相关论文: Dynamic Warp Resizing in High-Performance SIMT

Scheduling is the central concept used frequently in Operating System. It helps in choosing the processes for execution. Round Robin (RR) is one of the most widely used CPU scheduling algorithm. But, its performance degrades with respect to…

Variance reduction (VR) methods boost the performance of stochastic gradient descent (SGD) by enabling the use of larger, constant stepsizes and preserving linear convergence rates. However, current variance reduced SGD methods require…

This paper presents a dynamic network rewiring (DNR) method to generate pruned deep neural network (DNN) models that are robust against adversarial attacks yet maintain high accuracy on clean images. In particular, the disclosed DNR method…

Deep neural networks (DNNs) are frequently employed in a variety of computer vision applications. Nowadays, an emerging trend in the current video distribution system is to take advantage of DNN's overfitting properties to perform video…

CPU scheduling is one of the most crucial operations performed by operating system. Different algorithms are available for CPU scheduling amongst them RR (Round Robin) is considered as optimal in time shared environment. The effectiveness…

We investigate usage of dynamic time warping (DTW) algorithm for aligning raw signal data from MinION sequencer. DTW is mostly using for fast alignment for selective sequencing to quickly determine whether a read comes from sequence of…

Convolution is the most time-consuming operation in deep neural network operations, so its performance is critical to the overall performance of the neural network. The commonly used methods for convolution on GPU include the general matrix…

In the context of mapping high-level algorithms to hardware, we consider the basic problem of generating an efficient hardware implementation of a single threaded program, in particular, that of an inner loop. We describe a control-flow…

Read disturbance in modern DRAM chips is a widespread phenomenon and is reliably used for breaking memory isolation, a fundamental building block for building robust systems. RowHammer and RowPress are two examples of read disturbance in…

Asynchronous parallel optimization algorithms for solving large-scale machine learning problems have drawn significant attention from academia to industry recently. This paper proposes a novel algorithm, decoupled asynchronous proximal…

Stochastic optimization plays a crucial role in the advancement of deep learning technologies. Over the decades, significant effort has been dedicated to improving the training efficiency and robustness of deep neural networks, via various…

Deep neural networks are often overparameterized and may not easily achieve model generalization. Adversarial training has shown effectiveness in improving generalization by regularizing the change of loss on top of adversarially chosen…

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…

One of the primary sources of unpredictability in modern multi-core embedded systems is contention over shared memory resources, such as caches, interconnects, and DRAM. Despite significant achievements in the design and analysis of…

Digital twins (DTs) are envisioned as a key enabler of the cyber-physical continuum in future wireless networks. However, efficient deployment and synchronization of DTs in dynamic multi-access edge computing (MEC) environments remains…

Adaptive systems based on field programmable gate array (FPGA) architectures can greatly benefi t fro m th e high degree of flexibility offered by dynamic partial reconfiguration (DPR). By using this technique, hardware tasks can be loaded…

The dynamic time warping (DTW) is a widely-used method that allows us to efficiently compare two time series that can vary in speed. Given two strings $A$ and $B$ of respective lengths $m$ and $n$, there is a fundamental dynamic programming…

Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning. The state-of-the-art sparsity-aware deep learning solutions are restricted to pre-defined, static sparsity patterns due…

Dynamic network reconfiguration is described as the process of replacing one routing function with another while the network keeps running. The main challenge is avoiding deadlock anomalies while keeping limitations on message injection and…

Motivated by extreme multi-label classification applications, we consider training deep learning models over sparse data in multi-GPU servers. The variance in the number of non-zero features across training batches and the intrinsic GPU…