Each of the following is a collection of feedback from our recent inquiry from different HPC Europe online users...
Which HPC technology areas should the EU focus
its investment and support?
Technologies optimizing utilization of existing hardware - Also links to green values
Technologies improving application scalability.
Algorithms &Software for scaling on manycore architectures
Apps and tools.
Development of desktop supercomputing and software development
Energy efficiency in all its aspects; Environmental savings
Energy saving technologies for HPC, to minimize the energy consumption of the future computers
Engineering beyond sillicon; solar cells; biochips
EU should major in scalable algorithms and make everything else secondary. However, they would need to guarantee what the target platform downstream would be.
HPC systems, interconnect, middleware and system software,
HPC systems, interconnects, storage and applications scaling
HPC usability, Open source HPC toolkits, HPC-Clouds, FPGA-based HPC/FPGA-Clouds
Hybrid HPC systems & Exascale software
Infrastructure deployment and management solutions (the final piece of the “commoditization” puzzle?)
Integration of hardware especially interconnects and software, and software development
Intermediate software : between middleware and the applications; or between OS and the applications; innovative, environmental friendly and sustainable solutions for hosting very large infrastructures
Keep usability of HPC for domain scientists in focus, i.e. scientific visualization, provide systems insight through advanced hardware-software co-design
New applications software; Systems software, including operating systems; Parallel programming tools Debugging tools; Interconnect software; Storage software/file systems
Parallel computing, power saving
Parallel Programming on large Multicore systems
Reduce electrical power required to operate HPC facilities
Scalability of applications and tools; Interconnects; Energy Efficiency
Scalability techniques and programming and analysis tools towards Petascale and Exascale systems; Accelerators (GPGPUs; but also: capabilities of Quantum Computing) Energy-efficient highly parallel computer systems (like QPACE) Interconnect software for massively parallel computer systems
Scalability, programming models and tools, Application with strong focus on engineering
Software (message passing algorithms, solvers and workload management).
Software and applications
Software and optimization of scientific applications
Software development (system software, libraries), computer parallel languages both for general purpose CPUs and accelerators (FPGAs, GPGPUs, etc.) and interconnect future technologies.
Software systems because there is a lot of opportunity for improvement/leadership
Software: new paradigms and languages for parallel computing
Software, integration work, data, innovative computing (new methods and tools such as GPUs),green HPC
System architecture and integration Energy efficiency
Systems and software
The areas in which it has leadership since losing those will put Europe in an even worse condition
Very low latency interconnects, low-power technology (could be materials science), at processor level Europe is stronger in embedded computing.
WEATHER.NUCLEAR FUSION, ATOMIC RESEARCH, OCEAN RESEARCH, CRIME
How should EU change HPC market structures
or business models?
Provision of robust and persisting funding at EU level; 2) Synergies through mobilizing additional national or regional funding; 3) A bold attitude towards risk investment in science and engineering development beyond the boundaries of the bureaucratic precaution; 4) Promotion the way towards stronger funding involvement of industry through Public-Private Partnerships Models; 5) More aggressive approach when we talk about State Aid support.
Encourage smarter ways to access the HPC resources: community members receive (grant based on their scientific excellence, or buy) ” access vouchers” to HPC systems and services to use on a set of different infrastructures; crate a quality label for HPC and transnational clouds
Establish European Vendors
Introduce some pre-competitive approaches (cf 23) + foster the development of open source services offer (OS, middleware, libraries etc.)
It depends about the exact meaning of this question. Avoid PFI/PPP style approaches as they only focus on the short term and have proven to be counter productive. But yes, changes will be required in order to address the cohesion of the ecosystem and incentivise stakeholders to address challenges highlighted earlier.
Launch precompetitive programs and fund R&D
More focus on usability and scientific results
More investing on researches
Stop building supercomputers directly under the supervision of the EU. Support European utility HPC vendors
Switch from short-term to long-term ROI model and involve SME’s and industries
Try to establish at least two competing international manufacturers/vendors of European base.
What publc-private partnerships should the EU explore in HPC?
“Partnerships” are too often used to get a foot in the door. Emphasis should be on getting “better” engineering work done without expecting immediate financial backing from the industry. Results should be available to the community at large. I have been interpreting ”Private” in this context as “Industry”.
Please avoid this model, as it favours short term profit and compliance with KPIs above any other considerations.
A.) EU level: A form of PPP such as Joint Technology Initiatives in these technology areas where EU has competitive advantages B.) Regional level: Creation of Regional Associations including government, industries and research representatives form more than three countries. C.) National level: Government – National Associations for HPC; Government – National Associations for HPC – Industry; Government – National Associations for HPC – Industry – Universities and Research Institutions; and other combinations among these legal entities for the next activities: 1. execution of HPC projects; 2. HPC modernization of existing hardware, software and applications; 3. definition of strategic priorities, carrying out research HPC projects and promotion of the relationship: research - product.
ClusterVision is the only European HPC company with HPC as our core business. We would be very keen to start a dialogue with EU representatives, thus sharing information we currently have on the European market, sharing ideas on the EU HPC market growth, etc.
Co-financing grants for SME to use HPC centers facilities
Collaboration agreement to help developing/improving new technology and address wide markets
Continue with JuRoPa like R&D projects, as cooperations between HPC centers and industry.
Development of exascale applications
EU has to have partnership only with private companies would truly invest on research on HPC. Private-public partnership has to be evaluated by really independent experts.
Help in the emergence of vendors providing HPC-Clouds. Use its critical mass to negotiate contracts/prices on behalf of the European research institutions with HPC/HPC-Clouds/Clouds vendors. Negotiate contacts/prices with the vendors of software involved in large scale computational research. Work with the software vendors in redefining their pricing models towards a pay-per-use model.
HPC vendor + academia + computing centre, funding prototypes
If the “real” PPP model is questioned, then it is usually applied to build public infrastructure for private money to get this investment cost back through fees from users. It is difficult to imagine such a model for scientific community as the users paying fees to private investor for using supercomputer.
In almost all sectors like aviation industry, automotive, life sciences, nano-technology
In my view there is very little room for European partnership and the existing partnerships with non-European companies cannot be avoided but should be more “controlled”, so to speak.
Industry (Users and IT) and Academia
Integration of hard and software
Partnerships with HPC hardware vendors such as IBM, NEC, Intel
Partnerships with key European industries that have walked away from HPC (automotive for example), providing free access to large HPC facilities thru an INCITE like program
Partnerships with some industry sectors as users (aviation, utility companies, automotive, etc.) as well as vendors, big hardware/software vendors as well as software SMEs.
Perhaps real injection of effort into assisting commercial apps development (rather than just University based research programmes) to accelerate to market, EU based codes to be deployed on large scale multi-core for example or to run in an HPC cloud environment efficiently.
Pre competitive procurement procedure co-funding with industrial end-users.
Projects involving vendors / academia and not forgetting HPC centers that have great expertise and the end-use knowledge.
Technology and integration partnerships
Through PRACE-STRATOS, under FPx supervision if so wanted, set up long term relation ships between industry and public research institutes/universities (1:1:1-funding) & An INCITE type program for SME’s