
Appendix B: Instruction Execution Times
(Continued)
TABLE B-3. Average Instruction Execution Times with No Wait-States
(Continued)
Instruction
Number of Clock Cycles
Notes
BITWT
16
28
28
a
(shift
b
8)
Shift
e
0
Shift
e
1
x
8
Shift
l
8
Shift
e
0
x
8, Pre-Read
Shift
e
0
x
8, No Pre-Read
Shift
l
8, Pre-Read
Shift
l
8, No Pre-Read
EXTBLT
35
a
(19
a
12
*
width )
*
height
35
a
(13
a
12
*
width )
*
height
35
a
(17
a
13
*
width )
*
height
35
a
(11
a
13
*
width )
*
height
MOVMPB,W
16
a
7
*
R2
MOVMPD,W
16
a
8
*
R2
SBITS
39
42
R2
s
25
R2
l
25
SBITP
8
a
(34
*
R2)
TABLE B-4. Average Instruction Execution Times with Wait-States
Instruction
Number of Clock Cycles
Notes
BBOR
42
a
((107
a
2
*
Twaitblt)
a
(44
a
Twaitblt)
*
(width
b
2))
*
height
BBXOR
44
a
((107
a
2
*
Twaitblt)
a
(44
a
Twaitblt)
*
(width
b
2))
*
height
BBAND
45
a
((111
a
2
*
Twaitblt)
a
(44
a
Twaitblt)
*
(width
b
2))
*
height
BBFOR
48
a
((74
a
2
*
Twaitblt)
a
(32
a
Twaitblt)
*
(width
b
2))
*
height
BBSTOD
66
a
((170
a
2
*
Twaitblt)
a
(60
a
Twaitblt)
*
(width
b
2))
*
height
BITWIT
16
a
Twaitrds
a
Twaitrdd
a
Twaitwrd
28
a
Twaitblt
Shift
e
0
Shift
e
1
x
8
EXTBLT
35
a
(19
a
(12
a
(Twaitrds
a
Twaitrdd
a
Twaitwrd) )
*
width )
*
height
35
a
(13
a
(12
a
(Twaitrds
a
Twaitrdd
a
Twaitwrd))
*
width )
*
height
Pre-Read
No Pre-Read
MOVMPB,W
16
a
7
*
R2
a
(Twaitwr
b
1)
*
R2
16
a
7
*
R2
Twaitwr
l
1
Twaitwr
s
1
MOVMPD
16
a
8
*
R2
a
Twaitwr
*
R2
SBITS
39
a
(2
*
Twaitrdd
a
2
*
Twaitwrd
a
2
*
Twaitrds)
42
a
(2
*
Twaitrdd
a
2
*
Twaitrds)
R2
s
25
R2
l
25
SBITP
8
a
(34
*
R2)
a
((Twaitrdd
a
Twaitwrd)
*
R2)
B.3 DSPM INSTRUCTIONS
A DSPM instruction execution starts with the CPU core writ-
ing to the CTL register. The execution time is counted from
state T3 of this transaction until all the results are ready,
either in the accumulator or in the coefficient RAM array.
The execution times, in clock cycles, for the various DSPM
instructions are listed in Table B-5.
It is assumed that External Hold Requests do not occur in
the middle of a VCMAD, VCMUL or VCMAC instruction.
The parameters n and w represent the number of elements
in the vector instruction and the number of wait states ap-
plied to each DSPM bus transaction respectively.
TABLE B-5. DSPM Instruction Execution Times
Instruction
Number of Clock Cycles
VCMAD
VCMUL
VCMAC
VCMAG
9
a
8
*
n
a
2
*
n
*
w
9
a
8
*
n
a
2
*
n
*
w
6
a
8
*
n
a
2
*
n
*
w
5
a
8
*
n
86