Serena Curzel
A5033121816- Parallel Computing and Optimization Techniques
- Embedded Systems Design Techniques
- Interconnection Networks and Systems
- Advanced Neural Network Applications
- Gamma-ray bursts and supernovae
- Distributed and Parallel Computing Systems
- Radiation Effects in Electronics
- Astrophysics and Cosmic Phenomena
- Particle Detector Development and Performance
- Advanced Memory and Neural Computing
- Pulsars and Gravitational Waves Research
- Machine Learning in Materials Science
- Numerical Methods and Algorithms
- CCD and CMOS Imaging Sensors
- Ferroelectric and Negative Capacitance Devices
- Cloud Computing and Resource Management
- Spacecraft Design and Technology
- Distributed systems and fault tolerance
- VLSI and FPGA Design Techniques
- Neural Networks and Reservoir Computing
- Advanced Electron Microscopy Techniques and Applications
- Real-Time Systems Scheduling
- Satellite Communication Systems
- Scientific Computing and Data Management
- Spacecraft and Cryogenic Technologies
Politecnico di Milano
2020-2025
Pacific Northwest National Laboratory
2021-2022
This paper presents the open-source high-level synthesis (HLS) research framework Bambu. Bambu provides a environment to experiment with new ideas across HLS, verification and debugging, FPGA/ASIC design, design flow space exploration, parallel hardware accelerator design. The tool accepts as input standard C/C++ specifications compiler intermediate representations (IRs) coming from well-known Clang/LLVM GCC compilers. broad spectrum flexibility of formats allow electronic automation (EDA)...
Recent trends in deep learning (DL) imposed hardware accelerators as the most viable solution for several classes of high-performance computing (HPC) applications such image classification, computer vision, and speech recognition. This survey summarizes classifies recent advances designing DL suitable to reach performance requirements HPC applications. In particular, it highlights advanced approaches support accelerations including not only GPU TPU-based but also design-specific FPGA-based...
The generation of custom hardware accelerators for applications implemented within high-level productive programming frameworks requires considerable manual effort. To automate this process, we introduce SODA-OPT, a compiler tool that extends the MLIR infrastructure. SODA-OPT automatically searches, outlines, tiles, and pre-optimizes relevant code regions to generate high-quality through synthesis. can support any framework domain-specific language interface with By leveraging MLIR, solves...
Systems performing scientific computing, data analysis, and machine learning tasks have a growing demand for application-specific accelerators that can provide high computational performance while meeting strict size power requirements. However, the algorithms applications need to be accelerated are evolving at rate is incompatible with manual design processes based on hardware description languages. Agile tools compiler techniques help by quickly producing an integrated circuit (ASIC)...
HERMES (High Energy Rapid Modular Ensemble of Satellites) Technological and Scientific pathfinder is a space borne mission based on LEO constellation nano-satellites. The 3U CubeSat buses host new miniaturized detectors to probe the temporal emission bright high-energy transients such as Gamma-Ray Bursts (GRBs). Fast transient localization, in field view several steradians with arcmin-level accuracy, gained by comparing time delays among same event detection epochs occurred at least 3 With...
HERMES-TP/SP (High Energy Rapid Modular Ensemble of Satellites Technologic and Scientific Pathfinder) is a constellation six 3U nano-satellites hosting simple but innovative X-ray detectors, characterized by large energy band excellent temporal resolution, thus optimized for the monitoring Cosmic High transients such as Gamma Ray Bursts electromagnetic counterparts Gravitational Wave Events, determination their positions. The projects are funded Italian Ministry University Research Space...
The growing numbers of application areas for artificial intelligence (AI) methods have led to an explosion in availability domain-specific accelerators, which struggle support every new machine learning (ML) algorithm advancement, clearly highlighting the need a tool quickly and automatically transition from definition hardware implementation explore design space along variety SWaP (size, weight Power) metrics. software defined architectures (SODA) synthesizer implements modular...
Due to technology and power limitations, general-purpose processing units are experiencing progressively smaller performance gains. Computer architecture innovations essential keep steadily increasing. Thus domain-specific accelerators receiving renewed interest have shown benefit different scientific machine learning applications [1, 3]. High-Level-Synthesis (HLS) provides a way quickly generate hardware descriptions for starting from high-level applications. However, state-of-the-art tools...
Within Quantum Gravity theories, different models for space-time quantisation predict an energy dependent speed photons. Although the predicted discrepancies are minuscule, GRB, occurring at cosmological distances, could be used to detect this signature of granularity with a new concept modular observatory huge overall collecting area consisting in fleet small satellites low orbits, sub-microsecond time resolution and wide band (keV-MeV). The enormous number collected photons will allow...
This paper presents a methodology for the Synthesis of PARallel multi-Threaded Accelerators (SPARTA) from OpenMP annotated C/C++ specifications. SPARTA extends an open-source HLS tool, enabling generation accelerators that provide latency tolerance irregular memory accesses through multithreading, support fine-grained memory-level parallelism hot-potato deflection-based network-on-chip (NoC), synchronization constructs, and can instantiate memory-side caches. Our approach is based on custom...
European efforts to boost competitiveness in the sector of space services promote research and development advanced software hardware solutions. The EU-funded HERMES project contributes effort by qualifying radiation-hardened, high-performance programmable microprocessors, developing <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$a$</tex> ecosystem that facilitates deployment complex applications on such platforms. main objectives include...
The association of GW170817 with GRB170817A proved that electromagnetic counterparts gravitational wave events are the key to deeply understand physics NS-NS merges. Upgrades existing GW antennas and construction new ones will allow increase sensitivity down several hundred Mpc vastly increasing number possible counterparts. Monitoring hard X-ray/soft gamma-ray sky good localisation capabilities help effectively tackle this problem allowing fully exploit multi-messenger astronomy. However,...
Edge systems are required to autonomously make real-time decisions based on large quantities of input data under strict power, performance, area, and other constraints. Meeting these constraints is only possible by specializing through hardware accelerators purposefully built for machine learning analysis algorithms. However, science evolves at a quick pace, manual design custom has high non-recurrent engineering costs: general solutions needed automatically rapidly transition from the...
The Software Defined Architectures (SODA) Synthesizer is an open-source compiler-based tool able to automatically generate domain-specialized systems targeting Application-Specific Integrated Circuits (ASICs) or Field Programmable Gate Arrays (FPGAs) starting from high-level programming. SODA composed of a frontend, SODA-OPT, which leverages the multilevel intermediate representation (MLIR) framework interface with productive programming tools (e.g., machine learning frameworks), identify...
Model-based development techniques in Matlab/Simulink simplify the design and implementation of software for aerospace applications, providing required level abstraction scientists that work on complex navigation control algorithms. As Field Programmable Gate Arrays (FPGAs) have become more relevant space hardware platforms, developers could benefit from automated acceleration flows do not require extensive manual rewriting their code to port it FPGA. We analyze existing methods synthesize...
In recent years, the field of Deep Learning has seen many disruptive and impactful advancements. Given increasing complexity deep neural networks, need for efficient hardware accelerators become more pressing to design heterogeneous HPC platforms. The requires a multidisciplinary approach, combining expertise from several areas, spanning computer architecture approximate computing, computational models, machine learning algorithms. Several methodologies tools have been proposed Learning,...
The High Energy Rapid Modular Ensemble of Satellites (HERMES) Technological and Scientific pathfinder is a space borne mission based on constellation LEO nanosatellites. payloads these CubeSats consist miniaturized detectors designed for bright high-energy transients such as Gamma-Ray Bursts (GRBs). This platform aims to impact Gamma Ray Burst (GRB) science enhance the detection Gravitational Wave (GW) electromagnetic counterparts. goal will be achieved with field view several steradians,...
Modern big data workflows are characterized by computationally intensive kernels. The simulated results often combined with knowledge extracted from AI models to ultimately support decision-making. These energy-hungry increasingly executed in centers energy-efficient hardware accelerators since FPGAs well-suited for this task due their inherent parallelism. We present the H2020 project EVEREST, which has developed a system development kit (SDK) simplify creation of FPGA-accelerated kernels...