Assembly Code For Weighted Vector Sum - Texas Instruments TMS320C6000 Programmer's Manual

Example 6–40. Assembly Code for Weighted Vector Sum
LDW .D1
ADD .L2X
LDW .D2
|| LDW .D1
MVK .S2
LDW .D2
|| LDW .D1
|| MVK .S1
|| MVKH .S2
MPY .M1X
||[A1] SUB .L1
MPYHL .M2X
||[A1] B .S1
|| LDW .D2
|| LDW .D1
SHR .S1
|| AND .L2
|| MPY .M1X
||[A1] SUB .L1
SHR .S2
|| ADD .L1X
|| MPYHL .M2X
||[A1] B .S1
|| LDW .D2
|| LDW .D1
SHR .S2
|| STH .D1
|| SHR .S1
|| AND .L2
||[A1] SUB .L1
|| MPY .M1X
LOOP:
ADD .L2
|| SHR .S2
|| ADD .L1X
|| MPYHL .M2X
||[A1] B .S1
|| LDW .D2
|| LDW .D1
*A4++,A2 ; ai & ai+1
A6,2,B0 ; set pointer to ci+1
*B4++,B2 ; bi & bi+1
*A4++,A2 ;* ai & ai+1
–1,B10 ; set to all 1s (0xFFFFFFFF)
*B4++,B2 ;* bi & bi+1
*A4++,A2 ;** ai & ai+1
49,A1 ; set up loop counter
0,B10 ; clr upper 16 bits (0x0000FFFF)
A2,B6,A5 ; m * ai
A1,1,A1 ; decrement loop counter
A2,B6,B5 ; m * ai+1
LOOP ; branch to loop
*B4++,B2 ;** bi & bi+1
*A4++,A2 ;*** ai & ai+1
A5,15,A7 ; (m * ai) >> 15
B2,B10,B8 ; bi
A2,B6,A5 ;* m * ai
A1,1,A1 ;* decrement loop counter
B2,16,B1 ; bi+1
A7,B8,A9 ; ci = (m * ai) >> 15 + bi
A2,B6,B5 ;* m * ai+1
LOOP ;* branch to loop
*B4++,B2 ;*** bi & bi+1
*A4++,A2 ;**** ai & ai+1
B5,15,B7 ; (m * ai+1) >> 15
A9,*A6++[2] ; store ci
A5,15,A7 ;* (m * ai) >> 15
B2,B10,B8 ;* bi
A1,1,A1 ;** decrement loop counter
A2,B6,A5 ;** m * ai
B7,B1,B9 ; ci+1 = (m * ai+1) >> 15 + bi+1
B2,16,B1 ;* bi+1
A7,B8,A9 ;* ci = (m * ai) >> 15 + bi
A2,B6,B5 ;** m * ai+1
LOOP ;** branch to loop
*B4++,B2 ;**** bi & bi+1
*A4++,A2 ;***** ai & ai+1
Optimizing Assembly Code via Linear Assembly
Modulo Scheduling of Multicycle Loops
6-75