TANGO

Transparent heterogeneous hardware Architecture deployment for eNergy Gain in Operation

TANGO aims to develop programming tools and operational middleware to facilitate the use of heterogeneous hardware components to improve the software application execution time while reducing their energy consumption.

TANGO

Transparent heterogeneous hardware Architecture deployment for eNergy Gain in Operation

TANGO aims to develop programming tools and operational middleware to facilitate the use of heterogeneous hardware components to improve the software application execution time while reducing their energy consumption.

Objectives

The TANGO project aims at

  • Proposing a reference architecture to make software applications self-adaptable during their operation, in order to exploit the capabilities offered by new heterogeneous hardware such as many-core CPUs, GPUs and configurable hardware such as FPGAs;
  • Extending existing software development models and methodologies to enable developers to more easily exploit and optimize the design and code of their applications for execution on heterogeneous hardware;
  • Developing an energy consumption models to help developers quantify the energy requirements of software components when running on various types of heterogeneous hardware

Results

The TANGO project will

  • Develop a toolbox to exploit heterogeneous hardware capabilities while reducing energy consumption needs
  • Provide a development methodology to use the toolbox
  • Validate the various tools and development methodologies on two Industry use cases.

Added Value

Thanks to a rapid prototyping approach and emulation with associated IDE plugins, TANGO helps developers to better understand how to model sofware components in their application architecture to exploit adequately the capabilities offered by various types of heterogeneous hardware. The runtime middleware components of the TANGO toolbox also helps to abstract away from the implementation complexity of compiling, deploying and executing software on heterogeneous hardware effectively available at operation time.