Digital LP filter in multiplier free FPGA

[markp]

Hi All,

I need to implement a low pass digital filter on 12 bit ADC data in a Spatan
IIE device, but I'd like it to be multiplier free - in other words just use
adders and bit shifting for the coefficients. The sample rate is 12Mhz and I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and adding.

Thanks!

Mark.

 

[John Larkin]

On Sat, 13 Nov 2004 19:55:43 -0000, "markp" <map.nospam@f2s.com>
wrote:

Hi All,

I need to implement a low pass digital filter on 12 bit ADC data in a Spatan
IIE device, but I'd like it to be multiplier free - in other words just use
adders and bit shifting for the coefficients. The sample rate is 12Mhz and I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and adding.

Thanks!

Mark.

See zipfile in abse. If I post it here, the formatting gets lunched.

John

 

[markp]

"John Larkin" <jjlarkin@highlandSNIPtechTHISnologyPLEASE.com> wrote in
message news:g0ucp0l3v5pmv3a8afvlil3g7b1k7u2jc1@4ax.com...

On Sat, 13 Nov 2004 19:55:43 -0000, "markp" <map.nospam@f2s.com
wrote:

Hi All,

I need to implement a low pass digital filter on 12 bit ADC data in a
Spatan
IIE device, but I'd like it to be multiplier free - in other words just
use
adders and bit shifting for the coefficients. The sample rate is 12Mhz
and I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've
seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and
adding.

Thanks!

Mark.


See zipfile in abse. If I post it here, the formatting gets lunched.

Thanks John. Unfortunately I've got text only news server access, any chance
in emailing? (remove .nospam).

Cheers,

Mark.

John

 

[John Larkin]

On Sat, 13 Nov 2004 13:10:15 -0800, John Larkin
<jjlarkin@highlandSNIPtechTHISnologyPLEASE.com> wrote:

On Sat, 13 Nov 2004 19:55:43 -0000, "markp" <map.nospam@f2s.com
wrote:

Hi All,

I need to implement a low pass digital filter on 12 bit ADC data in a Spatan
IIE device, but I'd like it to be multiplier free - in other words just use
adders and bit shifting for the coefficients. The sample rate is 12Mhz and I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and adding.

Thanks!

Mark.


See zipfile in abse. If I post it here, the formatting gets lunched.

John

Oops, K1 should be 4, 1/16. File got scrambled somehow.

John

 

[Ken]

I need to implement a low pass digital filter on 12 bit ADC data in a
Spatan
IIE device, but I'd like it to be multiplier free - in other words just
use
adders and bit shifting for the coefficients. The sample rate is 12Mhz and
I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've
seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and adding.

Hi Mark,

I can help you out with this by automatically generating VHDL for an FIR
implementation for your filter that uses shifts and adds.

Please post the following details:


Do you want the filter to run at 12MHz (i.e. full-parallel) or do you have a
faster clock available that could be used to share hardware over multiple
clock cycles?

Is the filter single-rate or are you decimating?

Input bit-width?

Signed/unsigned input?

Quantised filter coefficients (integers ideally but fixed-point will do) or
more detailed spectral requirements (what -dB gain at 3MHz, pass-band ripple
etc., start rolling off at what freq, stop rolling of at what freq. etc.)


Cheers,

Ken

 

[Tom Seim]

"markp" <map.nospam@f2s.com> wrote in message news:<2vn75sF2o7m4kU1@uni-berlin.de>...

Hi All,

I need to implement a low pass digital filter on 12 bit ADC data in a Spatan
IIE device, but I'd like it to be multiplier free - in other words just use
adders and bit shifting for the coefficients. The sample rate is 12Mhz and I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and adding.

Thanks!

Mark.

You didn't say how sharp your cutoff needs to be, or how much gain
ripple you can tolerate. You might consider a pipelined multiplier
design. This will result in very high clock rates, permitting one
multiplier to handle 8-16 coefficients. Several multipliers can be
used in parallel to increase the number of coefficients even further.
Xilinx has numerous ap notes on digital filtering techniques. Here is
a good review of the topic:
http://www.andraka.com/multipli.htm
This is probably the best book on the subject:
http://www.amazon.com/exec/obidos/ASIN/3540413413/andraka/103-1626470-7551837

Tom

 

[markp]

<snip>

OK, done, I think.

John

Thanks John. I'm not really sure how to tweek this for my system, but very
interesting stuff nonetheless. I decided in the end to go for a 'rolling
average' type filter (rectangular) with 16 taps, and this seems to be
working quite nicely so I think I'll stick with this.

Regards,

Mark.

 

[markp]

"Ken" <aeu96186@NOSPAM.yahoo.co.uk> wrote in message
news:cn69m5$rme$05$1@news.t-online.com...

I need to implement a low pass digital filter on 12 bit ADC data in a
Spatan
IIE device, but I'd like it to be multiplier free - in other words just
use
adders and bit shifting for the coefficients. The sample rate is 12Mhz
and
I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've
seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and
adding.

Hi Mark,

I can help you out with this by automatically generating VHDL for an FIR
implementation for your filter that uses shifts and adds.

Please post the following details:


Do you want the filter to run at 12MHz (i.e. full-parallel) or do you have
a
faster clock available that could be used to share hardware over multiple
clock cycles?

Is the filter single-rate or are you decimating?

Input bit-width?

Signed/unsigned input?

Quantised filter coefficients (integers ideally but fixed-point will do)
or
more detailed spectral requirements (what -dB gain at 3MHz, pass-band
ripple
etc., start rolling off at what freq, stop rolling of at what freq. etc.)


Cheers,

Ken

Hi Ken,

Well I've gone for a rolling average filter at the moment, but the specs
are:

Do you want the filter to run at 12MHz (i.e. full-parallel) or do you
have a faster clock available that could be used to share hardware
over multiple clock cycles?

I've got a 65MHz clock and currently dividing by 6 to give 13MHz.

Is the filter single-rate or are you decimating?

Single rate so far.

Input bit-width?

12 bit ADC data.

Signed/unsigned input?

Unsigned.

Quantised filter coefficients (integers ideally but fixed-point will
do) or more detailed spectral requirements (what -dB gain at
3MHz, pass-band ripple etc., start rolling off at what freq, stop
rolling of at what freq. etc.)

-3db @ 3MHz, 4th order Butterworth type roll-off ideally, unity gain
otherwise.

Thanks!

Mark.

 

[markp]

Thanks! I'll have a look at this.

Mark.

"Antti Lukats" <antti@case2000.com> wrote in message
news:cn5s6o$9di$05$1@news.t-online.com...

"markp" <map.nospam@f2s.com> wrote in message
news:2vn75sF2o7m4kU1@uni-berlin.de...
Hi All,

I need to implement a low pass digital filter on 12 bit ADC data in a
Spatan
IIE device, but I'd like it to be multiplier free - in other words just
use
adders and bit shifting for the coefficients. The sample rate is 12Mhz
and
I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've
seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and
adding.

Thanks!

depending what you need, one solution is very simple "digital integrator"
its doable with only shift and add, there is some appnote or something at
xilinx web, I used that in digital carrier frequency amplifier, and it did
give actually very good filtering (for my application at least).

an example digital integrator source is appended
---------
--
-- 18 Bit Digital Integrator Feedback "multiplier"
-- constant 1 / 256 (fixed, no choices implemented)
-- Tested and working.
library IEEE;
use IEEE.STD_LOGIC_1164.ALL;
use IEEE.STD_LOGIC_ARITH.ALL;
use IEEE.STD_LOGIC_UNSIGNED.ALL;

library work;

entity integrator_18bit is Port (
rst : in std_logic;
clk : in std_logic;
din : in std_logic_vector(17 downto 0); -- Input: 18 Bit
Unsigned
INTEGER
k : in std_logic_vector(3 downto 0); -- multiplier select (not
implemented)
dout : out std_logic_vector(17 downto 0) -- Output: 18 Bit
Unsigned INTEGER
);
end integrator_18bit;

architecture Behavioral of integrator_18bit is

signal acc : std_logic_vector(25 downto 0);
signal vi_minus_vo : std_logic_vector(25 downto 0);
signal vi_minus_vo_sign_extended : std_logic_vector(7 downto 0);

begin
-- Microblaze "endian" conversion
dout(0) <= acc(25); dout(1) <= acc(24); dout(2) <= acc(23); dout(3)
=
acc(22);
dout(4) <= acc(21); dout(5) <= acc(20); dout(6) <= acc(19); dout(7)
=
acc(18);
dout(8) <= acc(17); dout(9) <= acc(16); dout(10) <= acc(15); dout(11)
= acc(14);
dout(12) <= acc(13); dout(13) <= acc(12); dout(14) <= acc(11);
dout(15)
= acc(10);
dout(16) <= acc(9); dout(17) <= acc(8);

-- Error Value
vi_minus_vo <= (din & "00000000") - acc;
-- Sign Extension for Error Value
with vi_minus_vo(25) select vi_minus_vo_sign_extended(7 downto 0) <=
"00000000" when '0', "11111111" when others;

process (clk) begin
if (rst='1') then
acc <= "00000000000000000000000000";
else
if (clk'event and clk='1') then
-- Accumulate
acc <= acc + (vi_minus_vo_sign_extended(7 downto 0) &
vi_minus_vo(25
downto 8));
end if;
end if;
end process;

end Behavioral;

 

[Ken]

Hi Mark,

Do you want the filter to run at 12MHz (i.e. full-parallel) or do you
have a faster clock available that could be used to share hardware
over multiple clock cycles?

I've got a 65MHz clock and currently dividing by 6 to give 13MHz.

OK - do you want the filter to run at 13MHz (I thought you said 12 before?)
and use more area or run at 65MHz and use less area?

I can generate something immediately for you that would run at 13MHz.

Cheers,

Ken

 

[Pete Fraser]

"markp" <map.nospam@f2s.com> wrote in message
news:2vq56eF2odbq7U1@uni-berlin.de...

snip

OK, done, I think.

John

Thanks John. I'm not really sure how to tweek this for my system, but very
interesting stuff nonetheless. I decided in the end to go for a 'rolling
average' type filter (rectangular) with 16 taps, and this seems to be
working quite nicely so I think I'll stick with this.

But previously you said a sharp cutoff. You won't get that with an average.

If your clock is at 12 MHz, and you want an LPF with a 3MHz
cutoff, I would use a half-band filter.

All even coefficients will be 0 (with the exception of a0 at 0.5).
Also, the filter is symmetric in the time domain allowing you
to use a folded ladder topology to use half the "multipliers".

This will give you a response that's skew symmetric around fs/4.

 

[markp]

"Tom Seim" <soar2morrow@yahoo.com> wrote in message
news:6c71b322.0411131750.5b2c5534@posting.google.com...

"markp" <map.nospam@f2s.com> wrote in message
news:<2vn75sF2o7m4kU1@uni-berlin.de>...
Hi All,

I need to implement a low pass digital filter on 12 bit ADC data in a
Spatan
IIE device, but I'd like it to be multiplier free - in other words just
use
adders and bit shifting for the coefficients. The sample rate is 12Mhz
and I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've
seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and
adding.

Thanks!

Mark.

You didn't say how sharp your cutoff needs to be, or how much gain
ripple you can tolerate. You might consider a pipelined multiplier
design. This will result in very high clock rates, permitting one
multiplier to handle 8-16 coefficients. Several multipliers can be
used in parallel to increase the number of coefficients even further.
Xilinx has numerous ap notes on digital filtering techniques. Here is
a good review of the topic:
http://www.andraka.com/multipli.htm
This is probably the best book on the subject:

http://www.amazon.com/exec/obidos/ASIN/3540413413/andraka/103-1626470-7551837

Tom

Thanks Tom! Interesting stuff.

Mark.

 

[Alan]

Hi Mark,

If you need synthesizable VHDL, testbenches etc, our software Tyd-IP Code
Generator and ONEoverT Digital Filter
Designer will give you all you need. There are other development packages
out there also. Have a look around to make sure
you get exactly what you need.

Good Luck
Alan
www.tyder.com

"markp" <map.nospam@f2s.com> wrote in message
news:2vn75sF2o7m4kU1@uni-berlin.de...

Hi All,

I need to implement a low pass digital filter on 12 bit ADC data in a
Spatan
IIE device, but I'd like it to be multiplier free - in other words just
use
adders and bit shifting for the coefficients. The sample rate is 12Mhz and
I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've
seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and adding.

Thanks!

Mark.

 

[John Larkin]

On Sat, 13 Nov 2004 21:19:25 -0000, "markp" <map.nospam@f2s.com>
wrote:

"John Larkin" <jjlarkin@highlandSNIPtechTHISnologyPLEASE.com> wrote in
message news:g0ucp0l3v5pmv3a8afvlil3g7b1k7u2jc1@4ax.com...
On Sat, 13 Nov 2004 19:55:43 -0000, "markp" <map.nospam@f2s.com
wrote:

Hi All,

I need to implement a low pass digital filter on 12 bit ADC data in a
Spatan
IIE device, but I'd like it to be multiplier free - in other words just
use
adders and bit shifting for the coefficients. The sample rate is 12Mhz
and I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've
seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and
adding.

Thanks!

Mark.


See zipfile in abse. If I post it here, the formatting gets lunched.

Thanks John. Unfortunately I've got text only news server access, any chance
in emailing? (remove .nospam).

Cheers,

Mark.
John

OK, done, I think.

John

 

[Ray Andraka]

Markp,

You can use a distributed arithmetic filter if you take advantage of the higher
available
clocks. With a 65 MHz clock, you have 5 clocks (13 MHz is 1/5 of 65, not 1/6)
per
pixel available. By using a two bit parallel distributed arithmetic filter you
can
get a quite compact filter. DA 'hides' the coefficient multiplies by summing
all the
bit partial products from all the taps before doing the shift-accumulate. The
Spartan
II has DLLs in it that can easily be used to double the 65 MHz clock to obtain a
130 MHz
clock. Doing that will cut the physical size of the filter in half, since then
you'd be able to
handle a 10 bit input with the serial filter. DA Filter designs at 130 MHz are
quite acheivable
in any of the SpartanII devices. I have a tutorial on distributed arithmetic on
my website at
http://www.andraka.com/distribu.htm . Also, the xilinx Coregen includes a
filter generator
that will create a distributed filter given a set of coefficients and a number
of parameters. The
major drawback to the coregen filter is that you cannot look inside to see how
it works nor to
improve the design. You can also take advantage of coefficient symmetry to
reduce the filter
size, and if it is acceptable to have the filter characteristic symmetic about
Fs/4 you can use a
half-band filter which has all the odd coefficients except the center one equal
to zero.



markp wrote:

"Ken" <aeu96186@NOSPAM.yahoo.co.uk> wrote in message
news:cn69m5$rme$05$1@news.t-online.com...
I need to implement a low pass digital filter on 12 bit ADC data in a
Spatan
IIE device, but I'd like it to be multiplier free - in other words just
use
adders and bit shifting for the coefficients. The sample rate is 12Mhz
and
I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've
seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and
adding.

Hi Mark,

I can help you out with this by automatically generating VHDL for an FIR
implementation for your filter that uses shifts and adds.

Please post the following details:


Do you want the filter to run at 12MHz (i.e. full-parallel) or do you have
a
faster clock available that could be used to share hardware over multiple
clock cycles?

Is the filter single-rate or are you decimating?

Input bit-width?

Signed/unsigned input?

Quantised filter coefficients (integers ideally but fixed-point will do)
or
more detailed spectral requirements (what -dB gain at 3MHz, pass-band
ripple
etc., start rolling off at what freq, stop rolling of at what freq. etc.)


Cheers,

Ken

Hi Ken,

Well I've gone for a rolling average filter at the moment, but the specs
are:

Do you want the filter to run at 12MHz (i.e. full-parallel) or do you
have a faster clock available that could be used to share hardware
over multiple clock cycles?

I've got a 65MHz clock and currently dividing by 6 to give 13MHz.

Is the filter single-rate or are you decimating?

Single rate so far.

Input bit-width?

12 bit ADC data.

Signed/unsigned input?

Unsigned.

Quantised filter coefficients (integers ideally but fixed-point will
do) or more detailed spectral requirements (what -dB gain at
3MHz, pass-band ripple etc., start rolling off at what freq, stop
rolling of at what freq. etc.)

-3db @ 3MHz, 4th order Butterworth type roll-off ideally, unity gain
otherwise.

Thanks!

Mark.

--
--Ray Andraka, P.E.
President, the Andraka Consulting Group, Inc.
401/884-7930 Fax 401/884-7950
email ray@andraka.com
http://www.andraka.com

"They that give up essential liberty to obtain a little
temporary safety deserve neither liberty nor safety."
-Benjamin Franklin, 1759

 

glen herrmannsfeldt <gah@ugcs.caltech.edu> writes:

markp wrote:

I need to implement a low pass digital filter on 12 bit ADC data in a Spatan
IIE device, but I'd like it to be multiplier free - in other words just use
adders and bit shifting for the coefficients. The sample rate is 12Mhz and I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and adding.

It would seem that if the coefficients are constants it would not
be hard to generate the appropriate shift and add hardware, pipelined
as appropriate. Presumably you could use adders and subtractors, and
the design could be optimized toward minimizing the number of adder/subtractor
stages. (I think that can be done, but I haven't
tried to do it.)

See <<http://www.mathworks.com/products/filterhdl/>> for one product
that can do exactly this (and more). You can for example create
multiplier-free filters in two styles with optional pipelining.

There are many other products in the marketplace for filter code
generation; just look around.

Disclaimer: I work for The MathWorks.

 

[glen herrmannsfeldt]

markp wrote:

I need to implement a low pass digital filter on 12 bit ADC data in a Spatan
IIE device, but I'd like it to be multiplier free - in other words just use
adders and bit shifting for the coefficients. The sample rate is 12Mhz and I
need a sharp cut-off at around 3MHz. Does anyone know of a simple design
(IIR?) to do this, or a website/tutorial to give me some pointers? I've seen
several websites with coefficient calculators, there are always a few
coefficients that can't be easily calculated with bit shifting and adding.

It would seem that if the coefficients are constants it would not
be hard to generate the appropriate shift and add hardware, pipelined
as appropriate. Presumably you could use adders and subtractors, and
the design could be optimized toward minimizing the number of
adder/subtractor stages. (I think that can be done, but I haven't
tried to do it.)

-- glen