Intel® Trace Analyzer and Collector 8.1

Understand MPI application behavior, quickly finding bottlenecks, and achieving high performance for parallel cluster applications

  • Powerful MPI Communications Profiling and Analysis
  • Scalable - Low Overhead & Effective Visualization
  • Flexible to Fit Workflow – Compile, Link or Run

Buy Now

Intel® Trace Analyzer and Collector is only available as part of Intel® Cluster Studio 2013 or Intel® Cluster Studio XE 2013

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 2013 or Intel® Cluster Studio XE 2013.

Intel® Trace Analyzer and Collector is a graphical tool for understanding MPI application behavior, quickly finding bottlenecks, improving correctness, and achieving high performance for parallel cluster applications based on Intel architecture. New features include trace file comparison, counter data displays, extensively detailed and aligned timelines, and an MPI correctness checking library. Improve weak and strong scaling for small and large applications all with Intel® Trace Analyzer and Collector MPI software.


  • 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 hotspots
  • Decrease time to solution and increase application efficiency


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.


  • 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.

Product in-depth

Videos to help you get started.

Register for future Webinars

Previously recorded Webinars:

  • Increase Cluster MPI Application Performance with a "MPI Tune" Up
  • MPI on Intel® Xeon Phi™ coprocessor
  • Quickly discover performance issues with the Intel® Trace Analyzer and Collector 9.0 Beta

Featured Articles

Nenhum conteúdo foi encontrado

More Tech Articles

Nenhum conteúdo foi encontrado
Assine o

Supplemental Documentation

Nenhum conteúdo foi encontrado
Assine o

You can reply to any of the forum topics below by clicking on the title. Please do not include private information such as your email address or product serial number in your posts. If you need to share private information with an Intel employee, they can start a private thread for you.

New topic    Search within this forum     Subscribe to this forum

Multi-threading with Intel MPI
By Kunal M.1
I am trying to establish communication between threads on different processes using Intel MPI. However, it does not seem to work as I would expect it to. Here's the code snippet:              MPI_Comm_dup(MPI_COMM_WORLD, &dup_world_comm0);              MPI_Comm_group(dup_world_comm0, &world_group0);              MPI_Comm_create(dup_world_comm0, world_group0, &world_comm0);                /*inside a thread*/                if (myrank == 0) {//process 0                         i = find_sum();                         if (index == 0) {//thread id 0                                 MPI_Send(&i, 1, MPI_INT, 1, 1, world_comm0);                                 MPI_Recv(&y, 1, MPI_INT, 1, 1, world_comm0, &status);                         }                 }                 if (myrank == 1) {//process 1                         if (index == 0) {//thread id 0                                 MPI_Recv(&i, 1, MPI_INT, 0, 1, world_comm0, &status);            ...
Intel Trace Collector Crashing with Large Number of Cores
By Mohamad Sindi2
Dear Support,                      I am currently running on RedHat Linux 6.2 64-bit with Intel compilers 12.1.0 and Intel MPI over Qlogic Infiniband QDR (PSM). I am also using Intel Trace Analyzer and Collector I am trying to debug an MPI problem when running on a large number of  cores (>6000) and I compile my application with "-check_mpi". My application is mixed FORTRAN, C, and C++ and most MPI calls are in FORTRAN. I launch my MPI job with the below options: mpiexec.hydra  -env I_MPI_FABRICS  tmi  -env I_MPI_TMI_PROVIDER  psm  -env I_MPI_DEBUG 5  ....... As soon as I launch the application the trace collector crashes with the below error: [0] Intel(R) Trace Collector ERROR: cannot create socket: socket(): Too many open files [32] Intel(R) Trace Collector ERROR: connection closed by peer #0, receiving remaining 8 of 8 bytes failed   It works fine on a less number of cores but I need to debug on a large number of cores beyond 6000 cores since that's when...
Problem with MPI_FILE_OPEN on Windows
By Ines F.0
I'm sorry, it's the second time I ask this question. I'm trying to use the MPI subroutine MPI_FILE_OPEN and even with a very simple code lines it doesn't work and I don't understand why !! The other MPI subroutines work very well and IERROR is equal to 0. It's not the case when I try to create or open a file : integer :: descripteur,ierr call MPI_FILE_OPEN(MPI_COMM_WORLD,"",MPI_MODE_RDWR + MPI_MODE_CREATE,MPI_INFO_NULL,descripteur,ierr)      The code works normally but the test file isn't created and when I print ierr I had this bizarre value 536929056 !! Can anyone please have an explanation !!
Malfunctioning of some MPI subroutines with Ifort Compiler for Windows
By Ines F.0
Hi, I started recently programming with the MPICH2 library associated to the Intel Visual Fortran composer for Windows. Even if my test code recognize the MPI library, many of the MPI simple subroutines didn't work, even well set ! For example, this simple code didn't create the file 'data.txt' : program main         use mpi         implicit none         integer :: descripteur,code         call MPI_INIT(code)         call MPI_COMM_SIZE ( MPI_COMM_WORLD ,nb_procs,code)         call MPI_COMM_RANK ( MPI_COMM_WORLD ,rang,code)       print * ,'Je suis le processus ',rang,' parmi ',nb_procs                 call MPI_FILE_OPEN(MPI_COMM_WORLD,"data.txt",MPI_MODE_RDWR+MPI_MODE_CREATE,MPI_INFO_NULL,descripteur,code)                  call MPI_FILE_CLOSE (descripteur,code)         call MPI_FINALIZE (code)           end  Result : Je suis le processus            5  parmi            8  Je suis le processus            3  parmi            8  Je suis le processus            1  parmi           ...
mpiexec.hydra -ppn 1 and intel-mpi
By Alin M Elena7
I have just installed intel-mpi onf a cluster... If I used mpiexec.hydra to start jobs one per node... it still spawns processes on all available resources... mpiexec.hydra -ppn 1 hostname on two nodes will show me 40 lines as oppose to only two expected. I have added a file with debug info when running I_MPI_HYDRA_DEBUG=1 mpiexec.hydra -ppn 1 hostname 2>&1 | tee debug.txt   regards, Alin
Problem with MPI_SCATTERV
By danielsue2
Hi All, I ran into a problem with MPI_SCATTERV. When the sendcounts (scounts) is the same for every process, it works fine, but if the sendcounts is different, (e.g., 1, 2, 3, 4 for 4 processes) there will be error as follows: Fatal error in PMPI_Scatterv: Message truncated, error stack: PMPI_Scatterv(376)................: MPI_Scatterv(sbuf=0000000000000000, scnts=0000000000E16CD0, displs=0000000000E16CA0,  MPI_INT, rbuf=0000000002BD0050, rcount=1, MPI_INT, root=0, MPI_COMM_WORLD) failed MPIR_Scatterv_impl(187)...........: MPIR_Scatterv(144)................: MPIDI_CH3U_Receive_data_found(129): Message from rank 0 and tag 6 truncated; 16 bytes received but buffer size is 4   The code is simple as follows: call MPI_SCATTERV(ja_in, scounts, displs, MPI_INT, ja, scounts, MPI_INT, 0, comm , ierr) Thanks and regards, Daniel
Problem with MPIRUN run on multi-nodes Under LINUX
By dingjun.chencmgl.ca4
HI, Dear Sir or Madam, I am testing the Intel MPI benchmar under RedHat Linux with 2 computers: node1-rh(8 cores) and node2-rh(8 cores). After I enter the following command on the local node1-rh: bash-4.1$ mpirun -hosts node2-rh, node1-rh -np 16 IMB-MPI1 dingjun@node1-rh's password: ********* IMB-MPI1 did not run. This indicates the IMB-MPI1 did not run on the remote computer node2-rh. Could you experience such a problem? please tell my your ideas on how to run a executable file on multi-nodes under Linux with the Intel MPI library. Thanks in advance. Have a good day and I look forward to hearing from you.          
IMB 4.0 bug report with RMA side
By Mingzhe L.1
Hi Sir/Madam, When I was running the latest IMB 4.0 which supports MPI-3 RMA, I found an issue with the benchmark. The benchmark didn't call MPI_Win_free to free the window when the benchmark exits. The following code is where MPI_Win_free is called inside IMB 4.0. It is called only for IMB-EXT, not for IMB-RMA. It seems to be a bug in the benchmark. Could you give me some feedbacks about this?   #ifdef EXT     if( c_info->WIN != MPI_WIN_NULL )         MPI_Win_free(&c_info->WIN); #endif /*EXT*/ Ming


Assine o Fóruns
  • What are some key things I can learn about my program using Intel® Trace Analyzer and Collector?
  • The Intel® Trace Analyzer and Collector is a graphical tool used primarily for MPI-based programs. It helps you understand your application's behavior across its full runtime.  It can help find temporal dependencies in your code and communication bottlenecks across the MPI ranks.  It also checks the correctness of your application and points you to potential programming errors, buffer overlaps, and deadlocks.
  • Will Intel® Trace Analyzer and Collector only work with Intel® MPI Library?
  • No, the Intel® Trace Analyzer and Collector support all major MPICH2-based implementations.  If you're wondering whether your MPI library can be profiled using the Intel Trace Analyzer and Collector, you can run a simple ABI-compatibility check by compiling the provided mpiconstants.c file and verifying the values with the ones provided in the Intel® Trace Collector Reference Guide.
  • Can Intel® Trace Analyzer and Collector be used on applications for Intel® Many Integrated Core Architecture (Intel® MIC Architecture)?
  • Yes, Intel® MIC Architecture is fully supported by the Intel® Trace Analyzer and Collector.
  • What file and directory permissions are required to use Intel® Trace Analyzer and Collector?
  • You do not need to install special drivers, kernels, or acquire extra permissions.  Simply install the Intel® Trace Analyzer and Collector in the $HOME directory and link it with your application of choice from there.
  • Should I recompile/relink my application to collect information?
  • It depends on your application. For Windows* OS, you have to relink your application by using the –trace link-time flag.
    For Linux* OS (and if your application is dynamically linked), you do not need to relink or recompile.  Simply use the –trace option at runtime (for example: mpirun –trace).
  • How do I control which part of my application should be profiled?
  • The Intel® Trace Collector provides several options to control the data collection.  By default, only information about MPI calls is collected.  If you'd like to filter which MPI calls should be traced, create a configuration file and set the VT_CONFIG environment variable.

    If you'd like to expand the information collected beyond MPI and include all user-level routines, recompile your application with the –tcollect switch available as part of the Intel® Compilers.  In this case, Intel Trace Collector will gather information about all routines in the application, not just MPI.  You can similarly filter this via the –tcollect-filter compiler option.

    If you'd like to be explicit about which parts of the code should be profiled, use the Intel Trace Collector API calls.  You can manually turn tracing on and off via a quick API call.
    For more Information on all of these methods, refer to the Intel® Trace Collector Reference Guide.
  • What file format is the trace data collected in?
  • Intel® Trace Collector stores all collected data in Structured Tracefile Format (STF) which allows for better scalability across both time and processes.  For more details, refer to the "Structured Tracefile Format" section of Intel® Trace Collector Reference Guide.
  • Can I import or export trace data to/from Intel® Trace Analyzer and Collector?
  • Yes, you can export the data from any of the Profile charts (Function Profile, Message Profile, and Collective Operations Profile) as part of the Intel® Trace Analyzer interface. To do this, open one of these profiles in the GUI, right-click to bring up the Context Menu, and select the "Export Data" option.  The data will be saved in simple text format for easy reading.

    At a separate level, you can save your current working Intel® Trace Analyzer environment via the Project Menu.  If you choose to "Save Project", your current open trace view and associated charts will be recorded as they are open on your screen.  You can later choose to "Load Project" from this same menu, which will bring up a previously-saved session.
  • What size MPI application can I analyze with Intel® Trace Analyzer and Collector?
  • It depends on how large or complex your application is, how many MPI calls you are making, and for how long you are running.  There are no internal limitations on the size of the MPI job but there are plenty of external ones.  It all depends on how much memory is available on the system (per core) both for the application, the MPI library, and for the Intel® Trace Collector processes, as well as disk space availability.  Any additional flags enabled (for example, storing call stack and source code locations) cause an increase in the size of the trace file. Filtering out unimportant information is always a good solution to reducing trace files.
  • How can I control the amount of data collected to a reasonable amount?  What is a reasonable amount?
  • Each application is different in terms of the profiling data it can provide.  The longer an application runs, and the more MPI calls it makes, the larger the STF files will be.  You can filter some of the unnecessary information out by applying appropriate filters (see Question #6 for more details or check out some tips on Intel® Trace Collector Filtering).

    Additionally, you can be restricted by the resources allocated to your account; consult your cluster administration about quotas and recommendations.
  • How can I analyze the collected information?
  • Once you have collected the trace data, you can analyze it via the Graphical Interface called the Intel® Trace Analyzer.  Simply call the command ($ traceanalyzer) or double-click on the Intel Trace Analyzer icon and navigate to your STF files via the File Menu.
    You can get started by opening up the Event Timeline chart (under the Charts Menu) and zooming in at an appropriate level.

    Check out the Detecting and Removing Unnecessary Serialization Tutorial on ideas how to get started. For details on all Intel Trace Analyzer functionality, refer to the Intel® Trace Analyzer Reference Guide.
  • Can I use Intel® Trace Analyzer and Collector with Intel® VTune™ Amplifier XE, Intel® Inspector XE, or other analysis tools?
  • While these tools would collect information separate from each other, in their own format, it's easy enough to use the Intel® VTune™ Amplifier XE and Intel® Inspector XE tools under an MPI environment.  Check each tool's respective User's Guide for more info on Viewing Collected MPI Data.

    You can use tools such as Intel VTune Amplifier XE and Intel Inspector XE for node-level analysis, and use the Intel Trace Analyzer and Collector for cluster-level analysis.

Intel® Trace Analyzer & Collector

Getting Started?

Click the Learn tab for guides and links that will quickly get you started.

Get Help or Advice

Search Support Articles
Forums - The best place for timely answers from our technical experts and your peers. Use it even for bug reports.
Support - For secure, web-based, engineer-to-engineer support, visit our Intel® Premier Support web site. Intel Premier Support registration is required.
Download, Registration and Licensing Help - Specific help for download, registration, and licensing questions.


Release Notes - View Release Notes online!
Intel® Trace Analyzer and Collector Product Documentation - View documentation online!
Documentation for other software products

Featured Support Topics

Nenhum conteúdo foi encontrado