Texas Instruments TMS320 DSP User Manual
Page 43
www.ti.com
Execution Time
Execution time should be expressed in instruction cycles whereas the period expressed in microseconds.
Worst-case execution time must be accompanied with a precise description of the run-time assumptions
required to reproduce this upper bound. For example, placement of code and data in internal or external
memory, placement of specified buffers in dual-access or single access on-chip memory, etc. In particular,
the worst-case execution time must be accompanied by a table of memory requirements (described
above) necessary to achieve the quoted execution time. Note that the entries in this table are not required
to be constants; they may be functions of the algorithm's instance creation parameters.
Operation
Period
Worst-Case Cycles/Period
process()
22500
µ
s
198000
In some cases, an algorithm's worst-case execution time is a periodic function of the frame number.
Suppose, for example, that an audio encoder consumes 10 milliseconds frames of data at a time but only
outputs encoded data on every 20 milliseconds. In this case, the encoder's worst-case execution time on
even frames will differ (perhaps significantly) from the worst-case execution time for odd numbered
frames; the output of data only occurs on odd frames. In these situations, it is important to characterize
the worst-case execution time for each frame; otherwise, system integrators may (falsely) conclude that an
algorithm will not be able to be combined with others.
All such algorithms must characterize their periodic execution time requirements by filling in the table
below; the number of Cycles/Period columns can be any finite number M. The worst-case number in the
Cycles/PeriodN column must be the worst-case number of cycles that can occur on frame number k * M +
N, where k is any positive integer.
Operation
Period
Cycles/Period
0
Cycles/Period
1
process()
22500
µ
s
59000
198000
SPRU352G – June 2005 – Revised February 2007
Algorithm Performance Characterization
43