Texas Instruments TMS320C6000 Programmer's Manual page 189

Software Pipelining
Example 6–30. Assembly Code for Fixed-Point Dot Product (Software Pipelined With
Removal of Prolog and Epilog)
MVK .S1
[A1] SUB .S1
|| ZERO .L1
|| ZERO .L2
[A1] SUB .S1
||[A1] B .S2
|| ZERO .L1
|| ZERO .L2
[A1] SUB .S1
||[A1] B .S2
|| ZERO .L1
|| ZERO .L2
[A1] SUB .S1
||[A1] B .S2
[A1] SUB .S1
||[A1] B .S2
[A1] SUB .S1
||[A1] B .S2
LOOP:
ADD .L1
|| ADD .L2
|| MPY .M1X
|| MPYH .M2X
||[A1] SUB .S1
||[A1] B .S2
|| LDW .D1
|| LDW .D2
; Branch occurs here
ADD
6-52
57,A1 ; set up loop counter
A1,1,A1 ; decrement loop counter
A7 ; zero out sum0 accumulator
B7 ; zero out sum1 accumulator
A1,1,A1 ;* decrement loop counter
LOOP ; branch to loop
A6 ; zero out add input
B6 ; zero out add input
A1,1,A1 ;** decrement loop counter
LOOP ;* branch to loop
A2 ; zero out mpy input
B2 ; zero out mpy input
A1,1,A1 ;*** decrement loop counter
LOOP ;** branch to loop
A1,1,A1 ;**** decrement loop counter
LOOP ;*** branch to loop
A1,1,A1 ;***** decrement loop counter
LOOP ;**** branch to loop
A6,A7,A7 ; sum0 += (ai * bi)
B6,B7,B7 ; sum1 += (ai+1 * bi+1)
A2,B2,A6 ;** ai * bi
A2,B2,B6 ;** ai+1 * bi+1
A1,1,A1 ;****** decrement loop counter
LOOP ;***** branch to loop
*A4++,A2 ;******* ld ai & ai+1 fm memory
*B4++,B2 ;******* ld bi & bi+1 fm memory
.L1X A7,B7,A4 ; sum = sum0 + sum1