09-06-2010, 05:19 PM
[attachment=3756]
SYNCHRONIZATION IN EMBEDDED SYSTEMS
PRESNTED BY
D.SWARNA LATHA
P.MADHAVI LATHA
AVANTHI INSTITUTE OF ENGINEERING AND TECHNOLOGY
ABSTRACT
As the sensory system for an accelerator, the beam instrumentation provides tremendous amount of diagnostic information. Access to this information can vary from periodic spot checks to operator to high bandwidth data acquisition during studies. In this paper, example applications will illustrate the requirement on interfaces between the control system and the instrumentation hardware. A survey of the major accelerator facilities will identify the most popular interface standards. The impact of developments such as isochronous protocols and embedded digital signal processing will also be discussed.
INTRODUCTION
Latencies and timing uncertainties involved in orchestrating the operation of multiple measurement components present a significant challenge in building automated test systems. These issues, often overlooked during the initial system design, limit the speed and accuracy of the system. However, with a good understanding of timing and synchronization technologies, you can address these issues from the onset and deploy a system optimized for throughput and performance. Before we proceed, first consider that most automated measurements for test fall into one of two categories. The first category, often called time-domain measurements, characterizes the variation of a device under test (DUTs) output over time. For these measurements, the accuracy of the measured response depends not only on the accuracy of its magnitude, but also on the time at which the signals are measured.
The second type or steady-state measurements occurs when one or more inputs of known value are applied to the DUT and its outputs can settle to their steady-state value before you measure the signals. In this case, the measurement process depends on the time of the measurement -- if you measure the signals too early, accuracy suffers because the source output may not have fully settled. Although you can measure the signals accurately any time after the output has settled, you must minimize the delay to reduce test time. Many test developers insert an arbitrary delay in their test programs to ensure accurate results. While this is a simple fix, test time suffers.
Synchronized Instrumentation for Analyzing and Monitoring Embedded Systems
Current embedded systems are becoming increasingly more complex with multiple processors communicating over various media including backplanes, data busses and discrete signal lines. This complexity has generated a need for tools that can provide visibility into how the system operates from a system-wide perspective. This visibility is required to support initial development as well as SystemTrace has been designed to provide global visibility into system operations by monitoring all key data flow media incorporated in the embedded system. This monitoring is accomplished using Real-Time Non-Intrusive (RTNI) techniques so that the act of monitoring does not affect the system operation. The data files collected at the key data flow points are time-correlated so that dependencies on actions among system elements can be observed. These time- correlated data files can then be used for multiple applications such as: Software Test and Evaluation System Integration Acceptance Testing Performance Monitoring Operational test Mission Monitoring Diagnostics Prognostics operation and maintenance of the system. The tools also need to provide this visibility without introducing changes to the systemâ„¢s operation. While there are many tools available for development and maintenance of the individual elements of the embedded system, there are few tools available to support the entire system throughout the life cycle of the product. Monitor and Analyze Data from Multiple VME Chassis and MIL-STD-1553 Busses ST-201 VME Data Monitor and Analyzer The ST-201VME Module is capable of monitoring and recording activity on all four VME backplane busses (Data Transfer Bus (DTB), Arbitration Bus, Interrupt Bus, and Utility Bus). This allows the analysis of data transfers between processors, or any other device that participates in data transfers and VME bus arbitration. VME Protocol interactions can be analyzed by specifying occurrences on the Arbitration, Utility and Interrupt Busses as "Events" for the Module to monitor and record. Any specific occurrence or group of occurrences on the bus may be recorded by setting up the Module to identify them as Events and selecting the Recording Action.
In addition to Event capture, a parallel circular History buffer with a 256K window may be
allowing the VME Probe to collect all activity from the time the target is powered up until
buffer is trigged or the Monitor is stopped. After the completion of Monitoring sessions,
collected may be uploaded and then displayed by the GUI Analysis program.
STX-1553 Mil-Std-1553 Monitor and Analyzer
The ST-101Mil-Std-1553 Module is capable of monitoring and recording activity on up to eight dual redundant MIL-STD-1553 busses (4 per Probe card). This allows the analysis of data transfers among all devices that participate in data transfers on the network. Data is monitored by symbolically specifying occurrences on the Bus as "Events" for the Module to monitor and record. Conditions for Event recording may be setup by the user, such as, number of Event occurrences, elapsed time, or a dependence on the occurrence of other Events. In addition to event capture, a parallel circular history buffer with a 100K window may be enabled allowing the module to collect all activity from the time the target is powered up until the History buffer is trigged or the Monitor is stopped. Pre- or post-trigger events may be designated to provide activity preceding and following the trigger.
SystemTrace„¢ Software Instrumentation
The System Trace„¢ Software Instrumentation feature provides the ability to add user software generated time tags and data records to the System Trace„¢ ST-201 VME Monitor log file, providing precise sequence and timing insight into program operation relative to other software modules, and to the bus being monitored. These time tags are generated when the user system accesses the installed System Trace„¢ ST-201 VME Monitor. In addition to the time tags, the values of other internal variables at different points in time can captured.
Use of this monitoring technique requires minor modifications to the user source code. The user first defines the test environment with the SystemTrace„¢ Control Console. The user inserts SystemTrace„¢ access code into the entry and exit points of each procedure or code segment to be analyzed. The user compiles the software with the GUI generated "include" file. During runtime, the access code writes specific The Event Timing report displays two types of events: Data Item and Procedure. On the screen, procedure event names are displayed with a special icon. A solid block depicts the time between entry and exit points for a procedure or timed operation.
A thin 'tick' represents a data event. To view more information about any event in the graph, place the solid time cursor on the event and select "View Details" from the menu. The user may add events from any card (up to 32) in the SystemTrace„¢ network and the data will be displayed based on a common time line.
data to the SystemTrace„¢ hardware. The SystemTrace„¢ hardware can monitor and collect timing data from these accesses. During post- run, the System Trace„¢ analysis tool displays timing information as illustrated on the GUI screen to the right. The SystemTrace Graphical User Interface (GUI) runs on a PC with Windows 2000/XP. The GUI includes three major modules: Setup, SystemTrace„¢ Graphical User Interface Run-Time Analysis and Post-Run Analysis.
The Setup module provides the ability to define system "Events", configure the instrumentation network and control the data collection scenarios.
The SystemTrace„¢ Data Analysis software provides Run-Time and Post-Run displays for data collected from any of the supported target types. Some of the applications included are: Event Table- provides a text table tracing the history of the logged data, Event Timing “ a graphical bar chart providing Event Timing measurements for multiple events, Event Graph “ a graphical plot of multiple Data Items over a timeline. Run-Time Data Graphs “ provides an automated graphical scroll chart of multiple Data Items. Run-Time Data Table “ provides a text table that displays Run-Time Data Items in user specified formats. The Analysis tools display data from any or all SystemTrace„¢ Modules in the instrumentation network. This provides the ability to compare the data captured across the system.
SystemTrace„¢ Characteristic
Extendable to All Embedded Systems Data Streams Support for System Life-Cycle Non-Intrusive Independent Provides local and Global Time Synchronization Provides State Machine Driven Cross Triggers Common User Interface for all Data Streams Event Triggered vs. Periodic Sampling Time-Correlated Displays Multiple Programmable Data Collection Scenarios Dynamic Context Switching for Collection Scenarios Local Processing in Monitor Module
Benefit
Provides system-wide visibility across all key data streams. Can be used during Development, Operation and Maintenance phases. Doesnâ„¢t perturb system operation during test. Requires no modifications to target application Correlates system Events among All elements. Allows remote monitoring. Allows Synchronized Data Collection across the System Saves training costs. Shortens development, operations analysis and maintenance cycles. Captures only data of interest. Allows extended test runs. Allows direct comparison of system event time sequences. Allows monitoring of pre-determined conditions. Allows a real-time change in monitoring scenarios based on system behavior. Allows monitoring module to send back information vs. data to user.
Conclusions
Computer-based measurement components are transforming creation of synchronized measurement systems from integration of loosely coupled, and often incompatible instruments, into an orderly engineering process that results in tightly integrated, high-performance systems. For synchronized measurements, timing and triggering details are critical keys to your automated measurements. Precise synchronization requires proper distribution of clocks and triggers. The three main synchronization schemes and proper knowledge of the pros and cons of each and the capabilities of your measurement devices help you to make the right decision in choosing your solution.
References:
Robert Hess
Altoll Brown
http://drrtvdefault.dspn
http://hanselminuts default.dspn
kontron.com
comsoc.org
