Related papers: Workload-Aware DRAM Error Prediction using Machine…

Collocating deep learning training tasks improves GPU utilization but risks resource contention, severe slowdowns, and out-of-memory (OOM) failures. Accurate memory estimation is essential for robust collocation, and GPU utilization…

Data privacy and security have become a non-negligible factor in load forecasting. Previous researches mainly focus on training stage enhancement. However, once the model is trained and deployed, it may need to `forget' (i.e., remove the…

Frequent-pattern mining is a common approach to reveal the valuable hidden trends behind data. However, existing frequent-pattern mining algorithms are designed for DRAM, instead of persistent memories (PMs), which can lead to severe…

In an era of escalating cyber threats, malware poses significant risks to individuals and organizations, potentially leading to data breaches, system failures, and substantial financial losses. This study addresses the urgent need for…

To reduce the resource demand of neural network (NN) inference systems, it has been proposed to use approximate memory, in which the supply voltage and the timing parameters are tuned trading accuracy with energy consumption and…

Background. Effort-aware metrics (EAMs) are widely used to evaluate the effectiveness of software defect prediction models, while accounting for the effort needed to analyze the software modules that are estimated defective. The usual…

In this work, we study a recently proposed direct shaping code for flash memory. This rate-1 code is designed to reduce the wear for SLC (one bit per cell) flash by minimizing the average fraction of programmed cells when storing structured…

In-DRAM Processing-In-Memory (DRAM-PIM) has emerged as a promising approach to accelerate memory-intensive workloads by mitigating data transfer overhead between DRAM and the host processor. Bit-serial DRAM-PIM architectures, further…

Interacting defect systems are ubiquitous in materials under realistic scenarios, yet gaining an atomic-level understanding of these systems from a computational perspective is challenging - it often demands substantial resources due to the…

Most of today's distributed machine learning systems assume {\em reliable networks}: whenever two machines exchange information (e.g., gradients or models), the network should guarantee the delivery of the message. At the same time, recent…

In this paper, we propose an empirical method for evaluating the performance of parallel code. Our method is based on a simple idea that is surprisingly effective in helping to identify causes of poor performance, such as high…

We devise a performance model for GPU training of Deep Learning Recommendation Models (DLRM), whose GPU utilization is low compared to other well-optimized CV and NLP models. We show that both the device active time (the sum of kernel…

Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the…

Quantum Random Access Memory (QRAM) holds the promise of enabling several large scale applications of quantum computers. However, designing fault tolerant QRAMs for large scale applications is still an open problem due to the poor error and…

Existing large language models (LLMs) evaluations use fixed-difficulty benchmarks that cannot adapt as models improve, and rarely isolate specific cognitive processes. We introduce Working Memory Fidelity-Active Manipulation (WMF-AM), a…

Characterizing and predicting the training performance of modern machine learning (ML) workloads on compute systems with compute and communication spread between CPUs, GPUs, and network devices is not only the key to optimization and…

In recent years, graph-processing has become an essential class of workloads with applications in a rapidly growing number of fields. Graph-processing typically uses large input sets, often in multi-gigabyte scale, and data-dependent graph…

Deep neural networks (DNNs) have been shown to tolerate "brain damage": cumulative changes to the network's parameters (e.g., pruning, numerical perturbations) typically result in a graceful degradation of classification accuracy. However,…

Hyperscalars run services across a large fleet of servers, serving billions of users worldwide. These services, however, behave differently than commonly available benchmark suites, resulting in server architectures that are not optimized…

It is needed to ensure the integrity of systems that process sensitive information and control many aspects of everyday life. We examine the use of machine learning algorithms to detect malware using the system calls generated by…