Profiling AlexNet on Raspberry Pi and HiKey 960 with the Arm Compute LibraryOverview Set up your Raspberry Pi NFS on Pi Build the Arm Compute Library on Pi Run the graph_alexnet application on Pi Start Streamline gatord on Pi Add Streamline annotations and rebuild on Pi Build the Arm Compute Library on HiKey 960 Profile with Streamline on HiKey 960 Next steps
Install and build the Arm Compute Library on Pi
The Arm Compute Library can be compiled natively on the Pi. It takes some time, but this is the easiest way. When building,
opencl=1 must be specified for the example application to be built, even though OpenCL is not going to be used on the Pi. Building the debug version, by specifying
debug=1, provides useful information during the performance analysis.
To install and build the Arm Compute Library, enter the following commands:
$ sudo apt-get install git scons -y $ git clone https://github.com/Arm-software/ComputeLibrary.git $ cd ComputeLibrary $ scons Werror=1 debug=1 asserts=0 neon=1 opencl=1 build=native –j2
This is a good time to take a short break while the Arm Compute Library compiles.