Texas Instruments TMS320C6000 Programmer's Manual page 53

Lesson 3: Packed Data Optimization of Memory Bandwidth
2.4 Lesson 3: Packed Data Optimization of Memory Bandwidth
Example 2–10. lesson2_c.asm
;*––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––*
;* SOFTWARE PIPELINE INFORMATION
;*
;* Loop Unroll Multiple
;* Known Minimum Trip Count
;* Known Maximum Trip Count
;* Known Max Trip Count Factor
;* Loop Carried Dependency Bound(^) : 0
;* Unpartitioned Resource Bound
;* Partitioned Resource Bound(*)
;* Resource Partition:
;*
;* .L units
;* .S units
;* .D units
;* .M units
;* .X cross paths
;* .T address paths
;* Long read paths
;* Long write paths
;* Logical
;* Addition ops (.LSD)
;* Bound(.L .S .LS)
;* Bound(.L .S .D .LS .LSD)
;*
;* Searching for software pipeline schedule at ...
;* ii = 3
;* done
;*
;* Epilog not entirely removed
;* Collapsed epilog stages
;*
;* Prolog not entirely removed
;* Collapsed prolog stages
;*
;* Minimum required memory pad : 8 bytes
;*
;* Minimum safe trip count
;*
;*––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––––*
2-18
Lesson 2 produced a 3–cycle loop that performed two iterations of the original
vector sum of two weighted vectors . This means that each iteration of our loop
now performs six memory accesses, four multiplies, two adds, two shift opera-
tions, a decrement for the loop counter, and a branch. You can see this phe-
nomenon in the feedback of lesson2_c.asm.
Open lesson2_c.asm
A–side
ops (.LS)
Schedule found with 5 iterations in parallel
: 2x
: 10
: 1073741823
: 1
: 3
: 3
B–side
0 0
2 1
3* 3*
2 2
1 1
3* 3*
1 1
0 0
1 1 (.L or .S unit)
0 1 (.L or .S or .D unit)
2 1
2 2
: 2
: 3
: 4