Texas Instruments TMS320C6000 Programmer's Manual page 281

Outer Loop Conditionally Executed With Inner Loop
Example 6–77. Linear Assembly for FIR With Outer Loop Conditionally Executed
With Inner Loop (With Functional Units) (Continued)
MV
MPYLH
[sctr] ADD
MPYHL
ADD
MPYLH
ADD
MPYHL
ADD
MPYLH
ADD
MPYHL
ADD
MPYLH
ADD
MPYHL
ADD
MPY
[sctr] ADD
MPYH
ADD
MPY
ADD
MPYH
ADD
MPY
ADD
MPYH
ADD
6-144
.L2X x01,x01b
.M2X h01,x01b,p10
.L2 p10,sum17,p10
.M1X h01,x23,p11
.L2X p11,p10,sum11
.M2 h23,x23,p12
.L2 p12,sum11,sum12
.M1X h23,x45,p13
.L2X p13,sum12,sum13
.M1 h45,x45,p14
.L2X p14,sum13,sum14
.M2X h45,x67,p15
.S2 p15,sum14,sum15
.M2 h67,x67,p16
.L2 p16,sum15,sum16
.M1X h67,x8,p17
.L2X p17,sum16,sum17
.M1 h01,x01,p00
.L1 p00,sum07,p00
.M1 h01,x01,p01
.L1 p01,p00,sum01
.M2 h23,x23,p02
.L1X p02,sum01,sum02
.M2 h23,x23,p03
.L1X p03,sum02,sum03
.M1 h45,x45,p04
.L1 p04,sum03,sum04
.M1 h45,x45,p05
.L1 p05,sum04,sum05
; move to other reg file
; p10 = h[i+0]*x[j+i+1]
; sum1(p10) = p10 + sum1
; p11 = h[i+1]*x[j+i+2]
; sum1 += p11
; p12 = h[i+2]*x[j+i+3]
; sum1 += p12
; p13 = h[i+3]*x[j+i+4]
; sum1 += p13
; p14 = h[i+4]*x[j+i+5]
; sum1 += p14
; p15 = h[i+5]*x[j+i+6]
; sum1 += p15
; p16 = h[i+6]*x[j+i+7]
; sum1 += p16
; p17 = h[i+7]*x[j+i+8]
; sum1 += p17
; p00 = h[i+0]*x[j+i+0]
; sum0(p00) = p00 + sum0
; p01 = h[i+1]*x[j+i+1]
; sum0 += p01
; p02 = h[i+2]*x[j+i+2]
; sum0 += p02
; p03 = h[i+3]*x[j+i+3]
; sum0 += p03
; p04 = h[i+4]*x[j+i+4]
; sum0 += p04
; p05 = h[i+5]*x[j+i+5]
; sum0 += p05