摘要:
A system comprises a circuit configured to execute instructions and output event data corresponding to the execution of the instructions. The system also comprises a monitoring device coupled to the circuit. The monitoring device receives information about said event data. The event data comprises event data selected from a group consisting of memory events and external events.
摘要:
A method and system of inserting marker values used to correlate trace data as between processor cores. At least some of the illustrative embodiments are integrated circuit devices comprising a first processor core, a first data collection portion coupled to the first processor core and configured to gather data comprising addresses of instructions executed by the first processor core, a second processor core communicatively coupled to the first processor core, and a second data collection portion coupled to the first processor core and configured to gather data comprising addresses of instructions executed by the second processor core. The integrated circuit device is configured to insert marker values into the data of the first and second processor cores which allow correlation of the data such that contemporaneously executed instruction are identifiable.
摘要:
When events are traced, the timing stream is used to associate events with instructions and indicate pipeline advances precluding the recording of stall cycles. Additional information is needed in the trace stream to identify an overlay whose execution of code is in a system where overlays or a memory management unit are used. In the case of PC trace, additional information is added when the memory system contents is changed. Information describing the configuration change is inserted into the export streams by placing this information in a message buffer. As long as a message word is available for output, it becomes the next export word as the output of message words is continuous.
摘要:
A method and system of identifying overlays used by a program. The overlays may be executable overlays (e.g., overlay programs and dynamically linked library programs), or the overlays may be data sets. Depending on the number of overlays and/or the type of information used to identify the overlays, an indication of the identity of the overlays may be written to a register (whose contents are inserted into the trace data stream), or the indication may comprise an entry in a log buffer and an index value written to the register (again whose contents are inserted into the trace data stream, and where the index value identifies the entry in the log buffer).
摘要:
A system and method of tracing a group of processor events in real-time in order to enable a programmer to debug and profile the operation and execution of code on the processor. This may be accomplished by running one or more traces on the same or different groups of processor events in order to gain a full understanding of how code is being executed by the processor.
摘要:
Disclosed herein is a system and method for receiving encoded events from a system that is being debugged or profiled. The encoded events are input to a decoder in order to decode the encoded events, wherein the decoder is configured to selectively adjust the bandwidth of decoded events. The decoded events are input to a monitoring system in order to enable a user to debug and profile the system.
摘要:
A method and system of identifying overlays. At least some of the illustrative embodiments are methods comprising executing a traced program on a target system (the traced program comprising a plurality of overlay programs), obtaining values indicative of which of the plurality of overlays of the traced program has executed on the target system, and displaying on a display device an indication of a proportion of an execution time on the processor of the target system dedicated to each of the plurality of overlay programs.
摘要:
A method and system of indexing into trace data based on entries in a log buffer. At least some of the illustrative embodiments are methods comprising executing a traced program on a target device. The traced program writes entries to a log buffer within the target device, and the traced program also contemporaneously writes an index value for each entry to a register. The index value written to the register becomes part of trace data regarding the traced program and correlates each entry to a respective portion of the trace data. Using the information one may either or both: display on a display device a portion of the trace data (the portion selected based on selecting an entry from the log buffer); or display on the display a portion of the log buffer (the portion selected based on selecting an entry from the trace data).
摘要:
When tracing memory events the required bandwidth may be reduced by forming a logical OR of several memory event signals to determine the location of memory events. A second trace run may be made after this, tracing only the limited portions of the application where the first run indicated possible problems.
摘要:
An information carrier medium containing software that, when executed by a processor, causes the processor to receive information from circuit logic that is adapted to collect the information from caches on different cache levels. At least some of the information from the caches is associated with a common address. The processor also provides the information to a user of the software.