Related papers: Low-Precision Hardware Architectures Meet Recommen…
Printed electronics (PE) promises on-demand fabrication, low non-recurring engineering costs, and sub-cent fabrication costs. It also allows for high customization that would be infeasible in silicon, and bespoke architectures prevail to…
The expanding scale of large neural network models introduces significant challenges, driving efforts to reduce memory usage and enhance computational efficiency. Such measures are crucial to ensure the practical implementation and…
Personalized recommendation systems leverage deep learning models and account for the majority of data center AI cycles. Their performance is dominated by memory-bound sparse embedding operations with unique irregular memory access patterns…
Quality inspection has become crucial in any large-scale manufacturing industry recently. In order to reduce human error, it has become imperative to use efficient and low computational AI algorithms to identify such defective products. In…
Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational…
We describe a universal modeling approach for predicting single- and multicore runtime of steady-state loops on server processors. To this end we strictly differentiate between application and machine models: An application model comprises…
Executing machine learning workloads locally on resource constrained microcontrollers (MCUs) promises to drastically expand the application space of IoT. However, so-called TinyML presents severe technical challenges, as deep neural network…
Printed electronics have gained significant traction in recent years, presenting a viable path to integrating computing into everyday items, from disposable products to low-cost healthcare. However, the adoption of computing in these…
Deep Neural Networks (DNNs) have achieved great success in a variety of machine learning (ML) applications, delivering high-quality inferencing solutions in computer vision, natural language processing, and virtual reality, etc. However,…
Deep learning (DL) has been widely adopted those last years but they are computing-intensive method. Therefore, scientists proposed diverse optimization to accelerate their predictions for end-user applications. However, no single inference…
The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like quantization and distillation have further expanded PTM…
In modern GPU inference, cache efficiency remains a major bottleneck, and heuristic policies such as \textsc{LRU} can perform far worse than the offline optimum. Existing learning-based caching systems improve hit rates mainly through…
Modern computational advertising platforms typically rely on recommendation systems to predict user responses, such as click-through rates, conversion rates, and other optimization events. To support a wide variety of product surfaces and…
The increasing demand of dedicated accelerators to improve energy efficiency and performance has highlighted FPGAs as a promising option to deliver both. However, programming FPGAs in hardware description languages requires long time and…
Recommender systems are a subset of information filtering systems designed to predict and suggest items that users may find interesting or relevant based on their preferences, behaviors, or interactions. By analyzing user data such as past…
Training machine learning (ML) algorithms is a computationally intensive process, which is frequently memory-bound due to repeatedly accessing large training datasets. As a result, processor-centric systems (e.g., CPU, GPU) suffer from…
Performance models are instrumental for optimizing performance-sensitive code. When modeling the use of functional units of out-of-order x86-64 CPUs, data availability varies by the manufacturer: Instruction-to-port mappings for Intel's…
Industrial systems increasingly depend on Machine Learning (ML), and operate on heterogeneous nodes that must satisfy tight latency, energy, and memory constraints. Dynamic ML models, which reconfigure their computational footprint at…
As we rapidly approach the frontiers of ultra large computing resources, software optimization is becoming of paramount interest to scientific application developers interested in efficiently leveraging all available on-Node computing…
This work elaborates on a High performance computing (HPC) architecture based on Simple Linux Utility for Resource Management (SLURM) [1] for deploying heterogeneous Large Language Models (LLMs) into a scalable inference engine. Dynamic…