Related papers: Exploration of Systolic-Vector Architecture with R…
Cloud computing has been regarded as a successful paradigm for IT industry by providing benefits for both service providers and customers. In spite of the advantages, cloud computing also suffers from distinct challenges, and one of them is…
Deep Neural Networks (DNNs) are increasingly deployed across diverse industries, driving demand for mobile device support. However, existing mobile inference frameworks often rely on a single processor per model, limiting hardware…
Energy conservation of large data centers for high-performance computing workloads, such as deep learning with big data, is of critical significance, where cutting down a few percent of electricity translates into million-dollar savings.…
In this paper, to analyze end-to-end timing behavior in heterogeneous processor and network environments accurately, we adopt a heterogeneous selection value on communication contention (HSV_CC) algorithm, which can synchronize tasks and…
As deep neural networks develop significantly more diverse and complex, achieving high performance and efficiency on complicated DNN models faces pressing challenges. Modern DNN workloads are increasingly diverse in operation types, tensor…
Cloud computing has been emerged in the last decade to enable utility-based computing resource management without purchasing hardware equipment. Cloud providers run multiple data centers in various locations to manage and provision the…
As deep neural networks (DNNs) are being applied to a wide range of edge intelligent applications, it is critical for edge inference platforms to have both high-throughput and low-latency at the same time. Such edge platforms with multiple…
Recently, Deep Convolutional Neural Network (DCNN) has achieved tremendous success in many machine learning applications. Nevertheless, the deep structure has brought significant increases in computation complexity. Largescale deep learning…
Modern cloud platforms increasingly host large-scale deep learning (DL) workloads, demanding high-throughput, low-latency GPU scheduling. However, the growing heterogeneity of GPU clusters and limited visibility into application…
We propose a novel job scheduling approach for homogeneous cluster computing platforms. Its key feature is the use of virtual machine technology to share fractional node resources in a precise and controlled manner. Other VM-based…
This paper presents Block, a distributed scheduling framework designed to optimize load balancing and auto-provisioning across instances in large language model serving frameworks by leveraging contextual information from incoming requests.…
Cloud-based Deep Neural Network (DNN) applications that make latency-sensitive inference are becoming an indispensable part of Industry 4.0. Due to the multi-tenancy and resource heterogeneity, both inherent to the cloud computing…
Scheduling deep learning (DL) models to train on powerful clusters with accelerators like GPUs and TPUs, presently falls short, either lacking fine-grained heterogeneity awareness or leaving resources substantially under-utilized. To fill…
Recent years have witnessed increasing interest in machine learning inferences on serverless computing for its auto-scaling and cost effective properties. Existing serverless computing, however, lacks effective job scheduling methods to…
The rapid development of deep neural networks (DNNs) is inherently accompanied by the problem of high computational costs. To tackle this challenge, dynamic voltage frequency scaling (DVFS) is emerging as a promising technology for…
Deep Neural Networks (DNNs) have revolutionized numerous applications, but the demand for ever more performance remains unabated. Scaling DNN computations to larger clusters is generally done by distributing tasks in batch mode using…
Machine learning inference is increasingly being executed locally on mobile and embedded platforms, due to the clear advantages in latency, privacy and connectivity. In this paper, we present approaches for online resource management in…
Modern Deep Neural Networks (DNNs) exhibit profound efficiency and accuracy properties. This has introduced application workloads that comprise of multiple DNN applications, raising new challenges regarding workload distribution. Equipped…
Data-intensive scientific workflows increasingly rely on high-performance computing (HPC) systems, complementing traditional Grid and Cloud platforms. However, workflow scheduling on HPC infrastructures remains challenging due to the…
In this article, we investigate the impact of architectural parameters of array-based DNN accelerators on accelerator's energy consumption and performance in a wide variety of network topologies. For this purpose, we have developed a tool…