Comparing Performance; Comparison Of Fixed-Point Dot Product Code Examples; Comparison Of Floating-Point Dot Product Code Examples - Texas Instruments TMS320C6000 Programmer's Manual

6.5.4

Comparing Performance

Table 6–10. Comparison of Fixed-Point Dot Product Code Examples
Code Example
Example 6–9 Fixed-point dot product linear assembly
Example 6–10 Fixed-point dot product parallel assembly
Example 6–19 Fixed-point dot product parallel assembly with LDW
Example 6–26 Fixed-point software-pipelined dot product
Example 6–28 Fixed-point software-pipelined dot product with no extrane-
ous loads
Example 6–30 Fixed-point software-pipelined dot product with no prolog or
epilog
Example 6–32 Fixed-point software-pipelined dot product with smallest
code size
Table 6–11. Comparison of Floating-Point Dot Product Code Examples
Code Example
Example 6–11 Floating-point dot product nonparallel assembly
Example 6–12 Floating-point dot product parallel assembly
Example 6–20 Floating-point dot product parallel assembly with LDDW
Example 6–27 Floating-point software-pipelined dot product
Example 6–29 Floating-point software-pipelined dot product with no extra-
neous loads
Example 6–31 Floating-point software-pipelined dot product with no prolog
or epilog
Example 6–33 Floating-point software-pipelined dot product with small-
est code size
Table 6–10 compares the performance of all versions of the fixed-point dot
product code. Table 6–11 compares the performance of all versions of the
floating-point dot product code.
Optimizing Assembly Code via Linear Assembly
Software Pipelining
100 Iterations Cycle Count
2 + 100 16
1 + 100 8
1 + (50 8) + 1
7 + 50 + 1
7 + 43 + 7 + 1
7 + 57 + 1
5 + 57 + 1
100 Iterations Cycle Count
2 + 100 21
1 + 100 10
1 + (50 10) + 7
9 + 50 + 15
9 + 41 + 9 + 15
7 + 59 + 15
5 + 59 + 15
1602
801
402
58
58
65
63
2102
1001
508
74
74
81
79
6-57