SOFTWARE & HARDWARE
Licensable technology created by BSC
Volcanic ash dispersal modelling. The model was originally developed for inert volcanic particles (tephra) and has a track record of 50+ publications on different model applications and code validation, as well as an ever-growing community of users worldwide, including academia, private, research, and several institutions tasked with operational forecast of volcanic ash clouds.
The FOCUS-Africa multi-annual shiny app is an interactive website based on the R Shiny App package that includes annual and multi-annual forecasts of climate variables and drought indicators for the Southern African region (maps and timeseries of regional averages). The forecast quality is also displayed on the website to inform stakeholders about the trustworthiness of the forecasts for each specific region, forecast period, and variable or indicator.
GenomeVariator is a tool for adding genomic variants to an existing genome (in SAM/BAM/CRAM format). Currently supported variants are SNVs, indels and SVs (insertions, deletions, translocations, inversions and duplications). It generates realistic genomes as almost always less than 99% of the original real genome is modified.
Conjunto de funcionalidades para componer análisis de genómica: alineado de genomas, 'calling' de variantes somáticas y germinales, estimación de número de copias, clonalidad, inmunogenicidad y otras.
Greasy is a tool designed to make easier the deployment of embarrassingly parallel simulations in any environment. It is able to run in parallel a list of different tasks, schedule them and run them using the available resources.
It is the perfect tool to use, for example, when your application is a serial program, and you need to run a large number of instances with different parameters. Greasy packs all these separate runs and uses the resources granted to run as many tasks as possible in parallel. As this tasks finish, Greasy will continue starting the tasks that were waiting for resources.
Horus is an innovative multi-platform GUI workflow manager which aids scientists in their computational research. It can serve as a local application on you computer or as a centralized server for collaborative teamwork. Integrated with a 2D infinite canvas, Horus presents itslef as a modular working environment. Its autonomous blocks enable customizable and distributable workflows via an accessible Python API.
It is a pipeline designed to be executed daily and gather data around disinformation. To this purpose, the pipeline takes the fact-checks that have been identified that day (through the APIs of Iberifier and Google), extracts keywords from these fact-checks, and uses these keywords to look for information related to these claims in digital media (MyNews service) and social networks (Twitter).
This software analyzes a large volumes of posts to massively profile potential criminals on social networks and media.
IOAnalyzer analises the I/O flow of a local node, and detects I/O patterns. With this information IOAnalyzer changes to the best I/O scheduler improving performance.
Iterative high-throughput calibration of epidemiological models is a workflow that performes optimization-via-simulation and uses time series on reported cases to find candidate values for unknown epidemiological parameters.
Lagarto Hun is a segmented scalar processor with in-order execution using the RISC-V open-source instruction set.
In collaboration between BSC and CIC-IPN, originally Lagarto Hun was a RV64IMA core with a 5-stage pipeline in order, supporting privileged ISA v1.11. As a first improvement, we have added support for single and double precision floating point operations, becoming Lagarto Hun into a RV64GCV + (subset RVV0.7.1) core, commonly named as RV64G for general purpose core.
It may be used for embedded systems and education.
One of the main goals in processor design is achieving high performance. Various proposals from academia and industry have explored innovative ideas leveraging Moore's Law, balancing complexity and performance. SUperscalar processors execute multiple instructions per clock cycle, effectively using instruction-level parallelism, dynamic scheduling, efficient memory management, and specialized accelerators.
libPRISM is designed to tune several hardware knobs of a processor. It is an interposition library for Linux platforms to manage hardware knobs at execution time without user intervention. There is no need to recompile software to use it. Easily extendable for different programming models and manage different hardware knobs. In its current form, libPRISM optimize the SMT level and the data prefetcher hardware knobs on a POWER8 processor for OpenMP applications.
This technology integrates a list of benchmarks for LLMs and computes their performance. Includes medical benchmarks, general purpose as well as bias and toxicity ones.