European Processor Initiative | |
---|---|
![]() | |
Country | European Union (mainly France [1] ) |
Ministry | EuroHPC |
Launched | December 2018 [2] [3] |
Budget | 70.000.000€ [4] |
Website | european-processor-initiative |
European Processor Initiative (EPI) is a European processor project to design and build a new family of European low-power processors for supercomputers, Big Data, automotive, [5] and offering high performance on traditional high-performance computing (HPC) applications and emerging applications such as on machine learning. It is led by a consortium of European companies and universities.
The project is divided in multiple phases funded under Specific Grant Agreements. The first grant agreement is implemented under the European Commission program Horizon 2020 (FPA: 800928) in the December 2018 to November 2021 time span. The second agreement will be implemented afterwards under the EuroHPC Joint Undertaking which issued a call, which was answered in January 2021 by the same consortium (H2020-JTI-EuroHPC-2020-02 FPA in EPI (phase II)).
The processor that is to be developed is a system on a chip (SoC) that makes use of the RISC technology, implements microprocessor cores of ARM architecture and accelerators, and specialises in matrix calculations and deep learning for artificial intelligence. The processor is designed to be integrated in an exascale supercomputer, but also to be implemented in cars.
The aim of the EPI project is to design and build a high-performance, low-power processor, implementing vector instructions and specific accelerators, such as accelerators for AI, with high-bandwidth memory access. The design will be based on the results obtained through an intensive use of simulation, the development of a complete software stack and the use of advanced semiconductor manufacturing technologies. During the development of the processor, a co-design methodology will be implemented to ensure that the processor is suitable for efficiently running many applications and that it is equipped with the appropriate software development tools. The objective of the EPI is to develop European know-how on the design and construction of processors for high-performance computing, allowing Europe technological sovereignty.[ citation needed ]
EPI is a non-legal entity, a project organized by 30 institutions from 10 countries in Europe. The members of the consortium are: [6]
Organization | type | Industry | Country |
---|---|---|---|
Atos | Company | IT services and consulting | ![]() |
BSC | Public research center | Supercomputing | ![]() |
Infineon | Company | Semiconductors | ![]() |
Semidynamics | Company | Semiconductors | ![]() |
CEA | Public research center | Energy, defense, security, IT, health | ![]() |
Chalmers University of Technology | Private university | Scientific and technological research, education | ![]() |
ETH Zurich | Public university | Scientific and technological research, education | ![]() |
Foundation for Research & Technology – Hellas | Public research center | Scientific and technological research | ![]() |
GENCI | State-owned company | Supercomputing | ![]() |
Tecnico Lisboa | Public university | Scientific and technological research, education | ![]() |
Forschungszentrum Jülich | Public research center | Scientific and technological research | ![]() |
University of Bologna | Public university | Scientific and technological research, education | ![]() |
Faculty of Electrical Engineering and Computing, University of Zagreb | Public university | Scientific and technological research, education | ![]() |
Fraunhofer | Public research center | Applied science | ![]() |
STMicroelectronics Italy | Company | Semiconductors | ![]() |
E4 Computer Engineering | Company | Engineering | ![]() |
University of Pisa | Public university | Scientific and technological research, education | ![]() |
Surf | Public research center | Scientific and technological research | ![]() |
Kalray | Company | Semiconductors | ![]() |
Extoll | Company | Semiconductors | ![]() |
CINECA | Public research center | Scientific and technological research | ![]() |
BMW Group | Company | Automobile | ![]() |
Elektrobit | Company | Automobile, software | ![]() |
Prove & Run | Company | Software | ![]() |
Karlsruhe Institute of Technology | Public university | Scientific and technological research, education | ![]() |
Menta | Company | Semiconductors | ![]() |
SiPearl | Company | Semiconductors | ![]() ![]() |
Kernkonzept | Company | Software | ![]() |
Leonardo | Company | Software | ![]() |
ZeroPoint Technologies | Company | Software | ![]() |
The initiative started in 2015, in the aim to produce an exascale supercomputer by 2023. The first phase of the project started in December 2018. [7] In the summer of 2019, the basis of the architecture was decided. [8] In January 2020, the first prototype was presented. [9]
The European Processor Initiative has five streams of operation. The first four are technical streams (Common Platform and Global Architecture, HPC General Purpose Processor, Accelerator, Automotive platform), while the last one is dedicated to the coordination and communication activities.
A supercomputer is a type of computer with a high level of performance as compared to a general-purpose computer. The performance of a supercomputer is commonly measured in floating-point operations per second (FLOPS) instead of million instructions per second (MIPS). Since 2017, supercomputers have existed which can perform over 1017 FLOPS (a hundred quadrillion FLOPS, 100 petaFLOPS or 100 PFLOPS). For comparison, a desktop computer has performance in the range of hundreds of gigaFLOPS (1011) to tens of teraFLOPS (1013). Since November 2017, all of the world's fastest 500 supercomputers run on Linux-based operating systems. Additional research is being conducted in the United States, the European Union, Taiwan, Japan, and China to build faster, more powerful and technologically superior exascale supercomputers.
High-performance computing (HPC) uses supercomputers and computer clusters to solve advanced computation problems.
Forschungszentrum Jülich (FZJ) is a German national research institution that pursues interdisciplinary research in the fields of energy, information, and bioeconomy. It operates a broad range of research infrastructures like supercomputers, an atmospheric simulation chamber, electron microscopes, a particle accelerator, cleanrooms for nanotechnology, among other things. Current research priorities include the structural change in the Rhineland lignite-mining region, hydrogen, and quantum technologies. As a member of the Helmholtz Association with roughly 6,800 employees in ten institutes and 80 subinstitutes, Jülich is one of the largest research institutions in Europe.
MareNostrum is the main supercomputer in the Barcelona Supercomputing Center. It is the most powerful supercomputer in Spain, one of thirteen supercomputers in the Spanish Supercomputing Network and one of the seven supercomputers of the European infrastructure PRACE.
The TOP500 project ranks and details the 500 most powerful non-distributed computer systems in the world. The project was started in 1993 and publishes an updated list of the supercomputers twice a year. The first of these updates always coincides with the International Supercomputing Conference in June, and the second is presented at the ACM/IEEE Supercomputing Conference in November. The project aims to provide a reliable basis for tracking and detecting trends in high-performance computing and bases rankings on HPL benchmarks, a portable implementation of the high-performance LINPACK benchmark written in Fortran for distributed-memory computers.
Arm Holdings plc is a British semiconductor and software design company based in Cambridge, England, whose primary business is the design of central processing unit (CPU) cores that implement the ARM architecture family of instruction sets. It also designs other chips, provides software development tools under the DS-5, RealView and Keil brands, and provides systems and platforms, system-on-a-chip (SoC) infrastructure and software. As a "holding" company, it also holds shares of other companies. Since 2016, it has been majority owned by Japanese conglomerate SoftBank Group.
Manycore processors are special kinds of multi-core processors designed for a high degree of parallel processing, containing numerous simpler, independent processor cores. Manycore processors are used extensively in embedded computers and high-performance computing.
Exascale computing refers to computing systems capable of calculating at least "1018 IEEE 754 Double Precision (64-bit) operations (multiplications and/or additions) per second (exaFLOPS)"; it is a measure of supercomputer performance.
Eurotech is a company dedicated to the research, development, production and marketing of miniature computers (NanoPCs) and high performance computers (HPCs).
Zero ASIC Corporation, formerly Adapteva, Inc., is a fabless semiconductor company focusing on low power many core microprocessor design. The company was the second company to announce a design with 1,000 specialized processing cores on a single integrated circuit.
Several centers for supercomputing exist across Europe, and distributed access to them is coordinated by European initiatives to facilitate high-performance computing. One such initiative, the HPC Europa project, fits within the Distributed European Infrastructure for Supercomputing Applications (DEISA), which was formed in 2002 as a consortium of eleven supercomputing centers from seven European countries. Operating within the CORDIS framework, HPC Europa aims to provide access to supercomputers across Europe.
The HPC-Europa programmes are European Union (EU) funded research initiatives in the field of high-performance computing (HPC). The programmes concentrate on the development of a European Research Area, and in particular, improving the ability of European researchers to access the European supercomputing infrastructure provided by the programmes' partners. The programme is currently in its third iteration, known as "HPC-Europa3" or "HPCE3", and fully titled the "Transnational Access Programme for a Pan-European Network of HPC Research Infrastructures and Laboratories for scientific computing".
Xeon Phi is a discontinued series of x86 manycore processors designed and made by Intel. It was intended for use in supercomputers, servers, and high-end workstations. Its architecture allowed use of standard programming languages and application programming interfaces (APIs) such as OpenMP.
T-Platforms was a Russian supercomputer company. Their main competitor was RSC Group.
The Hartree Centre is a high performance computing, data analytics and artificial intelligence (AI) research facility focused on industry-led challenges. It was formed in 2012 at Daresbury Laboratory on the Sci-Tech Daresbury science and innovation campus in Cheshire, UK. The Hartree Centre is part of the Science and Technology Facilities Council (STFC) which itself is part of United Kingdom Research and Innovation (UKRI).
The Sunway TaihuLight is a Chinese supercomputer which, as of November 2023, is ranked 11th in the TOP500 list, with a LINPACK benchmark rating of 93 petaflops. The name is translated as divine power, the light of Taihu Lake. This is nearly three times as fast as the previous Tianhe-2, which ran at 34 petaflops. As of June 2017, it is ranked as the 16th most energy-efficient supercomputer in the Green500, with an efficiency of 6.1 GFlops/watt. It was designed by the National Research Center of Parallel Computer Engineering & Technology (NRCPC) and is located at the National Supercomputing Center in Wuxi in the city of Wuxi, in Jiangsu province, China.
The European High-Performance Computing Joint Undertaking is a public-private partnership in High Performance Computing (HPC), enabling the pooling of European Union–level resources with the resources of participating EU Member States and participating associated states of the Horizon Europe and Digital Europe programmes, as well as private stakeholders. The Joint Undertaking has the twin stated aims of developing a pan-European supercomputing infrastructure, and supporting research and innovation activities. Located in Luxembourg City, Luxembourg, the Joint Undertaking started operating in November 2018 under the control of the European Commission and became autonomous in 2020.
Fugaku(Japanese: 富岳) is a petascale supercomputer at the Riken Center for Computational Science in Kobe, Japan. It started development in 2014 as the successor to the K computer and made its debut in 2020. It is named after an alternative name for Mount Fuji.
The A64FX is a 64-bit ARM architecture microprocessor designed by Fujitsu. The processor is replacing the SPARC64 V as Fujitsu's processor for supercomputer applications. It powers the Fugaku supercomputer, ranked in the TOP500 as the fastest supercomputer in the world from June 2020, until falling to second place behind Frontier in June 2022.
Aurora is an exascale supercomputer that was sponsored by the United States Department of Energy (DOE) and designed by Intel and Cray for the Argonne National Laboratory. It has been the second fastest supercomputer in the world since 2023. It is expected that after optimizing its performance it will exceed 2 ExaFLOPS, making it the fastest computer ever.