Hi,
Based on my experience, more cores does not means more work, unless you specify
more work. To elaborate: running same 1 thread application on 2 cores should be
relatively close to 8 cores. More time will be needed (I think close to
linearly) when you have more actual work, such as 8 threads
Hi,
I ran into similar issues before. Say I did, boot the cpus with atomic cpu,
then warmup the application with atomic cpu, then restore with atomic cpu for
ROI data collection. With this, the final numcycles are counted including
boot+warmup+roi, not just roi. If you did a finalTick/ frequency
This is what I did and made it work. Of course, I did this after I trace where
they increment the cycles and made the changes make sense to me. I am using
v22, so I would image it works for you. But, as Eliot pointed out, there are
more places you need to check. I would suggest you starting with
Hi,
I am trying to run some benchmark on ARM full system simulation. Already use
AtomicSimpleCPU to do the bootup and everything to speed up warmup, but still,
ROI is few seconds of machine time, which takes up to few days to simulate.
Also, for statistical confidence reasons, repeated run with
Hi all,
I noticed with the recent updates in ARM ISA support, now default machine setup
is using VExpress_GEM5_V1, which is great, with the 2019 build kernel and boot
loadert tested and everything. However, I also know that VExpress_GEM5 does not
support ethernet device. What would be best setu