Related papers: DPDPU: Data Processing with DPUs
Memory disaggregation addresses memory imbalance in a cluster by decoupling CPU and memory allocations of applications while also increasing the effective memory capacity for (memory-intensive) applications beyond the local memory limit…
Heterogeneous computing is one of the most important computational solutions to meet rapidly increasing demands on system performance. It typically allows the main flow of applications to be executed on a CPU while the most computationally…
Cloud Computing holds the potential to eliminate the requirements for setting up of high-cost computing infrastructure for IT-based solutions and services that the industry uses. It promises to provide a flexible IT architecture, accessible…
This paper consists of three parts. The first part provides a unified programming model for heterogeneous computing with CPU and accelerator (like GPU, FPGA, Google TPU, Atos QPU, and more) technologies. To some extent, this new programming…
Embedded Systems combine one or more processor cores with dedicated logic running on an ASIC or FPGA to meet design goals at reasonable cost. It is achieved by profiling the application with variety of aspects like performance, memory…
To satisfy the compute and memory demands of deep neural networks, neural processing units (NPUs) are widely being utilized for accelerating deep learning algorithms. Similar to how GPUs have evolved from a slave device into a mainstream…
Many important computational problems require utilization of high performance computing (HPC) systems that consist of multi-level structures combining higher and higher numbers of devices with various characteristics. Utilizing full power…
The increasing prevalence and growing size of data in modern applications have led to high costs for computation in traditional processor-centric computing systems. Moving large volumes of data between memory devices (e.g., DRAM) and…
Large language model (LLM) inference performance is increasingly bottlenecked by the memory wall. While GPUs continue to scale raw compute throughput, they struggle to deliver scalable performance for memory bandwidth bound workloads. This…
This lecture aims at providing a user's perspective on the main concepts used nowadays for the implementation of numerical algorithm on common computing architecture. In particular, the concepts and applications of Central Processing Units…
The heterogeneous edge-cloud computing paradigm can provide a more optimal direction to deploy scientific workflows than traditional distributed computing or cloud computing environments. Due to the different sizes of scientific datasets…
The cost of moving data between the memory units and the compute units is a major contributor to the execution time and energy consumption of modern workloads in computing systems. At the same time, we are witnessing an enormous amount of…
Cutting-edge embedded system applications, such as self-driving cars and unmanned drone software, are reliant on integrated CPU/GPU platforms for their DNNs-driven workload, such as perception and other highly parallel components. In this…
Due to the emergence of embedded applications in image and video processing, communication and cryptography, improvement of pictorial information for better human perception like deblurring, denoising in several fields such as satellite…
Data is a precious resource in today's society, and is generated at an unprecedented and constantly growing pace. The need to store, analyze, and make data promptly available to a multitude of users introduces formidable challenges in…
Recently, cloud systems composed of heterogeneous hardware have been increased to utilize progressed hardware power. However, to program applications for heterogeneous hardware to achieve high performance needs much technical skill and is…
Product Data Management (PDM) claims of producing desktop and web based systems to maintain the organizational data to increase the quality of products by improving the process of development, business process flows, change management,…
With the growing number of data-intensive workloads, GPU, which is the state-of-the-art single-instruction-multiple-thread (SIMT) processor, is hindered by the memory bandwidth wall. To alleviate this bottleneck, previously proposed…
Digital MemComputing machines (DMMs), which employ nonlinear dynamical systems with memory (time non-locality), have proven to be a robust and scalable unconventional computing approach for solving a wide variety of combinatorial…
We present a distributed framework of the Primal-Dual Hybrid Gradient (PDHG) algorithm for solving massive-scale linear programming (LP) problems. Although PDHG-based solvers demonstrate strong performance on single-node GPU architectures,…