Developers Club geek daily blog

The high-speed file transfer protocol – Aspera FASP

1 year, 7 months ago


Now, in a century of popularity the Internet and various content, including media which size in HD quality can occupy several Gigabyte most sharply there was a problem of a high-speed file transfer on a network. As an example it is possible to consider work of news television station where the reporter, being on other continent, has to transfer quickly the reporting shot in high quality to the central studio for processing and start in air. It is clear, that here transfer speed plays a key role as news will not be news any more if it appears in couple of days.

Or, for example, in a case when floating boring installation on which there is only satellite channel has to transfer a cube of geophysical data of drilling of a well for interpretation to high-performance computer centers, every day can lead delays to losses.

Read more »


Low-level optimization of parallel algorithms or SIMD in .NET

1 year, 7 months ago
image

Now the huge number of tasks demands the big performance of systems. Infinitely physical restrictions do not allow to increase the number of transistors on a processor crystal. The geometrical sizes of transistors cannot be reduced physically as when exceeding perhaps admissible sizes the phenomena which are not noticeable at the big sizes of active elements begin to be shown — quantum size effects begin to affect strongly. Transistors begin to work not as transistors.
And Moore's law here at anything. It was and remains the law of cost, and increase in number of transistors on a crystal is rather consequence from the law. Thus, to increase the power of computer systems it is necessary to look for other methods. This use of multiprocessors, multicomputers. Such approach is characterized by a large number of processor elements that execution of subtasks on each computing device brings to independent.

Read more »


IBM continues work with Apache Spark: the corporation starts Spark-as-a-service

1 year, 7 months ago


At conference it became known earlier that Apache Spark for Linux will be supported by z Systems.

Such support will be performed within the "analytics on mainframes" project. Thanks to it specialists on date-mayningu will be able to use Apache Spark on powerful mainframes of z Systems.

Read more »


IBM opens blockchain-laboratory

1 year, 7 months ago


The IBM corporation together with Innovate Finance non-profit organization is going to carry out studying of potential of the Blockchain technology for the purpose of development of new methods of business in modern conditions. On the basis of this technology the system of cryptocurrency Bitcoin which is successfully functioning several years was created. The cryptocurrency turned now into recognized means of payment, virtual monetary unit which is accepted by the large and small enterprises, corporations and services.

Now IBM is going to study additional opportunities of Blockchain, involving own computational and analytical capabilities. The technology about which there is a speech draws now attention of banks and financial structures which study Blockchain for the purpose of implementation of new projects.

Read more »


AI, BigData &HPC Digest #3

1 year, 7 months ago


Hi, Habr!

Our FlyElephant command wants to congratulate all with coming New Year, to wish all the best and successful implementation of all conceived projects forthcoming year and that at the weekend was what to esteem, we publish fresh number of the digest. Today in release a traditional selection of interesting links on news and materials in the directions: artificial intelligence, big data and high-performance calculations.

On January 14th we will hold a webinar on Introduction to machine learning"" on which we will talk about history and the basic concepts of machine learning. Let's consider popular problems / algorithms of machine learning, and also we will start their examples by means of FlyElephantthe platform and we learn as it is possible to use this platform for a solution of problems of artificial intelligence. It is possible to be registered on a webinar here.

Read more »


We increase search performance by means of an index partitsionirovaniye in Apache Solr

1 year, 7 months ago


Full-text search is used in Wrike almost everywhere. Search in the heading of the page gives the chance of quick access to the last tasks with sorting according to date of updating, with coincidence according to the name. Such option of search is presented in the sections "My Work" and "Task bar".
Search in the task list works on all fields: name, description, names of files of attachments, authors, comments, date of change. The maximum priority at tasks on which activity is connected with the current user, with phrase coincidence in the name, the description or in comments.
The simplified option of search in names is used:
  • at arrangement of dependences for Gant's chart (the previous and subsequent tasks),
  • when adding links to tasks of names (menshening),
  • when adding subtasks.

In these sections instant search with implicit wildcard is used: the user consistently enters u, up, upd, update, and search queries take a form: u *, up *, upd *, update*.
Besides, wildcards can be used in all options of search.
Thus, the "heavy" search queries causing repeated reading an index, the raised loading on CPU/IO on servers and, as a result, the general delays in request processing in "rush hours" often come.
In this article we will share the method of a solution of the problem of performance.
It will be a question of acceleration of search during the work with a search server of Apache Solr through a partitsionirovaniye of collections. The described method was tested by us on versions 4.9.0 and 4.10.2.

Read more »


I want that the websites opened instantly

1 year, 7 months ago
Hello, my name is Alexander Zelenin and I am web developer. I will tell how to make so that your website opened quickly. Very quickly.


Read more »


Development of the digital equipment on C ++/SystemC eyes of SystemVerilog of the programmer

1 year, 7 months ago


SystemC is a library for C ++ allowing to model various hardware systems at the different abstraction layer. It is supported as the traditional discrete and event modeling usual to programmers on Verilog and VHDL, and analog modeling in the spirit of SPICE/Verilog AMS. The library and methodology for virtual prototyping, library for writing of test environments and verification with use of randomized tests is also included in the package.

In this I will tell about a synthesizable subset of SystemC, comparing it to synthesizable SystemVerilog. I use SystemC about 3 years, and before wrote several years on Verilog/SystemVerilog. I will try to cover a subject from the different parties: since philosophical reasonings on origins of SystemC, the short overview of an ecosystem and tools and finishing with practical examples of syntax and semantics.

It is meant that readers are familiar with Verilog and C ++.

Read more »


The NetApp company declared purchase of SolidFire

1 year, 7 months ago
NetApp, inc signed the agreement on purchase of SolidFire, inc for 870 million a dale. USA cash.

Founded in 2010, SolidFire is a vendor of All Flash of storages for DPC of new generation where "configured simple scaling and management in a type and forgot" provides performance and the joint Multy-Tenancy environment.



With SolidFire NetApp will give the new sentence which will cover each of three parts of the All Flash market of storages:

  • For traditional infrastructures of Enterprise of customers, NetApp All Flas FAS (AFF), a product line which provides functions and possibilities of Enterprise of level.
  • For owners of applications, NetApp EF a series of the products showing incredibly high values of performance at the same time low speed of a response (Latency) according to open testing SPC-1, and also high availability "six nine".
  • For customers with infrastructures of new generation, the products from SolidFire distributed, self-repairing and the extending architecture, reasonable price and simple management.


SolidFire is active in cloudy community and provides to integrate an uravleniye storage by means of VMware vCenter plug-in, VAAI, SRM, OpenStack driver, CloudStack plug-in, Microsoft VSS provider, PowerShell, VMware SRM/SRA and other cloud solutions.

Through time products of SolidFire will be integrated into a paradigm of NetApp DataFabric providing seamless management of cloudy resources, and also the flash-resources and disk arrays.

Read more »


We invite to Tarantool meetup on January 28

1 year, 7 months ago


On January 28, 2016 in the Moscow office of Mail.Ru Group there will take place the second meeting of Tarantool meetup. If someone else does not know: Tarantool is the NoSQL In-Memory DBMS open source which is created for ensuring the greatest possible performance. On the second mitap we will consider the main benefits and features of Tarantool, we will tell about the experience of use of this product and plans for the future. First of all this meeting will be interesting to the developers, Unix-system administrators and other specialists anyway working with databases. You watch the program of a meeting under a cat.

Read more »