Search Results

Documents authored by Marongiu, Andrea

Document
Invited Paper
DOI: 10.4230/OASIcs.WCET.2024.5
Invited Paper: On the Granularity of Bandwidth Regulation in FPGA-Based Heterogeneous Systems on Chip

Authors: Gianluca Brilli, Giacomo Valente, Alessandro Capotondi, Tania Di Mascio, and Andrea Marongiu

Published in: OASIcs, Volume 121, 22nd International Workshop on Worst-Case Execution Time Analysis (WCET 2024)

Abstract
Main memory sharing in commercial, FPGA-based Heterogeneous System on Chips (HeSoCs) can cause significant interference, and ultimately severe slowdown of the executing workload, which bars the adoption of such systems in the context of time-critical applications. Bandwidth regulation approaches based on monitoring and throttling are widely adopted also in commercial hardware to improve the system quality of service (QoS), and previous work has shown that the finer the granularity of the mechanism, the more effective the QoS control. Different mechanisms, however, might exploit more or less effectively the available residual memory bandwidth, provided that the QoS requirement is satisfied. In this paper we present an exhaustive experimental evaluation of how three bandwidth regulation mechanisms with coarse, fine and ultra-fine granularity compare in terms of exploitation of the system memory bandwidth. Our results show that a very fine-grained regulation mechanism might experience worse system-level memory bandwidth exploitation compared to a coarser-grained approach.
Cite as

Gianluca Brilli, Giacomo Valente, Alessandro Capotondi, Tania Di Mascio, and Andrea Marongiu. Invited Paper: On the Granularity of Bandwidth Regulation in FPGA-Based Heterogeneous Systems on Chip. In 22nd International Workshop on Worst-Case Execution Time Analysis (WCET 2024). Open Access Series in Informatics (OASIcs), Volume 121, pp. 5:1-5:11, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{brilli_et_al:OASIcs.WCET.2024.5,
  author =	{Brilli, Gianluca and Valente, Giacomo and Capotondi, Alessandro and Di Mascio, Tania and Marongiu, Andrea},
  title =	{{Invited Paper: On the Granularity of Bandwidth Regulation in FPGA-Based Heterogeneous Systems on Chip}},
  booktitle =	{22nd International Workshop on Worst-Case Execution Time Analysis (WCET 2024)},
  pages =	{5:1--5:11},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-346-1},
  ISSN =	{2190-6807},
  year =	{2024},
  volume =	{121},
  editor =	{Carle, Thomas},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.WCET.2024.5},
  URN =		{urn:nbn:de:0030-drops-204732},
  doi =		{10.4230/OASIcs.WCET.2024.5},
  annote =	{Keywords: Bandwidth Regulation, System-on-Chip, FPGA}
}
Document
Invited Paper
DOI: 10.4230/OASIcs.NG-RES.2024.1
HMB: Scheduling PREM-Like Real-Time Tasks at High Memory Bandwidth (Invited Paper)

Authors: Mohammadhassan Gholami Derouei, Paolo Valente, Marco Solieri, and Andrea Marongiu

Published in: OASIcs, Volume 117, Fifth Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2024)

Abstract
Current homogeneous and heterogeneous computing systems reach high performance through parallelization. Yet, parallel execution of tasks entails non-trivial latency-vs-throughput issues when it comes to concurrent accesses to shared memory. In this respect, effective bandwidth regulation solutions do exist, and provide a basic mechanism to control the latency of memory accesses. Such solutions, though, are often cumbersome to deploy and to configure to guarantee both bounded latency and high utilization of the memory bandwidth. The problem is that memory latency varies non-linearly with the number and type of concurrent accesses, and the latter may in turn vary with time, often unpredictably. For this reason, previous attempts at memory regulation in scheduling solutions resulted either in poor real-time execution guarantees, or in severe underutilization of the memory bandwidth. In this paper, we outline High Memory Bandwidth (HMB), a scheduling solution that guarantees bounded response times to real-time task sets through memory regulation, while also reaching a high utilization memory bandwidth. Since the complete solution is complex, just like the problem it addresses, this preliminary work defines in full detail only the core mechanism. This mechanism builds on the notion of memory access slowdown experienced by any processor performing back-to-back memory operations; this slowdown is due to the interference generated by other processors also accessing the memory at the same time. The core mechanism assumes that each processor can tolerate a certain amount of slowdown before the timing behavior of the task(s) it is running is compromised. Each processor has a priority assigned: the higher the priority, the more stringent the timing requirements. The slowdown can be controlled by regulating with precision the maximum amount of system bandwidth each processor is allowed to use, based on its priority. The proposed mechanism finds the maximum bandwidth each processor can use such that the highest number of processors simultaneously accessing memory is found (thus avoiding memory bandwidth underutilization) while guaranteeing that the slowdown of each processor is kept within the tolerated limits.
Cite as

Mohammadhassan Gholami Derouei, Paolo Valente, Marco Solieri, and Andrea Marongiu. HMB: Scheduling PREM-Like Real-Time Tasks at High Memory Bandwidth (Invited Paper). In Fifth Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2024). Open Access Series in Informatics (OASIcs), Volume 117, pp. 1:1-1:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{gholamiderouei_et_al:OASIcs.NG-RES.2024.1,
  author =	{Gholami Derouei, Mohammadhassan and Valente, Paolo and Solieri, Marco and Marongiu, Andrea},
  title =	{{HMB: Scheduling PREM-Like Real-Time Tasks at High Memory Bandwidth}},
  booktitle =	{Fifth Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2024)},
  pages =	{1:1--1:18},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-313-3},
  ISSN =	{2190-6807},
  year =	{2024},
  volume =	{117},
  editor =	{Yomsi, Patrick Meumeu and Wildermann, Stefan},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.NG-RES.2024.1},
  URN =		{urn:nbn:de:0030-drops-197049},
  doi =		{10.4230/OASIcs.NG-RES.2024.1},
  annote =	{Keywords: Heterogenous systems, Parallel execution, Shared memory, Bandwidth regulation, Memory access, Real-time execution, Memory bandwidth utilization, High Memory Bandwidth (HMB), Memory access slowdown, Memory interference, Memory-centric scheduling}
}
Document
DOI: 10.4230/OASIcs.WCET.2014.63
The Challenge of Time-Predictability in Modern Many-Core Architectures

Authors: Vincent Nélis, Patrick Meumeu Yomsi, Luís Miguel Pinho, José Carlos Fonseca, Marko Bertogna, Eduardo Quiñones, Roberto Vargas, and Andrea Marongiu

Published in: OASIcs, Volume 39, 14th International Workshop on Worst-Case Execution Time Analysis (2014)

Abstract
The recent technological advancements and market trends are causing an interesting phenomenon towards the convergence of High-Performance Computing (HPC) and Embedded Computing (EC) domains. Many recent HPC applications require huge amounts of information to be processed within a bounded amount of time while EC systems are increasingly concerned with providing higher performance in real-time. The convergence of these two domains towards systems requiring both high performance and a predictable time-behavior challenges the capabilities of current hardware architectures. Fortunately, the advent of next-generation many-core embedded platforms has the chance of intercepting this converging need for predictability and high-performance, allowing HPC and EC applications to be executed on efficient and powerful heterogeneous architectures integrating general-purpose processors with many-core computing fabrics. However, addressing this mixed set of requirements is not without its own challenges and it is now of paramount importance to develop new techniques to exploit the massively parallel computation capabilities of many-core platforms in a predictable way.
Cite as

Vincent Nélis, Patrick Meumeu Yomsi, Luís Miguel Pinho, José Carlos Fonseca, Marko Bertogna, Eduardo Quiñones, Roberto Vargas, and Andrea Marongiu. The Challenge of Time-Predictability in Modern Many-Core Architectures. In 14th International Workshop on Worst-Case Execution Time Analysis. Open Access Series in Informatics (OASIcs), Volume 39, pp. 63-72, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2014)

Copy BibTex To Clipboard

@InProceedings{nelis_et_al:OASIcs.WCET.2014.63,
  author =	{N\'{e}lis, Vincent and Yomsi, Patrick Meumeu and Pinho, Lu{\'\i}s Miguel and Fonseca, Jos\'{e} Carlos and Bertogna, Marko and Qui\~{n}ones, Eduardo and Vargas, Roberto and Marongiu, Andrea},
  title =	{{The Challenge of Time-Predictability in Modern Many-Core Architectures}},
  booktitle =	{14th International Workshop on Worst-Case Execution Time Analysis},
  pages =	{63--72},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-939897-69-9},
  ISSN =	{2190-6807},
  year =	{2014},
  volume =	{39},
  editor =	{Falk, Heiko},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.WCET.2014.63},
  URN =		{urn:nbn:de:0030-drops-46050},
  doi =		{10.4230/OASIcs.WCET.2014.63},
  annote =	{Keywords: Time-Predictability, Many-Cores, Multi-Cores, Timing Analysis}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact