Loading ...

Picasso

At the University of Malaga (UMA)

The University of Málaga (UMA) has a strong tradition on Supercomputing that goes back to the decade of the 90's where parallel computers were mainly used for research on parallelization of computation-intensive applications.

It was on 1997 when the first supercomputer was installed, dedicated exclusively to the execution of scientific applications by the UMA researchers. It was called "Picasso", a SGI Origin 2000.

Nowadays the supercomputing facilities that gives support to research activity is composed by a set of HP supercomputers accessible to the entire scientific community. Supercomputing managers and administrators are also giving advise to users on computation problems or on data processing, as well as on the optimal use of the available tools at the hardware and software levels.

Visit the RES node website

Machine information

HPC Resources

Machine name Picasso
% of the machine provided to RES 20 %
Peak performance 4 PFlop/s
Main memory 156 TB
Number of nodes 310
Main nodes characteristics
  • 126 nodes SD530, with 2 Intel Xeon Gold 6230R processors and 192GB RAM
  • 156 nodes Lenovo sr645, with 2 AMD EPYC 7H12 processors and 512GB RAM
  • 24 nodes Bull R282-Z90, with 2 AMD EPYC 7H12 processors and 2TB RAM
Type of CPU Intel Xeon Gold 6230R, 26 cores per processor, 2.1GHz
AMD EPYC 7H12, 64 cores per processor, 2.6 GHz
Other characteristics 4 nodes nvidia DGX with 8 gpus each 
Disk storage 881 TB net
Interconnection networks Infiniband HDR 200
Operating system openSuse 15.3

 

Data projects Resources

Core Features: Archival projects and Data storage, regardless of discipline

Available storage space (TB)

 2000 TB

Standard protocol for external access

 Acceso mediante cuenta local, o por S3 con proxy

Standard data transfer protocol

 ftp and rsync

High speed network connection RedIRIS/autonomous networks

Yes

Backup protocol

 No

Security system

Yes

Monitorization system

Yes

Personnel assigned to support users who access the center through the network

FTEs

Optional characteristics: data storage and exploration projects (basic exploitation), generic and/or specific by subject area

Federated access protocol (EduGAIN, SIR, …)

 No

Optimized transfer system for large volumes of data

Yes, rsync

Treatment of personal data and ethics committee

 No

Data management policy

 TBA

 

Additional features: More specific exploitation projects, with advanced tools, and/or depending on the subject area

Data services for scientific projects (maintained by the node)

 

 TBA

Support and consulting service for other nodes of the data network

 No

Support team / Contact

The Support Team is responsible for direct user support providing detailed knowledge of programming models, libraries, performance tools and applications, having more than 300 applications available in Picasso.

Support is available via email in the address res_support@res.uma.es