
Analysis Breakpoints, Watchpoints, and Counter(s)
7-21
Emulation Features
code 2 pipeline phase. The counter counts wait states caused by instructions
that are fetched but not executed. In most cases, these effects cancel each
other out. Benchmarking is best used for larger portions of code. Do not rely
heavily on the precision of the benchmarking. (For more information about the
pipeline, see Chapter 4.)
Alternatively, you can configure the 40-bit performance counter as two 16-bit
or one 32-bit event counter if you want to generate a debug event when the
counter equals a match value. The comparison between the counter value and
the match value is done before the count value is incremented. For example,
suppose you initialize a counter to 0. A match value of 0 causes an immediate
debug event (when the action to be counted occurs), and the counter holds
1 afterward.
You can also clear the counter when a hardware breakpoint or address watch-
point occurs. With this feature, you can implement a mechanism similar to a
watchdog timer: if a certain address is not seen on the address bus within a
certain number of CPU clock cycles, a debug event occurs.
7.7.4 Typical Analysis Unit Configurations
Each analysis unit can be configured to perform one analysis job at a time.
Typical configurations for these two analysis units can be any one of the follow-
ing:
-
Two analysis breakpoints (i.e., hardware breakpoints)
Detect when an instruction is executed from a specified address or range
of addresses. Each hardware breakpoint only requires one analysis unit.
-
Two hardware address watch points
Detect when any value is either read from or written to a specified address
or a range of addresses. In this case, the data written or read is not speci-
fied. Only the address of the location is specified and whether to watch for
reads or writes to that address. Each watchpoint only requires one analy-
sis unit.
-
One address with data watchpoint
Detect when a specified data value is either read from or written to a speci-
fied address. In this configuration you can either watch for a read or a write
but not both reads and writes. This type of watchpoint requires both analy-
sis units.
-
A set of two chained breakpoints
Detect when a given instruction is executed after another specified in-
struction.
Содержание TMS320C28x
Страница 30: ...1 12...
Страница 80: ...This page intentionally left blank 2 50 This page intentionally left blank...
Страница 269: ...IN loc16 PA 6 112 MOV AL 0 AL 0 UOUT IORegC AL IOspace IORegC AL 10...
Страница 308: ...MAXCUL P loc32 6 151 Saturate MOVL Var64 2 ACC Store result into Var64 MOVL Var64 P...
Страница 509: ...SUBL ACC P PM 6 352 SUBL ACC P PM ACC S B 11 M X 4 MOVH Y ACC 5 Store Q15 result into Y...
Страница 585: ...This page intentionally left blank 7 32 This page intentionally left blank...