a similar config
script (instantiate multiple processes all with the same binary file p
*Hi *
*I wrote a configuration script for a multicore system based on ARM and it
seems fine except for the workload. i wanted to try testing the
configuration by assigning a hello world executable for each CPU.*
*I tried creating different processes but I've got some indexing error then
i made a f