Abstract Recent advances in AI culminate a shift in science and engineering away from strong reliance on algorithmic and symbolic knowledge towards new data-driven approaches. How does the emerging intelligent data-centric world impact research on real-time and embedded computing? We argue for two effects: (1) new challenges in embedded system contexts, and (2) new opportunities for community expansion beyond the embedded domain. First, on the embedded system side, the shifting nature of computing towards data-centricity affects the types of bottlenecks that arise. At training time, the bottlenecks are generally data-related. Embedded computing relies on scarce sensor data modalities, unlike those commonly addressed in mainstream AI, necessitating solutions for efficient learning from scarce sensor data. At inference time, the bottlenecks are resource-related, calling for improved resource economy and novel scheduling policies. Further ahead, the convergence of AI around large language models (LLMs) introduces additional model-related challenges in embedded contexts. Second, on the domain expansion side, we argue that community expertise in handling resource bottlenecks is becoming increasingly relevant to a new domain: the cloud environment, driven by AI needs. The paper discusses the novel research directions that arise in the data-centric world of AI, covering data-, resource-, and model-related challenges in embedded systems as well as new opportunities in the cloud domain.

This paper investigates the optimization of memory sampling in status updating systems, where source updates are published in shared memory, and reader process samples the memory for source updates by paying a sampling cost. We formulate a discrete-time decision problem to find a sampling policy that minimizes average cost comprising age at the client and the cost incurred due to sampling. We establish that an optimal policy is a stationary and deterministic threshold-type policy, and subsequently derive optimal threshold and the corresponding optimal average cost.

We examine status updating systems in which time-stamped status updates are stored/written in shared-memory. Specifically, we compare Read-Copy-Update (RCU) and Readers-Writer lock (RWL) as shared-memory synchronization primitives on the update freshness. To demonstrate the tension between readers and writers accessing shared-memory, we consider a network scenario with a pair of coupled updating processes. Location updates of a mobile terminal are written to a shared-memory Forwarder Information Base (FIB) at a network forwarder. An application server sends "app updates" to the mobile terminal via the forwarder. Arriving app updates at forwarder are addressed (by reading the FIB) and forwarded to the mobile terminal. If a FIB read returns an outdated address, the misaddressed app update is lost in transit. We redesign these reader and writer processes using preemption mechanisms that improve the timeliness of updates. We present a Stochastic Hybrid System (SHS) framework to analyze location and app update age processes and show how these two age processes are coupled through synchronization primitives. Our analysis shows that using a lock-based primitive (RWL) can serve fresher app updates to the mobile terminal at higher location update rates while lock-less (RCU) mechanism favors timely delivery of app updates at lower location update rates.

We consider a system where the updates from independent sources are disseminated via a publish-subscribe mechanism. The sources are the publishers and a decision process (DP), acting as a subscriber, derives decision updates from the source data. We derive the stationary expected age of information (AoI) of decision updates delivered to a monitor. We show that a lazy computation policy in which the DP may sit idle before computing its next decision update can reduce the average AoI at the monitor even though the DP exerts no control over the generation of source updates. This AoI reduction is shown to occur because lazy computation can offset the negative effect of high variance in the computation time.