I
nte
rna
t
io
na
l
J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
2
,
A
p
r
il
2
0
2
1
,
p
p
.
1
7
0
9
~
1
7
1
8
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
1
i
2
.
pp
1
7
0
9
-
1
7
1
8
1709
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Desig
n and
i
m
ple
m
en
tatio
n of
DA
FIR
f
il
ter
f
o
r
b
io
-
i
nspired
c
o
m
pu
ting
a
rchi
t
ecture
B
.
U
.
V
.
P
ra
s
ha
nth
1
,
M
o
ha
m
m
e
d Riy
a
z
Ah
m
ed
2
,
M
a
njuna
t
h R
.
K
o
un
t
e
3
1,
3
S
c
h
o
o
l
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
,
RE
V
A
Un
iv
e
rsit
y
,
In
d
ia
2
S
c
h
o
o
l
o
f
M
u
lt
id
isc
ip
li
n
a
ry
S
tu
d
ies
,
REV
A
Un
iv
e
rsi
y
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
23
,
2
0
20
R
ev
i
s
ed
J
u
l
2
7
,
20
20
A
cc
ep
ted
Sep
1
6
,
2
0
20
T
h
is
p
a
p
e
r
e
lu
c
id
a
tes
th
e
s
y
ste
m
c
o
n
stru
c
t
o
f
D
A
-
F
IR
f
il
ter
o
p
ti
m
ize
d
f
o
r
d
e
sig
n
o
f
d
istri
b
u
te
d
a
rit
h
m
e
ti
c
(
DA
)
f
in
it
e
i
m
p
u
lse
re
sp
o
n
se
(F
IR)
f
il
ter
a
n
d
is
b
a
se
d
o
n
a
rc
h
it
e
c
tu
re
w
it
h
ti
g
h
tl
y
c
o
u
p
le
d
c
o
-
p
ro
c
e
ss
o
r
b
a
se
d
d
a
ta
p
ro
c
e
ss
in
g
u
n
it
s.
W
it
h
a
se
ries
o
f
lo
o
k
-
up
-
tab
le
(L
U
T
)
a
c
c
e
ss
e
s
i
n
o
rd
e
r
to
e
m
u
late
m
u
lt
ip
ly
a
n
d
a
c
c
u
m
u
lat
e
o
p
e
ra
ti
o
n
s
th
e
c
o
n
str
u
c
ted
DA
b
a
se
d
F
IR
f
il
ter
is
i
m
p
le
m
e
n
ted
o
n
F
P
GA
.
T
h
e
v
e
r
y
h
ig
h
sp
e
e
d
in
teg
ra
t
e
d
c
ircu
it
h
a
rd
w
a
re
d
e
sc
rip
ti
o
n
lan
g
u
a
g
e
(VH
DL
)
is u
se
d
im
p
le
m
e
n
t
th
e
p
r
o
p
o
se
d
f
il
ter
a
n
d
th
e
d
e
sig
n
is
v
e
ri
f
ied
u
s
in
g
si
m
u
latio
n
.
T
h
is
p
a
p
e
r
d
isc
u
ss
e
s
t
w
o
o
p
ti
m
iza
ti
o
n
a
lg
o
rit
h
m
s
a
n
d
re
s
u
lt
in
g
o
p
ti
m
iza
ti
o
n
s
a
re
in
c
o
r
p
o
ra
ted
in
t
o
L
U
T
la
y
e
r
a
n
d
a
rc
h
it
e
c
tu
re
e
x
t
ra
c
ti
o
n
s.
T
h
e
p
ro
p
o
se
d
m
e
th
o
d
o
ff
e
rs
a
n
o
p
ti
m
ize
d
d
e
sig
n
in
th
e
f
o
rm
o
f
o
ff
e
rs
a
v
e
ra
g
e
m
i
m
in
i
m
iza
ti
o
n
s
o
f
th
e
n
u
m
b
e
r
o
f
L
U
T
,
re
d
u
c
ti
o
n
in
p
o
p
u
late
d
slice
s
a
n
d
g
a
te
m
in
im
iz
a
ti
o
n
f
o
r
DA
-
f
in
it
e
i
m
p
u
lse
r
e
sp
o
n
se
f
il
ter
.
T
h
is
re
s
e
a
rc
h
p
a
v
e
s
a
d
irec
ti
o
n
to
w
a
rd
s
d
e
v
e
lo
p
m
e
n
t
o
f
b
io
in
sp
ired
c
o
m
p
u
ti
n
g
a
rc
h
it
e
c
tu
re
s
d
e
v
e
lo
p
e
d
w
it
h
o
u
t
lo
g
ica
ll
y
in
ten
siv
e
o
p
e
ra
ti
o
n
s,
o
b
tai
n
in
g
th
e
d
e
sire
d
sp
e
c
if
ica
ti
o
n
s
w
it
h
re
sp
e
c
t
to
p
e
rf
o
rm
a
n
c
e
,
ti
m
in
g
,
a
n
d
re
li
a
b
il
it
y
.
K
ey
w
o
r
d
s
:
B
io
-
i
n
s
p
ir
ed
c
o
m
p
u
t
in
g
Dis
tr
ib
u
ted
a
r
it
h
m
e
tic
Fin
ite
i
m
p
u
ls
e
r
esp
o
n
s
e
MA
C
an
d
p
ar
allel
f
i
lter
s
P
r
o
ce
s
s
o
r
a
r
ch
itectu
r
e
S
y
s
to
lic
a
r
r
a
y
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
B
.
U
.
V
.
P
r
ash
an
t
h
Sch
o
o
l o
f
E
lectr
o
n
ic
s
a
n
d
C
o
m
m
u
n
icatio
n
E
n
g
i
n
ee
r
in
g
R
E
V
A
U
n
iv
er
s
it
y
R
u
k
m
i
n
i K
n
o
w
led
g
e
P
ar
k
,
Yela
h
an
k
a,
B
en
g
al
u
r
u
-
5
6
0
0
6
4
,
I
n
d
ia
E
m
ail:
p
r
as
h
an
t
h
b
u
v
@
r
ev
a.
ed
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
Hig
h
t
h
r
o
u
g
h
p
u
t
i
s
r
eq
u
ir
ed
s
in
ce
t
h
e
f
i
n
ite
i
m
p
u
ls
e
r
esp
o
n
s
e
f
ilter
s
ar
e
u
s
ed
i
n
ten
s
i
v
e
ly
in
v
id
eo
,
co
m
m
u
n
icatio
n
s
s
y
s
te
m
s
as
w
ell
as
b
io
-
i
n
s
p
ir
ed
co
m
p
u
ti
n
g
s
y
s
te
m
s
.
E
s
s
en
t
iall
y
,
d
ig
i
t
al
f
i
lter
s
ar
e
u
s
ed
in
ti
m
e
a
n
d
f
r
eq
u
en
c
y
d
o
m
ai
n
to
ad
j
u
s
t
th
e
c
h
ar
ac
ter
is
tic
s
o
f
th
e
s
ig
n
al
s
an
d
ar
e
id
en
ti
f
ied
as
th
e
p
r
i
m
ar
y
d
ig
i
tal
s
ig
n
al
p
r
o
ce
s
s
i
n
g
f
ea
t
u
r
e
[1
]
.
T
h
e
DSP
d
esig
n
tech
n
iq
u
es
f
o
cu
s
m
a
in
l
y
o
n
m
u
ltip
lier
-
b
as
ed
ar
ch
itectu
r
es
f
o
r
m
u
ltip
l
y
-
a
n
d
-
ac
c
u
m
u
late
(
MA
C
)
b
lo
ck
s
i
m
p
le
m
e
n
tatio
n
w
h
ich
r
ep
r
esen
t
t
h
e
FIR
f
ilt
er
s
a
n
d
s
ev
er
al
f
u
n
ctio
n
s
.
Hi
g
h
s
p
ee
d
p
ar
allel
f
ilter
d
esig
n
s
ar
e
elu
cid
ated
in
ex
cr
u
ciati
n
g
d
et
ail.
Fin
ite
i
m
p
u
ls
e
r
esp
o
n
s
e
(
FIR)
f
ilter
s
ar
e
p
r
o
m
i
n
e
n
t
b
u
ild
in
g
b
lo
ck
s
f
o
r
s
e
v
er
al
ap
p
licatio
n
s
i
n
t
h
e
f
ield
o
f
d
ig
it
al
s
ig
n
al
p
r
o
ce
s
s
i
n
g
(
DSP
)
.
Hig
h
-
s
p
ee
d
FI
R
f
ilter
s
h
a
v
e
b
ee
n
w
id
el
y
u
s
ed
to
p
er
f
o
r
m
s
ig
n
al
eq
u
aliza
tio
n
o
n
th
e
r
ec
eiv
ed
d
ata
i
n
r
ea
l
ti
m
e
d
u
e
to
th
e
i
n
cr
ea
s
i
n
g
d
e
m
a
n
d
f
o
r
v
id
eo
-
s
i
g
n
al
p
r
o
ce
s
s
in
g
a
n
d
tr
a
n
s
m
is
s
io
n
.
T
h
er
ef
o
r
e
a
s
tr
u
ctu
r
ed
VL
SI
ar
ch
itect
u
r
e
is
n
ee
d
ed
f
o
r
a
p
r
o
g
r
am
m
ab
le
f
as
t FI
R
f
ilt
er
[
2
]
.
T
h
e
v
ar
io
u
s
FI
R
Fi
lter
s
w
er
e
s
u
g
g
es
ted
in
la
s
t
f
e
w
d
ec
ad
es,
m
an
y
s
tr
u
ct
u
r
es a
n
d
d
if
f
er
e
n
t
alg
o
r
ith
m
s
h
av
e
b
ee
n
u
tili
ze
d
f
o
r
th
e
en
h
a
m
ce
m
en
t
o
f
th
e
f
ilter
w
ei
g
h
t
s
.
T
h
e
v
er
y
co
m
m
o
n
s
tr
u
ct
u
r
es
u
tili
ze
d
w
er
e
least
m
ea
n
s
q
u
ar
e
(
L
MS)
d
er
iv
ed
m
o
d
el
s
s
i
n
ce
th
eir
r
esp
o
n
s
e
i
n
co
n
v
er
g
en
ce
i
s
s
tr
o
n
g
.
B
lo
ck
p
r
o
ce
s
s
in
g
w
it
h
d
is
tr
ib
u
ted
ar
ith
m
et
ic
m
eth
o
d
s
is
e
x
p
lo
r
ed
to
d
er
iv
e
a
d
e
s
ig
n
t
h
at
s
h
o
u
ld
g
iv
e
h
i
g
h
t
h
r
o
u
g
h
p
u
t
[3
]
.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il 2
0
2
1
:
1
7
0
9
-
1718
1710
p
ar
allelis
m
a
s
s
i
s
ts
i
n
m
i
n
i
m
i
zin
g
th
e
n
u
m
b
er
o
f
clo
c
k
c
y
cles
d
esire
d
f
o
r
p
ar
tial
p
r
o
d
u
ct
ca
lcu
latio
n
.
T
h
is
in
cr
ea
s
es t
h
e
p
r
o
p
o
s
ed
p
r
o
ce
s
s
in
g
s
p
ee
d
as c
o
m
p
ar
ed
w
it
h
c
u
r
r
en
t s
y
s
te
m
s
.
D
is
tr
ib
u
ted
ar
i
th
m
etic
(
D
A
)
i
s
a
s
tr
ate
g
y
o
f
h
i
g
h
-
s
p
ee
d
m
u
ltip
licatio
n
w
h
ic
h
is
a
b
it
s
er
ial
w
o
r
d
p
ar
allel
tech
n
iq
u
e
w
h
er
e
t
h
e
t
h
r
o
u
g
h
p
u
t
r
ate
d
o
es
n
o
t
d
ep
en
d
o
n
th
e
d
ata
s
ize.
T
h
e
DA
f
ac
ilit
ates
to
av
o
id
th
e
m
u
ltip
lier
s
i
n
th
e
d
esi
g
n
an
d
m
ak
e
s
th
e
ar
ea
o
f
t
h
e
s
y
s
te
m
ef
f
icien
t
in
t
h
e
th
r
o
u
g
h
p
u
t
a
n
d
s
ev
er
al
D
A
b
ased
s
tr
u
ct
u
r
es
w
er
e
d
esi
g
n
ed
i
n
o
r
d
er
to
m
i
n
i
m
ize
t
h
e
ar
ea
a
n
d
t
o
r
ed
u
ce
th
e
co
s
t
o
f
p
r
o
ce
s
s
i
n
g
[
4
]
.
T
h
e
p
r
i
m
ar
y
o
p
er
atio
n
s
n
ec
es
s
ar
y
f
o
r
D
A
-
b
ased
p
r
o
ce
s
s
in
g
ar
e
a
s
er
ies
o
f
ac
ce
s
s
e
s
to
a
lo
o
k
u
p
tab
le
(
L
UT
)
,
p
r
ec
ed
ed
b
y
th
e
L
UT
o
u
tp
u
t
'
s
s
h
i
f
t
-
ac
c
u
m
u
latio
n
o
p
er
atio
n
s
.
T
h
e
s
tan
d
a
r
d
f
r
am
e
w
o
r
k
o
f
D
A
u
s
ed
to
i
m
p
le
m
en
t
t
h
e
FIR
f
ilter
i
m
p
lie
s
t
h
at
t
h
e
co
ef
f
icie
n
ts
o
f
t
h
e
i
m
p
u
ls
e
r
esp
o
n
s
e
ar
e
f
i
x
ed
an
d
t
h
i
s
ac
tio
n
allo
w
s
u
s
e
o
f
R
OM
b
ased
L
UT
s
.
Ho
w
ev
er
,
w
it
h
li
n
ea
r
f
ilter
o
r
d
er
th
e
m
e
m
o
r
y
r
eq
u
ir
e
m
en
t
f
o
r
D
is
tr
ib
u
ted
A
r
ith
m
etic
i
m
p
le
m
e
n
tat
io
n
o
f
FIR
f
i
lter
s
r
is
e
s
e
x
p
o
n
en
ti
all
y
i
s
o
n
e
o
f
t
h
e
h
ar
d
p
r
o
b
le
m
s
to
b
e
ad
d
r
ess
ed
[
5
]
.
T
h
e
k
e
y
co
n
tr
ib
u
t
io
n
s
o
f
th
is
r
esear
c
h
ar
e:
-
Dev
elo
p
s
y
s
to
lic
ar
r
a
y
ar
ch
ite
ctu
r
e
w
it
h
tig
h
tl
y
co
u
p
led
co
-
p
r
o
ce
s
s
o
r
b
ased
d
ata
p
r
o
c
ess
i
n
g
u
n
its
.
-
Dev
elo
p
o
p
ti
m
izatio
n
al
g
o
r
ith
m
s
w
i
th
o
p
ti
m
izatio
n
s
i
n
co
r
p
o
r
ated
in
to
L
UT
lay
er
w
i
th
ar
ch
i
tectu
r
e
ex
tr
ac
tio
n
s
an
d
p
r
o
p
o
s
e
b
io
i
n
s
p
ir
ed
co
m
p
u
ti
n
g
ar
ch
itec
tu
r
e
to
co
m
p
u
te
FIR
f
ilter
s
a
t
h
ig
h
p
r
o
ce
s
s
i
n
g
s
p
e
ed
s
u
s
i
n
g
r
ec
o
n
f
i
g
u
r
ab
le
co
m
p
u
ti
n
g
b
ased
o
n
D
A
s
tr
ateg
y
.
2.
RE
L
AT
E
D
WO
RK
Mo
d
u
lar
f
i
n
ite
-
i
m
p
u
l
s
e
r
esp
o
n
s
e
(
FI
R
)
f
ilter
w
h
o
s
e
f
ilter
co
ef
f
icie
n
t
s
s
w
itc
h
d
y
n
a
m
ica
ll
y
d
u
r
in
g
laten
c
y
,
w
h
ic
h
p
la
y
s
a
m
aj
o
r
r
o
le
in
ar
c
h
itect
u
r
es
f
o
r
s
o
f
t
w
a
r
e
-
d
ef
i
n
ed
r
ad
io
(
SDR
)
,
m
u
lti
-
ch
a
n
n
el
f
ilter
s
,
b
i
-
in
s
p
ir
ed
co
m
p
u
ti
n
g
an
d
d
i
g
ita
l
u
p
/d
o
w
n
co
n
v
er
ter
s
.
Ho
w
ev
er
,
w
h
en
t
h
e
f
ilter
co
e
f
f
icien
t
s
v
ar
y
d
y
n
a
m
icall
y
,
th
e
w
ell
-
k
n
o
w
n
m
u
ltip
le
co
n
s
tan
t
m
u
lt
ip
licatio
n
(
MCM)
-
b
ased
m
eth
o
d
s
t
h
at
ar
e
w
id
el
y
u
s
ed
to
r
ea
lize
th
e
FIR
f
ilter
s
ca
n
n
o
t
b
e
u
s
ed
.
Ad
d
r
ess
in
g
to
th
e
s
o
lu
tio
n
to
t
h
e
p
r
o
b
le
m
o
f
s
u
c
h
lar
g
e
m
e
m
o
r
y
r
eq
u
ir
e
m
e
n
t,
s
y
s
to
lic
d
ec
o
m
p
o
s
itio
n
tec
h
n
i
q
u
es
ar
e
u
tili
ze
d
f
o
r
D
A
-
b
ase
d
i
m
p
le
m
en
ta
tio
n
o
f
lo
n
g
-
le
n
g
th
co
n
v
o
l
u
tio
n
s
a
n
d
FIR
f
ilter
o
f
lar
g
e
o
r
d
er
s
.
I
t
is
n
ec
es
s
ar
y
to
u
s
e
r
e
w
r
itab
le
R
A
M
b
ased
L
UT
in
s
tead
o
f
R
OM
b
ased
L
UT
f
o
r
r
ec
o
n
f
i
g
u
r
ab
le
D
A
b
ased
FIR
f
ilter
w
h
o
s
e
f
ilter
co
ef
f
icie
n
ts
alter
d
y
n
a
m
icall
y
.
An
o
th
er
m
e
th
o
d
is
to
s
to
r
e
th
e
an
alo
g
d
o
m
ai
n
co
ef
f
icien
ts
u
s
in
g
s
er
ial
d
ig
ita
l
to
an
alo
g
co
n
v
er
ter
s
,
r
esu
l
tin
g
i
n
m
i
x
ed
-
s
ig
n
al
ar
ch
itec
t
u
r
e
s
[
6
]
.
A
p
ip
eli
n
ed
d
esi
g
n
f
o
r
a
n
ad
ap
tiv
e
FI
R
f
ilter
ca
r
r
y
o
u
t
t
h
e
s
av
e
ac
cu
m
u
latio
n
tec
h
n
iq
u
e
w
h
ic
h
i
s
u
s
ed
f
o
r
p
ar
tial
in
n
er
p
r
o
d
u
ct
ca
lcu
latio
n
th
at
f
ac
ilit
ate
s
in
e
n
h
a
n
ci
n
g
t
h
e
th
r
o
u
g
h
p
u
t
w
it
h
b
lo
ck
p
r
o
ce
s
s
in
g
is
u
tili
ze
d
in
i
n
cr
ea
s
i
n
g
t
h
e
co
m
p
u
ta
tio
n
al
s
p
ee
d
o
f
th
e
s
y
s
te
m
.
On
th
e
o
th
er
h
an
d
,
a
p
ar
ticu
lar
m
u
ltip
lier
-
b
ased
s
tr
u
ct
u
r
e
r
eq
u
ir
es
a
w
id
e
c
h
ip
r
eg
io
n
,
a
n
d
th
er
eb
y
co
n
tr
o
ls
li
m
ita
tio
n
s
o
n
t
h
e
h
ig
h
e
s
t
allo
w
ab
le
o
r
d
er
o
f
th
e
f
ilter
t
h
at
ca
n
b
e
i
n
ter
p
r
eted
f
o
r
h
ig
h
-
th
r
o
u
g
h
p
u
t a
p
p
licatio
n
s
[
7
]
.
I
n
r
ec
en
t y
ea
r
s
,
d
is
tr
ib
u
te
d
ar
ith
m
etic
(
D
A
)
-
b
ased
tech
n
iq
u
e
h
as
g
ai
n
ed
s
u
b
s
ta
n
tial
p
o
p
u
lar
it
y
d
u
e
to
i
ts
h
i
g
h
ca
p
ac
it
y
f
o
r
p
r
o
ce
s
s
i
n
g
t
h
r
o
u
g
h
p
u
t
an
d
in
cr
ea
s
ed
r
eg
u
lar
it
y
,
r
es
u
lti
n
g
in
co
s
t
-
ef
f
ec
ti
v
e
a
n
d
ar
ea
-
ti
m
e
ef
f
ic
ien
t c
o
m
p
u
ti
n
g
s
tr
u
ctu
r
e
s
.
T
h
e
p
r
im
a
r
y
o
p
er
atio
n
s
r
eq
u
ir
ed
f
o
r
DA
-
b
ased
p
r
o
ce
s
s
in
g
ar
e
a
s
eq
u
en
ce
o
f
ac
ce
s
s
es
to
a
lo
o
k
u
p
tab
le
(
L
UT
)
,
f
o
llo
w
ed
b
y
th
e
L
UT
o
u
tp
u
t
'
s
s
h
i
f
t
-
a
cc
u
m
u
lat
io
n
o
p
er
atio
n
s
[
8
]
.
T
h
e
co
n
v
e
n
tio
n
al
i
m
p
le
m
en
ta
tio
n
o
f
th
e
D
A
u
s
ed
to
i
m
p
le
m
e
n
t
t
h
e
FI
R
f
il
ter
ass
u
m
es
th
a
t
t
h
e
c
o
e
f
f
icie
n
ts
o
f
th
e
i
m
p
u
l
s
e
r
esp
o
n
s
e
ar
e
f
ix
ed
a
n
d
t
h
is
b
eh
av
io
r
allo
w
s
t
h
e
u
s
e
o
f
R
O
M
b
ased
L
UT
s
.
Ho
w
e
v
er
,
w
it
h
t
h
e
f
ilter
o
r
d
er
th
e
m
e
m
o
r
y
r
eq
u
ir
e
m
e
n
t
f
o
r
DA
-
b
ased
i
m
p
le
m
e
n
tatio
n
o
f
FIR
f
ilter
s
in
cr
ea
s
e
s
ex
p
o
n
e
n
tial
l
y
[
9
]
.
T
h
e
s
y
s
to
lic
d
ec
o
m
p
o
s
itio
n
te
ch
n
iq
u
es
ar
e
u
s
ed
to
g
e
t
r
id
o
f
t
h
e
p
r
o
b
le
m
o
f
s
u
ch
a
lar
g
e
m
e
m
o
r
y
r
eq
u
ir
e
m
en
t.
Fo
r
lo
n
g
-
le
n
g
th
co
n
v
o
lu
tio
n
s
an
d
lar
g
e
-
o
r
d
er
FIR
f
ilter
f
o
r
D
A
-
b
ased
i
m
p
le
m
en
tatio
n
,
w
e
m
u
s
t
u
s
e
r
e
w
r
itab
le
R
A
M
b
ased
L
UT
in
s
tead
o
f
R
OM
b
ased
L
UT
f
o
r
r
ec
o
n
f
ig
u
r
ab
le
DA
-
b
a
s
ed
FIR
f
ilter
w
h
o
s
e
f
ilter
co
ef
f
icie
n
ts
c
h
an
g
e
d
y
n
a
m
icall
y
.
A
n
o
t
h
er
ap
p
r
o
ac
h
is
to
s
to
r
e
th
e
co
ef
f
icie
n
ts
i
n
th
e
an
alo
g
d
o
m
ain
b
y
u
s
i
n
g
s
er
ial
d
ig
ital
to
an
alo
g
co
n
v
er
ter
s
r
esu
l
tin
g
i
n
m
i
x
e
d
-
s
i
g
n
al
ar
c
h
itect
u
r
e.
W
e
also
f
in
d
q
u
ite
a
f
e
w
w
o
r
k
s
o
n
D
A
b
ased
i
m
p
le
m
e
n
tatio
n
o
f
ad
ap
tiv
e
f
ilter
s
,
w
h
er
e
th
e
co
ef
f
icie
n
ts
c
h
an
g
e
at
ev
er
y
c
y
cle
[
1
0
]
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
AND
AL
G
O
RI
T
H
M
DE
SI
G
N
Dis
tr
ib
u
ted
a
r
ith
m
et
ic
is
a
p
o
p
u
lar
ar
ch
itectu
r
e
w
it
h
o
u
t
t
h
e
u
s
e
o
f
m
u
ltip
lier
s
to
i
m
p
l
e
m
en
t
FI
R
f
ilter
s
.
D
A
m
ak
e
s
ef
f
icie
n
t
u
s
e
o
f
L
UT
s
,
s
h
if
ter
s
,
an
d
ad
d
e
r
s
to
ca
lcu
late
th
e
s
u
m
o
f
p
r
o
d
u
cts
r
eq
u
ir
ed
f
o
r
FIR
f
ilter
s
.
Si
n
ce
th
e
s
e
o
p
er
atio
n
s
e
f
f
ec
ti
v
el
y
m
ap
o
n
to
a
n
F
P
GA
,
Di
s
tr
ib
u
ted
ar
it
h
m
etic
o
n
t
h
ese
d
ev
ice
s
i
s
a
f
av
o
u
r
ab
le
ar
ch
itect
u
r
e
[
1
1
]
.
T
h
e
Fig
u
r
e
1
ill
u
s
tr
ates
th
e
e
x
p
er
i
m
e
n
tal
d
e
s
ig
n
o
f
t
h
e
r
e
s
ea
r
ch
w
o
r
k
p
r
ese
n
ted
i
n
th
i
s
m
an
u
s
cr
ip
t.
Dis
tr
ib
u
ted
A
r
it
h
m
etic
is
a
p
r
o
m
i
n
en
t a
r
c
h
itect
u
r
e
w
it
h
o
u
t t
h
e
u
s
e
o
f
m
u
ltip
li
er
s
to
i
m
p
le
m
en
t FI
R
f
ilter
s
.
D
A
m
ak
e
s
ef
f
icie
n
t
u
s
e
o
f
L
UT
s
,
s
h
i
f
ter
s
,
an
d
ad
d
er
s
to
ca
lcu
late
th
e
s
u
m
o
f
m
u
lt
ip
licatio
n
f
ac
to
r
s
n
ee
d
ed
f
o
r
FIR
f
i
lter
s
.
T
h
o
u
g
h
d
is
tr
ib
u
te
d
ar
ith
m
etic
i
m
p
le
m
en
ts
t
h
e
FIR
f
i
lter
b
y
s
er
ializatio
n
b
its
o
f
in
p
u
ts
,
a
f
ilte
r
q
u
an
ti
s
atio
n
is
r
eq
u
ir
ed
.
Du
e
to
th
e
f
ix
ed
d
ata
p
ath
r
eq
u
ir
em
en
ts
in
i
n
p
u
t
an
a
lo
g
to
d
ig
it
al
co
n
v
er
ter
(
A
D
C
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Desig
n
a
n
d
imp
leme
n
ta
tio
n
o
f
DA
F
I
R
filt
er fo
r
b
io
-
in
s
p
ir
ed
co
mp
u
tin
g
a
r
ch
itectu
r
e
(
B
.
U
.
V
.
P
r
a
s
h
a
n
th
)
1711
an
d
t
h
e
o
u
tp
u
t
d
i
g
ital
to
an
alo
g
co
n
v
er
ter
(
D
AC
)
w
id
t
h
s
th
e
len
g
t
h
o
f
t
h
e
w
o
r
d
w
it
h
1
2
b
it
in
p
u
t
a
n
d
o
u
tp
u
t
w
it
h
1
1
f
r
ac
tio
n
al
b
it
s
ar
e
ass
u
m
ed
to
b
e
r
eq
u
ir
ed
to
q
u
an
tize
th
e
FIR
f
ilter
[
1
2
]
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
a
m
o
f
e
x
p
er
im
e
n
tal
d
esi
g
n
Af
ter
th
e
q
u
a
n
tizat
io
n
p
r
o
ce
s
s
th
e
HD
L
C
o
d
e
is
g
e
n
er
ate
d
w
it
h
D
A
ar
ch
itect
u
r
e.
T
h
e
HDL
co
d
e
g
en
er
ato
r
u
s
e
s
d
is
tr
ib
u
ted
ar
i
th
m
etic
ar
c
h
itect
u
r
e,
an
d
p
ar
t
itio
n
s
t
h
e
lo
o
k
-
up
-
tab
le
(
L
U
T
)
in
to
a
s
p
ec
if
ied
n
u
m
b
er
o
f
L
UT
p
ar
titi
o
n
s
w
i
t
h
th
e
r
a
n
g
e
o
f
tap
s
ea
ch
p
ar
tit
io
n
ass
o
ciate
s
.
I
t
is
b
est
to
d
iv
id
e
th
e
tap
s
i
n
to
a
n
u
m
b
er
o
f
L
UT
s
f
o
r
a
f
ilter
with
m
a
n
y
tap
s
,
w
it
h
ea
c
h
L
UT
s
to
r
in
g
t
h
e
s
u
m
o
f
co
ef
f
icie
n
t
s
o
n
l
y
f
o
r
th
e
t
ap
s
th
at
ar
e
ass
o
ciate
d
w
it
h
it.
T
h
e
FIR
f
ilter
s
tr
u
ct
u
r
e
h
a
s
s
y
m
m
etr
ic
co
ef
f
icie
n
ts
,
a
n
d
w
e
co
n
s
id
er
co
n
v
er
ti
n
g
th
e
s
tr
u
ctu
r
e
t
o
r
ed
u
ce
th
e
ar
ea
.
Her
e
w
e
co
n
v
er
t
th
e
f
ilter
s
tr
u
ct
u
r
e
to
d
ir
ec
t
f
o
r
m
s
y
m
m
etr
ic
a
n
d
g
e
n
er
ate
th
e
HD
L
co
d
e
f
o
r
d
ef
au
lt
r
ad
ix
o
f
2
.
I
n
h
ar
d
w
ar
e,
a
s
y
m
m
etr
ical
f
il
ter
s
tr
u
ct
u
r
e
o
f
f
er
s
ad
v
an
ta
g
es,
as
it
h
al
v
es
th
e
n
u
m
b
er
o
f
co
ef
f
icie
n
t
s
to
w
o
r
k
w
it
h
wh
ich
s
u
b
s
tan
tiall
y
r
ed
u
ce
s
t
h
e
co
m
p
le
x
it
y
o
f
t
h
e
h
ar
d
w
a
r
e.
T
h
e
p
r
ed
ef
in
ed
ar
ch
itect
u
r
e
is
a
n
i
m
p
le
m
en
ta
tio
n
o
f
R
ad
i
x
2
th
a
t
r
u
n
s
o
n
o
n
e
b
it
o
f
i
n
p
u
t
d
ata
p
er
clo
ck
p
er
io
d
.
B
ef
o
r
e
an
o
u
tp
u
t i
s
o
b
tain
ed
,
th
e
n
u
m
b
er
o
f
clo
ck
p
h
a
s
es e
lap
s
ed
is
eq
u
al
to
t
h
e
n
u
m
b
er
o
f
b
its
i
n
t
h
e
in
p
u
t d
ata
a
n
d
D
A
m
a
y
ef
f
ec
ti
v
el
y
li
m
it
th
e
th
r
o
u
g
h
p
u
t.
D
A
ca
n
b
e
co
n
f
ig
u
r
e
d
to
p
r
o
ce
s
s
m
u
l
tip
le
b
its
i
n
p
ar
allel,
t
o
i
m
p
r
o
v
e
th
e
D
A
th
r
o
u
g
h
p
u
t.
T
h
e
p
r
o
ce
s
s
i
n
g
o
f
1
2
b
its
at
a
ti
m
e
f
o
r
a
1
2
b
it
in
p
u
t
w
o
r
d
le
n
g
t
h
ca
n
b
e
s
p
ec
i
f
ied
w
it
h
th
e
co
r
r
esp
o
n
d
in
g
D
A
-
R
ad
i
x
v
alu
e
s
o
f
2
12
.
T
h
e
s
p
ee
d
v
s
.
a
r
ea
is
tr
a
d
e
o
f
f
b
y
s
elec
t
in
g
d
if
f
er
en
t
'
D
AR
ad
i
x
'
v
alu
e
s
a
n
d
th
e
a
m
o
u
n
t
o
f
p
ar
allel
b
its
il
lu
s
tr
ates
t
h
e
f
ac
to
r
w
it
h
t
h
e
i
n
cr
ea
s
ed
r
ate
o
f
th
e
clo
ck
w
h
ich
i
s
t
h
e
n
u
m
b
er
o
f
c
y
cles
to
p
er
f
o
r
m
an
iter
atio
n
[
1
3
]
.
T
h
e
T
ab
les
1
-
3
elu
cid
ate
t
h
e
i
n
f
o
r
m
atio
n
o
f
D
A
ar
ch
itect
u
r
e.
T
h
e
T
a
b
le
1
d
ep
icts
th
e
'
D
A
R
ad
ix
'
v
al
u
es
w
it
h
co
r
r
esp
o
n
d
in
g
v
al
u
es
o
f
n
u
m
b
er
o
f
c
y
cles
to
p
er
f
o
r
m
an
iter
atio
n
an
d
m
u
lt
ip
le
f
o
r
L
U
T
s
ets
f
o
r
th
e
g
i
v
en
f
ilter
.
Fu
r
th
er
T
a
b
le
2
illu
s
tr
ates
t
h
e
d
etails
o
f
L
UT
s
w
it
h
co
r
r
esp
o
n
d
in
g
'
D
AL
UT
P
ar
titi
o
n
'
v
al
u
es.
Deta
ils
o
f
L
UT
in
d
icate
n
u
m
b
er
o
f
L
UT
s
w
it
h
t
h
e
s
ize
s
o
f
L
UT
f
o
r
ex
a
m
p
le
(
1
x
1
0
2
4
x
1
8
)
im
p
lie
s
1
L
UT
o
f
1
0
2
4
1
8
-
b
it
w
id
e
lo
ca
tio
n
s
[
1
4
]
.
T
ab
le
1
.
'
DARad
ix
'
v
al
u
es
w
it
h
n
u
m
b
er
o
f
c
y
cles to
p
er
f
o
r
m
an
iter
atio
n
a
n
d
m
u
ltip
le
f
o
r
L
UT
s
ets
F
o
l
d
i
n
g
F
a
c
t
o
r
L
U
T
S
e
t
s M
u
l
t
i
p
l
e
D
A
R
a
d
i
x
1
12
2
12
2
6
2
6
3
4
2
4
4
3
2
3
6
2
2
2
12
1
2
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il 2
0
2
1
:
1
7
0
9
-
1718
1712
T
ab
le
2
.
Deta
ils
o
f
L
UT
s
w
ith
co
r
r
esp
o
n
d
in
g
p
ar
titi
o
n
s
o
f
D
A
-
L
UT
A
d
d
r
e
ss
W
i
d
t
h
S
i
z
e
(
b
i
t
s)
L
U
T
D
A
L
U
T
P
a
r
t
i
t
i
o
n
W
12
b
’
2
5
9
0
7
2
[
1
0
2
4
x
1
3
]
,
[
1
3
x
4
0
9
6
]
,
[
1
4
x
4
0
9
6
]
,
[
1
5
x
4
0
9
6
]
,
[
1
8
x
4
0
9
6
]
(
1
2
)
(
1
2
)
(
1
2
)
(
1
2
)
(
1
0
)
W
11
b
’
1
4
7
5
4
4
[
2
x
2
0
4
8
x
1
4
]
,
[
1
x
2
0
4
8
x
1
8
]
,
[
2
x
2
0
4
8
x
1
3
]
,
[
1
x
8
x
1
1
]
(
1
1
)
(
1
1
)
(
1
1
)
(
1
1
)
(
1
1
)
(
3
)
W
10
b
’
7
8
0
8
0
[
1
x
1
0
2
4
x
1
8
]
,
[
3
x
1
0
2
4
x
1
3
]
,
[
1
x
1
0
2
4
x
1
6
]
,
[
1
x
2
5
6
x
1
3
]
(
1
0
)
(
1
0
)
(
1
0
)
(
1
0
)
(
1
0
)
(
8
)
W
09
b
’
4
3
7
1
2
[
1
x
5
1
2
x
1
2
]
,
[
1
x
5
1
2
x
1
4
]
,
[
1
x
5
1
2
x
1
8
]
,
[
1
x
1
6
x
1
2
]
,
[
2
x
5
1
2
x
1
3
]
,
[
1
x
5
1
2
x
1
5
]
(
9
)
(
9
)
(
9
)
(
9
)
(
9
)
(
9
)
(
4
)
W
08
b
’
2
5
3
8
4
[
1
x
4
x
1
0
]
,
[
1
x
2
5
6
x
1
4
]
,
[
1
x
2
5
6
x
1
8
]
,
[
4
x
2
5
6
x
1
3
]
,
[
1
x
2
5
6
x
1
5
]
(
8
)
(
8
)
(
8
)
(
8
)
(
8
)
(
8
)
(
8
)
(
2
)
W
07
b
’
1
4
2
4
8
[
1
x
1
2
8
x
1
4
]
,
[
1
x
1
2
8
x
1
6
]
,
[
1
x
4
x
1
0
]
,
[
2
x
1
2
8
x
1
2
]
,
[
3
x
1
2
8
x
1
3
]
,
[
1
x
1
2
8
x
1
8
]
(
7
)
(
7
)
(
7
)
(
7
)
(
7
)
(
7
)
(
7
)
(
2)
W
06
b
’
8
0
0
0
[
4
x
6
4
x
1
2
]
,
[
1
x
1
6
x
1
2
]
,
[
1
x
6
4
x
1
7
]
,
[
2
x
6
4
x
1
4
]
,
[
1
x
6
4
x
1
6
]
,
[
1
x
6
4
x
1
3
]
o
n
e
(
9
,
1
)
*
(
6
)
,
(
4
)
W
05
b
’
4
6
9
6
[
1
x
8
x
1
1
]
,
[
4
x
3
2
x
1
2
]
,
[
3
x
3
2
x
1
3
]
,
[
1
x
3
2
x
1
5
]
,
[
1
x
3
2
x
1
4
]
,
[
1
x
3
2
x
1
7
]
,
[
1
x
3
2
x
1
1
]
o
n
e
(
1
,
1
1
)
*
(
5
)
,
(
3
)
W
04
b
’
2
9
0
4
[
1
x
1
6
x
1
5
]
,
[
5
x
1
6
x
1
2
]
,
[
2
x
1
6
x
1
3
]
,
[
2
x
1
6
x
1
4
]
,
[
1
x
1
6
x
1
7
]
,
[
1
x
4
x
1
0
]
,
[
3
x
1
6
x
1
1
]
o
n
e
(
1
,
1
4
)
*
(
4
)
,
(
2
)
W
03
b
’
1
9
2
6
[
8
x
8
x
1
2
]
,
[
2
x
8
x
1
4
]
,
[
2
x
8
x
1
5
]
,
[
1
x
8
x
1
7
]
,
[
1
x
2
x
7
]
,
[
5
x
8
x
1
1
]
,
[
1
x
8
x
1
3
]
o
n
e
(
1
,
1
9
)
*
(
3
)
,
1
W
02
b
’
1
4
1
2
[
1
2
x
4
x
1
1
]
,
[
2
x
4
x
1
3
]
,
[
2
x
4
x
1
5
]
,
[
1
x
4
x
1
7
]
,
[
2
x
4
x
1
0
]
,
[
6
x
4
x
1
2
]
,
[
4
x
4
x
1
4
]
o
n
e
(
1
,
2
9
)
*
(
2
)
T
ab
le
3
.
T
a
b
u
lar
co
lu
m
n
o
f
co
m
p
lete
t
w
id
d
le
f
ac
to
r
f
o
r
ea
ch
L
UT
in
p
u
ts
F
o
l
d
i
n
g
F
a
c
t
o
r
L
U
T
I
n
p
u
t
s
L
U
T
S
i
z
e
L
U
T
D
e
t
a
i
l
s
1
L
U
T
4
S
(
3
4
8
4
8
)
(
1
x
4
x
1
0
,
5
x
1
6
x
1
2
,
2
x
1
6
x
1
4
,
2
x
1
6
x
1
3
,
1
x
1
6
x
1
5
,
1
x
1
6
x
1
7
,
3
x
1
6
x
1
1
)
x
1
2
2
L
U
T
4
S
(
1
7
4
2
4
)
(
3
x
1
6
x
1
7
,
5
x
1
6
x
1
2
,
2
x
1
6
x
1
4
,
2
x
1
6
x
1
3
,
1
x
1
6
x
1
5
,
1
x
1
6
x
1
1
,
1
x
4
x
1
0
)
x
6
3
L
U
T
4
S
(
1
1
6
1
6
)
(
1
x
4
x
1
0
,
5
x
1
6
x
1
2
,
2
x
1
6
x
1
4
,
2
x
1
6
x
1
3
,
1
x
1
6
x
1
7
,
1
x
1
6
x
1
5
,
3
x
1
6
x
1
1
)
x
4
4
L
U
T
4
S
(
8
7
1
2
)
(
1
x
4
x
1
0
,
5
x
1
6
x
1
2
,
2
x
1
6
x
1
4
,
2
x
1
6
x
1
3
,
1
x
1
6
x
1
7
,
1
x
1
6
x
1
5
,
3
x
6
x
1
1
)
x
3
6
L
U
T
4
S
(
5
8
0
8
)
(
1
x
4
x
1
0
,
5
x
1
6
x
1
2
,
2
x
1
6
x
1
4
,
2
x
1
6
x
1
3
,
1
x
1
6
x
1
7
,
1
x
1
6
x
1
5
,
3
x
6
x
1
1
)
x
2
12
L
U
T
4
S
(
2
9
0
4
)
(
1
x
4
x
1
0
,
5
x
1
6
x
1
2
,
2
x
1
6
x
1
4
,
2
x
1
6
x
1
3
,
1
x
1
6
x
1
7
,
1
x
1
6
x
1
5
,
3
x
6
x
1
1
)
x
1
As
d
ep
icted
in
T
ab
le
3
,
if
it
is
r
eq
u
ir
ed
to
i
n
cr
ea
s
e
t
h
e
clo
ck
r
ate
b
y
f
o
u
r
s
ca
le
s
t
h
e
s
a
m
p
li
n
g
f
r
eq
u
en
c
y
a
n
d
u
t
ilize
s
ix
i
n
p
u
t
L
UT
s
th
e
n
w
e
ca
n
v
er
if
y
t
h
at
th
e
d
etail
s
o
f
L
UT
m
ee
t
s
th
e
ar
ea
r
eq
u
ir
e
m
en
t
s
.
Nex
t
a
te
s
t
b
en
c
h
i
s
d
esi
g
n
ed
w
i
th
a
s
ta
n
d
ar
d
s
etu
p
,
a
n
d
u
s
es
a
s
i
m
u
lato
r
to
v
er
if
y
t
h
e
g
en
er
ated
co
d
e
f
o
r
d
is
tr
ib
u
ted
ar
it
h
m
e
tic
ar
c
h
itec
tu
r
e
[
1
5
]
.
T
h
e
s
y
n
t
h
esi
s
to
o
l
is
u
tili
ze
d
to
co
m
p
ar
e
t
h
e
ar
e
a
an
d
s
p
ee
d
o
f
t
h
e
DA
ar
c
h
itect
u
r
e.
T
h
e
A
lg
o
r
it
h
m
1
ill
u
s
tr
ate
s
th
e
p
er
f
o
r
m
a
n
ce
an
al
y
s
i
s
an
d
o
p
ti
m
at
io
n
o
f
L
UT
la
y
er
.
As
s
h
o
w
n
i
n
Alg
o
r
it
h
m
2
,
t
h
e
c
o
s
t
f
u
n
ctio
n
co
u
ld
b
e
an
y
ar
b
itra
r
y
p
ar
a
m
eter
s
d
ela
y
,
p
o
w
er
o
r
p
o
w
er
d
ela
y
m
u
ltip
licatio
n
(
P
DM
)
r
etu
r
n
ed
f
r
o
m
o
p
t
i
m
ized
L
UT
.
A
l
g
o
r
ith
m
1
: P
er
f
o
r
m
an
ce
a
n
a
l
y
s
i
s
an
d
o
p
ti
m
iza
tio
n
o
f
L
UT
la
y
er
Result: Optimization of LUT Layer
Start
Optimize LUT (Addr bits: k, num LUTs: m)
Delay(LUTi,1) ← dlut[j] ;
for all j set of [k]
Power(LUTi,1)← plut[j]
for all j set of [
k]
Power Delay(LUTj,1)← pdlut[j];
for all j set of [k]
While {Read the Input Parameters}{
for (i=2; i <= k; i++)
for (j=2; j <= m; j++)
else If{Perform Optimization}
{
Delay(LUTi,j)←minu{max{ dlut[u] +D(LUTi
-
u,j
-
1)}
};
P(LUTi,j)←minima w{plut[w]
+ Power(LUTi
-
w,j
-
1)};
PD(LUTi,j)←minima{Delay(LUTi,
j.Power Utilization (LUTi,j)};
end for
}{
Compute:return Delay(LUTk,m), Power(LUTk,m) Power Delay(LUTk,m)}
Calculate the performance;
}
Stop
A
l
g
o
r
ith
m
2
:
A
l
g
o
r
ith
m
s
tep
s
to
o
p
tim
ized
ar
ch
itec
tu
r
e
e
x
tr
ac
tio
n
s
Result: Optimized Architecture Extractions
Start;
Define parameters;
While {Read the Input Parameters}
{
Architecture Optimize (N:Filter Order):
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Desig
n
a
n
d
imp
leme
n
ta
tio
n
o
f
DA
F
I
R
filt
er fo
r
b
io
-
in
s
p
ir
ed
co
mp
u
tin
g
a
r
ch
itectu
r
e
(
B
.
U
.
V
.
P
r
a
s
h
a
n
th
)
1713
Optimized Solution← infinity;
Select cost from (Delay | Power | Power Delay Muliplication)
for
(i=1; i <= N; i++)
for (j=1; j <=i; j++)
else If{Perform Optimization}
{
ArchCost = cost(OptimizeLUT(i,j))
if (Architecture Cost )
Optmized response←Architecture Cost;
end for
end for
}
Compute:
return:
Optimum Solution
Calculate the performa
nce;
Stop
}
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
NS
T
h
e
f
ix
ed
p
o
in
t
s
etti
n
g
s
ar
e
ap
p
lied
in
o
r
d
e
r
to
o
b
tain
th
e
ch
ar
ac
ter
is
tic
p
lo
t
o
f
m
a
g
n
it
u
d
e
r
esp
o
n
s
e
(
d
B
)
in
d
icatin
g
t
h
e
c
u
r
v
e
s
b
et
w
ee
n
t
h
e
m
ag
n
it
u
d
e
(
d
B
)
an
d
th
e
n
o
r
m
alize
d
f
r
eq
u
en
c
y
(
π
r
ad
ian
s
p
er
s
a
m
p
le)
w
it
h
th
e
co
m
p
ar
is
o
n
b
et
w
ee
n
r
ef
er
en
ce
a
n
d
q
u
a
n
tized
f
i
lter
as
d
ep
icted
in
Fi
g
u
r
e
2
(
a)
.
T
h
e
ch
ar
ac
ter
is
t
ic
p
lo
t
r
ep
r
esen
tin
g
t
h
e
co
m
p
lete
d
esi
g
n
s
p
ec
if
icat
io
n
o
f
D
A
FIR
f
il
ter
alo
n
g
w
it
h
t
h
e
L
o
g
m
a
g
n
it
u
d
e
(
d
B
)
an
d
p
h
ase
(
d
eg
r
ee
s
)
is
as
d
ep
icted
in
Fi
g
u
r
e
2
(
b
)
.
I
n
th
is
ca
s
e
th
e
f
u
ll
p
r
ec
is
io
n
o
v
er
r
id
e
is
n
o
t
co
n
s
id
er
ed
an
d
cu
s
to
m
co
ef
f
icie
n
t
d
ata
t
y
p
e
i
s
co
n
s
id
er
ed
in
t
h
e
d
esi
g
n
.
W
it
h
th
e
o
p
ti
m
izatio
n
s
ad
d
r
ess
e
d
b
y
v
ar
iatio
n
s
i
n
ar
ch
itect
u
r
al
lev
el
e
n
h
an
ce
m
en
ts
u
s
i
n
g
D
A
co
n
ce
p
t
o
f
d
ig
ital
f
ilter
i
n
g
w
h
ic
h
i
m
p
r
o
v
e
s
d
ev
i
ce
u
tili
za
tio
n
[
1
6
,
1
7
]
.
(
a)
(
b
)
Fig
u
r
e
2
.
P
lo
t
o
f
(
a)
m
ag
n
it
u
d
e
r
esp
o
n
s
e
(
d
B
)
,
(
b
)
l
o
g
m
a
g
n
i
tu
d
e
(
d
B
)
-
p
h
ase
(
d
eg
r
ee
s
)
Her
e
th
e
clo
c
k
r
ate
i
s
f
o
u
r
ti
m
es
th
e
in
p
u
t
s
a
m
p
le
r
ate
f
o
r
th
i
s
ar
ch
i
tectu
r
e
a
n
d
t
h
e
e
f
f
e
ctiv
e
f
ilter
len
g
th
f
o
r
s
er
ial
p
ar
titi
o
n
v
al
u
e
is
5
8
alo
n
g
w
it
h
th
r
ee
s
am
p
les
o
f
HD
L
late
n
c
y
,
ac
h
i
ev
ed
w
ith
th
e
FI
R
co
m
p
iler
a
n
d
t
h
e
co
r
r
esp
o
n
d
in
g
f
r
eq
u
e
n
c
y
r
esp
o
n
s
e
d
ia
g
r
a
m
o
b
tain
ed
i
n
FI
R
co
m
p
ile
r
is
as
d
ep
icted
in
Fig
u
r
e
3
(
a)
an
d
w
i
th
r
ef
er
e
n
c
e
to
th
is
th
e
p
o
le
-
ze
r
o
(P
-
Z
)
d
iag
r
a
m
i
s
as
d
ep
icted
in
Fig
u
r
e
3
(
b
)
.
B
ec
au
s
e
o
f
m
id
-
s
ta
g
e
p
ip
elin
in
g
,
t
h
e
e
n
tir
e
ar
ch
itect
u
r
e
is
s
p
lit
in
to
t
w
o
s
ec
tio
n
s
,
n
a
m
el
y
t
h
e
in
p
u
t
s
ec
tio
n
a
n
d
th
e
o
u
tp
u
t
s
ec
tio
n
.
Her
e
th
e
p
o
w
er
co
n
s
u
m
p
tio
n
o
f
t
h
e
D
A
ar
ch
itect
u
r
e
is
esti
m
ated
at
2
0
MH
z
f
r
eq
u
en
c
y
a
n
d
th
e
f
i
n
al
DA
ar
ch
i
tectu
r
e
is
d
esig
n
ed
u
s
i
n
g
t
h
e
s
y
s
to
lic
r
ea
r
r
an
g
e
m
en
t
o
f
d
ela
y
ele
m
e
n
ts
.
T
h
e
p
r
ec
o
n
f
i
g
u
r
ed
lo
g
ic
f
u
n
ctio
n
s
,
th
a
t
is
th
e
i
n
tellect
u
al
p
r
o
p
er
ty
(
I
P
)
co
r
es
o
p
tim
i
ze
d
f
o
r
FP
GA
s
is
g
e
n
e
r
ated
u
s
in
g
FIR
co
m
p
iler
an
d
Fi
g
u
r
e
4
ill
u
s
tr
ates
th
e
b
l
o
ck
d
esi
g
n
to
v
er
if
y
th
e
D
A
F
I
R
f
ilter
r
esp
o
n
s
es
as
o
b
tain
ed
in
t
h
e
F
ig
u
r
e
2
a
n
d
Fig
u
r
e
3.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il 2
0
2
1
:
1
7
0
9
-
1718
1714
(
a)
(
b
)
Fig
u
r
e
3
.
P
lo
t o
f
(
a)
f
r
eq
u
en
c
y
r
esp
o
n
s
e
(
d
B
)
,
(
b
)
p
o
le
-
z
er
o
(P
-
Z
)
d
iag
r
a
m
Fig
u
r
e
4
.
A
s
y
s
te
m
co
n
s
tr
u
c
t o
f
D
A
-
FIR
f
ilter
o
p
ti
m
ized
f
o
r
Z
YNQ
FP
GA
As
d
ep
icted
in
Fi
g
u
r
e
4
t
h
e
R
A
M
b
ased
s
h
i
f
t
r
eg
i
s
ter
is
h
av
i
n
g
1
6
b
it
w
id
t
h
a
n
d
1
6
b
it
d
ep
th
is
co
n
f
i
g
u
r
ed
as
a
cir
cu
lar
b
u
f
f
er
an
d
it
is
i
n
itialized
w
it
h
m
e
m
o
r
y
i
n
itial
izatio
n
r
ad
ix
a
n
d
m
e
m
o
r
y
i
n
itializa
tio
n
v
ec
to
r
o
f
1
6
-
b
it
s
a
s
ar
b
itar
y
w
a
v
e
f
o
r
m
g
en
er
ato
r
a
n
d
o
n
ev
er
y
c
y
cle
o
f
1
0
0
MH
z
clo
ck
,
t
h
e
s
h
i
f
t
R
AM
o
u
tp
u
ts
th
e
la
s
t
s
a
m
p
le
f
ir
s
t
a
n
d
p
r
o
ce
ed
s
to
w
ar
d
s
t
h
e
i
n
itia
l
s
eq
u
e
n
ce
an
d
lo
o
p
s
b
ac
k
.
F
u
r
th
er
t
h
e
co
m
p
lete
DA
FI
R
f
il
ter
is
p
r
o
ce
s
s
ed
u
s
in
g
th
e
Z
YNQ
FP
G
A
as
a
s
p
ec
ial
p
u
r
p
o
s
e
tig
h
tl
y
co
u
p
l
ed
p
r
o
ce
s
s
o
r
.
T
h
e
Fig
u
r
e
5
ill
u
s
tr
ate
s
t
h
e
p
er
f
o
r
m
an
ce
ev
al
u
atio
n
o
f
th
e
d
esi
g
n
w
it
h
b
eh
a
v
io
r
al
s
i
m
u
latio
n
o
f
D
A
FI
R
Fi
lter
o
b
tain
ed
in
Xilin
x
I
SE
en
v
ir
o
n
m
e
n
t
w
it
h
p
h
ase
(
p
h
a
s
e
0
,
3
)
an
d
s
er
ial
(
s
er
ial
o
u
t
1,
2,
3
)
an
d
th
e
Fig
u
r
e
6
d
ep
icts
th
e
p
er
f
o
r
m
a
n
ce
ev
al
u
atio
n
w
it
h
an
al
y
s
is
o
f
f
ilter
co
ef
f
icien
t v
al
u
es.
T
h
e
Fig
u
r
e
7
co
m
p
ar
es
t
h
e
p
r
o
p
o
s
ed
DA
FIR
f
ilter
d
esi
g
n
w
it
h
t
h
e
p
r
ev
io
u
s
d
esi
g
n
s
av
ailab
le
i
n
[
1
8
-
21
]
in
ter
m
s
o
f
n
u
m
b
er
o
f
m
u
ltip
lier
s
v
er
s
u
s
t
h
e
f
i
lter
o
r
d
er
as
d
ep
ic
ted
in
Fig
u
r
e
7
(
a)
.
I
n
Fi
g
u
r
e
7
(
b
)
th
e
n
u
m
b
er
o
f
ad
d
er
s
v
er
s
u
s
o
r
d
er
o
f
Fil
ter
is
i
llu
s
tr
ated
alo
n
g
w
it
h
t
h
e
L
UT
o
p
tim
izatio
n
w
i
th
n
u
m
b
er
o
f
L
UT
s
v
er
s
u
s
o
r
d
er
o
f
f
ilter
in
Fi
g
u
r
e
7
(
c)
,
th
e
Fig
u
r
e
7
(
d
)
r
e
p
r
esen
ts
th
e
n
u
m
b
er
o
f
r
eg
is
ter
s
v
er
s
u
s
t
h
e
f
il
ter
o
r
d
er
.
T
h
e
esti
m
ated
d
ela
y
b
ased
o
n
(
Gate
d
elay
-
DG)
f
o
r
Dis
tr
ib
u
ted
A
r
it
h
m
etic
u
n
it
o
f
L
UT
,
L
UT
-
less
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Desig
n
a
n
d
imp
leme
n
ta
tio
n
o
f
DA
F
I
R
filt
er fo
r
b
io
-
in
s
p
ir
ed
co
mp
u
tin
g
a
r
ch
itectu
r
e
(
B
.
U
.
V
.
P
r
a
s
h
a
n
th
)
1715
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
i
m
p
le
m
en
tatio
n
[
2
2
,
2
3
]
is
as
s
h
o
w
n
in
th
e
Fi
g
u
r
e
8
.
Her
e
th
e
d
ela
y
o
f
th
e
p
r
o
p
o
s
ed
ar
ch
itect
u
r
e
is
1
4
%
(
f
o
r
8
-
o
r
d
er
f
ilter
)
a
n
d
6
4
.
7
%
(
f
o
r
1
4
0
-
o
r
d
er
f
ilter
)
less
d
ela
y
in
co
m
p
ar
is
o
n
o
f
L
UT
-
less
ar
ch
itect
u
r
e
[
2
4
,
2
5
].
Fig
u
r
e
5
.
P
er
f
o
r
m
a
n
ce
ev
al
u
at
io
n
w
ith
s
i
m
u
latio
n
o
f
D
A
-
FI
R
Fil
ter
w
it
h
p
h
a
s
e,
an
d
s
er
ial
o
u
tp
u
t
s
Fig
u
r
e
6
.
P
er
f
o
r
m
a
n
ce
ev
al
u
at
io
n
w
ith
s
i
m
u
latio
n
o
f
D
A
-
FI
R
Fil
ter
w
it
h
f
ilter
co
ef
f
icie
n
ts
Fig
u
r
e
7
.
C
o
m
p
ar
is
o
n
s
o
f
p
r
ev
io
u
s
r
esear
ch
w
i
th
p
r
o
p
o
s
ed
r
e
s
ea
r
ch
w
it
h
f
ilter
o
r
d
er
v
er
s
u
s
(
a)
Nu
m
b
er
o
f
m
u
ltip
lier
s
,
(
b
)
Nu
m
b
er
o
f
a
d
d
er
s
,
(
c)
Nu
m
b
er
o
f
L
UT
’
s
,
(
d
)
Nu
m
b
er
o
f
r
eg
i
s
ter
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il 2
0
2
1
:
1
7
0
9
-
1718
1716
Fig
u
r
e
8
.
E
s
ti
m
ated
g
ate
d
ela
y
o
f
FIR Filt
er
s
f
o
r
D
A
b
ased
ar
ch
itect
u
r
es
T
h
e
T
ab
le
4
illu
s
tr
ate
s
th
e
co
m
p
ar
is
o
n
o
f
th
e
o
b
tain
ed
s
y
n
th
e
s
i
s
r
esu
lt
s
o
f
th
e
p
r
o
p
o
s
e
d
r
esear
ch
w
o
r
k
w
i
th
t
h
e
p
r
ev
io
u
s
l
y
p
u
b
lis
h
ed
liter
atu
r
e.
Her
e
t
h
e
f
ac
to
r
B
is
d
en
o
ted
as
b
it
w
id
t
h
o
f
t
h
e
f
ilter
co
ef
f
icie
n
t
s
.
F
u
r
th
er
e
x
te
n
d
in
g
t
h
is
co
n
ce
p
t
i
n
t
h
e
f
o
l
lo
w
i
n
g
m
at
h
e
m
a
tical
f
o
r
m
u
lae
co
m
p
ar
es
th
e
h
ar
d
w
ar
e
an
d
ti
m
e
co
m
p
le
x
it
ies o
f
o
u
r
p
r
o
p
o
s
ed
DA
-
FI
R
s
tr
u
ct
u
r
es
w
i
th
o
th
er
f
ilter
s
tr
u
ctu
r
e
s
.
Her
e
if
:
B
: =
b
it w
id
th
o
f
f
ilter
co
ef
f
ici
en
ts
,
M:
=
i
m
a
g
e
w
id
th
,
T
M
: =
d
elay
o
f
m
u
ltip
lier
,
T
P
A
: =
d
ela
y
o
f
p
ar
al
lel
ad
d
er
)
T
h
en
:
T
1
=T
PA
+
2
.
T
FA
(
lo
g
2
N
−1
)
,
T
DA
HL
U
T
=2
T
PA
,
T
PU
=
T
MUX
+
T
SAB
,
T
SAB
= T
FA
+ T
XOR
+
T
D
T
ab
le
4
.
Sy
n
t
h
e
s
is
r
es
u
lt
s
co
m
p
ar
is
o
n
o
f
p
r
o
p
o
s
ed
s
tr
u
ctu
r
e
w
it
h
p
ast
w
o
r
k
s
D
e
si
g
n
M
i
n
i
m
u
m
S
a
m
p
l
i
n
g
P
e
r
i
o
d
(
n
s)
A
r
e
a
(
μm
2
)
P
o
w
e
r
(
mw
)
A
r
e
a
D
e
l
a
y
P
r
o
d
u
c
t
(
μm
2
n
s)
En
e
r
g
y
p
e
r
o
u
t
p
u
t
T
h
r
o
u
g
h
p
u
t
(
M
H
z
)
[
2
6
]
B
=
8
,
1
1
.
7
9
B
=
1
6
,
1
3
.
3
1
,
7
2
0
,
9
6
2
.
1
4
7
1
1
2
,
6
6
1
,
7
8
3
.
5
2
5
0
.
0
1
0
6
1
8
1
.
1
6
5
2
,
5
3
7
,
5
5
8
1
0
,
5
5
0
,
4
3
1
3
1
2
.
5
6
5
6
6
.
1
4
6
7
8
.
1
9
1
2
0
0
[
2
7
]
B
=
8
,
1
3
.
0
1
B
=
1
6
,
1
4
.
6
5
3
5
6
,
2
9
3
.
0
2
1
6
1
,
1
5
4
,
1
2
3
.
0
8
8
0
9
.
3
8
0
7
2
6
.
9
9
4
1
4
,
6
3
6
,
0
8
4
1
6
,
9
0
7
,
9
0
3
1
3
1
9
.
0
7
3
1
2
.
5
6
7
6
.
8
0
6
8
.
2
5
[
2
8
]
B
=
3
,
2
.
1
1
B
=
7
,
2
.
3
4
B
=
1
5
,
2
.
4
1
98
,
266
.
83
4
1
2
,
2
6
7
.
34
1
,
7
3
4
,
7
4
3
.
62
2
.
4
7
8
.
9
1
3
6
.
4
8
2
0
7
,
3
4
3
.
01
9
6
4
,
7
0
4
.
78
4
,
1
8
0
,
7
3
2
.
12
1
2
3
5
4
5
5
5
18
,
240
-
T
h
i
s W
o
r
k
B
=
8
,
6
.
7
3
B
=
1
6
,
6
.
9
2
6
5
1
,
6
1
5
.
4
7
0
9
4
,
9
3
6
,
0
8
1
.
6
7
5
9
2
0
.
1
0
6
9
1
0
2
.
3
4
3
2
5
3
1
,
8
8
0
2
,
1
3
1
,
7
7
0
1
7
5
.
6
6
3
1
9
.
8
2
1
3
2
5
.
1
1
2
3
2
5
.
4
8
T
h
e
T
MUX
,
T
FA
,
T
XOR
an
d
T
D
ar
e
th
e
d
ela
y
o
f
MU
X,
f
u
ll
ad
d
er
,
XO
R
g
ate
a
n
d
D
f
lip
-
f
lo
p
,
r
esp
ec
tiv
el
y
.
T
h
is
co
m
p
ar
i
s
o
n
o
f
ti
m
e
co
m
p
le
x
it
ies
a
n
d
h
a
r
d
w
ar
e
o
f
p
r
o
p
o
s
ed
DA
-
FI
R
d
esig
n
s
w
i
th
o
th
er
f
ilter
d
esi
g
n
s
is
as
d
ep
icted
in
T
a
b
le
5
.
T
h
e
T
ab
le
4
illu
s
tr
a
tes
o
u
r
b
est
s
o
lu
tio
n
an
d
co
m
p
ar
es
th
e
o
b
tain
ed
p
ar
am
eter
s
o
f
o
u
r
s
y
n
t
h
es
is
r
esu
lt
s
w
it
h
p
r
ev
io
u
s
w
o
r
k
s
i
n
ter
m
s
o
f
n
u
m
er
ical
v
al
u
es
o
f
(
MSP
)
-
Mi
n
i
m
u
m
Sa
m
p
li
n
g
P
er
io
d
(
n
s
)
,
A
r
ea
(
μm
2
)
,
P
o
w
er
(
m
w
)
,
(
A
DP
)
-
A
r
e
a
Dela
y
P
r
o
d
u
ct
(
μm
2
ns
)
,
E
n
er
g
y
p
er
o
u
tp
u
t,
T
h
r
o
u
g
h
p
u
t(
MH
z)
[
29
,
3
0
]
.
Fu
r
t
h
er
th
e
T
ab
le
5
c
o
m
p
ar
es
th
e
o
b
tain
ed
r
esu
l
ts
i
n
o
u
r
w
o
r
k
w
i
th
p
r
ev
io
u
s
w
o
r
k
s
w
it
h
n
u
m
er
icall
y
ad
d
r
ess
i
n
g
w
i
th
m
at
h
e
m
atica
l
f
o
r
m
u
las
o
f
v
ar
io
u
s
p
ar
a
m
eter
s
s
u
ch
as
T
h
r
o
u
g
h
p
u
t,
m
u
ltip
lier
s
,
ad
d
er
s
a
n
d
r
eg
is
te
r
s
[3
1
,
3
2
]
.
T
h
e
i
m
p
le
m
e
n
tati
o
n
o
f
m
u
lt
i
-
co
r
e
co
m
p
u
ti
n
g
s
y
s
t
e
m
is
d
o
n
e
o
n
t
h
e
Z
YNQ
p
lat
f
o
r
m
w
i
th
t
h
e
u
s
e
o
f
VE
R
I
L
OG
la
n
g
u
a
g
e
to
p
r
o
g
r
a
m
a
n
d
co
m
p
ile
th
e
f
r
a
m
e
wo
r
k
[3
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Desig
n
a
n
d
imp
leme
n
ta
tio
n
o
f
DA
F
I
R
filt
er fo
r
b
io
-
in
s
p
ir
ed
co
mp
u
tin
g
a
r
ch
itectu
r
e
(
B
.
U
.
V
.
P
r
a
s
h
a
n
th
)
1717
T
ab
le
5
.
T
im
e
co
m
p
le
x
ities
a
n
d
h
ar
d
w
ar
e
o
f
p
r
o
p
o
s
ed
DA
-
F
I
R
d
esig
n
s
w
i
th
o
t
h
er
d
esig
n
s
D
e
si
g
n
T
h
r
o
u
g
h
p
u
t
M
u
l
t
i
p
l
i
e
r
s
A
d
d
e
r
s
R
e
g
i
st
e
r
s
[
34
]
L/
(
T
M
+
T
1
)
M
2
M
2
−
1
(
M
+
N
)(
M
−
1)
[3
5
]
1
/
(
T
M
+2
T
PA
)
M
N
2
L
(
[
N
x
N
]
−
1)
(
M
+
N
)(
M
−
1)
T
h
i
s
W
o
r
k
N
/
(3
T
PA
+
2
.
B
.
T
PU
)
-
N
(
7
(
L
+
N
)
−
2
6
)
+
L
((3
M
2
/
5
)
−
1)
N
(
M
−
1
)
+
N
.
L
c
5.
CO
NCLU
SI
O
NS
T
h
e
VHDL
is
u
s
ed
i
m
p
le
m
e
n
t
t
h
e
p
r
o
p
o
s
ed
D
A
f
i
n
ite
i
m
p
ls
e
r
e
s
p
o
n
s
e
f
i
lter
a
n
d
t
h
e
d
esig
n
is
v
er
if
ied
u
s
i
n
g
s
i
m
u
la
tio
n
.
T
h
e
ca
lcu
lated
th
eo
r
etica
l
v
al
u
e
s
o
f
th
e
d
esi
g
n
m
atc
h
w
it
h
o
b
tain
ed
p
r
ac
tical
v
alu
e
s
i
n
t
h
e
r
ea
l
ti
m
e
s
i
m
u
la
tio
n
en
v
ir
o
n
m
e
n
t.
T
w
o
o
p
ti
m
i
za
tio
n
alg
o
r
it
h
m
s
ar
e
p
r
o
p
o
s
ed
an
d
th
e
r
es
u
lti
n
g
o
p
tim
izatio
n
s
ar
e
i
n
co
r
p
o
r
ate
d
in
to
L
UT
la
y
er
a
n
d
ar
ch
itec
tu
r
e
ex
tr
ac
tio
n
s
o
f
d
es
ig
n
ed
b
lo
ck
.
T
h
e
p
r
o
p
o
s
ed
w
o
r
k
o
f
f
er
s
a
n
o
p
ti
m
ized
d
esi
g
n
in
th
e
f
o
r
m
o
f
av
er
a
g
e
r
ed
u
ctio
n
s
o
f
n
u
m
b
er
o
f
L
UT
,
r
ed
u
ctio
n
in
p
o
p
u
lated
s
lices
a
n
d
r
ed
u
ctio
n
i
n
t
h
e
n
u
m
b
er
o
f
g
ate
s
f
o
r
D
A
-
f
i
n
i
te
i
m
p
u
ls
e
r
e
s
p
o
n
s
e
f
il
ter
i
m
p
le
m
en
ta
tio
n
.
T
h
i
s
r
esear
ch
p
av
es
a
w
a
y
f
o
r
b
io
in
s
p
ir
ed
co
m
p
u
ti
n
g
ar
ch
ite
ctu
r
e
w
it
h
r
ec
o
n
f
ig
u
r
ab
le
co
m
p
u
ti
n
g
s
tr
ate
g
ie
s
d
esig
n
ed
to
av
o
id
co
m
p
u
tatio
n
all
y
i
n
te
n
s
iv
e
o
p
er
atio
n
s
,
ac
h
iev
in
g
th
e
d
esire
d
s
p
ec
if
icati
o
n
s
w
it
h
r
esp
ec
t
to
f
le
x
ib
ilit
y
,
ti
m
in
g
,
an
d
p
er
f
o
r
m
an
ce
.
RE
F
E
R
E
NC
E
S
[1
]
C.
S
.
V
i
n
it
h
a
a
n
d
R.
K
.
S
h
a
rm
a
,
“
Ne
w
a
p
p
ro
a
c
h
to
lo
w
-
a
re
a
,
lo
w
-
late
n
c
y
m
e
m
o
r
y
-
b
a
s
e
d
s
y
sto
li
c
a
rc
h
it
e
c
tu
re
f
o
r
F
IR
f
il
ters
,
”
J
o
u
rn
a
l
o
f
In
f
o
rm
a
ti
o
n
a
n
d
Op
t
imiza
ti
o
n
S
c
ien
c
e
s,
vol
.
4
0
,
n
o
.
2
,
p
p
.
2
4
7
-
2
6
2
,
2
0
1
9
.
[2
]
A
.
A
g
a
r
w
a
l
a
n
d
L
.
Bo
p
a
n
n
a
,
“
L
o
w
Late
n
c
y
A
re
a
-
E
ff
icie
n
t
Distrib
u
te
d
A
rit
h
m
e
ti
c
Ba
s
e
d
M
u
lt
i
-
Ra
te
F
il
ter
A
rc
h
it
e
c
tu
re
f
o
r
S
DR Re
c
e
iv
e
rs,
”
J
o
u
rn
a
l
o
f
Circ
u
i
ts S
y
ste
ms
a
n
d
Co
mp
u
ter
s
,
v
o
l
.
2
7
,
n
o
.
8
,
p
p
.
1
-
2
1
,
2
0
1
8
.
[3
]
T
.
X
u
,
e
t
a
l.
,
“
Ef
f
ici
e
n
t
re
a
l
-
ti
m
e
d
ig
it
a
l
su
b
c
a
rrier cro
ss
-
c
o
n
n
e
c
t
b
a
se
d
o
n
d
istri
b
u
ted
a
rit
h
m
e
ti
c
DS
P
a
lg
o
ri
th
m
,
”
in
J
o
u
rn
a
l
o
f
L
i
g
h
tw
a
v
e
T
e
c
h
n
o
lo
g
y
,
v
o
l.
3
8
,
n
o
.
1
3
,
p
p
.
3
4
9
5
-
35
0
5
,
20
20
.
[4
]
D.
Da
tt
a
,
e
t
a
l.
,
“
F
P
G
A
i
m
p
le
m
e
n
tatio
n
o
f
h
ig
h
p
e
rf
o
r
m
a
n
c
e
d
ig
it
a
l
d
o
w
n
c
o
n
v
e
rter
f
o
r
so
f
t
wa
re
d
e
f
in
e
d
ra
d
io
,
”
M
icr
o
sy
ste
m T
e
c
h
n
o
lo
g
ies
,
2
0
1
9
.
[5
]
B.
K.
M
o
h
a
n
ty
a
n
d
P
ra
m
o
d
K
.
M
.
,
“
A
n
Eff
icie
n
t
P
a
ra
ll
e
l
DA
-
B
a
se
d
F
ix
e
d
-
W
id
th
De
sig
n
A
p
p
ro
x
In
n
e
r
-
P
ro
d
u
c
t
Co
m
p
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ver
y
L
a
rg
e
S
c
a
le In
te
g
ra
ti
o
n
S
y
ste
ms
,
v
o
l
.
28
,
n
o
.
5
,
p
p
.
1
2
2
1
-
1
2
2
9
,
2
0
2
0
.
[6
]
P
.
Ku
m
a
r,
e
t
a
l.
,
“
A
S
IC
i
m
p
le
m
e
n
tatio
n
o
f
a
re
a
e
ff
icie
n
t
h
ig
h
th
ro
u
g
h
p
u
t
2
-
D
IIR
f
il
ter
u
s
in
g
d
istri
b
u
ted
a
rit
h
m
e
ti
c
,
”
Circ
u
it
s S
y
st.
S
i
g
n
a
l
Pro
c
e
ss
,
v
o
l
.
3
7
,
n
o
.
7
,
p
p
.
2
9
3
4
-
2
9
5
7
,
2
0
1
8
.
[7
]
G
.
N.
J
y
o
th
i,
e
t
a
l.
,
“
A
S
IC
im
p
le
m
e
n
tatio
n
o
f
d
istri
b
u
ted
a
rit
h
m
e
ti
c
b
a
se
d
F
IR
f
il
ter
u
sin
g
RNS
f
o
r
h
ig
h
sp
e
e
d
D
S
P
s
y
ste
m
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
p
e
e
c
h
T
e
c
h
n
o
lo
g
y
,
v
o
l
.
2
3
,
p
p
.
259
-
2
6
4
,
2
0
2
0
.
[8
]
G
.
N
.
J
y
o
th
i
a
n
d
S
.
S
rid
e
v
i,
“
Hig
h
sp
e
e
d
a
n
d
lo
w
a
r
e
a
d
e
c
isio
n
f
e
e
d
-
b
a
c
k
e
q
u
a
li
z
e
r
w
it
h
n
o
v
e
l
m
e
m
o
r
y
les
s
d
istri
b
u
ted
a
rit
h
m
e
ti
c
f
il
ter
,”
M
u
lt
ime
d
ia
T
o
o
ls a
n
d
Ap
p
li
c
a
ti
o
n
s,
v
o
l
.
78,
n
o
.
2
3
,
p
p
.
79
-
9
3
,
2
0
1
9
.
[9
]
P
.
V
.
P
.
S
u
n
d
a
r,
e
t
a
l.
,
“
L
o
w
p
o
w
e
r
a
r
e
a
e
ff
icie
n
t
a
d
a
p
ti
v
e
F
IR
f
il
ter
f
o
r
h
e
a
rin
g
a
id
s
u
sin
g
d
istri
b
u
ted
a
rit
h
m
e
ti
c
a
rc
h
it
e
c
tu
re
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
S
p
e
e
c
h
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
,
p
p
.
1
-
1
0
,
2
0
2
0
.
[1
0
]
M
.
R.
A
h
m
e
d
a
n
d
B.
K.
S
u
jath
a
,
“
A
r
e
v
ie
w
o
n
m
e
th
o
d
s,
iss
u
e
s
a
n
d
c
h
a
ll
e
n
g
e
s
in
n
e
u
ro
m
o
rp
h
ic
e
n
g
in
e
e
rin
g
,”
2015
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mm
u
n
ica
t
io
n
s a
n
d
S
ig
n
a
l
Pro
c
e
ss
in
g
(
ICCS
P)
,
2
0
1
5
,
p
p
.
0
8
9
9
-
0
9
0
3
.
[1
1
]
K.
V
ij
e
t
h
a
a
n
d
B.
R
.
Na
ik
,
“
Hig
h
p
e
rf
o
r
m
a
n
c
e
a
re
a
e
ff
icie
n
t
D
A
b
a
se
d
F
IR
f
il
ter
f
o
r
c
o
n
c
u
rre
n
t
d
e
c
isio
n
f
e
e
d
b
a
c
k
e
q
u
a
li
z
e
r
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
S
p
e
e
c
h
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
3
,
p
p
.
1
-
7
,
2
0
2
0
.
[1
2
]
X
.
L
o
u
,
e
t
a
l.
,
“
L
o
w
e
r
b
o
u
n
d
a
n
a
ly
sis
p
e
rtu
rb
a
ti
o
n
c
rit
ica
l
p
a
th
f
o
r
a
re
a
-
ti
m
e
e
ff
icie
n
t
m
u
lt
ip
le
c
o
n
sta
n
t
m
u
lt
ip
li
c
a
ti
o
n
s,”
IE
EE
T
r
a
n
s.C
o
mp
u
t.
Ai
d
e
d
De
s.
In
te
g
r.
Circ
u
it
s
S
y
st
,
v
o
l
.
3
6
,
n
o
.
2
,
p
p
.
3
1
3
-
3
2
4
,
2
0
1
6
.
[1
3
]
M.
D’A
rc
o
,
e
t
a
l.
,
“
Dig
it
a
l
Circu
it
f
o
r
S
e
a
m
les
s
Re
sa
m
p
li
n
g
A
DC
Ou
tp
u
t
S
trea
m
s
,”
S
e
n
so
rs
,
v
o
l
.
2
0
,
n
o
.
6
,
p
.
1
6
1
9
,
2
0
2
0
.
[1
4
]
M
.
R.
A
h
m
e
d
a
n
d
B.
K.
S
u
jath
a
,
“
A
re
v
ie
w
o
f
re
in
f
o
rc
e
m
e
n
t
lea
rn
in
g
in
n
e
u
ro
m
o
rp
h
ic
V
L
S
I
c
h
ip
s
u
sin
g
c
o
m
p
u
tatio
n
a
l
c
o
g
n
it
iv
e
n
e
u
ro
sc
ien
c
e
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
i
n
Co
mp
u
ter
a
n
d
Co
mm
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
,
v
o
l
.
2
,
n
o
.
8
,
p
p
.
3
3
1
5
-
3
3
2
0
,
2
0
1
3
.
[1
5
]
L
.
Ca
o
,
e
t
a
l.
,
“
Ha
rd
w
a
re
-
e
ff
i
c
ie
n
t
im
p
le
m
e
n
tatio
n
o
f
d
ig
it
a
l
F
IR
f
il
ter
u
sin
g
fa
st
f
irst
-
o
rd
e
r
m
o
m
e
n
t
a
lg
o
rit
h
m
,
”
M
IPP
R2
0
1
7
:
Pa
ra
ll
e
l
Pro
c
e
ss
o
f
Ima
g
e
s,Op
ti
miz
a
ti
o
n
T
e
c
h
n
iq
u
e
s;
a
n
d
M
e
d
ica
l
Ima
g
in
g
,
v
o
l.
1
0
6
1
0
,
2
0
1
8
.
[1
6
]
H.
Ya
o
,
e
t
a
l.
,
“
E
x
p
e
rime
n
tal
d
e
m
o
n
stra
ti
o
n
o
f
4
-
P
A
M
f
o
r
h
ig
h
-
sp
e
e
d
in
d
o
o
r
f
re
e
-
sp
a
c
e
O
W
c
o
m
m
u
n
ica
ti
o
n
b
a
se
d
o
n
c
a
sc
a
d
e
F
IR
-
L
M
S
a
d
a
p
ti
v
e
e
q
u
a
li
z
e
r,
”
Op
ti
c
s Co
mm
u
n
ica
ti
o
n
s,
v
o
l
.
4
2
6
,
p
p
.
4
9
0
-
4
9
6
,
2
0
1
8
.
[1
7
]
E.
Ch
it
ra
,
e
t
a
l.
,
“
A
n
a
ly
sis
a
n
d
im
p
le
m
e
n
tatio
n
o
f
h
ig
h
p
e
rf
o
rm
a
n
c
e
re
c
o
n
f
ig
u
ra
b
le
F
IR
f
il
ter
u
sin
g
d
istri
b
u
ted
a
rit
h
m
e
ti
c
,
”
W
ir
e
les
s P
e
rs
o
n
a
l
Co
mm
u
n
ic
a
ti
o
n
s,
v
o
l
.
1
0
2
,
n
o
.
4
,
2
0
1
8
.
[1
8
]
H.
Jia
n
g
,
e
t
a
l.
,
“
A
re
v
ie
w
,
c
las
s
if
ica
ti
o
n
,
a
n
d
c
o
m
p
a
ra
ti
v
e
e
v
a
lu
a
ti
o
n
o
f
a
p
p
r
o
x
im
a
te
a
rit
h
m
e
ti
c
c
ircu
it
s,
”
ACM
J
o
u
rn
a
l
o
n
Eme
rg
i
n
g
T
e
c
h
n
o
lo
g
i
e
s in
Co
mp
u
ti
n
g
S
y
ste
ms
(
J
ET
C),
v
o
l
.
1
3
,
n
o
.
4
,
2
0
1
7
.
[1
9
]
G
.
S
a
n
c
h
e
z
,
e
t
a
l.
,
“
A
h
ig
h
ly
s
c
a
l
a
b
le p
a
ra
ll
e
l
sp
ik
e
-
b
a
se
d
d
ig
it
a
l
n
e
u
ro
m
o
rp
h
ic arc
h
it
e
c
tu
re
f
o
r
h
ig
h
-
o
rd
e
r
f
ir
f
il
ters
u
sin
g
L
M
S
a
d
a
p
ti
v
e
a
lg
o
rit
h
m
,
”
Ne
u
ro
c
o
mp
u
ti
n
g
,
v
o
l
.
3
3
0
,
2
0
1
9
.
[2
0
]
B.
K.
M
o
h
a
n
ty
,
e
t
a
l.
,
“
L
UT
Op
ti
m
iza
ti
o
n
f
o
r
D.A
-
Ba
s
e
d
Blo
c
k
L
e
a
st
M
e
a
n
S
q
u
a
re
A
d
a
p
ti
v
e
F
il
ter,”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ver
y
L
a
rg
e
S
c
a
l
e
In
teg
ra
ti
o
n
S
y
ste
ms
,
v
o
l.
2
4
,
n
o
.
5
,
p
p
.
1
9
2
6
-
1
9
3
5
,
2
0
1
6
.
[2
1
]
M.
S
h
a
rm
a
a
n
d
S.
K.
S
in
g
h
,
“
Ne
w
T
e
c
h
n
iq
u
e
Ba
se
d
P
e
a
sa
n
t
M
u
lt
ip
li
c
a
ti
o
n
f
o
r
Ef
f
c
ien
t
S
ig
n
a
l
P
ro
c
e
ss
in
g
A
p
p
li
c
a
ti
o
n
s
,
”
I
n
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
(
IJ
EE
CS
)
,
v
o
l.
8
,
n
o
.
3
,
pp.
7
2
6
-
7
2
9
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il 2
0
2
1
:
1
7
0
9
-
1718
1718
[2
2
]
M
.
T
.
Kh
a
n
a
n
d
R
.
A
.
S
h
a
ik
,
“
Op
ti
m
a
l
c
o
m
p
lex
it
y
a
rc
h
it
e
c
tu
re
s
f
o
r
p
ip
e
li
n
e
d
D.A
-
b
a
se
d
L
M
S
a
d
a
p
ti
v
e
f
il
ter,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Circ
u
it
s
a
n
d
S
y
ste
ms
I:
Reg
u
la
r
Pa
p
e
rs
,
v
o
l
.
6
6
,
n
o
.
2
,
p
p
.
6
3
0
-
6
4
2
,
2
0
1
8
.
[2
3
]
H.
Jia
n
g
,
e
t
a
l.
,
“
A
h
ig
h
-
p
e
rf
o
r
m
a
n
c
e
a
n
d
e
n
e
rg
y
-
e
ff
icie
n
t
F
IR
a
d
a
p
ti
v
e
f
il
ter
u
sin
g
a
p
p
ro
x
ima
t
e
D.
A
c
ircu
it
s,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Circ
u
it
s
a
n
d
S
y
ste
ms
I:
Reg
u
la
r
Pa
p
e
rs
,
v
o
l
.
6
6
,
n
o
.
1
,
p
p
.
3
1
3
-
3
2
6
,
2
0
1
8
.
[2
4
]
M.
S
u
m
a
lath
a
,
e
t
a
l.
,
“
L
o
w
p
o
w
e
r
a
n
d
lo
w
a
re
a
V
L
S
I
i
m
p
le
m
e
n
tatio
n
o
f
v
e
d
ic
d
e
sig
n
F
IR
f
il
ter
f
o
r
ECG
si
g
n
a
l
d
e
-
n
o
isi
n
g
,
”
M
icr
o
p
ro
c
e
ss
o
rs
a
n
d
M
icr
o
sy
ste
ms
,
v
o
l.
7
1
,
p
p
.
1
-
1
3
,
2
0
1
9
.
[2
5
]
R.
K.
S
a
rm
a
,
e
t
a
l.
,
“
A
n
o
v
e
l
ti
m
e
-
sh
a
r
e
d
a
n
d
lu
t
-
les
s
p
i
p
e
li
n
e
d
a
rc
h
it
e
c
tu
re
f
o
r
l
m
s
a
d
a
p
ti
v
e
f
il
ter,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ver
y
L
a
rg
e
S
c
a
l
e
In
teg
ra
ti
o
n
S
y
ste
ms
,
v
o
l
.
2
8
,
n
o
.
1
,
p
p
.
1
8
8
-
1
9
7
,
2
0
1
9
.
[2
6
]
B.
U.
V
.
P
ra
sh
a
n
t
h
a
n
d
M
.
R
.
A
h
m
e
d
,
“
D
e
sig
n
a
n
d
P
e
rf
o
rm
a
n
c
e
A
n
a
l
y
sis
o
f
A
rti
f
ici
a
l
Ne
u
ra
l
Ne
tw
o
rk
Ba
s
e
d
A
rti
f
icia
l
S
y
n
a
p
se
f
o
r
Bio
-
in
sp
i
re
d
Co
m
p
u
ti
n
g
,
”
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mp
u
t
a
ti
o
n
a
l
Vi
sio
n
a
n
d
B
i
o
In
sp
ire
d
C
o
mp
u
ti
n
g
,
S
p
ri
n
g
e
r,
Ch
a
m
,
2
0
1
9
,
p
p
.
1
2
9
4
-
1
3
0
2
.
[2
7
]
B.
U.
V
.
P
ra
sh
a
n
th
a
n
d
M
.
R
.
A
h
m
e
d
,
“
F
P
G
A
I
m
p
le
m
e
n
tatio
n
o
f
Bio
-
in
s
p
ired
C
o
m
p
u
ti
n
g
Ba
se
d
D.L
M
o
d
e
l,
”
Ad
v
a
n
c
e
s i
n
Distrib
u
ted
C
o
mp
u
ti
n
g
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
in
g
.
S
p
ri
n
g
e
r,
S
in
g
a
p
o
re
,
p
p
.
2
3
7
-
2
4
5
,
2
0
2
0
.
[2
8
]
M
.
Z.
A
lo
m
,
e
t
a
l.
,
“
A
sta
te
-
of
-
th
e
-
a
rt
su
rv
e
y
o
n
d
e
e
p
lea
rn
i
n
g
th
e
o
ry
a
n
d
a
rc
h
it
e
c
tu
re
s,
”
El
e
c
tro
n
ic
s,
v
o
l
.
8
,
n
o
.
3
,
p.
2
9
2
,
2
0
1
9
.
[2
9
]
A
.
M
a
h
a
b
u
b
,
“
De
sig
n
a
n
d
im
p
lem
e
n
tatio
n
o
f
c
o
st
-
e
ff
e
c
ti
v
e
si
m
p
le
F
IR
f
il
ter
f
o
r
EE
G
si
g
n
a
l
o
n
F
P
GA
,
”
W
o
rld
S
c
ien
ti
fi
c
Ne
ws,
v
o
l
.
1
2
5
,
p
p
.
1
-
1
7
,
2
0
1
9
.
[3
0
]
A
.
M
a
h
a
b
u
b
,
“
De
sig
n
a
n
d
Im
p
lem
e
n
tatio
n
o
f
a
No
v
e
l
Co
m
p
lete
F
il
ter
f
o
r
EE
G
A
p
p
li
c
a
ti
o
n
o
n
F
P
G
A
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Im
a
g
e
,
G
ra
p
h
ics
a
n
d
S
ig
n
a
l
Pro
c
e
ss
in
g
,
v
o
l.
1
0
,
n
o
.
6
,
p
p
.
2
2
-
3
0
,
2
0
1
8
.
[3
1
]
B.
Kh
u
rsh
id
a
n
d
R
.
N
.
M
ir,
“
A
n
e
ff
icie
n
t
F
IR
f
il
ter
stru
c
tu
re
b
a
se
d
o
n
tec
h
n
o
lo
g
y
-
o
p
ti
m
ize
d
m
u
lt
ip
ly
-
a
d
d
e
r
u
n
it
targ
e
ti
n
g
L
U
T
-
b
a
se
d
F
P
G
As
,
”
Circ
u
it
s,
S
y
ste
ms
,
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
in
g
,
v
o
l
.
3
6
,
n
o
.
2
,
p
p
.
6
0
0
-
6
3
9
,
2
0
1
7
.
[3
2
]
K.
S
.
Re
d
d
y
a
n
d
H.
S
u
re
sh
,
“
A
Lo
w
-
P
o
w
e
r
V
L
S
I
Im
p
le
m
e
n
tatio
n
o
f
RF
IR
F
il
ter
De
sig
n
u
sin
g
Ra
d
i
x
-
2
A
lg
o
rit
h
m
w
it
h
L
CS
LA
,
”
IET
E
J
o
u
rn
a
l
o
f
R
e
se
a
rc
h
,
p
p
.
1
-
1
0
,
2
0
1
9
.
[3
3
]
B.
S
rik
a
n
th
,
e
t
a
l
.
,
“
T
h
e
e
n
h
a
n
c
e
m
e
n
t
o
f
se
c
u
rit
y
m
e
a
su
re
s
in
a
d
v
a
n
c
e
d
e
n
c
ry
p
ti
o
n
sta
n
d
a
rd
u
sin
g
d
o
u
b
le
p
re
c
isio
n
f
lo
a
ti
n
g
p
o
in
t
m
u
lt
ip
li
c
a
ti
o
n
m
o
d
e
l,
”
Wi
ley
-
T
ra
n
sa
c
ti
o
n
s o
n
Eme
rg
in
g
T
e
lec
o
mm
u
n
ica
ti
o
n
s T
e
c
h
n
o
lo
g
ies
,
p
p
.
1
-
13
,
2
0
2
0
.
[3
4
]
W
.
Zh
a
o
,
e
t
a
l.
,
“
A
d
iv
isio
n
-
f
re
e
a
n
d
v
a
riab
le
-
re
g
u
lariz
e
d
L
M
S
-
b
a
se
d
g
e
n
e
ra
li
z
e
d
sid
e
lo
b
e
c
a
n
c
e
ll
e
r
f
o
r
a
d
a
p
ti
v
e
b
e
a
m
f
o
r
m
in
g
a
n
d
it
s e
ff
icie
n
t
h
a
rd
w
a
re
re
a
li
z
a
ti
o
n
,
”
IEE
E
Acc
e
ss
,
v
o
l.
6
,
p
p
.
6
4
4
7
0
-
6
4
4
8
5
,
2
0
1
8
.
[3
5
]
S.
Dix
it
a
n
d
D
.
Na
g
a
ria,
“
L
M
S
A
d
a
p
ti
v
e
F
il
ters
f
o
r
No
ise
Ca
n
c
e
ll
a
ti
o
n
:
A
Re
v
ie
w
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
,
vol
.
7
,
n
o
.
5,
p
p
.
2
5
2
0
-
2
5
2
9
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.