相关论文: A Low-Footprint Class Loading Mechanism for Embedd…

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

Machine learning models and libraries can train datasets of different sizes and perform prediction and classification operations, but machine learning models and libraries cause slow and long training times on large datasets. This article…

Non-volatile memory (NVM) is a promising technology for low-energy and high-capacity main memory of computers. The characteristics of NVM devices, however, tend to be fundamentally different from those of DRAM (i.e., the memory device…

Deep learning models generally display catastrophic forgetting when learning new data continuously. Many incremental learning approaches address this problem by reusing data from previous tasks while learning new tasks. However, the direct…

PCM is a popular backing memory for DRAM main memory in tiered memory systems. PCM has asymmetric access energy; writes dominate reads. MLC asymmetry can vary by an order of magnitude. Many schemes have been developed to take advantage of…

Transport phenomena play a key role in a variety of application domains, and efficient simulation of these dynamics remains an outstanding challenge. While quantum computers offer potential for significant speedups, existing algorithms…

A novel parallel patterns library, Groovy Parallel Patterns, is presented which, from the outset, has been designed to exploit more general process parallelism than the usual data and task parallel architectures. The library executes on a…

Multi-vector embedding models have emerged as a powerful paradigm for document retrieval, preserving fine-grained visual and textual details through token-level representations. However, this expressiveness comes at a staggering cost:…

The ever-growing scale of deep neural networks (DNNs) has lead to an equally rapid growth in computational resource requirements. Many recent architectures, most prominently Large Language Models, have to be trained using supercomputers…

In multi-server distributed queueing systems, the access of stochastically arriving jobs to resources is often regulated by a dispatcher, also known as load balancer. A fundamental problem consists in designing a load balancing algorithm…

Modern deep learning-based recommendation systems exploit hundreds to thousands of different categorical features, each with millions of different categories ranging from clicks to posts. To respect the natural diversity within the…

Cloud computing is widely adopted by corporate as well as retail customers to reduce the upfront cost of establishing computing infrastructure. However, switching to the cloud based services poses a multitude of questions, both for…

In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the quality of the reconstruction of the network outputs rather…

The increasing use of Non-Volatile Memory (NVM) in computer architecture has brought about new challenges, one of which is the write endurance problem. Frequent writes to a particular cache cell in NVM can lead to degradation of the memory…

Sequential learning of tasks using gradient descent leads to an unremitting decline in the accuracy of tasks for which training data is no longer available, termed catastrophic forgetting. Generative models have been explored as a means to…

So far, various solutions have been proposed for symmetric distribution of load cloud computing environments. In this article, a new solution to the optimal allocation of virtual machines in the cloud data centers is presented to provide a…

The technologies of heterogeneous multi-core architectures, co-location, and virtualization can be used to reduce server power consumption and improve system utilization, which are three important technologies for data centers. This article…

Current quantum programming is dominated by low-level, circuit-centric approaches that limit the potential for compiler optimization. This work presents how a high-level programming construct provides compilers with the semantic information…

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

In lifelong learning, data are used to improve performance not only on the present task, but also on past and future (unencountered) tasks. While typical transfer learning algorithms can improve performance on future tasks, their…