Intel® Trace Analyzer and Collector
MPI Profiling for Cluster Applications
Understand MPI Application Behavior across Its Full Runtime
The Intel® Trace Analyzer and Collector profiles and analyzes MPI applications to help focus your optimization efforts.
- Find temporal dependencies and bottlenecks in your code.
- Check the correctness of your application.
- Locate potential programming errors, buffer overlaps, and deadlocks.
- Visualize and understand parallel application behavior.
- Evaluate profiling statistics and load balancing.
- Analyze performance of subroutines or code blocks.
- Learn about communication patterns, parameters, and performance data.
- Identify communication hot spots.
- Decrease time to solution and increase application efficiency.
Develop, Test, and Run Your oneAPI Code in the Cloud
Get what you need to build and optimize your oneAPI projects for free. With an Intel® DevCloud account, you get 120 days of access to the latest Intel® hardware—CPUs, GPUs, FPGAs—and Intel oneAPI tools and frameworks. No software downloads. No configuration steps. No installations.
Download the Tool
Intel Trace Analyzer and Collector is included as part of the Intel® oneAPI HPC Toolkit.
Features
MPI Checking
- Detect deadlocks, data corruption, and errors with MPI parameters, data types, buffers, communicators, point-to-point messages, and collective operations.
- Scale to extremely large systems and detect errors among a large number of processes.
Displays
- Access a customizable, full-color interface with many detailed view options.
- Rapidly unwind the call stack and use debug information to map instruction addresses to source code.
- Set up batch runs or do interactive analyses with command lines and visual interfaces.
Scalability
- Low overhead allows random access to portions of a trace, making it suitable for analyzing large amounts of performance data.
- Thread safety allows you to trace multithreaded MPI applications for event-based tracing and non-MPI threaded applications.
Instrumentation & Tracing
- Low-intrusion instrumentation supports MPI applications with C, C++, Fortran, or OpenSHMEM.
- Automatically record performance data from parallel threads in C, C++, Fortran, and OpenSHMEM.
Documentation & Training
Documentation
- Get Started Guide
- Intel® Trace Collector User and Reference Guide | PDF
- Intel® Trace Analyzer User and Reference Guide | PDF
- Intel Trace Analyzer and Collector Installation Guide Linux | Windows
Specifications
Processors:
- Intel® Xeon® processors and compatible processors
Languages:
- C, C++, Fortran, OpenSHMEM
Operating systems:
- Linux
- Windows
Development environments:
- Works with compilers from Microsoft*, GNU Compiler Collection (GCC)*, Intel, and others that follow the same standards
Support for all major MPICH2-based implementations
Priority Support
All paid versions of Intel® Software Development Products automatically include Priority Support for one year from your date of purchase. Get direct access to our technical experts when you purchase Intel Trace Analyzer and Collector bundled with Intel® oneAPI Base & HPC Toolkit.
What Customers are Saying
"Intel Trace Analyzer and Collector for Linux helped to drastically improve the performance of RIKEN's molecular dynamics cluster software. We were able to shorten MPI communication time by half by finding and removing bottlenecks with nonblocking communication patterns. Since Intel Trace Analyzer and Collector can embed instrumentation into the program, we can tell the execution time of each function and its load balance, which enabled us to very easily understand where to optimize. Intel® MPI Library and Intel® Cluster Tools provide us the best cluster development environment."
—Dr. Takhiro Koishi, RIKEN
"Our FEKO* electromagnetics code runs on various parallel environments (for example, clusters of different sizes, shared memory machines) and utilizes complex numerical algorithms that are nontrivial to parallelize. Intel Trace Analyzer and Collector has proven to be a very valuable tool to help understand FEKO parallel communication patterns, and consequently in optimizing the message-passing call that results in an extremely well-performing electromagnetics ISV cluster application."
—Dr. Ing Ulrich Jakobus, technical director, EM Software & Systems
Novosibirsk State University boosts its simulation tool’s performance by three times with Intel Parallel Studio, Intel® Advisor, and Intel Trace Analyzer and Collector.