Related papers: LINTS^RT: A Learning-driven Testbed for Intelligen…
We present LTLS, a technique for multiclass and multilabel prediction that can perform training and inference in logarithmic time and space. LTLS embeds large classification problems into simple structured prediction problems and relies on…
Deep learning (DL) frameworks take advantage of GPUs to improve the speed of DL inference and training. Ideally, DL frameworks should be able to fully utilize the computation power of GPUs such that the running time depends on the amount of…
To improve the utility of learning applications and render machine learning solutions feasible for complex applications, a substantial amount of heavy computations is needed. Thus, it is essential to delegate the computations among several…
Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demands low latency for LLM inference. Existing LLM serving systems use…
We introduce a new approach to take into account the memory architecture and the memory mapping in the High- Level Synthesis of Real-Time embedded systems. We formalize the memory mapping as a set of constraints used in the scheduling step.…
As the Moore's scaling era comes to an end, application specific hardware accelerators appear as an attractive way to improve the performance and power efficiency of our computing systems. A massively heterogeneous system with a large…
Modern deployments of Large Language Models (LLMs) increasingly require serving multiple models with diverse architectures, sizes, and specialization on shared, heterogeneous hardware. This setting introduces new challenges for resource…
While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches…
Personal development through self-directed learning is essential in today's fast-changing world, but many learners struggle to manage it effectively. While AI tools like large language models (LLMs) have the potential for personalized…
Recent advances in modern containerized execution environments have resulted in substantial benefits in terms of elasticity and more efficient utilization of computing resources. Although existing schedulers strive to optimize performance…
Cyber-physical systems, such as mobile robots, must respond adaptively to dynamic operating conditions. Effective operation of these systems requires that sensing and actuation tasks are performed in a timely manner. Additionally, execution…
Energy consumption is one of the most critical concerns in designing computing devices, ranging from portable embedded systems to computer cluster systems. Furthermore, in the past decade, cluster systems have increasingly risen as popular…
The increasing proliferation of IoT devices and AI applications has created a demand for scalable and efficient computing solutions, particularly for applications requiring real-time processing. The compute continuum integrates edge and…
In this paper, we present RT-Gang: a novel real-time gang scheduling framework that enforces a one-gang-at-a-time policy. We find that, in a multicore platform, co-scheduling multiple parallel real-time tasks would require highly…
This paper introduces a novel reinforcement learning (RL) approach to scheduling mixed-criticality (MC) systems on processors with varying speeds. Building upon the foundation laid by [1], we extend their work to address the non-preemptive…
Optimizing the quality of result (QoR) and the quality of service (QoS) of AI-empowered autonomous systems simultaneously is very challenging. First, there are multiple input sources, e.g., multi-modal data from different sensors, requiring…
With growing deployment of Internet of Things (IoT) and machine learning (ML) applications, which need to leverage computation on edge and cloud resources, it is important to develop algorithms and tools to place these distributed…
Space missions are characterized by long distances, difficult or unavailable communication and high operating costs. Moreover, complexity has been constantly increasing in recent years. For this reason, improving the autonomy of space…
In Real-time system, utilization based schedulability test is a common approach to determine whether or not tasks can be admitted without violating deadline requirements. The exact problem has previously been proven intractable even upon…
The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where…