Modern processors often provide cache locking capability which can be applied statically and dynamically to manage cache in a predictable manner. the selection of instructions to be locked in the instruction cache (I-...
详细信息
ISBN:
(纸本)9780769537870
Modern processors often provide cache locking capability which can be applied statically and dynamically to manage cache in a predictable manner. the selection of instructions to be locked in the instruction cache (I-Cache) has dramatic influence on the performance of multi-task real-timeembeddedsystems. this paper focuses on using cache locking techniques on a shared I-Cache in a real-timeembedded system with multi-tasks to minimize its worst-case utilization (WCU) which is one of the most important criteria for designing real-timeembeddedsystems. We analyze the static and dynamic strategies to perform I-Cache locking and propose different algorithms which utilize the foreknowing information of the real-timeembeddedapplications. Experiments show that the proposed algorithms can reduce WCU further compared to previous techniques. Design suggestions on which strategy should be utilized under different situations are also induced from the experimental results.
Processor partitioning and hierarchical scheduling have been widely used for composing hard real-timesystems on a shared hardware platform while preserving the timing requirements of the systems. Due to the safety cr...
详细信息
ISBN:
(纸本)9781479908509
Processor partitioning and hierarchical scheduling have been widely used for composing hard real-timesystems on a shared hardware platform while preserving the timing requirements of the systems. Due to the safety critical nature of hard real-timesystems, a conservative analysis is often used for deriving a sufficient partition size. Applying the exact same analysis for deriving the partition sizes for soft real-timesystems result in unnecessary processors overallocation and consequently waste of the CPU resource. In this paper, to address the problem of composing soft and hard real-timesystems on a resource constrained shared hardware, we present a multi-level adaptive hierarchical scheduling framework. In our framework, we adapt the processor partition sizes of soft real-timesystems according to their need at each time point by on-line monitoring their processor demand. Furthermore, we implement our adaptive framework in the Linux kernel and show the performance of our framework using a case study.
Model Driven Engineering provides facilities to tackle complexity in real-timesystems, from early requirements capture to validation & verification down to code generation. We note that models are built from a sy...
详细信息
ISBN:
(纸本)9780769537870
Model Driven Engineering provides facilities to tackle complexity in real-timesystems, from early requirements capture to validation & verification down to code generation. We note that models are built from a system perspective, and resources are allocated to meet communication, energy or scheduling constraints. Yet, it is seldom optimal. In this paper, we explore transformations applied at model-level that preserve schedulability of the system, yet reduce the overall resource consumption. We use A AD L as input formalism. By automating this process, we show how to transition from a system view to an implementation view, closer to actual hardware constraints.
Modern real-timeembeddedsystems have increasingly penetrated our daily life and are also often constrained in terms of temperature and energy. In this paper, a thesis is defended that from a real-timesystems perspe...
详细信息
ISBN:
(纸本)9781479908516
Modern real-timeembeddedsystems have increasingly penetrated our daily life and are also often constrained in terms of temperature and energy. In this paper, a thesis is defended that from a real-timesystems perspective, thermally constrained dynamic power management approaches behave very similar to idealised dynamic voltage and frequency scaling. Hence, existing dynamic voltage and frequency scaling solutions proposed for periodic/sporadic task models can be applied to thermally constrained dynamic power management systems with moderate effort. this work presents the similarities along withthe distinctive elements between two approaches. Within the case study, the porting of a dynamic voltage and frequency scaling algorithm of the literature to thermally constrained dynamic power management system is demonstrated.
Deployment of deep learning models to embedded devices like smart phones or other smart end-user devices has been the hotspot in computer vision and artificial intelligence. However, the performance of recent state-of...
详细信息
ISBN:
(纸本)9781450376426
Deployment of deep learning models to embedded devices like smart phones or other smart end-user devices has been the hotspot in computer vision and artificial intelligence. However, the performance of recent state-of-the-art CNNs is dissatisfactory in real-world face applications. To solve this issue, we refined an efficient CNN architecture for face verification with extreme efficiency for real-time face applications in embedded environment, namely R-MobileFaceNet. We also proposed Dynamically Fuzzy Image Dataset, namely DFID, to evaluate the capacity of the models to deploy on embedded platforms. Our experiments proved our refined model was capable of embedded deployment, achieving higher accuracy improvement on DFID and neglectable accuracy loss on LFW. this paper also serves as an effective and efficient solution for deploying deep learning models to real-world face applications.
Increasing demand for performance and further integration promotes the use of multi-and many-core systems - also in safety-critical embeddedsystems. In this domain, hardware platforms obviously have to support real-t...
详细信息
ISBN:
(纸本)9781479908516
Increasing demand for performance and further integration promotes the use of multi-and many-core systems - also in safety-critical embeddedsystems. In this domain, hardware platforms obviously have to support real-time, predictability constrained applications such as an anti-lock braking system. However, the on-going trend to integrate multiple functions with different criticalities (mixed critical) on a single platform calls for a paradigm shift. Mixed-critical systems require special attention with respect to functional (access protection) and non-functional (performance) isolation. An additional layer of protection and guaranteed service on the underlying infrastructure enables the efficient adoption of such architectures in safety-critical domains. In this paper, we present the IDAMe, a many-core platform which provides mechanisms to integrate applications of different criticalities on a single platform.
Unified L2 caches can lead to runtime interferences between instructions and data, making it very hard, if not impossible, to perform timing analysis for real-timesystems. this paper proposes a priority cache to achi...
详细信息
ISBN:
(纸本)9780769541556
Unified L2 caches can lead to runtime interferences between instructions and data, making it very hard, if not impossible, to perform timing analysis for real-timesystems. this paper proposes a priority cache to achieve bothtime predictability and high performance for real-timesystems. the priority cache allows boththe instruction and data streams to share the aggregate L2 cache;however, instructions and data cannot replace each other to enable independent instruction cache and data cache timing analyses. Our performance evaluation shows that the instruction priority cache outperforms separate L2 caches, both of which can achieve time predictability. On average, the number of execution cycles of the instruction priority cache is only 1.1% more than that of a unified L2 cache.
In this paper we consider data freshness and overload handling in embeddedsystems. the requirements on data management and overload handling are derived from an engine control software. Data items need to be up-to-da...
详细信息
ISBN:
(纸本)0769526764
In this paper we consider data freshness and overload handling in embeddedsystems. the requirements on data management and overload handling are derived from an engine control software. Data items need to be up-to-date, and to achieve this data dependencies must be considered, i.e., updating a data item requires other data items are up-to-date. We also note that a correct result of a calculation can in some cases be calculated using a subset of the inputs. Hence, data dependencies can be divided into required and not required data items, e.g., only a subset of data items affecting the fuel calculation in an engine control needs to be calculated during a transient overload in order to reduce the number of calculations. Required data items must always be up-to-date, whereas not required data items can be stale. We describe an algorithm that dynamically determines which data items need to be updated taking workload, data freshness, and data relationships into consideration. Performance results show that the algorithm suppresses transient overloads better than (m, k) - and skip-over scheduling combined with established algorithms to update data items. the performance results are collected from an implementation of a real-time database on the realtime operating system mu C/OS-H. To investigate whether the system is occasionally overloaded an offline analysis algorithm estimating period times of updates is presented.
Procedural abstraction reduces code size by replacing repeated code fragments with call instructions to a sub-routine that executes the repeated fragment. However, in order to build a subroutine, extra instructions ar...
详细信息
In modern embedded platforms, safety-critical functionalities that must be certified correct to very high levels of assurance may co-exist with less critical software that are not subject to certification requirements...
详细信息
ISBN:
(纸本)9781479908516
In modern embedded platforms, safety-critical functionalities that must be certified correct to very high levels of assurance may co-exist with less critical software that are not subject to certification requirements. One seeks to satisfy two, sometimes contradictory, goals upon such mixed-criticality platforms: (i) certify the safety-critical functionalities under very conservative assumptions, and (ii) achieve high resource utilization during run-time, when actual behavior does not live up to the pessimistic assumptions under which certification was made. this paper describes efforts at designing fixed-priority scheduling algorithms that balance these two requirements, when scheduling recurrent tasks that are triggered by external events of unknown exact frequency.
暂无评论