Hi Dave
I use fi to convert coefficients to be stored from parallel matlab
double precision format into single unsigned words that will accurately
be converted back by slicing and using convert blocks. I think it is
possible to create the same functionality, I will have a quick try.
Cheers
Andrew
Hi, Andrew,
Can you elaborate on how you use fi? I think much of the functionality can be accomplished by
judicious use of the multiplication, rounding, and modulo math (for wrapping) or
"x(x>max)=max" (for saturation). It might be possible to create a "clean room"
replacement function that does what you need.
Thanks,
Dave
On Sep 25, 2013, at 7:36 AM, Andrew Martens wrote:
Hi
Thanks Andrew! Would you know approximately how much time it would take for you
to look into this? Meanwhile, would you know the latest commit that does not
use fi, and hence, does not need Floating-point toolbox?
Replacing fi will be difficult. I will probably rather provide a parameter that
allows the user to choose not to pack coefficients next to each other in the
same BRAM (which fi is part of now). This will allow the user to trade off BRAM
for license fees :)
The last commit not using fi would be before my FFT upgrade, so somewhere near
the first quarter of the year.
Regards
Andrew
Thanks,
Nimish
On Wed, Sep 25, 2013 at 1:24 AM, David MacMahon <dav...@astro.berkeley.edu>
wrote:
Thanks, Andrew!
Dave
On Sep 24, 2013, at 10:13 PM, Andrew Martens wrote:
Hi
I do use the fi constructor to generate fixed point values when generating
twiddle values for storage.
I will see if it can be done in another way as it seems wasteful to require a
license just for that.
Regards
Andrew
Thanks, Nimish,
Looking at the recently updated casper-astro repository, the following mask init scripts use the
"fi" function (technically a "constructor", I think) to crete fixed point
objects:
casper_library/cosin_init.m
casper_library/feedback_osc_init.m
casper_library/pfb_fir_coeff_gen_init.m
Any block that uses the scripts (e.g. via sub-blocks) will probably need a Fixed Point
Toolbox license. I suspect it wouldn't be too difficult to rewrite these files in a way
that maintain the functionality, but avoids the "fi" (and any related) call(s).
It looks like Andrew Martens introduced at least some of the "fi" dependencies,
so maybe he would be willing to redo the relevant bits of these files?
Dave
On Sep 24, 2013, at 5:00 PM, Nimish Sane wrote:
Some more investigation:
I am seeing these messages:
License checkout failed.
License Manager Error -5
Cannot find a license for Fixed_Point_Toolbox.
Troubleshoot this issue by visiting:
http://www.mathworks.com/support/lme/R2012b/5
Diagnostic Information:
Feature: Fixed_Point_Toolbox
License path:
/home/observer/.matlab/R2012b_licenses:/home/observer/tools/MATLAB/R2012b/licenses/license.dat:/home/observer/tools/MATLAB/R2012b/licenses/license_fpgadev_277254_R2012b.lic
Licensing error: -5,357.
Simulink:Masking:Bad_Init_Commands: Error in
'fft_wideband_real_core/fft_wideband_real/fft_direct/butterfly0_0/twiddle/coeff_gen/feedback_osc':
Initialization commands cannot be evaluated.
Backtrace 1: reuse_block:138
Backtrace 2: coeff_gen_init:498
Backtrace 3: reuse_block:51
Backtrace 4: add_convert_init:496
Backtrace 5: draw_basic_partial_cycle:407
Backtrace 6: cosin_init:165
Backtrace 7: xlUpdateIcon:207
Backtrace 8: xlBlockLoadCallback:79
Backtrace 9: UpdateDiagramCB:221
If I turn OFF the option "Generate coeffs with multipliers where useful", these
messages do not appear. Still, I get the following error:
Error in
'fft_wideband_real_core/fft_wideband_real/fft_biplex_real_4x/biplex_core/fft_stage_10/butterfly_direct/twiddle/coeff_gen':
Initialization commands cannot be evaluated.
Caused by:
Error in
'fft_wideband_real_core/fft_wideband_real/fft_biplex_real_4x/biplex_core/fft_stage_10/butterfly_direct/twiddle/coeff_gen/cosin':
Initialization commands cannot be evaluated.
Unable to check out a license for the Fixed-Point Toolbox.
I will let you know if I find something more.
Thanks,
Nimish
On Tue, Sep 24, 2013 at 7:36 PM, David MacMahon <dav...@astro.berkeley.edu>
wrote:
Thanks. I was hoping to narrow it down a little more than that. There's a lot
of stuff inside that little green block!
Dave
On Sep 24, 2013, at 4:33 PM, Nimish Sane wrote:
To be precise, that is the only green block in the design apart from bunch of
gateway blocks and XSG block (as I am black boxing it).
Thanks,
Nimish
On Tue, Sep 24, 2013 at 7:32 PM, Nimish Sane <nimishs...@gmail.com> wrote:
The design only has fft_wideband_real block, and whenever I click "Apply/Ok" or
"Update Diagram", I get these error messages. These are the only error messages I see in
Matlab window. So it is definitely the fft_wideband_real block.
Thanks,
Nimish
On Tue, Sep 24, 2013 at 7:30 PM, David MacMahon <dav...@astro.berkeley.edu>
wrote:
Thanks, Nimish,
Is there any other info that might help pinpoint which block and/or init script
is causing Matlab to look for a Fixed_Point_Tollbox license?
Thanks,
Dave
On Sep 24, 2013, at 4:21 PM, Nimish Sane wrote:
License checkout failed.
License Manager Error -5
Cannot find a license for Fixed_Point_Toolbox.
Troubleshoot this issue by visiting:
http://www.mathworks.com/support/lme/R2012b/5
Diagnostic Information:
Feature: Fixed_Point_Toolbox
License path:
/home/observer/.matlab/R2012b_licenses:/home/observer/tools/MATLAB/R2012b/licenses/license.dat:/home/observer/tools/MATLAB/R2012b/licenses/license_fpgadev_277254_R2012b.lic
Licensing error: -5,357.
Nimish
On Tue, Sep 24, 2013 at 5:45 PM, David MacMahon <dav...@astro.berkeley.edu>
wrote:
Hi, Nimish,
What error messages are you getting?
Thanks,
Dave
On Sep 24, 2013, at 2:28 PM, Nimish Sane wrote:
Hi all,
A question related to this:
Like Glenn, we never had Fixed point toolboxes (Fixed point Toolbox and
Simulink Fixed point) installed, and still were able to compile our correlator
designs using 11.5 and Matlab2009b.
I recently upgraded to ISE 14.5 with Matlab 2012b as well as upgraded libraries
to the latest version of casper-astro/mlib_devel. Even in the current
installation, we do not have Fixed point toolboxes (names have changed to
Fixed-point designer Toolbox, Simulink Fixed-point as Jonathan has
mentioned).
The current fft_wideband_real block has some differences compared to the older
version that I was using so far and it seems it now requires Fixed-point
Toolbox. I am getting errors that this particular toolbox has not been
installed. I am not sure if there are other blocks that give similar errors.
Does anyone have any experience with this and provide some insight as to how to
deal with this situation?
Specifically,
(1) Is there any way to use the latest fft_wideband_real block without
Fixed-point Toolboxes? (Glenn, have you tried this?)
(2) Does one have to install both the Fixed-point toolboxes (Fixed-point
designer Toolbox, Simulink Fixed-point) or just the Fixed-point designer
Toolbox?
(I have attached lists of toolboxes in our previous and current installation.)
Thanks a lot,
Nimish
On Tue, Sep 17, 2013 at 7:20 PM, G Jones <glenn.calt...@gmail.com> wrote:
As one data point I'm successfully compiling designs w/o the fixed point
toolboxes. I haven't tried simulating a large design which is where it's
claimed to be needed with busses wider than 53 bits or whatever it is
On Sep 17, 2013 7:15 PM, "Jonathan Weintroub" <jweintr...@cfa.harvard.edu>
wrote:
Hi fellow CASPERians,
This is a question that comes up periodically. At SAO we are now paying full
fare for Matlab licenses so the cost impact of an imperfect understanding can
be significant.
The latest MSSGE wiki page is:
https://casper.berkeley.edu/wiki/MSSGE_Setup_with_Xilinx_14.5_and_Matlab_2012b
However this page does not mention Matlab optional components (historically
termed toolboxes and blocksets).
There are clues in an earlier setup page:
https://casper.berkeley.edu/wiki/MSSGE_Toolflow_Setup
from which it appears one needs something like:
Fixed-Point Toolbox
Signal Processing Blockset
Signal Processing Toolbox
Simulink Fixed Point
Each time I buy a new license I iterate on these components with the Matlab
distributer. The terminology changes year by year and I am currently
being quoted on the following components, in addition to the base Matlab
and Simulink distributions:
SIGNAL PROCESSING TOOLBOX, V2013A
SIMULINK FIXED POINT, V2012B
DSP SYSTEM TOOLBOX, V2013A
FIXED-POINT DESIGNER TOOLBOX, V2013A,
(sorry about the all-caps which pasted in directly from the quotation).
So it is still four components, but the names have changed. The term blockset seems to have evolved out in favor of
toolbox, one of the "signal processing"s has morphed into "DSP", and the fixed point toolbox now
has "designer". Appropriately enough the price for this latter "designer" component alone has more
than doubled in a year to over $2k per seat.
Having set the scene, my two questions are:
1. Are we ordering the right components?
2. Do we really need all these components?
(At one point I seem to recall hearing the fixed point stuff is to some extent
optional, though the ability to simulate properly at the Simulink level is
important to us.)
Subject to confirmation from the tool flow experts, I will be happy to update
the wiki notes with current information.
Thanks,
Jonathan
<installed-tools>
