Innocenzo Mungiello

Ph. D in
Information Technology and Electrical Engineering

Innocenzo Mungiello received a Ph. D. in Information Technology and Electrical Engineering, in 2019 from the University of Naples Federico II. Innocenzo Mungiello's research activity focuses on Multi / Many-Cores source code transformations to improve performance / performance per watt, including the application of high-level parallel programming paradigms like MMX and AVX to Intel CPU's and CUDA Programming Model to GPU design. He is also involved in several research projects related to embedded systems design, reconfigurable computing design techniques and heterogeneous manycore architectures for HPC. One of them is the MANGO project ("MANGO: exploring Manycore Architectures for Next-GeneratiOn HPC systems") funded by the European Union under Horizon 2020, the EU's research and innovation funding scheme. He belonged to a group of researchers, supervised by Professor Alessandro Cilardo, which works on the development of Nu+, a deeply configurable, open-source GPU-like processor core.

Highlights

  • The MANGO project ("MANGO: exploring Manycore Architectures for Next-GeneratiOn HPC systems") is a large-scale European project exploring heterogeneous manycore architectures for HPC, with a particular focus on architectural mechanisms for Performance/Power-efficiency/time-Predictability objectives. The project, whose total budget is 5.8 Million euro, is based on the cooperation of the Polytechnical University of Valencia, University of Naples Federico II (CeRICT), Politecnico di Milano, University of Zagreb, Philips, Thales, EPFL, PRO-DESIGN, and Eaton.

  • Nu+ is an open-source GPU-like compute core, developed by CeRICT in the framework of the MANGO FETHPC project. The main objective of Nu+ is to enable resource-efficient HPC based on special-purpose customized hardware.

Research Interests

I am involved in many research activities, related to Multi / Many-Cores Architectures. In particular:

  • Sorce Code Optimizations
  • gem5 Emulator Integration
  • Discovery new Memory Access Patterns
  • Performance per Watt Efficiency
  • NVIDIA GPU Architectures

Publications

Journals and periodical publications

Book Chapters and Edited Volumes

Conferences

  1. A. Cilardo, I. Mungiello, "Experimental evaluation of memory optimizations on an embedded GPU platform", 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC), 2015

  2. A. Cilardo, I. Mungiello and F. De Rosa, "Adaptive Modular Mapping to Reduce Shared Memory Bank Conflicts on GPUs", 11th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC), 2016

Italian Conferences

Technical Reports

Submitted Papers

Theses

  • Energy analysis of code-level transformations on GPUs ,
    M. S. Thesis, Università degli Studi di Napoli Federico II, Napoli, Italy, July 2015.
  • Improving Multibank Memory Access Parallelism on SIMT Architectures ,
    Ph. D. Thesis, Università degli Studi di Napoli Federico II, Napoli, Italy, February 2019.

Contact Me

University of Naples Federico II
Department of Electrical Engineering and Information Technology
Room 4.03, via Claudio 21, 80125 Napoli, Italy
Office phone: +39 081 768 3829   Mobile phone: +39 333 1264953
e-mail address: innocenzo.mungiello@unina.it

If you are interested in my activities, please do not hesitate to send me an email.