Author Archives: Marco Aldinucci

About Marco Aldinucci

Marco Aldinucci is an assistant professor at Computer Science Department of the University of Torino since 2008. Previously, he has been researcher at University of Pisa and Italian National Research Agency. He is the author of over a hundred papers in international journals and conference proceeding (Google scholar h-index 21). He has been participating in over 20 national and international research projects concerning parallel and autonomic computing. He is the recipient of the HPC Advisory Council University Award 2011 and the NVidia Research award 2013. He has been leading the “Low-Level Virtualization and Platform-Specific Deployment” workpackage within the EU-STREP FP7 ParaPhrase (Parallel Patterns for Adaptive Heterogeneous Multicore Systems) project, the GPGPU workpackage within the IMPACT project (Innovative Methods for Particle Colliders at the Terascale), and he is the contact person for University of Torino for the European Network of Excellence on High Performance and Embedded Architecture and Compilation. In the last year he delivered 5 invited talks in international workshops (March 2012 – March 2013). He co-designed, together with Massimo Torquati, the FastFlow programming framework and several other programming frameworks and libraries for parallel computing. His research is focused on parallel and distributed computing.

Stay foolish, build your own supercomputer at UNITO

The novel Competence Center for Scientific Computing at University of Torino and INFN Torino (C3S@UNITO) is eventually opening this week. The inauguration workshop will take place on October 7, 2016 at main theatre of the Campus Luigi Einaudi. The center involves over 16 departments of University of Torino and hosts the brand new OCCAM platform.

The program and (free) registration form is here. Everybody is invited.

The Open Computing Cluster for Advanced data Manipulation (OCCAM) is a multi-purpose flexible HPC cluster designed and operated by a collaboration between the University of Torino and the Torino branch of the Istituto Nazionale di Fisica Nucleare. It is aimed at providing a flexible, reconfigurable and extendable infrastructure to cater to a wide range of different scientific computing needs, as well as a platform for R&D activities on computational technologies themselves. Extending it with novel architecture CPU, accelerator or hybrid microarchitecture (such as forthcoming Intel Xeon Phi Knights Landing) should be as a simple as plugging a node in a rack.

The initial system counts slightly more than 1100 cpu cores and includes different types of computing nodes (standard dual-socket nodes, large quad-sockets nodes with 768 GB RAM, and multi-GPU nodes) and two separate disk storage subsystems: a smaller high-performance scratch area, based on the Lustre file system, intended for direct computational I/O and a larger one, of the order of 1PB, to archive near-line data for archival purposes. All the components of the system are interconnected through a 10Gb/s Ethernet layer with one-level topology and an InfiniBand FDR 56Gbps layer in fat-tree topology.

A system of this kind, heterogeneous and reconfigurable by design, poses a number of challenges related to the frequency at which heterogeneous hardware resources might change their availability and shareability status, which in turn affect methods and means to allocate, manage, optimize, bill, monitor VMs, virtual farms, jobs, interactive bare-metal sessions.

The topic of the workshop is indeed the description of some of the use cases that prompted the design ad construction of the HPC cluster, its architecture and a first characterisation of its performance by some synthetic benchmark tools and a few realistic use-case tests.

More technical details at CHEP 2016: M. Aldinucci, S. Bagnasco, S. Lusso, P. Pasteris, and S. Rabellino, “The Open Computing Cluster for Advanced data Manipulation (OCCAM),” in The 22nd International Conference on Computing in High Energy and Nuclear Physics (CHEP), San Francisco, USA, 2016. 


3.5M € EU project REPARA: A success story for UNITO

The EU FP7 REPARA project @reparaproject is now completed. Running for 3 years (2013-2016) with total cost 3.5M €, it has been evaluated “excellent” during mid-term EU review demonstrating its absolute scientific value. Among the other results, the REPARA project paves the way to efficient but easy to use parallel patterns into standard C++.

In the news

occam@UNITO> Hello, world!

occam@UNITO> Hello, world!

Occam, our own first pleasantly-sized oddly-heterogenous computer is born. Here 5 the IB switches to build a fat-tree of ~1K cores HT, ~16K CUDA cores, ~1PB archive, ~320 TB high-performance scratch storage. In absolute terms certainly not a huge machine, for research on HPC and BigData at University of Torino certainly a huge opportunity. Thanks to Fondazione SanPaolo and its 960,000 Euro funding.


Claudia Misale from Alpha@UNITO is the recipient of a IBM award

Claudia Misale, a PhD student from the Alpha@UNITO parallel computing group is the recipient of a IBM Ph.D. Scholarship award 2016. Few awards of this kind are assigned every year.

Congratulations to Claudia.

It is my pleasure to inform you that your nomination of Claudia Misale has been approved to receive an IBM Ph.D. Scholarship. This award is highly competitive and recognizes your student as well as the quality of your institution.In order to nurture the student relationship the IBM Ph.D. Scholarship program has asked Yoonho Park to act as Claudia’s mentor and principal IBM relationship contact for this award. The award check will be for the amount of $10,000 USD and will be made payable to the university for Claudia to use as the student wishes for educational purposes – such as, but not limited to tuition, conference travel, or stipend. Again, IBM is delighted to provide your student an IBM Ph.D. Scholarship Award.

Joseph Calabrese
Program Executive
IBM PhD Fellowship Program

Pint-of-Science Torino: Supercomputing and Quantum computing – May 25

First edition in Torino of Pint of Science “alcoholic” conference series will be focused on next generation computing platforms.

Title: Computer coming from the future

Abstract: Exascale and quantum computing probably represent the evolution and the revolution of computing as we know it today. The goal is the same: overcome by orders of magnitude the computing power available today. The means are different but possibly related. And what if evolution and revolution were a result of a “spooky action at a distance” ?

Speakers: Marco Aldinucci (UNITO) and Marco Genovese (INRIM)

When and where:
Wednesday 25th May, 2016 – 9.00PM
Officine Ferroviarie
Corso Germano Sommeiller , 12, Torino, 10125, Italia

More information at:

Italian version

Il calcolo alle exascale e quantistico rappresentano probabilmente l’evoluzione e la rivoluzione del calcolo come lo conosciamo oggi. Il fine è lo stesso: superare di ordini di grandezza la potenza di calcolo oggi disponibile. I mezzi sono diversi ma forse correlati. E se evoluzione e rivoluzione fossero effetto di una “azione fantasmaticamente a distanza”?


Marco Aldinucci si è laureato e dottorato in Informatica nonostante il suo principale interesse di ricerca riguardasse le feste erasmus. E’ professore associato a Informatica e guida il gruppo di ricerca in parallel computing e lo NVidia GPU research center. Almeno finchè non verrà introdotto l’ etilometro…

Marco Genovese è responsabile del Programma di Ricerca INRIM “Ottica Quantistica”; membro del consiglio scientifico di INRIM. Studia i fondamenti della meccanica quantistica ed applicazioni alle nascenti tecnologie quantistiche.


FastData: Where Big Data meets HPC @ UNITO

FastData: An open symposium on beyond Big Data challenges for researcher, industrial stakeholders, students, practitioners, …


March 21st, 2016

Computer Science Department, University of Torino
Entryway from Via Pessinetto 12, Torino

As planet evolves, an increasingly connected ecosystem of heterogeneous devices produces more volumes and variety of digital data. They range from devices-in-the-fog to insanely complicated machineries looking with ever increasing precision to “the Ultimate Question of Life, the Universe, and Everything”. To keep up with the pace, very large volumes of dynamically changing data ought to be processed, synthesised, and eventually turned into knowledge. High-velocity data brings high value, especially to volatile business processes, mission-critical tasks and scientific grand challenges. Some of this data loses its operational value in a short time frame, some other is simply too much to be stored. Ultimately, any forecast on tomorrow must arrive by tomorrow.

This is the ground where the data science meets high-performance computing.

Participation is free of charge. See more at FastData@UNITO web page

Marco Aldinucci is the recipient of a 2015 IBM Faculty award


IBM faculty award 2015, happy ending at alpha@unito

I am a recipient of a 2015 IBM Faculty award related with high performance data analytics. An award that I am going to share with all people in the alpha group. Their work actually brought the award at the Computer Science department of the University of Torino.



Congratulations, you have been selected to receive a 2015 IBM Faculty Award for $20,000.00 USD. This award is highly competitive and recognizes the quality of your program and its importance to our industry.

I am pleased to inform you that your Faculty Award for $20,000.00 USD has been transferred to your bank of record. The Clearing Date is 11/23/2015, and the Transaction Reference # is XXXX.

Please note that the IBM Faculty Award is a gift in recognition of your achievement and not a contract for services. It will be processed as a donation to your university. Hence, we expect that no overhead will be charged against this award.