Apache Hadoop is a set of 2 domains: data computation such as Spark, MapReduce, Flink, etc and data storage - HDFS. HDFS is a distributed file system. Current HDFS provides 3x replication for data redundancy and availability. But it has 200% storage overhead. However there is a big improvement in Hadoop 3 for replication which is Erasure Coding (EC).
Erasure Coding gives the same level of...
Spiking neural networks are an interesting candidate for signal processing at the High-Luminosity LHC, the next stage of the LHC upgrade. For HL-LHC, new particle detectors will be built, what will allow to take a time-sequence of snapshots for a given collision. This additional information will allow to separate the signal belonging to the interesting collision from those generated parasitic...
Exploring the use of cupla to write accelerator-independent code.
Knative is a relatively new technology that extends the Kubernetes API to support deployment of server-less apps. On the CERN cloud team, we are investigating Knative as a candidate technology for offering Function-as-a-Service (FaaS) infrastructure to CERN cloud users.
Performance Study of Parquet Codecs
support JS rendering websites in The CERN Search Crawler