This experiment has been executed using:

• Model: Decision Tree regressor (test.yaml)
• n_samples: 8 (number of ALYA simulations to be run)
• Nodes used in the MN5 supercomputer: 4
• ALYA_PROCS = 56

Adapted version of a workflow used in CAELESTIS for mechanical testing simulation which was developed by Riccardo Cecco (Workflows and Distributed Computing Group, BSC) with the guidance of Gerard Guillamet (Dual Technologies Research Group, BSC) and Aravind Sasikumar (AMADE Research UDG). The workflow ...

This experiment has been executed using:

• Model: SVR (test_SVR.yaml)
• n_samples: 8 (number of ALYA simulations to be run)
• Nodes used in the MN5 supercomputer: 2
• ALYA_PROCS = 28

Adapted version of a workflow used in CAELESTIS for mechanical testing simulation which was developed by Riccardo Cecco (Workflows and Distributed Computing Group, BSC) with the guidance of Gerard Guillamet (Dual Technologies Research Group, BSC) and Aravind Sasikumar (AMADE Research UDG). The workflow is distributed ...

Lysozyme in water full COMPSs application example, used during the Supercomputing 24 conference at the COMPSs Tutorial session.

Sensitivity Analysis to identify the material properties governing the structural failure of an open-hole test

Introduction

The certification of composite structures in the aeronautical sector follows a building-block pyramid approach, in which structural complexity, material uncertainties, and computational cost increase progressively across scales. To reduce reliance on extensive experimental campaigns, high-fidelity finite element simulations are increasingly employed for virtual testing. ...

[DTC-T1] WF6101: Tsunami impact forecasting

This repository contains a Common Workflow Language (CWL) and Ro-Crate metadata definition for DTC-T1 workflow 6101, which is designed for providing tsunami impact forecasting following a tsunamigenic earthquake event, based on a probabilistic approach. The workflow integrates real-time earthquake data, runs HPC simulations, and generates tsunami hazard maps.

The main CWL implementation is found in WF6101.cwl, together with ST610106 and ST610109 ...

Forecasting the atmospheric dispersal of volcanic products requires accurate input parameters for transport models, including meteorological data and ash/gas emission terms. Such forecasting builds upon three basic ingredients:

1. Meteorological Data. Typically derived from global, regional, or local-scale models, meteorological data drive the transport and deposition of volcanic particles.
2. Transport Models. These models simulate atmospheric dispersal, incorporating processes such as wind ...

Application that perform the multiplication between matrices.

COMPSs Matrix Multiplication resourceUsage profiling example.

MN5 MSIZE=20 BSIZE=768 7 Nodes (6 workers) (--num_nodes=7 --worker_in_master_cpus=0).

• Total number of tasks: 20^3 = 8000
• Maximum code parallelism: 20^2 = 400
• Total cores: 112*6 = 672
• Maximum utilisation: 400 / 112 = 3,57 Nodes

Overall stats from "pycompss inspect":

│ └── overall 
│ ├── matmul_tasks 
│ │ └── multiply 
│ │ ├── maxTime = 91,111 ms 
│ │ ├── executions = 8,000 
│ │ ├── avgTime = 84,839 ms 
│ │ └── minTime = 79,278 ms
...

Application that perform the multiplication between matrices. In this experiment, a new profiling visualization is available, showing the resource usage such as CPU, memory, data read and written to disk, and data sent and received over the network.

Name: Matrix Multiplication Contact Person: [email protected] Access Level: public License Agreement: Apache2 Platform: COMPSs

Description

Matrix multiplication is a binary operation that takes a pair of matrices and produces another matrix.

If A is an n×m matrix and B is an m×p matrix, the result AB of their multiplication is an n×p matrix defined only if the number of columns m in A is equal to the number of rows m in B. When multiplying A and B, the elements of the ...