9 Search Results for "Solieri, Marco"

Document
DOI: 10.4230/LIPIcs.ECRTS.2025.2
Multi-Objective Memory Bandwidth Regulation and Cache Partitioning for Multicore Real-Time Systems

Authors: Binqi Sun, Zhihang Wei, Andrea Bastoni, Debayan Roy, Mirco Theile, Tomasz Kloda, Rodolfo Pellizzoni, and Marco Caccamo

Published in: LIPIcs, Volume 335, 37th Euromicro Conference on Real-Time Systems (ECRTS 2025)

Abstract
Memory bandwidth regulation and cache partitioning are widely used techniques for achieving predictable timing in real-time computing systems. Combined with partitioned scheduling, these methods require careful co-allocation of tasks and resources to cores, as task execution times strongly depend on available allocated resources. To address this challenge, this paper presents a 0-1 linear program for task-resource co-allocation, along with a multi-objective heuristic designed to minimize resource usage while guaranteeing schedulability under a preemptive EDF scheduling policy. Our heuristic employs a multi-layer framework, where an outer layer explores resource allocations using Pareto-pruned search, and an inner layer optimizes task allocation by solving a knapsack problem using dynamic programming. To evaluate the performance of the proposed optimization algorithm, we profile real-world benchmarks on an embedded AMD UltraScale+ ZCU102 platform, with fine-grained resource partitioning enabled by the Jailhouse hypervisor, leveraging cache set partitioning and MemGuard for memory bandwidth regulation. Experiments based on the benchmarking results show that the proposed 0-1 linear program outperforms existing mixed-integer programs by finding more optimal solutions within the same time limit. Moreover, the proposed multi-objective multi-layer heuristic performs consistently better than the state-of-the-art multi-resource-task co-allocation algorithm in terms of schedulability, resource usage, number of non-dominated solutions, and computational efficiency.
Cite as

Binqi Sun, Zhihang Wei, Andrea Bastoni, Debayan Roy, Mirco Theile, Tomasz Kloda, Rodolfo Pellizzoni, and Marco Caccamo. Multi-Objective Memory Bandwidth Regulation and Cache Partitioning for Multicore Real-Time Systems. In 37th Euromicro Conference on Real-Time Systems (ECRTS 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 335, pp. 2:1-2:23, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{sun_et_al:LIPIcs.ECRTS.2025.2,
  author =	{Sun, Binqi and Wei, Zhihang and Bastoni, Andrea and Roy, Debayan and Theile, Mirco and Kloda, Tomasz and Pellizzoni, Rodolfo and Caccamo, Marco},
  title =	{{Multi-Objective Memory Bandwidth Regulation and Cache Partitioning for Multicore Real-Time Systems}},
  booktitle =	{37th Euromicro Conference on Real-Time Systems (ECRTS 2025)},
  pages =	{2:1--2:23},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-377-5},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{335},
  editor =	{Mancuso, Renato},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2025.2},
  URN =		{urn:nbn:de:0030-drops-235807},
  doi =		{10.4230/LIPIcs.ECRTS.2025.2},
  annote =	{Keywords: Multi-objective optimization, memory bandwidth regulation, cache partitioning, partitioned scheduling, real-time systems}
}
Document
DOI: 10.4230/LIPIcs.ECRTS.2025.21
Hardware Compute Partitioning on NVIDIA GPUs for Composable Systems

Authors: Joshua Bakita and James H. Anderson

Published in: LIPIcs, Volume 335, 37th Euromicro Conference on Real-Time Systems (ECRTS 2025)

Abstract
As GPU-using tasks become more common in embedded, safety-critical systems, efficiency demands necessitate sharing a single GPU among multiple tasks. Unfortunately, existing ways to schedule multiple tasks onto a GPU often either result in a loss of ability to meet deadlines, or a loss of efficiency. In this work, we develop a system-level spatial compute partitioning mechanism for NVIDIA GPUs and demonstrate that it can be used to execute tasks efficiently without compromising timing predictability. Our tool, called nvtaskset, supports composable systems by not requiring task, driver, or hardware modifications. In our evaluation, we demonstrate sub-1-μs overheads, stronger partition enforcement, and finer-granularity partitioning when using our mechanism instead of NVIDIA’s Multi-Process Service (MPS) or Multi-instance GPU (MiG) features.
Cite as

Joshua Bakita and James H. Anderson. Hardware Compute Partitioning on NVIDIA GPUs for Composable Systems. In 37th Euromicro Conference on Real-Time Systems (ECRTS 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 335, pp. 21:1-21:25, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{bakita_et_al:LIPIcs.ECRTS.2025.21,
  author =	{Bakita, Joshua and Anderson, James H.},
  title =	{{Hardware Compute Partitioning on NVIDIA GPUs for Composable Systems}},
  booktitle =	{37th Euromicro Conference on Real-Time Systems (ECRTS 2025)},
  pages =	{21:1--21:25},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-377-5},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{335},
  editor =	{Mancuso, Renato},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2025.21},
  URN =		{urn:nbn:de:0030-drops-235998},
  doi =		{10.4230/LIPIcs.ECRTS.2025.21},
  annote =	{Keywords: Real-time systems, composable systems, graphics processing units, CUDA}
}
Document
DOI: 10.4230/OASIcs.NG-RES.2025.5
SP-IMPact: A Framework for Static Partitioning Interference Mitigation and Performance Analysis

Authors: Diogo Costa, Gonçalo Moreira, Afonso Oliveira, José Martins, and Sandro Pinto

Published in: OASIcs, Volume 128, Sixth Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2025)

Abstract
Modern embedded systems are evolving toward complex, heterogeneous architectures to accommodate increasingly demanding applications. Driven by industry SWAP-C (Size, Weight, Power, and Cost) constraints, this shift has led to the consolidation of multiple systems onto single hardware platforms. Static Partitioning Hypervisors (SPHs) offer a promising solution to partition hardware resources and provide spatial isolation between critical workloads. However, shared hardware resources like the Last-Level Cache (LLC) and system bus can introduce significant temporal interference between virtual machines (VMs), negatively impacting performance and predictability. Over the past decade, academia and industry have focused on developing interference mitigation techniques, such as cache partitioning and memory bandwidth reservation. Configuring these techniques, however, is complex and time-consuming. Cache partitioning requires careful balancing of cache sections across VMs, while memory bandwidth reservation requires tuning bandwidth budgets and periods. With numerous possible configurations, testing all combinations is impractical and often leads to suboptimal configurations. Moreover, there is a gap in understanding how these techniques interact, as their combined use can result in compounded or conflicting effects on system performance. Static analysis solutions that estimate worst-case execution times (WCET) and upper bounds on execution times provide some guidance for configuring interference mitigation techniques. While useful in identifying potential interference effects, these tools often fail to capture the full complexity of modern multi-core systems, as they typically focus on a limited set of shared resources and neglect other sources of contention, such as IOMMUs and interrupt controllers. To address these challenges, we introduce SP-IMPact, an open-source framework designed to analyze and guide the configuration of interference mitigation techniques, through the deployment of diverse VM configurations and setups, and assessment of hardware-level contention (leveraging SPHs). It supports two mitigation techniques: (i) cache coloring and (ii) memory bandwidth reservation, while also evaluating the interactions between these techniques and their cumulative impact on system performance. By providing insights on real hardware platforms, SP-IMPact helps to optimize the configuration of these techniques in mixed-criticality systems, ensuring both performance and predictability.
Cite as

Diogo Costa, Gonçalo Moreira, Afonso Oliveira, José Martins, and Sandro Pinto. SP-IMPact: A Framework for Static Partitioning Interference Mitigation and Performance Analysis. In Sixth Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2025). Open Access Series in Informatics (OASIcs), Volume 128, pp. 5:1-5:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{costa_et_al:OASIcs.NG-RES.2025.5,
  author =	{Costa, Diogo and Moreira, Gon\c{c}alo and Oliveira, Afonso and Martins, Jos\'{e} and Pinto, Sandro},
  title =	{{SP-IMPact: A Framework for Static Partitioning Interference Mitigation and Performance Analysis}},
  booktitle =	{Sixth Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2025)},
  pages =	{5:1--5:15},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-366-9},
  ISSN =	{2190-6807},
  year =	{2025},
  volume =	{128},
  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.2025.5},
  URN =		{urn:nbn:de:0030-drops-229911},
  doi =		{10.4230/OASIcs.NG-RES.2025.5},
  annote =	{Keywords: Virtualization, Contention, Multi-core Interference, Mixed-Criticality Systems, Arm}
}
Document
DOI: 10.4230/OASIcs.NG-RES.2025.4
H-MBR: Hypervisor-Level Memory Bandwidth Reservation for Mixed Criticality Systems

Authors: Afonso Oliveira, Diogo Costa, Gonçalo Moreira, José Martins, and Sandro Pinto

Published in: OASIcs, Volume 128, Sixth Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2025)

Abstract
Recent advancements in fields such as automotive and aerospace have driven a growing demand for robust computational resources. Applications that were once designed for basic Microcontroller Units (MCUs) are now deployed on highly heterogeneous System-on-Chip (SoC) platforms. While these platforms deliver the necessary computational performance, they also present challenges related to resource sharing and predictability. These challenges are particularly pronounced when consolidating safety-critical and non-safety-critical systems, the so-called Mixed-Criticality Systems (MCS) to adhere to strict Size, Weight, Power, and Cost (SWaP-C) requirements. MCS consolidation on shared platforms requires stringent spatial and temporal isolation to comply with functional safety standards (e.g., ISO 26262). Virtualization, mainly leveraged by hypervisors, is a key technology that ensures spatial isolation across multiple OSes and applications; however ensuring temporal isolation remains challenging due to contention on shared resources, such as main memory, caches, and system buses, which impacts real-time performance and predictability. To mitigate this problem, several strategies (e.g., cache coloring and memory bandwidth reservation) have been proposed. Although cache coloring is typically implemented on state-of-the-art hypervisors, memory bandwidth reservation approaches are commonly implemented at the Linux kernel level or rely on dedicated hardware and typically do not consider the concept of Virtual Machines that can run different OSes. To fill the gap between current memory bandwidth reservation solutions and the deployment of MCSs that operate on a hypervisor, this work introduces H-MBR, an open-source VM-centric memory bandwidth reservation mechanism. H-MBR features (i) VM-centric bandwidth reservation, (ii) OS and platform agnosticism, and (iii) reduced overhead. Empirical results evidenced no overhead on non-regulated workloads, and negligible overhead (<1%) for regulated workloads for regulation periods of 2 µs or higher.
Cite as

Afonso Oliveira, Diogo Costa, Gonçalo Moreira, José Martins, and Sandro Pinto. H-MBR: Hypervisor-Level Memory Bandwidth Reservation for Mixed Criticality Systems. In Sixth Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2025). Open Access Series in Informatics (OASIcs), Volume 128, pp. 4:1-4:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{oliveira_et_al:OASIcs.NG-RES.2025.4,
  author =	{Oliveira, Afonso and Costa, Diogo and Moreira, Gon\c{c}alo and Martins, Jos\'{e} and Pinto, Sandro},
  title =	{{H-MBR: Hypervisor-Level Memory Bandwidth Reservation for Mixed Criticality Systems}},
  booktitle =	{Sixth Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2025)},
  pages =	{4:1--4:15},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-366-9},
  ISSN =	{2190-6807},
  year =	{2025},
  volume =	{128},
  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.2025.4},
  URN =		{urn:nbn:de:0030-drops-229905},
  doi =		{10.4230/OASIcs.NG-RES.2025.4},
  annote =	{Keywords: Virtualization, Multi-core Interference, Mixed-Criticality Systems, Arm, Memory Bandwidth Reservation}
}
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.NG-RES.2020.3
Bao: A Lightweight Static Partitioning Hypervisor for Modern Multi-Core Embedded Systems

Authors: José Martins, Adriano Tavares, Marco Solieri, Marko Bertogna, and Sandro Pinto

Published in: OASIcs, Volume 77, Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2020)

Abstract
Given the increasingly complex and mixed-criticality nature of modern embedded systems, virtualization emerges as a natural solution to achieve strong spatial and temporal isolation. Widely used hypervisors such as KVM and Xen were not designed having embedded constraints and requirements in mind. The static partitioning architecture pioneered by Jailhouse seems to address embedded concerns. However, Jailhouse still depends on Linux to boot and manage its VMs. In this paper, we present the Bao hypervisor, a minimal, standalone and clean-slate implementation of the static partitioning architecture for Armv8 and RISC-V platforms. Preliminary results regarding size, boot, performance, and interrupt latency, show this approach incurs only minimal virtualization overhead. Bao will soon be publicly available, in hopes of engaging both industry and academia on improving Bao’s safety, security, and real-time guarantees.
Cite as

José Martins, Adriano Tavares, Marco Solieri, Marko Bertogna, and Sandro Pinto. Bao: A Lightweight Static Partitioning Hypervisor for Modern Multi-Core Embedded Systems. In Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2020). Open Access Series in Informatics (OASIcs), Volume 77, pp. 3:1-3:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)

Copy BibTex To Clipboard

@InProceedings{martins_et_al:OASIcs.NG-RES.2020.3,
  author =	{Martins, Jos\'{e} and Tavares, Adriano and Solieri, Marco and Bertogna, Marko and Pinto, Sandro},
  title =	{{Bao: A Lightweight Static Partitioning Hypervisor for Modern Multi-Core Embedded Systems}},
  booktitle =	{Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2020)},
  pages =	{3:1--3:14},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-136-8},
  ISSN =	{2190-6807},
  year =	{2020},
  volume =	{77},
  editor =	{Bertogna, Marko and Terraneo, Federico},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.NG-RES.2020.3},
  URN =		{urn:nbn:de:0030-drops-117795},
  doi =		{10.4230/OASIcs.NG-RES.2020.3},
  annote =	{Keywords: Virtualization, hypervisor, static partitioning, safety, security, real-time, embedded systems, Arm, RISC-V}
}
Document
Artifact
DOI: 10.4230/DARTS.5.1.4
API Comparison of CPU-To-GPU Command Offloading Latency on Embedded Platforms (Artifact)

Authors: Roberto Cavicchioli, Nicola Capodieci, Marco Solieri, and Marko Bertogna

Published in: DARTS, Volume 5, Issue 1, Special Issue of the 31st Euromicro Conference on Real-Time Systems (ECRTS 2019)

Abstract
High-performance heterogeneous embedded platforms allow offloading of parallel workloads to an integrated accelerator, such as General Purpose-Graphic Processing Units (GP-GPUs). A time-predictable characterization of task submission is a must in real-time applications. We provide a profiler of the time spent by the CPU for submitting stereotypical GP-GPU workload shaped as a Deep Neural Network of parameterized complexity. The submission is performed using the latest API available: NVIDIA CUDA, including its various techniques, and Vulkan. Complete automation for the test on Jetson Xavier is also provided by scripts that install software dependencies, run the experiments, and collect results in a PDF report.
Cite as

Roberto Cavicchioli, Nicola Capodieci, Marco Solieri, and Marko Bertogna. API Comparison of CPU-To-GPU Command Offloading Latency on Embedded Platforms (Artifact). In Special Issue of the 31st Euromicro Conference on Real-Time Systems (ECRTS 2019). Dagstuhl Artifacts Series (DARTS), Volume 5, Issue 1, pp. 4:1-4:3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)

Copy BibTex To Clipboard

@Article{cavicchioli_et_al:DARTS.5.1.4,
  author =	{Cavicchioli, Roberto and Capodieci, Nicola and Solieri, Marco and Bertogna, Marko},
  title =	{{API Comparison of CPU-To-GPU Command Offloading Latency on Embedded Platforms}},
  pages =	{4:1--4:3},
  journal =	{Dagstuhl Artifacts Series},
  ISSN =	{2509-8195},
  year =	{2019},
  volume =	{5},
  number =	{1},
  editor =	{Cavicchioli, Roberto and Capodieci, Nicola and Solieri, Marco and Bertogna, Marko},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DARTS.5.1.4},
  URN =		{urn:nbn:de:0030-drops-107322},
  doi =		{10.4230/DARTS.5.1.4},
  annote =	{Keywords: GPU, Applications, Heterogeneus systems}
}
Document
DOI: 10.4230/LIPIcs.ECRTS.2019.22
Novel Methodologies for Predictable CPU-To-GPU Command Offloading

Authors: Roberto Cavicchioli, Nicola Capodieci, Marco Solieri, and Marko Bertogna

Published in: LIPIcs, Volume 133, 31st Euromicro Conference on Real-Time Systems (ECRTS 2019)

Abstract
There is an increasing industrial and academic interest towards a more predictable characterization of real-time tasks on high-performance heterogeneous embedded platforms, where a host system offloads parallel workloads to an integrated accelerator, such as General Purpose-Graphic Processing Units (GP-GPUs). In this paper, we analyze an important aspect that has not yet been considered in the real-time literature, and that may significantly affect real-time performance if not properly treated, i.e., the time spent by the CPU for submitting GP-GPU operations. We will show that the impact of CPU-to-GPU kernel submissions may be indeed relevant for typical real-time workloads, and that it should be properly factored in when deriving an integrated schedulability analysis for the considered platforms. This is the case when an application is composed of many small and consecutive GPU compute/copy operations. While existing techniques mitigate this issue by batching kernel calls into a reduced number of persistent kernel invocations, in this work we present and evaluate three other approaches that are made possible by recently released versions of the NVIDIA CUDA GP-GPU API, and by Vulkan, a novel open standard GPU API that allows an improved control of GPU command submissions. We will show that this added control may significantly improve the application performance and predictability due to a substantial reduction in CPU-to-GPU driver interactions, making Vulkan an interesting candidate for becoming the state-of-the-art API for heterogeneous Real-Time systems. Our findings are evaluated on a latest generation NVIDIA Jetson AGX Xavier embedded board, executing typical workloads involving Deep Neural Networks of parameterized complexity.
Cite as

Roberto Cavicchioli, Nicola Capodieci, Marco Solieri, and Marko Bertogna. Novel Methodologies for Predictable CPU-To-GPU Command Offloading. In 31st Euromicro Conference on Real-Time Systems (ECRTS 2019). Leibniz International Proceedings in Informatics (LIPIcs), Volume 133, pp. 22:1-22:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)

Copy BibTex To Clipboard

@InProceedings{cavicchioli_et_al:LIPIcs.ECRTS.2019.22,
  author =	{Cavicchioli, Roberto and Capodieci, Nicola and Solieri, Marco and Bertogna, Marko},
  title =	{{Novel Methodologies for Predictable CPU-To-GPU Command Offloading}},
  booktitle =	{31st Euromicro Conference on Real-Time Systems (ECRTS 2019)},
  pages =	{22:1--22:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-110-8},
  ISSN =	{1868-8969},
  year =	{2019},
  volume =	{133},
  editor =	{Quinton, Sophie},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECRTS.2019.22},
  URN =		{urn:nbn:de:0030-drops-107595},
  doi =		{10.4230/LIPIcs.ECRTS.2019.22},
  annote =	{Keywords: Heterogeneous systems, GPU, CUDA, Vulkan}
}
Document
DOI: 10.4230/LIPIcs.FSCD.2017.17
Is the Optimal Implementation Inefficient? Elementarily Not

Authors: Stefano Guerrini and Marco Solieri

Published in: LIPIcs, Volume 84, 2nd International Conference on Formal Structures for Computation and Deduction (FSCD 2017)

Abstract
Sharing graphs are a local and asynchronous implementation of lambda-calculus beta-reduction (or linear logic proof-net cut-elimination) that avoids useless duplications. Empirical benchmarks suggest that they are one of the most efficient machineries, when one wants to fully exploit the higher-order features of lambda-calculus. However, we still lack confirming grounds with theoretical solidity to dispel uncertainties about the adoption of sharing graphs. Aiming at analysing in detail the worst-case overhead cost of sharing operators, we restrict to the case of elementary and light linear logic, two subsystems with bounded computational complexity of multiplicative exponential linear logic. In these two cases, the bookkeeping component is unnecessary, and sharing graphs are simplified to the so-called "abstract algorithm". By a modular cost comparison over a syntactical simulation, we prove that the overhead of shared reductions is quadratically bounded to cost of the naive implementation, i.e. proof-net reduction. This result generalises and strengthens a previous complexity result, and implies that the price of sharing is negligible, if compared to the obtainable benefits on reductions requiring a large amount of duplication.
Cite as

Stefano Guerrini and Marco Solieri. Is the Optimal Implementation Inefficient? Elementarily Not. In 2nd International Conference on Formal Structures for Computation and Deduction (FSCD 2017). Leibniz International Proceedings in Informatics (LIPIcs), Volume 84, pp. 17:1-17:16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2017)

Copy BibTex To Clipboard

@InProceedings{guerrini_et_al:LIPIcs.FSCD.2017.17,
  author =	{Guerrini, Stefano and Solieri, Marco},
  title =	{{Is the Optimal Implementation Inefficient? Elementarily Not}},
  booktitle =	{2nd International Conference on Formal Structures for Computation and Deduction (FSCD 2017)},
  pages =	{17:1--17:16},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-047-7},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{84},
  editor =	{Miller, Dale},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FSCD.2017.17},
  URN =		{urn:nbn:de:0030-drops-77337},
  doi =		{10.4230/LIPIcs.FSCD.2017.17},
  annote =	{Keywords: optimality, sharing graphs, lambda-calculus, complexity, linear logic, proof nets}
}
  • Refine by Type
  • 9 Document/PDF
  • 4 Document/HTML

  • Refine by Publication Year
  • 4 2025
  • 1 2024
  • 1 2020
  • 2 2019
  • 1 2017

  • Refine by Author
  • 5 Solieri, Marco
  • 3 Bertogna, Marko
  • 3 Martins, José
  • 3 Pinto, Sandro
  • 2 Capodieci, Nicola
  • Show More...

  • Refine by Series/Journal
  • 4 LIPIcs
  • 4 OASIcs
  • 1 DARTS

  • Refine by Classification
  • 3 Computer systems organization → Embedded software
  • 2 Computer systems organization → Real-time system architecture
  • 2 Computer systems organization → Real-time system specification
  • 2 Computer systems organization → Real-time systems
  • 2 Computer systems organization → System on a chip
  • Show More...

  • Refine by Keyword
  • 3 Arm
  • 3 Virtualization
  • 2 CUDA
  • 2 GPU
  • 2 Mixed-Criticality Systems
  • Show More...

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact