Hi!
I am a PhD student and I am using OpenAMP for a research work. I am trying
to compare latencies between a FreeRTOS application in R5 with OpenAMP and
a FreeRTOS application in A53 with Xen hypervisor. I am using a zynq ZCU102
platform.
I have just started the PhD, so I am not completely sure of what I am going
to do for the thesis. I wanted to relate this (OpenAMP, hypervisors...)
with the FPGA, but I don't know how. Now my intention is to do a paper (my
first article) about the latencies with OpenAMP and Xen. If someone has any
advice for me, I'd be glad to listen to it. Also, when I get stuck at
something (I am new using OpenAMP) I wolud like to ask you for support if
you agree.
Thank you very much!
Sara
Hi!
I am a PhD student and I am using OpenAMP for a research work. I am
trying to compare latencies between a FreeRTOS application in R5 with
OpenAMP and a FreeRTOS application in A53 with Xen hypervisor. I am
using a zynq ZCU102 platform.
I have just started the PhD, so I am not completely sure of what I am
going to do for the thesis. I wanted to relate this (OpenAMP,
hypervisors...) with the FPGA, but I don't know how. Now my intention
is to do a paper (my first article) about the latencies with OpenAMP
and Xen. If someone has any advice for me, I'd be glad to listen to it.
Also, when I get stuck at something (I am new using OpenAMP) I wolud
like to ask you for support if you agree.
Thank you very much!
Sara
Hello all,
There is a meeting today at the normal time: 4 PM GMT, 11 AM US Eastern
We are still using the same zoom meeting number.
(I will switch after this call.)
Thanks,
Bill
--
Bill Mills
Principal Technical Consultant, Linaro
+1-240-643-0836
TZ: US Eastern
Work Schedule: Tues/Wed/Thur
All,
We have our normal OpenAMP meeting today (Jan 14) in 1 hour: 11 AM US
Eastern, 4PM GMT
Thanks,
Bill
--
Bill Mills
Principal Technical Consultant, Linaro
+1-240-643-0836
TZ: US Eastern
Work Schedule: Tues/Wed/Thur
Branch: refs/heads/master
Home: https://github.com/OpenAMP/libmetal
Commit: f252f0e007fbfb8b3a52b1d5901250ddac96baad
https://github.com/OpenAMP/libmetal/commit/f252f0e007fbfb8b3a52b1d5901250dd…
Author: Ed Mooring <ed.mooring(a)linaro.org>
Date: 2021-01-11 (Mon, 11 Jan 2021)
Changed paths:
M lib/system/freertos/sleep.h
Log Message:
-----------
FreeRTOS: Allow tick rates greater than 1000 for metal_sleep_usec().
metal_sleep_usec() used portTICK_PERIOD_MS to determine how long to
sleep. If the FreeRTOS tick rate is set to greater than 1000, this will
be 0, resulting in a divide by zero error at run time. This changes it
to use pdMS_TO_TICKS(), which can accomodate higher tick rates.
Signed-off-by: Ed Mooring <ed.mooring(a)linaro.org>
Branch: refs/heads/master
Home: https://github.com/OpenAMP/open-amp
Commit: c7757cf52c3a13404c50860f08cd2252d2e2edec
https://github.com/OpenAMP/open-amp/commit/c7757cf52c3a13404c50860f08cd2252…
Author: Xiang Xiao <xiaoxiang(a)xiaomi.com>
Date: 2021-01-04 (Mon, 04 Jan 2021)
Changed paths:
M lib/include/openamp/remoteproc.h
M lib/remoteproc/remoteproc.c
Log Message:
-----------
remoteproc: add get_mem callback to remoteproc_ops
Since the mapping info is normally managed inside the porting
layer, the new callback could avoid the mapping duplication.
Signed-off-by: Xiang Xiao <xiaoxiang(a)xiaomi.com>
Hello,
There were only four of us on the call today so we called it off after
10 minutes.
There is no meeting on Dec 31 so our next meeting will be Jan 14.
(I did send a cancellation for the Dec 31 but it may still be on your
calendar so please delete it manually.)
I hope everyone enjoys whatever winter holidays you practice. See you
in the new year.
Thanks,
Bill
Branch: refs/heads/master
Home: https://github.com/OpenAMP/libmetal
Commit: 73f746ecf6d384ea328632a31e7f2982e343ebc8
https://github.com/OpenAMP/libmetal/commit/73f746ecf6d384ea328632a31e7f2982…
Author: Leo Sartre <sartre.l(a)ecagroup.com>
Date: 2020-12-15 (Tue, 15 Dec 2020)
Changed paths:
M lib/system/linux/device.c
Log Message:
-----------
lib/system/linux: pass correct offset to metal_map()
According to UIO documentation, the offset device tree property
purpose is to be used "if the device’s memory is not page aligned".
Quoting the same documentation:
"To map the memory of mapping N, you have to use N times the page
size as your offset"
So wee need to pass i * getpagesize() to get the correct mapping,
otherwise, we end up with all io_region pointing to the same area.
Signed-off-by: Leo Sartre <sartre.l(a)ecagroup.com>
Commit: f52728d078578cb985940c9e6a7f247fa1baa8d1
https://github.com/OpenAMP/libmetal/commit/f52728d078578cb985940c9e6a7f247f…
Author: Leo Sartre <sartre.l(a)ecagroup.com>
Date: 2020-12-15 (Tue, 15 Dec 2020)
Changed paths:
M README.md
Log Message:
-----------
README.md: note about non page aligned devices on Linux
According to the Linux kernel UIO documentation, access to device's
memory that is not page aligned requires to add the proper offset to
the pointer returned by mmap() that is stored into the 'virt' field of
the metal_io_region structure.
Document this limitation until this offset is handled properly by the
library.
Signed-off-by: Leo Sartre <sartre.l(a)ecagroup.com>
Compare: https://github.com/OpenAMP/libmetal/compare/9c807f04e779...f52728d07857