Related papers: Light-weight Locks
The computational and memory challenges of large language models (LLMs) have sparked several optimization approaches towards their efficient implementation. While prior LLM-targeted quantization, and prior works on sparse acceleration have…
Modern databases use dynamic search structures that store an enormous amount of data, and often serve them using multi-threaded algorithms to support the ever-increasing throughput needs. When this throughput need exceeds the capacity of…
Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for defending against jailbreak attacks are primarily based on auxiliary models. These strategies, however, often require extensive data collection or…
As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms designed to filter malicious queries while being easy to implement and update. In this…
Large language models (LLMs) have shown impressive capabilities across various tasks. However, training LLMs from scratch requires significant computational power and extensive memory capacity. Recent studies have explored low-rank…
Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm…
We present LOCUS (LOw-cost Customization for Universal Specialization), a pipeline that consumes few-shot data to streamline the construction and training of NLP models through targeted retrieval, synthetic data generation, and…
Development, deployment and maintenance of networked software has been revolutionized by DevOps, which have become essential to boost system software quality and to enable agile evolution. Meanwhile the Internet of Things (IoT) connects…
Choosing the best memory layout for each hardware architecture is increasingly important as more and more programs become memory bound. For portable codes that run across heterogeneous hardware architectures, the choice of the memory layout…
B$^+$-trees are prevalent in traditional database systems due to their versatility and balanced structure. While binary search is typically utilized for branch operations, it may lead to inefficient cache utilization in main-memory…
There has been a significant amount of work in the literature proposing semantic relaxation of concurrent data structures for improving scalability and performance. By relaxing the semantics of a data structure, a bigger design space, that…
We present a novel characterization of how a program stresses cache. This characterization permits fast performance prediction in order to simulate and assist task scheduling on heterogeneous clusters. It is based on the estimation of stack…
In the field of cryptography till date the 1-byte in 1-clock is the best known RC4 hardware design [1], while the 1-byte in 3clocks is the best known implementation [2,3]. The design algorithm in [1] considers two consecutive bytes together…
Flash-based disk caches, for example Bcache and Flashcache, has gained tremendous popularity in industry in the last decade because of its low energy consumption, non-volatile nature and high I/O speed. But these cache systems have a worse…
A history-independent data structure does not reveal the history of operations applied to it, only its current logical state, even if its internal state is examined. This paper studies history-independent concurrent dictionaries, in…
Consistent hashing is fundamental to distributed systems, but ring-based schemes can exhibit high peak-to-average load ratios unless they use many virtual nodes, while multi-probe methods improve balance at the cost of scattered memory…
Intel SGX is known to be vulnerable to a class of practical attacks exploiting memory access pattern side-channels, notably page-fault attacks and cache timing attacks. A promising hardening scheme is to wrap applications in hardware…
Next-generation wireless technologies (for immersive-massive communication, joint communication and sensing) demand highly parallel architectures for massive data processing. A common architectural template scales up by grouping tens to…
In today's digital age, the ease of data collection, transfer, and storage continue to shape modern society and the ways we interact with our world. The advantages are numerous, but there is also an increased risk of information…
Data compression is a well-studied (and well-solved) problem in the setup of long coding blocks. But important emerging applications need to compress data to memory words of small fixed widths. This new setup is the subject of this paper.…