Interface and Displays

Metrics Tracking

Scalability

Instrumentation and Tracing

Compatibility

• Displays concurrent behavior of parallel applications
• Calculates statistics for specific time intervals, processes, or functions
• Displays application activities, event source code locations, and message-passing along time axis

• Manages displays and statistics with fast interface
• Uses object point-and-zoom for enhanced detail, context-sensitive sub-menus, and coupled displays
• Supplies automatic updates of recomputed statistics

• Navigates through trace data levels of abstraction: cluster, node, process, thread, and function

• Examines aspects of application runtime behavior, grouped by functions or processes
• Easily identifies the amount of time spent in MPI communication
• Easily see the performance differences between two program runs

• Offers user-friendly application programming interface (API) to control or record user events
• Adds versatile recording and analysis of counter data

• Displays concurrent behavior of parallel applications
• Displays metrics for an arbitrary time interval
• Keeps track of the performance increase of an algorithm change

• Provides subroutine execution metrics or call-tree characteristics

• Records distributed, event-based trace data

• Logs information for function calls, sent messages, and collective operations

• Records distributed, event-based trace data

• Provides structured trace file (STF) format for scalability
• Generates trace files faster
• Allows random access to portions of a trace, making it suitable for analysis of large amounts of trace data

• Traces multi-threaded MPI applications for event-based tracing to non-MPI applications

• Writes trace files, even for premature exit of program

• Caches trace data in memory to reduce runtime overhead and memory consumption

• Supports MPI applications with C, C++, or Fortran
• Library supports distributed non-MPI applications, with C, C++, Fortran, or Java*
• Automatically records performance data from parallel threads in C, C++, Fortran, or Java multithreaded processes

• Creates and adds instrumentation to existing binary executables which allows automatic monitoring of function entry/exit points for detailed analysis of user code and application runtime
• Traces C++ and Java class hierarchies with instrumentation capabilities

• Supports tracing of internal MPI states

• Red Hat Enterprise Linux* 3.0 or 4.0
• SUSE LINUX Enterprise Server* 9 or 10
• SGI Altix*

• Intel® Compilers and GNU compilers
• Intel MPI Library
• MPICH (and compatible derivatives)
• SGI Message Passing Toolkit
• SHMEM support for Quadrics hardware

• Runs on Linux
• Runs on Windows* XP

• Contains all of the Intel® cluster software development solutions, including Intel Trace Analyzer and Collector
• Also includes the Intel® MPI Benchmarks, an open source set of MPI benchmark kernels

With the purchase of Intel® Software Development Products, you will receive one year of technical support and product updates from Intel® Premier Support, our interactive issue management and communication Web site. This premium support service allows you to submit questions, download product updates, and access technical notes, application notes, and other documentation.