 |
Indispensable MPI optimizing tool Intel® Trace Analyzer and Collector Address MPI application behavior, bottlenecks, and performance with this powerful MPI software tool for Windows* and Linux*.
Intel® Trace Analyzer and Collector is only available as part of Intel® Cluster Studio or Intel® Cluster Studio XE. |
 |
|
Intel® Trace Analyzer and Collector is a powerful tool for understanding MPI application behavior, quickly finding bottlenecks, and achieving high performance for parallel cluster applications. It supports Intel® architecture-based cluster systems, features a high degree of compatibility with current standards, and now includes trace file comparison, counter data displays, and an MPI correctness checking library. Analyze MPI performance, speed up parallel application runs, locate hotspots and bottlenecks, and compare trace files with graphics providing extensively detailed analysis and aligned timelines—all with Intel® Trace Analyzer and Collector MPI software. |
|
Benefits:
|
|
|
|
||
Product in-depth › |
|
Features MPI Checking A unique MPI Correctness Checker detects deadlocks, data corruption, and errors with MPI parameters, data types, buffers, communicators, point-to-point messages and collective operations. The Correctness Checker allows the user to scale to extremely large systems and detect errors even among a large number of processes. Interface and Displays Intel® Trace Analyzer and Collector includes full-color customizable GUI with many drill-down view options.
The analyzer is able to extremely rapidly unwind the call stack and use debug information to map instruction addresses to source code.
With both command-line and GUI interfaces, the user can additionally set up batch runs or do interactive debugging.
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 as well as non-MPI threaded applications.
Instrumentation and Tracing Low-intrusion instrumentation supports MPI applications with C, C++, or Fortran.
Intel® Trace Analyzer and Collector automatically records performance data from parallel threads in C, C++, or Fortran.
|
|
|
||
| Identify MPI Bottlenecks
This short video shows how Intel® Trace Analyzer and Trace Collector can be used to visualize bottlenecks in MPI traffic to help the developer tune the code for better performance. |
|
Flexible MPI Analysis with Intel Trace Analyzer Event Timeline
|
|
|
||
 |
||
|
|
||
|
|
||
|
Dominic Holland, SDSC "One can very easily determine the overall expense of communication, and further get a breakdown into the amount of time spent in each MPI routine. The degree and cause of load imbalance is also easily determined at any number of processes. One particularly useful feature is the Message Statistics display, giving an overall view on a grid of which processors are communicating with each other. Another nice feature is the ability to see, and focus on, the amount of time spent in communication mode as the simulation proceeds." |
|
|
|
||
|
Dr. Takahiro Koishi, Computational Astrophysics Laboratory, RIKEN, Japan "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 non-blocking 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's MPI software and cluster software tools provide us the best cluster development environment." |
|
|
|
||
|
Jinwoo Park, Senior System Manager SPCC, University of Seoul, South Korea "We evaluated the Cluster Toolkit and concluded that we would get much better performance on the Intel® platform with the Intel® software tools. For each application, Intel's compiler gave us better performance than before and using the Intel® cluster software tools let us know how the cluster system ran and how to improve it." |
|
|
|
||
|
Dr. Ing. Ulrich Jakobus, Technical Director, EM Software & Systems "Our FEKO electromagnetics code runs on various parallel environments (e.g., clusters of different sizes, shared memory machines) and utilizes complex numerical algorithms that are non-trivial to parallelize. Intel Trace Analyzer and Collector have proven to be very valuable tools 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." |
|
|
|
||
Browse the Intel Trace Analyzer and Collector for Linux* Knowledge Base
Browse the Intel Trace Analyzer and Collector for Windows* Knowledge Base
Ask Experts Online
Search and post a new question to the Intel® Software Network Forum for Intel® Trace Analyzer and Collector. The forums allow you to search a growing archive of technical questions and answers from both Intel experts and our developer community. If an answer can't be found in Search, you can ask a new question. An Intel® Software Development Products Registration Center login will allow you to participate in the Intel® Software Network User Forums without any additional registration.
Get Help from Intel
If you do not find what you need above:
Submit Software Tools bugs through Intel® Premier Support. Registration is required.
For more complete information about compiler optimizations, see our Optimization Notice.