Related papers: Verifying and Optimizing Compact NUMA-Aware Locks …

Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method for adapting large language models (LLMs) to downstream tasks. Meanwhile, Compute-in-Memory (CIM) architectures demonstrate superior energy efficiency due to…

Cryptographic algorithms such as AES-128 and SHA-256 are fundamental to ensuring data security and integrity. Although these algorithms are computationally efficient, their performance is often constrained by the processor-centric…

Logic-in-memory (LIM) describes the execution of logic gates within memristive crossbar structures, promising to improve performance and energy efficiency. Utilizing only binary values, LIM particularly excels in accelerating binary neural…

The rise of disaggregated AI GPUs has exposed a critical bottleneck in large-scale attention workloads: non-uniform memory access (NUMA). As multi-chiplet designs become the norm for scaling compute capabilities, memory latency and…

Compute-Near-Memory (CNM) systems offer a promising approach to mitigate the von Neumann bottleneck by bringing computational units closer to data. However, optimizing for these architectures remains challenging due to their unique hardware…

In 2024, the Linux kernel became its own Common Vulnerabilities and Exposures (CVE) Numbering Authority (CNA), formalizing how kernel vulnerabilities are identified and tracked. We analyze the anatomy and dynamics of kernel CVEs using…

Convolutional Neural Networks (CNNs), one of the most representative algorithms of deep learning, are widely used in various artificial intelligence applications. Convolution operations often take most of the computational overhead of CNNs.…

Resistive crossbars enabling analog In-Memory Computing (IMC) have emerged as a promising architecture for Deep Neural Network (DNN) acceleration, offering high memory bandwidth and in-situ computation. However, the manual,…

Securing neural networks (NNs) against model extraction and parameter exfiltration attacks is an important problem primarily because modern NNs take a lot of time and resources to build and train. We observe that there are no…

Classic test-and-test (TS) mutual exclusion locks are simple, and enjoy high performance and low latency of ownership transfer under light or no contention. However, they do not scale gracefully under high contention and do not provide any…

Compute-in-memory (CIM) has emerged as a pivotal direction for accelerating workloads in the field of machine learning, such as Deep Neural Networks (DNNs). However, the effective exploitation of sparsity in CIM systems presents numerous…

Executing machine learning workloads locally on resource constrained microcontrollers (MCUs) promises to drastically expand the application space of IoT. However, so-called TinyML presents severe technical challenges, as deep neural network…

The growing disparity between CPU core counts and available memory bandwidth has intensified memory contention in servers. This particularly affects highly parallelizable applications, which must achieve efficient cache utilization to…

Nowadays, avoiding system calls during cluster communication (e.g., in Data Centers and High Performance Computing) in modern high-speed interconnection networks has become a necessity, due to the high overhead of multiple data copies…

Open-source software projects are foundational to modern software ecosystems, with the Linux kernel standing out as a critical exemplar due to its ubiquity and complexity. Although security patches are continuously integrated into the Linux…

Computing-in-Memory (CiM) architectures based on emerging non-volatile memory (NVM) devices have demonstrated great potential for deep neural network (DNN) acceleration thanks to their high energy efficiency. However, NVM devices suffer…

Convolutional Neural Networks (CNNs) are widely used in deep learning applications, e.g. visual systems, robotics etc. However, existing software solutions are not efficient. Therefore, many hardware accelerators have been proposed…

We introduce QUICK, a group of novel optimized CUDA kernels for the efficient inference of quantized Large Language Models (LLMs). QUICK addresses the shared memory bank-conflict problem of state-of-the-art mixed precision matrix…

Synchronous Mirroring (SM) is a standard approach to building highly-available and fault-tolerant enterprise storage systems. SM ensures strong data consistency by maintaining multiple exact data replicas and synchronously propagating every…

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…