insideHPC talks with Vsevolod (Seva) Opanasenko, CEO of T-Platforms Group
T-Platforms Group, headquartered in Moscow, has quietly been expanding its installed base throughout Russia and CIS, now approaching 200 supercomputer installations, and starting to build a presence in Western Europe. The company’s next-generation operating system, Clustrx, combined with an innovative architectural approach, is getting significant attention in the HPC community.
Last week they announced the award of a $6 million nanotechnology and supercomputing enablement program funded by the Russian Corporation of Nanotechnologies, Rusnano. The program is somewhat unique and could stand out as a model for other countries in that it is designed to create real-world adoption of advanced HPC and nanotechnologies in production environments.
Neither T-Platforms nor Rusnano are very well known throughout this community, so we wanted to give our readers more insight to both this announcement and the organizations behind it. We were fortunate to catch up with Vsevolod (Seva) Opanasenko, CEO of T-Platforms Group, and as a result, are pleased to bring you this feature interview.
insideHPC: Can you tell us a little more about Rusnano?
Vsevolod (Seva) Opanasenko: Rusnano is the Russian Corporation of Nanotechnology and was established by the Russian government in 2007 as a state corporation chartered to co-invest in nanotechnology and supercomputing industry projects that have high commercial potential or social benefit. The corporation also provides scientific and educational programs to help ensure the success of the various investment projects.
Collaborative funding from Rusnano is very specific toward the development of actual real-life simulations to bring companies immediate value and benefits — accelerating the evaluation and analysis of the impact of supercomputing to industrial and scientific discovery. Overall, the Rusnano program goals have been established to eliminate technical barriers to adoption and to improve production and productivity.
insideHPC: What are some of the specific deliverables from this program, and what level of support will organizations receive?
Seva: Well first, T-Services will oversee the project management for this program. We will accept and review the many submissions to determine their feasibility based on a number of criteria such as potential importance, practicality, possible ROI, and applicability to spawning commercially sound results or products.
There are two engagement scenarios we anticipate as being ideally suited for this program: organizations that have appropriate computational tasks identified but have no expertise or computational capacity, or those who have the expertise in software and need only the computational capacity.
We will provide extensive consulting expertise from helping to fully define the computational problems being addressed, to preparing the task budgets, and finally selecting the most promising tasks to be presented to the Rusnano Expert Council. Then, once an organization is engaged in the program, T-Services will provide, as necessary, the actual modeling, simulation and analysis of the computational tasks. This in itself makes this program quite unique — setting it apart from other programs in which organizations are granted use of computers — but nothing at this level of deep technical support.
It’s actually quite amazing to think that the program will fund the efforts for 40 different tasks — half of the selected tasks will be directly involved with nanotechnology, or nanoscience, and half will be in support of engineering efforts in areas such as shipbuilding, aerospace, oil and gas, chemistry, pharmaceuticals, energy and construction.
insideHPC: Could you expand on that just a bit. What kind of tasks?
Seva: Well, think of this as a nanotechnology / HPC industry watershed. Essentially, half of the tasks should come from industrial companies and organizations engaged in actual, real-life production or manufacturing, while the other 50% can come from the organizations involved in science and R&D. The bottom line though is that these task — or projects — should be aimed at research and development of technologies that can subsequently be commercialized. So, for example, an organization might have a very creative approach requiring a new computational process that could greatly assist in the search for new oil or gas deposits. But, the type or capability of computer power may be way out of their reach, or they may not even have the in-house expertise to develop the software for modeling and simulating the process. If the potential for this task looks promising and fits the program criteria, they could in theory receive funding that would provide both the computational cycles and the deep technical expertise necessary to proceed to a proof of concept stage — and even on to production.
insideHPC: Will this program have an impact on HPC adoption outside of Russia?
Seva: HPC adoption, in general, and having nothing to do with geography, faces many barriers when it comes to commercial organizations. HPC systems, historically, have not been practical for organizations without specific expertise in this area of computing. The lack of talent such as the skilled resources needed to develop modeling and simulation software is a deal breaker for many companies. The high Total Cost of Ownership (TCO) often associated with HPC systems has made it extremely difficult for smaller and mid-size companies to justify moving in this direction — especially without a proof of concept, which is essentially impossible to provide in the absence of professional end-to-end technical services.
Programs such as the U.S. Department of Energy’s INCITE program, will give away approximately 1.6 billion supercomputer processor hours in 2011. This is an amazing commitment on the part of the U.S. Federal Government to accelerate scientific discovery. However, and not to downplay the vital importance of this program in any way, but this type of program only helps those organizations who already have extensive modeling and simulations expertise in place. In contrast, the Rusnano program is designed to engage companies with little or no expertise in these areas of advanced computing. An organization only has to have an idea of how relatively large-scale computation, modeling and simulation could help. The organization doesn’t have to boast expertise in software or even have CAD models. In Russia, this will help to ignite many innovative tasks with companies who would not get there on their own. But, beyond Russia, this is an example of market building on a much broader scale. The Rusnano program will bring HPC into many new companies to advance discovery in nanotechnology, a number of scientific research disciplines, and critical production areas requiring advanced computation — with both the supercomputing physical resources and the technical expertise necessary to make it happen.
insideHPC: So, the contract described in this announcement is between Rusnano and T-Services, which I understand is a T-Platforms Group company. Can you tell us a little more about T-Services?
Seva: You are correct in that T-Services is one of the T-Platforms Group companies. The easiest way to describe the unique value proposition of T-Services is to discuss it in the context of T-Platforms.
T-Platforms provides solution integration consulting to assist with basic HPC enablement such as hardware integration and system configuration as well as software optimization focused on helping customers improve application performance. The technical benchmarking and integration specialists at T-Platforms work with customers to develop optimum hardware and software configurations, matching the unique requirements of the user, along with application software optimization to achieve improved application performance where necessary.
T-Services however provides end-to-end simulations and modeling for customers using a wide range of traditional HPC applications. The company’s deep technical expertise includes disciplines such as CFD and structural analysis. T-Services also offers supercomputer center management services to deliver maximum effective use of all HPC systems to improve an organization’s ROI, as well as on-demand computing services from simply allocating compute cycles to implementation, operations and administration of commercial software packages.
The powerful combination of T-Platforms’ flexible hardware architecture and technical system management expertise, combined with the end-to-end modeling, simulation and technical services available from T-Services, enables organizations to achieve time-to-solution advantages while avoiding pre-packaged, pre-configured systems ill-suited to their unique challenges.
T-Services delivers value to organizations who only need HPC occasionally — or would rather outsource certain parts of the HPC simulation workflow.
Another level of support offered by T-Services is management of supercomputer sites. T-Services can act as a management company, taking responsibility for all resources and providing not only the operation and administration talent, but also managing the workflow with customers, from marketing and sales to actually doing the technical tasks.
insideHPC: And can you elaborate just a bit on the working process of this program and the role T-Services will play in the overall program management?
Seva: Sure. This program is actually very well structured and organized. The first stage is the initial evaluation and selection phase. T-Services will interface with all the applicants to help define the proposed tasks, identify and choose appropriate software, establish the proposed working budgets for each task, and generally organize the selected applicants and task descriptions, along with all the requirements for submission to the Rusnano Expert Council.
Then, for the next stage, members of the Rusnano Expert Council will review the submissions based on the defined criteria which I can break down into six pieces.
- Does the project fit the scope of industries authorized for this program?
- Is HPC really needed and applicable?
- Is the project innovative — and could it lead to creation of an original technology?
- Can this project be co-financed by the author of the problem?
- Specific to industry — how would any potential profit from solving this computational problem be measured for the organization?
- Specific to research organizations — might this research lead to creating a technology with a good commercialization potential?
insideHPC: What organizations are eligible for consideration within this program and how would they apply? What do they need to know?
Seva: This program is being launched within Russia only. Any organization, either research or industrial, nano or other qualified industries, may apply, but their ideas should meet the criteria of Rusnano that we’ve mentioned. Organizations should note that the Rusnano Expert Council includes representatives from Rusnano, experts in modeling in engineering and nano applications (not ISVs but users), experts from industry and nanoscience (to evaluate the potential benefits to industry and the degree of innovation of the projects), a representative from the government, and even a representative of a T-Services competitor, to control budget evaluations and methods chosen by T-Services. The organizations apply first to T-Services through the web-site, submitting their ideas and explaining their correspondence to the criteria, and then after the evaluation process mentioned earlier, T-Services submits the chosen projects to the Rusnano Expert council.
insideHPC: How long will this program run? What will happen when the program ends?
Seva: Overall, 10 months. The expert council gathers several times through the project but it should select all the 40 tasks within 5 months from the project start — otherwise some simulation tasks that take a couple of months to complete might not be fulfilled in the program’s identified window of ten months. The preliminary results should be presented and evaluated seven months from the project start.
So, there should be at least 40 computational problems corresponding to criteria and approved by the council. The level of co-financing from the participating organizations will be an important measure of success. And finally, upon completion, Rusnano will consider whether it is worthwhile to build a supercomputer center for collective use, for nano and other industries.