Licensable technology created by BSC

Showing 21 - 40 results of 127

Latest Version

Coyote is an execution-driven simulator based on the open source RISC-V standard, built upon two preexisting simulation tools: Spike and Sparta.

Latest Version

Crossmapper is an automated bioinformatics pipeline for asessing the rate of read crossmapping when two or more organisms are sequenced as one sample. The software can be used for planning such kind of experimental setups as dual- or multiple RNA-seq (mainly for host-pathogen, symbiont and cohabitant interaction studies), metagenomics studies, sequencing and analysis of hybrid species, allele-specific expression studies, and can be extended for the use in large sequencing facilities for resource optimization.

Latest Version

CSDownscale is a software containing a set statistical downscaling methods for climate predictions. 

Latest Version

Both the software and its products are suitable for commercialization to end-users from several sectors that evaluate climate forecasts or impact models. For instance, the result of the assessment of indicators tailored for the agriculture sector can be summarized with a scorecard. This tool becomes especially relevant when several versions of the product delivered in a service need to be evaluated or compared.

dataClay is a distributed data store that enables applications to store and access objects in the same format they have in memory, and executes object methods within the data store. These two main features accelerate both the development of applications and their execution.
Stable release: dataClay 4.0 - Claystone (June 2024)

The technology is a deep generative model for synthetic data generation. The model is a VAE (Variational AutoEncoder) equipped with two algorithms for explainability, XGBoost (Extreme Gradient Boosting) and SHAP (SHapley Additive exPlanations).

BSC derivatives of R-LINE are a collection of new implementation on top of the Research LINE source model (R-LINE) wich is a software for near-surface releases originally developed by the University of North Carolina.
dislib is a distributed computing library highly focused on machine learning on top of PyCOMPSs. Inspired by NumPy and scikit-learn, dislib provides various supervised and unsupervised learning algorithms through an easy-to-use API.

Latest Version

A Package that contains two mathematical distributions to estimate extreme value data coming from embedded Systems.

DLB is a library devoted to speedup hybrid parallel applications. And at the same time DLB improves the efficient use of the computational resources inside a computing node.
More information and downloads can be found at:

The Dynamic Management of Resources Application Programming Interface (DMR API) is conceived to facilitate the programmability of malleable applications automating resource reallocation, process handling, and data distribution. Process malleability is the capability of reconfiguring the number of processes of an application on-the-fly, in other words, during its execution.

A library designed to offer the global advantages of process malleability while providing a minimalist MPI-like syntax.

DYON selects a suitable CPU partition for a set of processes to improve a metric. For example, if we have a process that improves I/O and another that is using CPU. The partition will offer a CPU partition (20%-80%) if that improves the target metric. The technique allows to use metrics that are no monotonic, for example, in some cases increasing the CPU count for a shared application could decrease the performance if other processes get hung.

EAR software is a management framework optimizing the energy and efficiency of a cluster of interconnected nodes. To improve the energy of the cluster, EAR provides energy control, accounting, monitoring and optimization of both the applications running on the cluster and of the overall global cluster.


ecoHMEM is a software ecosystem implementing novel and proven methodology to address automatic object-level placement for heterogeneous memory systems equipped with DRAM, HBM, Persistent Memory, etc.

ENDCast: El Niño Driven Disease Forecasting is a web application that can provide early warnings of climate-sensitive infectious disease outbreaks in hotspots impacted by El Niño Southern Oscillation (ENSO). In the initial prototype, 1 to 6 month forecasts were generated in hotspots across the Latin America and Caribbean region for two vector-borne diseases (dengue and malaria) and one water-borne zoonosis (leptospirosis).

Latest Version

Platform based on machine learning likely to have the following characteristics:

• It will extract features from input esterase sequences in FASTA format.

• It will filter those sequences that are too different from the training dataset because of the applicability domain phenomenon, since using a model to predict on proteins that the system has not seen and trained on before will likely produce errors.

• Finally, it will classify the sequences based on its promiscuity, >20 will be considered promiscuous and <20 non promiscuous.

This is a version of the Compiler Explorer tool tailored for EPI. It's a web application that allows running a compiler interactively to obtain the output of the compiler.

OpenPiton is an open-source scalable framework for supporting different cores interconnected through a NoC. It integrates the OpenPiton design in new FPGA HW platfrom: Alveo U280. The addition will help other designers to use OpenPiton in a different HW platforms further than the ones provided by the OpenPiton Framework by default. More specifically, adding support for the Xilinx Alveo U280, and U55C.

Latest Version

Extraction of information on transcription factors and their targets from the literature.