With the pervasiveness of high-speed computers and processors, computer companies are  looking for new technologies to incorporate into their products and use as a competitive advantage  in the market. Two modern and rapidly growing techniques are quantum computing and the use 

The HPC service at CERN provides linux batch infrastructure to run high performance computing  applications that require MPI clusters.The HPC cluster  is therefore dedicated to run MPI programs. 

This report describes EOS Winston, an event driven alerting and mitigation automation platform.  Through the use of expert rules and online anomaly detection algorithms, it catches events which 

Sepsis is a life-threatening condition where microbes present in the blood stream cause an  unregulated immune response from the body which can result in tissue damage, multi-organ failure 

This report describes performance analysis of the CernVM-FS FUSE which is a software distribution  service used in high-energy physics research. The performance analysis was conducted in both kernel 

The purpose of this report is to provide a brief overview of what OpenStack is, focusing on the  advantages of the integration of its Manila component at CERN. Furthermore, this document briefly 

On this project, we decided to implement two solutions that integrate REANA and GitLab. They vary  on two main points. The first one is the amount of configuration necessary to set up the integration, 

In 2005, the first installation of the Oracle HTML DB came out in production. Very soon the CERN developer community adopted the technology, using it in all the areas of the organization, from administrative applications to accelerators control system.

The IoT security framework is a computer security platform designed to assess the risks of various heterogeneous IoT devices. The framework is currently being developed at CERN and analyses different IoT devices connected to CERN’s General Purpose Network (GPN). The GPN mostly

Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of particles produced in high-energy physics collisions.

Hadoop ecosystem is distributed computing platform for Big Data solutions by comprising  autonomous components such as HDFS, Spark, YARN etc. HDFS is a Hadoop Distributed File  System for data storage. Current HDFS supports 3x replication for data fault-tolerance. When a 

This work has successfully deployed two different use cases of interest for High Energy Physics  using cloud resources:   CMS Big data reduction: This use case consists in running a data reduction workloads for 

T​he CERN Cloud Infrastructure team provides compute resources as a service to teams  across CERN. Users can provision resources to process experiment data, host web  applications, and accomplish other computing tasks. 

The main idea of this project is to carry out performance analysis on the RDataFrame class within the  ROOT operational framework. For this purpose, scalability analysis are performed on the execution 

The Elasticsearch Service is a distributed search and analytics engine widely used across CERN. Currently,  issues in the service are resolved manually after being detected through internal monitoring by service 

On this project we focused on benchmarking Influx against Oracle database. One of the  primary reason is ETM/Seimens were already working on Influx database backend. To  perform benchmarking using the Query Benchmark Tool we needed to have same data 

This report describes the work carried out to study and evaluate the performance and  footprint of different parquet compression codecs on data retrival and  analytics scenarios Parquet is a standard-de-facto and the data format used to persist 

When developing new programs or scientific libraries most of the efforts are focused on providing  efficient algorithms, the state-of-the-art techniques and maximum flexibility. However, in order for a 

The Database Services Group (IT-DB) is responsible for providing database and middleware services to  the laboratory. For these services, it is necessary to provide proper monitoring solutions to different user 

Neutrinos are subatomic particles, very similar to an electron, but without any electrical charge and  a very negligible rest mass. They are the most abundant and perhaps the most mysterious matter  particles in the universe!  

In run 4 of the LHC, the extreme high luminosity is expected to generate an enormous pileup of up to 200  proton-proton collisions for each bunch crossing. This has to be read out at 750 kHz with a maximum 

Big Data Technologies popularity continues to increase each year. The vast amount of data produced at the LHC experiments, which will increase further after the upgrade to HL-LHC, makes the exploration of new ways to perform physics

This project uses Wasserstain Generative Adversatial Networks (WGANs) to supply the demand for large simulation samples in the event of the CMS Phase II Upgrade. The distributions of real

At CERN we have many systems which provide critical services and scheduling downtime for them is quite difficult. Live kernel patching is a technique which aims to update the system without

The High Luminosity upgrade scheduled for 2026 will greatly increase the number of events per collision. Moore’s law will optimistically get a factor 4 performance gain, not enough to handle the

This reports summarises the project I worked on during my internship with the IT-DB-IMS team. This  report will detail my efforts to configure various technologies to work with Java Mission Control, the 

In recent times a tool for efficient unpacking of software work-flows from CernVM File System (CVMFS) into standalone images has become necessary. There are two types of use cases for such images: On the one hand they can be used to deliver

The interest on machine learning workloads in the HEP community has increased exponentially in the last years, making more and more important the need of a thorough benchmarking of the most relevant/significant workloads that are going to run on the experiments. The purpose

On this project, we chose to work with Clair, the tool developed by CoreOS, which uses static analysis to find vulnerabilities in container images. To use Clair, we had to build a Python client,

WinCC Open Architecture is a toolkit for creating Supervisory Control and Data  Acquisition (SCADA) applications, which is widely used at CERN. Hundreds of controls  applications, both in the accelerator complex and the experiments are based on it, 

The purpose of this report is to document the project I was working on for nine weeks during the summer of 2018. As part of the CERN openlab Summer Student Program 2018 I had the opportunity to work with the Digital Repositories (IT-CDA-DR) section at CERN on developing a

The interest in using containers to package applications is constantly growing in the software  development community, especially with new technologies such as Kubernetes, Open-shift  being adopted more frequently as well. This project also based on modularising the currently 

In June 2018, more than 68.5 Million people across the globe were reported to be fleeing war or persecution. Within the United Nations, UNOSAT is the organ in charge of collecting demo-

There are two very popular concepts that we hear in the world of technology​, Big  Data and Internet of Things. Big data is referring to a data which size, complexity and  velocity is really high and is difficult to capture, pre-process and analyze it with 

Computer simulations have become a very powerful tool for scientific research. In order to fa- cilitate research in computational biology, the BioDynaMo project aims at a general platform for

Simulations of beam dynamics vastly profit from parallelisation with high performance computing tech- niques. The two simulation libraries SixTrackLib and PyHEADTAIL are GPGPU accelerated. The former

In 2019 the LHCb experiment will go through an important upgrade, that will improve performance in many fields. One oh these fields is the DAQ system: it consists of a big flow of data that comes

One of the most time consuming algorithms that is currently employed for the reconstruction of High Energy Physics (HEP) workflows is the local energy reconstruction. The time spent to execute this algorithm constitutes 24% of the total processing time, thus achieving substantial

Improving the performance of an application is an important objective carried out from the application  conception until its deprecation. Developers are constantly trying to improve the performance of their 

The project described in this report is related to XRootD framework development. It was divided into two parts. First part was about publishing XRootD python bindings called PyXRootD to Python Package Index. This makes PyXRootD installation much easier and resolves problem

Puppet is a great tool for making changes on systems, and ensuring that those changes happen. But Puppet is not intended to make this happen on many systems at the same time. Puppet is intended for eventual compliance over time. Each agent checks in over a period of time, al-

In this report thin, single elements were compared between MAD-X and SixTrack. A testing framework for efficient comparisons between the two tracking codes was developed. A few dif- ferences between the tracking codes were found then documented and two bugs, one in the

CERN operates an OpenStack based private cloud to provide its users with resources on demand. It is one  of the largest OpenStack deployments in the world, with more than 300,000 cores over 9,000 hypervisors  [1].  

MPI Learn is a framework for the distributed training of neural networks. This platform is aimed at machine learning users, who can use it to train models faster, without dealing with the com-

Function as a service (FaaS) is a category of cloud computing services that  provides a platform allowing customers to develop, run, and manage application  functionalities without the complexity of building and maintaining the infrastructure 

The goal of this Openlab project is to create a Smart Data Analytics Platform for Science that will host analytical tools, publish data, share resources, interact with bots, collaborate and build communities of researchers with various backgrounds in a single ecosystem. With

We propose a novel neural network architecture called Hierarchical Latent Autoencoder to exploit the underlying hierarchical nature of the CMS Trigger System for data quality monitoring.

Some of the main challenges in scientific computing today deal with performance-preserving portability of software and reproducibility of the final results; likewise, with the advent of modern

Squid-Frontier system [1] is currently used to manage access to the COOL database [2].  This system includes many widely distributed computing sites and applications. Clients  presented by PanDA (Production ANd Distributed Analysis system, the ATLAS’ 

Malware Analysis Management (M.A.M.) or the automated sandbox analysis of  quarantined malware samples focuses on a detailed analysis of malware samples  reaching CERN through email traffic. M.A.M. is a side process of the main email pipeline 

REANA is a reusable analysis platform which offers physicists the ability to structure their research  data analysis and run their computational workflows in a containerized computing cloud. 

Computer simulations have become a very powerful tool for scientific research. In order to facilitate research in computational biology, the BioDynaMo project aims at a general platform for biological computer simulations, which should be executable on hybrid cloud computing systems.

In the competitive market for large-scale storage solutions the current main disk storage system at CERN EOS has been showing its excellence in the multi-Petabyte high-concurrency regime.

Exploring RapidIO RapidIO (http://rapidio.org/) technology is a packet-switched high-performance fabric, which has been under active development since 1997. The technology is used in all 4G/LTE basestations worldwide.

RapidIO (http://rapidio.org/) technology is a packet-switched high-performance fabric, which has been under active development since 1997. Originally meant to be a front side bus, it developed into a system level interconnect which is today used in all 4G/LTE base stations world wide.

Machine Learning techniques have been used in different applications by the HEP community: in this talk, we discuss the case of detector simulation.

Current research in the field of computational biology often involves simulations on high-performance computer clusters. It is crucial that the code of such simulations is efficient and correctly reflects the model specifications.

LHC Run3 and Run4 represent an unprecedented challenge for HEP computing in terms of both data volume and complexity. New approaches are needed for how data is collected and filtered, processed, moved, stored and analysed if these challenges are to be met with a realistic budget.

As computing power and I/O performance is increasing at an aggressive rate several RDMA enabled interconnect technologies have been entering the market, promising low latency and high throughput.

In this white paper, CERN openlab sets out challenges to tackle together through joint R&D projects with our industry collaborators over the coming years.This unique public-private partnership between research and leading ICT companies is ideally placed to tackle these challenges, producing r

RapidIO technology is a packet-switched high-performance fabric, which has been under active development since 1997. The technology is used in all 4G/LTE base stations worldwide.