Related papers: CRAC: Checkpoint-Restart Architecture for CUDA wit…
Deep neural network (DNN) training continues to scale rapidly in terms of model size, data volume, and sequence length, to the point where multiple machines are required to fit large models for training. Different distributed and parallel…
The memory capacity in edge devices is often limited due to constraints on cost, size, and power. Consequently, memory competition leads to inevitable page swapping in memory-constrained mixed-criticality edge devices, causing slow storage…
Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent UDA methods based on Vision Transformers (ViTs) have achieved strong performance through attention-based…
To be able to run tasks asynchronously on NVIDIA GPUs a programmer must explicitly implement asynchronous execution in their code using the syntax of CUDA streams. Streams allow a programmer to launch independent concurrent execution tasks,…
Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test…
Recently, code reuse attacks (CRAs), such as return-oriented programming (ROP) and jump-oriented programming (JOP), have emerged as a new class of ingenious security threatens. Attackers can utilize CRAs to hijack the control flow of…
The wide adoption of IoT gadgets and Cyber-Physical Systems (CPS) makes embedded devices increasingly important. While some of these devices perform mission-critical tasks, they are usually implemented using Micro-Controller Units (MCUs)…
Deep Neural Networks (DNNs) have been widely deployed for many Machine Learning applications. Recently, CapsuleNets have overtaken traditional DNNs, because of their improved generalization ability due to the multi-dimensional capsules, in…
The growing complexity and scale of visual model pre-training have made developing and deploying multi-task computer-aided diagnosis (CAD) systems increasingly challenging and resource-intensive. Furthermore, the medical imaging community…
Solid-State Drives (SSDs) have significant performance advantages over traditional Hard Disk Drives (HDDs) such as lower latency and higher throughput. Significantly higher price per capacity and limited lifetime, however, prevents…
TCP/IP network stack is irreplaceable for Web services in datacenter front-end servers, and the demand for which is growing rapidly for emerging high concurrency network service applications (including Internet, Internet of Things, mobile…
Winograd convolution is originally proposed to reduce the computing overhead by converting multiplication in neural network (NN) with addition via linear transformation. Other than the computing efficiency, we observe its great potential in…
Recently, contention resolution diversity slotted ALOHA (CRDSA) has been introduced as a simple but effective improvement to slotted ALOHA. It relies on MAC burst repetitions and on interference cancellation to increase the normalized…
This paper investigates hardware-based memory compression designs to increase the memory bandwidth. When lines are compressible, the hardware can store multiple lines in a single memory location, and retrieve all these lines in a single…
The present von Neumann computing paradigm involves a significant amount of information transfer between a central processing unit (CPU) and memory, with concomitant limitations in the actual execution speed. However, it has been recently…
Continual learning (CL) has remained a significant challenge for deep neural networks as learning new tasks erases previously acquired knowledge, either partially or completely. Existing solutions often rely on experience rehearsal or full…
A popular run-time attack technique is to compromise the control-flow integrity of a program by modifying function return addresses on the stack. So far, shadow stacks have proven to be essential for comprehensively preventing return…
3D perception in point clouds is transforming the perception ability of future intelligent machines. Point cloud algorithms, however, are plagued by irregular memory accesses, leading to massive inefficiencies in the memory sub-system,…
Network failure diagnosis is challenging yet critical for high-performance computing (HPC) systems. Existing methods cannot be directly applied to HPC scenarios due to data heterogeneity and lack of accuracy. This paper proposes a novel…
As AI-based applications become pervasive, CPU vendors are starting to incorporate matrix engines within the datapath to boost efficiency. Systolic arrays have been the premier architectural choice as matrix engines in offload accelerators.…