TEXTAROSSA (Towards EXtreme scale Technologies and AcceleRatOrS for HW/SW Supercomputing Applications for exascale) has been selected for funding by the European High Performance Computing (EuroHPC) Joint Undertaking as one of the key programs that will innovate and widen the overall efficiency of High Performance Computing (HPC) systems. The three-year project, led by ENEA, aggregates 17 institutions and companies located in 5 European countries: CINI (an Italian consortium grouping together three leading universities, Politecnico di Milano, Università degli Studi di Torino, and Università di Pisa),  FRAUNHOFER (Germany), INRIA (France), ATOS (France), E4 Computer Engineering (Italy), BSC (Spain), PSNC (Poland), INFN (Italy), CNR (Italy), In Quattro (Italy), Université de Bordeaux (France), CINECA (Italy) and Universitat Politècnica de Catalunya (UPC). 

Massive financial and scientific efforts are ongoing to push the scale of HPC infrastructures to the next level, exascale - a scale where a single machine would be able to perform twice as much computation as the current 100 most powerful supercomputers in Europe.

The TEXTAROSSA project aims to achieve a broad impact on the High Performance Computing (HPC) field both in pre-exascale and exascale scenarios. The TEXTAROSSA consortium will develop new hardware accelerators, innovative two-phase cooling equipment, advanced algorithms, methods and software products for traditional HPC domains as well as for emerging domains in High Performance Artificial Intelligence (HPC-AI) and High Performance Data Analytics (HPDA).

To achieve high performance and high energy efficiency on near-future exascale computing systems, a technology gap needs to be bridged: increase efficiency of computation with extreme efficiency in HW and new arithmetics, as well as providing methods and tools for seamless integration of reconfigurable accelerators in heterogeneous HPC multi-node platforms. TEXTAROSSA aims at tackling this gap through applying a co-design approach to develop heterogeneous HPC solutions, supported by the integration and extension of IPs, programming models and tools derived from other European research projects led by TEXTAROSSA partners.

The main directions for innovation that TEXTAROSSA will pursue are:

1. developing energy-efficient HPC solutions by exploiting accelerators, advanced cooling equipment, new and disruptive algorithmic approaches;
2. enabling mixed-precision computing, through the definition of IPs, libraries, and compilers supporting novel data types (including Posits);
3. implementing new multilevel thermal management and an innovative two-phase cooling;
4. ensuring secure HPC operation through HW accelerated cryptography;
5. providing RISC-V based IP for fast task scheduling and IPs for low-latency intra/inter-node communication and improved data-movement/storage through a compression IP.

These technologies will be tested on the Integrated Development Vehicles (IDV) mirroring and extending the European Processor Initiative’s ARM64-based architecture, and on an OpenSequana testbed. To drive the technology development and assess the impact of the proposed innovations from node to system levels, TEXTAROSSA will use a selected but representative number of HPC, HPDA and AI applications covering challenging HPC domains such as general-purpose numerical kernels, High Energy Physics (HEP), Oil & Gas, climate modelling, as well as emerging domains such as High Performance Data Analytics (HPDA) and High Performance Artificial Intelligence (HPC-AI).

Fostering the European competitiveness in the development and deployment of advanced solutions for science and industry, TEXTAROSSA will make available indispensable tools and systems in the competitive and critical field of HPC. It also constitutes a testbed for a EU-developed, innovative two-phase cooling technology to mature and be applied in different architectures.

Politecnico di Milano participates in the project through the HEAP Lab of Dipartimento di Elettronica, Informazione e Bioingegneria, represented by Prof. William Fornaciari and Prof. Giovanni Agosta, who participate in the HPC laboratory of CINI (National Interuniversity Consortium for Informatics).