Analyzing the market, we have found the importance of exploiting parallelism is of increasing significance, as parallelization has become a dominant method of delivering higher performance and improved energy efficiency.
In this context, some of the biggest challenges to future application performance are:
- Future application performance lie with not only efficient node-level execution but power consumption as well,
- Developers need to fully understand, and use an approach that abstracts, the nuances of different hardware configurations and software systems (both rapidly evolving),
- Developers need ways to address additional difficulties in performance, security mixed-criticality and power consumption resulting from the heterogeneous system.
- An important step in software design for low power is that software must correctly fit to the capabilities of the underlying (and heterogeneous) hardware.
Simplify & Optimize Heterogeneity: Simplifying the way programmers approach the development of next generation applications.
TANGO tools help control and abstract underlying heterogeneous hardware architectures, configurations and software systems including heterogeneous clusters, chips and programmable logic devices while providing tools to optimize various dimensions of software design and operations (energy efficiency, performance, data movement and location, cost, time-criticality, security, dependability on target architectures).
The results will be packaged and released in TANGO Toolbox as Open Source. The toolbox will include:
- A toolbox based implementation of the reference architecture
- Reference software development models and methodologies for best practice
- A collection of reusable IDE plugins, programming models and runtimes
- An adaptive quality model for holistic system performance
- Automatic code generation including software and hardware energy modeling.
TANGO will impact on both the IT industry and the market. It will also impact on the research community advancing future application development processes to a new stage in which the development process for parallel architectures will be simplified, abstracted from underlying architectures and hardware, and will enable tools to consider optimized control and self-adaptation.
Besides the release of the technologies under an Open Source approach, TANGO considers the foundation of a research alliance –TANGO Heterogeneous Hardware Alliance (HHW Alliance), in which it will seek complementary efforts of other research projects, initiatives and IT community organizations to nurture a strong research collaboration, integration and effective promotion of the results and continue evolving the work done during the project to become a relevant influencer in the developing HHW market.
More concretely, we identify potential in the following contexts:
- Abstracting hardware heterogeneity to help create & operate next-gen apps
- Embracing new hardware in the Data Center extending HPC workloads
- Code taking control of Performance vs Energy Awareness