| Reading time: | 15 min |
| Last updated: | 23 Apr 2026 |
| Reading time: |
| 15 min |
| Last updated: |
| 23 Apr 2026 |
| Author: | Florent Lebeau, Arm |
| Official docs: | View |
| Tags: |
| Author: |
|
| Official docs: |
| View |
| Tags: |
This guide shows you how to install and use the tool with the most common configuration. For advanced options and complete reference information, see the official documentation. Some install guides also include optional next steps to help you explore related workflows or integrations.
Linaro Forge is a server and High Performance Computing (HPC) development tool suite for C, C++, Fortran, and Python high-performance code on Linux.
Linaro Forge consists of the following:
Linaro Forge runs on Linux hosts and multiple architectures. For a full list of supported configuration, see the Linaro Forge documentation .
This install guide assumes that you have access to an Arm AArch64 platform running Ubuntu Linux.
Download and extract the appropriate installation package:
The following command uses Linaro Forge version 25.1.3. The same command works with other versions. Replace the file used in this step with the file for your version of choice. To find the latest version, see Linaro Forge Downloads .
sudo apt install wget
wget https://downloads.linaroforge.com/25.1.3/linaro-forge-25.1.3-linux-aarch64.tar
tar -xf linaro-forge-25.1.3-linux-aarch64.tar
The installation steps depend on the operating system of your machine.
Run the installer from the command line:
./textinstall.sh [--accept-license] [install_dir]
If no install directory is specified, you’ll be prompted to specify a directory when the installer runs.
To install to the default directory non-interactively:
linaro-forge-25.1.3-linux-aarch64/textinstall.sh --accept-license /home/ubuntu/linaro/forge/25.1.3
Drag and drop the client application bundle icon into the Applications directory.
Run the Windows file executable to install the Linaro Forge Remote Client.
Optionally, you can run the installer executable with a graphical interface:
cd linaro-forge-25.1.3-linux-aarch64/
./installer
To debug or profile with Linaro Forge, you need a license file installed on the machine running the tools.
For license-specific setup instructions, see the Linaro Forge documentation .
You don’t need to install a license file for a locally installed Linaro Forge Remote Client. Linaro Forge uses the license of the remote system when it connects.
You can find free trial licenses to try out Linaro Forge.
After installing Linaro Forge, you can use it to debug programs and profile applications. You can also generate performance reports.
When compiling the program that you want to debug, you need to add the debug flag to your compile command. For most compilers, this is -g.
Turn off compiler optimizations as they can produce unexpected results when debugging.
You can launch Linaro Forge’s debugging tool, Linaro DDT, with the ddt command. For Message Passing Interface (MPI) applications, you can prefix the mpirun/mpiexec command normally used to run in parallel:
ddt mpirun -n 128 myapp
This startup method is called Express Launch and is the quickest way to get started. If your MPI is not supported by Express Launch, you can run the following command instead:
ddt -n 128 myapp
These commands will launch the Linaro DDT GUI. When running on a HPC cluster, you may need to debug on compute nodes where this may not be possible. In this case, you can start the GUI on the frontend node with the ddt command. After that, when running or submitting a job to the compute nodes, use ddt --connect :
With Express Launch:
ddt --connect mpirun -n 128 myapp
Without Express Launch:
ddt --connect -n 128 myapp
This mode is called Reverse Connect. A window will appear in the GUI when the application runs to notify of the incoming request.
In most cases, if your program is already compiled with debugging symbols (-g), you don’t need to recompile it to profile it with Linaro Forge. However, in some cases, it might need to be relinked. For more information, see
Linking
.
Rather than profiling a debug build, you should keep optimization flags enabled when profiling. This will give more representative results.
Linaro Forge’s profiling tool, Linaro MAP, can be launched with the map command to launch the GUI. When running on a HPC cluster with MPI, you should use map --profile when running or submitting a job to the compute nodes.
With Express Launch:
map --profile mpirun -n 128 myapp
Without Express Launch:
map --profile -n 128 myapp
When the application terminates, a *.map file will be created in the current directory with profiling results. This file can then be opened from the GUI launched on the frontend node or with the following command:
map myapp_128p_<timestamp>.map
Linaro Forge’s reporting tool Linaro Performance Reports is designed to run on unmodified production executables, so in general no preparation step is necessary. However, there is one important exception: Statically linked applications require additional libraries at the linking step. For more information, see user guide .
Linaro Performance Reports doesn’t use a GUI. Instead, it produces HTML and TXT files when the application terminates to summarize the application behavior. To use the tool on MPI applications:
With Express Launch:
perf-report mpirun -n 128 myapp
Without Express Launch:
perf-report -n 128 myapp
Two files myapp_128p_<timestamp>.html and myapp_128p_<timestamp>.txt will be created in the current directory.
You’re now ready to use Linaro Forge.
How would you rate this tool quick-install guide?
What is the primary reason for your feedback ?
Thank you! We're grateful for your feedback.