Theory of a Large Supercomputer
Dell HPC comes to the aid of scientists
We have repeatedly heard about British scientists who gave the world more than a dozen discoveries of varying degrees of doubtfulness. But discussing the next of them, we rarely think about how discoveries are generally made and what is needed for them to take place. Let us set aside the scientific base, experience and training of scientists (this is all a topic for a separate material), and concentrate on the technological component of their work. It is logical to assume that in modern universities calculations are made on powerful modern equipment, experiments are conducted on the latest laboratory equipment, otherwise it will be almost impossible to bring something new to science today.
So what kind of technology are used by world-renowned university scientists? What level of computers and servers are able to cope with a crazy load - such as a result of which we are witnessing a new discovery? Today we want to tell about our modest contribution to science and high-performance solution Dell HPC - High Performance Computing.
It all started with the fact that the George Washington University American University had an urgent need to introduce a fundamentally new technology based on a high-performance system that would satisfy all the needs of university staff. The task was initially not easy, because it was about one of the world's largest centers of scientific research. George Washington University accepts students, teachers and researchers from around the world, and its leadership does not hide the desire to make the school one of the best in the United States and, accordingly, to attract the most outstanding specialists to its ranks. For these purposes, the university does not spare money and has already invested a lot in network infrastructure and data storage. But, as it is not hard to guess, this is just a drop in the ocean: the institution badly needed a powerful computational solution.
To make it easier to understand the scale of the calculations that are carried out by university researchers, try to present a thousand million equations with a thousand million unknowns. Only a very powerful system can cope with such tasks. Not only physicists, but also mathematicians, biologists, chemists, and engineers needed a high-performance computer — any exact science in our time cannot move forward without reliable technological support.
')
However, aspiration alone was clearly not enough. The university simply had no place to install computing clusters. If the educational institution were located outside the city, then this problem would not exist, but in urban conditions every square meter was on the account. Companies that took part in the tender offered to split the system into several parts and install small clusters in different buildings, but the management did not like this decision because it made the administration of such a system much more time consuming and time consuming. Thus, the university needed a centralized system that could serve several faculties at the same time.
And it is not known what the matter would have ended if the university management hadn’t turned to Dell on time. The Dell team had discussed their needs with scientists in detail, and as a result the HPC cluster Colonial One was installed in the building of the science and technology building. It consists of 96 nodes, based on Intel Xeon E5-2670 processors. The cluster is integrated with the FDR InfiniBand bus, which provides data transfer rates of up to 54.5 Gbit / s on each port. It combines all the nodes of a cluster with two data storage platforms. The solution is based on Dell PowerEdge C8000 Series servers, 4U flexible chassis, GPUs and storage nodes. The last is the Dell PowerVault MD3260 array, which can hold 180 TB of information in each 4U-high bay. The cluster also includes a HPC Dell | Terascala storage solution - a high-performance 300 TB file system. Any university community can get centralized access to the cluster.
By the way, the merit of Dell lies not only in the fact that we managed to assemble a relatively compact system that fit in one room without sacrificing performance. The fact is that the supercomputer Colonial One was built from scratch in two weeks. Yes, just 14 days.
Time-lapse video of the whole process from different cameras:
With the Dell HPC system, staff at George Washington University were able to conduct research in a shorter time. What used to take weeks, now takes about one or two days - for example, this applies to genetic and microbiological research. Thanks to Colonial One's ultra-productive solution for determining a species or strain from a sample of its DNA, it now takes only 24 hours, while this procedure used to take more than a week. Reducing the time during which the nature of microorganisms is determined means more effective and timely treatment in the future.
In addition, the HPC system allowed scientists to conduct research that was previously unavailable to them due to insufficient computing power of the equipment. The University’s Physics Department, for example, is now mastering new directions in the study of quantum chromodynamics on a lattice. Without certain calculations that only a powerful computer could provide, they were previously unavailable.
The high-performance system Colonial One helps the university's management to attract new researchers to their ranks, since it has almost no analogues in other educational institutions and research centers. Many promising scientists see new opportunities for their work in the HPC-system of Dell - you will agree that very few people will refuse to facilitate their own work and bring another scientific discovery closer.
Another important advantage of implementing such a solution is to simplify cooperation between departments of the university. Previously, physicists, biologists, chemists, engineers worked with local servers, now they were able to use a single centralized system and conduct joint research.
Colonial One will evolve with the university. As the needs of researchers grow, the cluster capacity will increase. The architecture of Dell C8000 allows you to consistently replace components and expand the system, including increasing the capacity of drives. Perhaps, the solution we developed will allow the university to effectively interact with other research organizations.
It is always nice to make your own contribution to the development of science :)
PS A little video in the end
We have repeatedly heard about British scientists who gave the world more than a dozen discoveries of varying degrees of doubtfulness. But discussing the next of them, we rarely think about how discoveries are generally made and what is needed for them to take place. Let us set aside the scientific base, experience and training of scientists (this is all a topic for a separate material), and concentrate on the technological component of their work. It is logical to assume that in modern universities calculations are made on powerful modern equipment, experiments are conducted on the latest laboratory equipment, otherwise it will be almost impossible to bring something new to science today.
So what kind of technology are used by world-renowned university scientists? What level of computers and servers are able to cope with a crazy load - such as a result of which we are witnessing a new discovery? Today we want to tell about our modest contribution to science and high-performance solution Dell HPC - High Performance Computing.
It all started with the fact that the George Washington University American University had an urgent need to introduce a fundamentally new technology based on a high-performance system that would satisfy all the needs of university staff. The task was initially not easy, because it was about one of the world's largest centers of scientific research. George Washington University accepts students, teachers and researchers from around the world, and its leadership does not hide the desire to make the school one of the best in the United States and, accordingly, to attract the most outstanding specialists to its ranks. For these purposes, the university does not spare money and has already invested a lot in network infrastructure and data storage. But, as it is not hard to guess, this is just a drop in the ocean: the institution badly needed a powerful computational solution.
To make it easier to understand the scale of the calculations that are carried out by university researchers, try to present a thousand million equations with a thousand million unknowns. Only a very powerful system can cope with such tasks. Not only physicists, but also mathematicians, biologists, chemists, and engineers needed a high-performance computer — any exact science in our time cannot move forward without reliable technological support.
')
However, aspiration alone was clearly not enough. The university simply had no place to install computing clusters. If the educational institution were located outside the city, then this problem would not exist, but in urban conditions every square meter was on the account. Companies that took part in the tender offered to split the system into several parts and install small clusters in different buildings, but the management did not like this decision because it made the administration of such a system much more time consuming and time consuming. Thus, the university needed a centralized system that could serve several faculties at the same time.
And it is not known what the matter would have ended if the university management hadn’t turned to Dell on time. The Dell team had discussed their needs with scientists in detail, and as a result the HPC cluster Colonial One was installed in the building of the science and technology building. It consists of 96 nodes, based on Intel Xeon E5-2670 processors. The cluster is integrated with the FDR InfiniBand bus, which provides data transfer rates of up to 54.5 Gbit / s on each port. It combines all the nodes of a cluster with two data storage platforms. The solution is based on Dell PowerEdge C8000 Series servers, 4U flexible chassis, GPUs and storage nodes. The last is the Dell PowerVault MD3260 array, which can hold 180 TB of information in each 4U-high bay. The cluster also includes a HPC Dell | Terascala storage solution - a high-performance 300 TB file system. Any university community can get centralized access to the cluster.
By the way, the merit of Dell lies not only in the fact that we managed to assemble a relatively compact system that fit in one room without sacrificing performance. The fact is that the supercomputer Colonial One was built from scratch in two weeks. Yes, just 14 days.
Time-lapse video of the whole process from different cameras:
With the Dell HPC system, staff at George Washington University were able to conduct research in a shorter time. What used to take weeks, now takes about one or two days - for example, this applies to genetic and microbiological research. Thanks to Colonial One's ultra-productive solution for determining a species or strain from a sample of its DNA, it now takes only 24 hours, while this procedure used to take more than a week. Reducing the time during which the nature of microorganisms is determined means more effective and timely treatment in the future.
In addition, the HPC system allowed scientists to conduct research that was previously unavailable to them due to insufficient computing power of the equipment. The University’s Physics Department, for example, is now mastering new directions in the study of quantum chromodynamics on a lattice. Without certain calculations that only a powerful computer could provide, they were previously unavailable.
The high-performance system Colonial One helps the university's management to attract new researchers to their ranks, since it has almost no analogues in other educational institutions and research centers. Many promising scientists see new opportunities for their work in the HPC-system of Dell - you will agree that very few people will refuse to facilitate their own work and bring another scientific discovery closer.
Another important advantage of implementing such a solution is to simplify cooperation between departments of the university. Previously, physicists, biologists, chemists, engineers worked with local servers, now they were able to use a single centralized system and conduct joint research.
Colonial One will evolve with the university. As the needs of researchers grow, the cluster capacity will increase. The architecture of Dell C8000 allows you to consistently replace components and expand the system, including increasing the capacity of drives. Perhaps, the solution we developed will allow the university to effectively interact with other research organizations.
It is always nice to make your own contribution to the development of science :)
PS A little video in the end
Source: https://habr.com/ru/post/203704/
All Articles