Bounding DMA Interference on Hard-Real-Time Embedded Systems
نویسندگان
چکیده
A DMA controller that operates in the cycle-stealing mode transfers data by stealing bus cycles from the CPU. The concurrent contention for the I/O bus by a CPU task and a cycle-stealing DMA I/O task retards their progress and extends their execution times. In this paper we first describe a method for bounding the worst-case execution time (WCET) of a CPU task when cycle-stealing DMA I/O is present. We next use the dynamic-programming technique to develop a method for bounding the WCET of a cyclestealing DMA I/O task executing concurrently with a set of CPU tasks. We conducted exhaustive simulations on a widely-used embedded processor. The experimental results demonstrate that our methods tightly bound the WCETs of CPU tasks and of cycle-stealing DMA I/O tasks.
منابع مشابه
Timing Analysis for DAG-based and GFP Scheduled Tasks
Modern embedded systems have made the transition from single-core to multi-core architectures, providing performance improvement via parallelism rather than higher clock frequencies. DAGs are considered among the most generic task models in the real-time domain and are well suited to exploit this parallelism. In this paper we provide a schedulability test using response-time analysis exploiting...
متن کاملCompositional Verification of Real-Time Fault-Tolerant Programs
A hard-masking real-time program is one that satisfies safety (including timing constraints) and liveness properties in the absence and presence of faults. It has been shown that any hard-masking program can be decomposed into a faultintolerant version and a set of fault-tolerance components known as detectors and δ-correctors. In this paper, we introduce a set of sufficient conditions for inte...
متن کاملILP-Based Program Path Analysis for Bounding Worst-Case Inter-Task Cache Conflicts
SUMMARY The unpredictable behavior of cache memory makes it difficult to statically analyze the worst-case performance of real-time systems. This problem is further exacerbated in the case of preemptive multitask systems because of inter-task cache interference, called Cache-Related Pre-emption Delay (CRPD). This paper proposes an approach to analyzing the tight upper bound on CRPD which a task...
متن کاملA Network Interface Card Architecture for I/O Virtualization in Embedded Systems
In this paper we present an architectural concept for network interface cards (NIC) targeting embedded systems and supporting I/O virtualization. Current solutions for high performance computing do not sufficiently address embedded system requirements i.e., guarantee real-time constraints and differentiated service levels as well as only utilize limited HW resources. The central ideas of our wo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- J. Inf. Sci. Eng.
دوره 22 شماره
صفحات -
تاریخ انتشار 2006