D3.4: Automatic kernel identication and assessment

The aim of this deliverable is to describe the Automatic Kernel Identification Tool (AKI) that aims to identify potential kernels in C++ sequential applications. AKI looks for hotspots that can be oined on heterogeneous computing devices. Finally, AKI annotates the hotspots as kernels by using REPARA C++ attributes mapping the kernels to the suitable heterogeneous computing devices. This process analyzes not only the kernels themselves but also their associated data, including kernels and data interdependencies. These annotations can aid future automatic source-to-source transformation tools for heterogeneous platforms.

This document includes all the information related to the AKI workow including:

  • the AKI workow description, including its main features,
  • the AKI user manual,
  • and nally, an evaluation of the tool.


Comments are closed.