That means the packet (which gem5 uses to communicate between components)
doesn't have anywhere to hold data, either static (which should not be
cleaned up) or dynamic (which should be deleted once used). It doesn't have
anything to do with the kernel necessarily/directly or a particular type of
Hi Abhishek,
I have been playing around with the issue. It seems more and more likely to
me that the issue is coming from the build of the gem5 simulator, not the
kernel, as I have run it with multiple kernels (including the pre-built
kernel from the gem5 webpage ) all of which are giving the
Hi Stefan Waczynski,
Were you able to fix the problem?
Best regards,
Abhishek
On Tue, Jun 4, 2019 at 9:32 AM Stefan Waczynski <
stefan.waczynsk...@gmail.com> wrote:
> Hi All,
>
> I looked at my previous message and noticed that I missed possibly the most
> "meaningful" (at-least to me) part
Hi All,
I looked at my previous message and noticed that I missed possibly the most
"meaningful" (at-least to me) part of the error print-out for all my
crashes with the detailed model.
In all cases I get (just prior to the LibC backtrace):
gem5.opt: build/X86/mem/packet.hh:1047: T*
On 3 Jun 2019, at 15:37, Stefan Waczynski wrote:
I also saw an error in the terminal output when booting with
AtomicSimpleCPU, but it did not seem to affect the booting process and
functionality for the Atomic model:
ACPI: Early table checksum verification disabled
ACPI BIOS Error (bug): A
Hi All,
Sorry for the late note. The patch seems to have fixed the hard-crashing
with the older kernel. Unfortunately, this has not alleviated all issues
with the newer kernels.
I have played around with newer kernels (recompiled them) and have been
getting consistent hard-crashes when using the
Hi Stefan,
This seems to be a bug. There is a fix on the reviewbord:
https://gem5-review.googlesource.com/c/public/gem5/+/18508. Please give it a
try!
Cheers,
- Gabor
On 25/04/2019, 16:54, "gem5-dev on behalf of Stefan Waczynski"
wrote:
I will place them into the body of the email:
I will place them into the body of the email:
Script:
m5 checkpoint
ls
ls
ls
ls
LibC Backtrace:
gem5 compiled Apr 10 2019 12:23:15
gem5 started Apr 11 2019 16:30:49
gem5 executing on brahms, pid 6734
command line: ./build/X86/gem5.opt configs/example/fs.py
It looks like the mailing list stripped out your attachment.
Ryen
On Thu, Apr 25, 2019, 08:47 Stefan Waczynski
wrote:
> Hi All,
>
> I have been trying to start work with gem5 Full-System simulation (my
> intent is to run multiple workloads in parallel and observe interference
> effects along
Hi All,
I have been trying to start work with gem5 Full-System simulation (my
intent is to run multiple workloads in parallel and observe interference
effects along with some OS behavior for these parallel workloads).
I boot into the simulation using the atomic CPU model with a runtime script
10 matches
Mail list logo
