Dear all,
I wish to study how gnuradio handles the dataflow,e.g., buffering,
scheduling, synchronization, optimization as well as resultant latency
in
detail. However, I can not find any material that explain such things
clearly. Could you please point me to direct or indirect resources e.g.,
in
literature which present I need. I would appreciate it much,
With best regards,
Nguyen Anh Duc
On Wed, Jul 23, 2014 at 12:37 PM, Anh Duc N. [email protected]
wrote:
that presentation? I would grateful for it.
My first intuitive question is that since each signal processing block does
require both input and output buffers, then it may cause the source-sink
latency to be significantly large. Is this true and is there any design
analysis on this?With best regards,
Nguyen Anh Duc
Anh,
There’s a very small number of papers that are specifically about the
GNU Radio scheduler. Depending on the level of detail you require the
source code may be the best place (and it helps to be looking at the
flowcharts in the previously mentioned slides).
Second, I’m not sure what your last question is getting at. Each block
has an input and an output buffer, but that buffer is shared with
either the output or the input of a neighboring block. If you believe
that alone is causing a high latency between source and sink then I’m
curious what alternatives you have in mind.
Are you looking only at GNU Radio’s scheduler or schedulers in
general? Almohanad F.‘s dissertation, “Design Space Decomposition
for Cognitive and Software Defined Radios” might have some things of
interest in it. He uses KPN to analyze buffer sizes (among other
things). Michael D.’ dissertation (not about GNU Radio) also has
a pretty good overview of what SDR frameworks are out there and a high
level design approach some notable frameworks take. Between those two
dissertations there’s quite a bit of reading and a great way to speed
up on what’s out there, especially since they’re both fairly recent.
Nathan
Thank Vanush,
I have read this presentation already; unfortunately, I found it rather
hard to draw an overall picture of gnuradio scheduler to some extent of
details. Perhaps, as Tom said on his webpage (
Explaining the GNU Radio Scheduler — Rondeau Research)
the scheduler is the most mysterious and complicated part of gnuradio -
not
easy to digest it
Could you please provide me with some relevant or supplement readings to
that presentation? I would grateful for it.
My first intuitive question is that since each signal processing block
does
require both input and output buffers, then it may cause the source-sink
latency to be significantly large. Is this true and is there any design
analysis on this?
With best regards,
Nguyen Anh Duc
Anh,
On Wed, Jul 23, 2014 at 8:22 PM, Anh Duc N. [email protected]
wrote:
It should be better if there are some references to guide us through the
complicated codes such as the one Tom wrote, hopefully, there should be
more similar presentations/documents like that.
As part of my GSoC I’m working on such a guide as I need to make changes
to
the GNU Radio buffer management system. I started a wiki page about 2
weeks
ago detailing some of my findings and it may help you out. It is
incomplete
but feedback is much appreciated as it will help me write the page
better.
http://gnuradio.org/redmine/projects/gnuradio/wiki/runtime
Thank Nathan and Marcus,
Yes, as you said the source code should be the best place to study the
details. However, as you may experience, it is fairly challenging to
just
look at the code, analyze, and make connections among stuffs. It should
be
better if there are some references to guide us through the complicated
codes such as the one Tom wrote, hopefully, there should be more similar
presentations/documents like that. With that references, I believe we
can
have got how gnuradio works more comprehensively and more rapidly. I
also
agree it is not easy to describe the scheduler in a short, simple, but
pretty in-depth ways; then I have asked for just some supplement
readings
Thank Nathan for your recommended two dissertations, I have just given
them
a quick look, and they appear to satisfy my desire. I also thank Marcus
for
key points and trends in the gnuradio scheduler and your frank
suggestions
how to approach the problems.
To be honest, I am studying software structures/platform for software
defined radio (SDR), of which, the scheduler is one of the most crucial
that I wish to analyze in detail; and in turn, gnuradio scheduler for
sure
draws much of my attention due to it success and popularity. I hope I
could
receive more support and help from you all
With best regards,
Nguyen Anh Duc
On Thu, Jul 24, 2014 at 12:51 AM, Marcus Müller
[email protected]
Hi!
On 24.07.2014 05:22, Anh Duc N. wrote:
To be honest, I am studying software structures/platform for software
defined radio (SDR), of which, the scheduler is one of the most crucial
that I wish to analyze in detail; and in turn, gnuradio scheduler for sure
draws much of my attention due to it success and popularity. I hope I could
receive more support and help from you all
That sounds really interesting! I think there will be lots of interest
in that, so keep the questions coming
Greetings,
Marcus
On Thu, Jul 24, 2014 at 2:56 AM, Marcus Müller
[email protected]
wrote:
That sounds really interesting! I think there will be lots of interest in
that, so keep the questions comingGreetings,
Marcus
It does sound interesting, and Nathan W. pointed out a good place to
start researching this. I agree with Marcus to keep the questions
coming.
However, I would add that it would be better served for all of us here
if
you had very focused questions that we could talk about. Open ended
questions like “how does the scheduler work” would require a lot of time
to
construct an answer; time that very few of us have. But a conversation
like
this done with the right questions could eventually turn into a nice set
of
discussion topics that could then be turned into something more
substantive
for others looking at the same questions.
Tom
Hello everyone,
I’ve been asking the same questions as Anh, since we have a PhD student
working on dataflow programming, specifically for GNU Radio.
I think this discussion can benefit a lot of people who work with
dataflow,
but also the rest of us, who just want to understand what’s going on
under
the hood.
Maybe, one day we can compile all questions and answers into a nice
formatted document that will serve as a reference for the rest of us…
Best regards,
Leo
Leonardo S. Cardoso
[email protected]
Hello all,
Yeah, I also think this topic is interesting to find out this vague and
unclear scheduler! I’m waiting for further discussions.
Best,
Mostafa
On Thu, Jul 24, 2014 at 5:50 PM, Leonardo S. Cardoso [email protected]
On Thu, Jul 24, 2014 at 12:02 PM, Mostafa A.
[email protected] wrote:
formatted document that will serve as a reference for the rest of us…
Best regards,
Leo
Leonardo S. Cardoso
[email protected]
This seems like a good opportunity to plug the working groups and
upcoming conference. For information on the working groups:
http://gnuradio.org/redmine/projects/gnuradio/wiki/WorkingGroups . The
embedded and especially coprocessor working groups should be
interesting to anyone interested in dataflow problems.
For information on the conference: GNU Radio Conference 2014 — Rondeau Research .
Several presentations will be covering distributed scheduling,
coprocessors, and generic dataflow scheduling with an obvious emphasis
on SDR and GNU Radio. The working group sessions should also be a good
time to share ideas and learn from others while getting a sense of
what others are working on.
Nathan
This forum is not affiliated to the Ruby language, Ruby on Rails framework, nor any Ruby applications discussed here.
Sponsor our Newsletter | Privacy Policy | Terms of Service | Remote Ruby Jobs