Daniele Spampinato

Daniele Spampinato

dgspampinato

Computing Systems Lab
Huawei Zurich Research Center
Airgate Building
Thurgauerstrasse 40
8050, Zurich, Switzerland

daniele.giuseppe.spampinato at huawei dot com

I am a principal researcher in the Computing Systems Laboratory (CSL) at the Huawei Zurich Research Center located in Zurich, Switzerland.

My research interests are in the area of domain-specific languages and programming models for high-performance mathematical software. Keep an eye on new releases of ALP, the algebraic programming framework developed by researchers at CSL and the Huawei Paris Research Center.

Short Bio

Laurea in Computer Engineering (B.Sc., Politecnico di Milano, Italy, 2006) and double degree Laurea Magistrale and Master i teknologi/sivilingeniør in Computer Science (M.Sc., Politecnico di Milano, Italy and NTNU, Norway, 2009).

Ph.D. in Computer Science (ETH Zurich, 2017) in the Advanced Computing Laboratory under the supervision of Prof. Markus Püschel. I investigated the problem of generating efficient code for small-scale, dense linear algebra programs developing the LGen and the SLinGen program generators. A copy of my thesis is available from the ETH Research Collection.

Postdoc (2017-2019) and research scientist (2019-2020) in the SPIRAL team in the Electrical and Computer Engineering Department at Carnegie Mellon University, Pittsburgh, PA, USA.

Selected Publications (or full list)

2023

Towards Structured Algebraic Programming
D. G. Spampinato, D. Jelovina, J. Zhuang, and A. N. Yzelman
Workshop on Libraries, Languages and Compilers for Array Programming (ARRAY@PLDI), pp. 50-61

2019

Delta-Stepping SSSP: From Vertices and Edges to GraphBLAS Implementations
U. Sridhar, M. Blanco, R. Mayuranath, D. G. Spampinato, T. M. Low and S. McMillan
International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 241-250
Linear Algebraic Depth-First Search
D. G. Spampinato, U. Sridhar, T. M. Low
Workshop on Libraries, Languages and Compilers for Array Programming (ARRAY@PLDI), pp. 93-104

2018

Program Generation for Small-Scale Linear Algebra Applications
D. G. Spampinato, D. Fabregat-Traver, P. Bientinesi and M. Püschel
Code Generation and Optimization (CGO), pp. 327-339
SPIRAL: Extreme Performance Portability
F. Franchetti, T. M. Low, T. Popovici, R. Veras, D. G. Spampinato, J. Johnson, M. Püschel, J. C. Hoe and J. M. F. Moura
Proc. of the IEEE, special issue on ``From High Level Specification to High Performance Code'', Vol. 106, No. 11
Linear Algebraic Formulation of Edge-centric K-truss Algorithms with Adjacency Matrices
T. M. Low, D. G. Spampinato, A. Kutuluru, U. Sridhar, T. Popovici, F. Franchetti and S. McMillan
High Performance Extreme Computing (HPEC), pp. 1-7
IEEE/DARPA/Amazon Graph Challenge Finalists

2016

A Basic Linear Algebra Compiler for Structured Matrices
D. G. Spampinato and M. Püschel
Code Generation and Optimization (CGO), pp. 117-127
CGO 2016 Highest Ranked Artifact

2015

A Basic Linear Algebra Compiler for Embedded Processors
N. Kyrtatas, D. G. Spampinato and M. Püschel
Design, Automation and Test in Europe (DATE), pp. 1054-1059

2014

A Basic Linear Algebra Compiler
D. G. Spampinato and M. Püschel
Code Generation and Optimization (CGO), pp. 23-32
Best Paper Award Nominee (4 out of 29)