Related papers: Model2Kernel: Model-Aware Symbolic Execution For S…

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions…

Recent studies have demonstrated the potential of Large Language Models (LLMs) in generating GPU Kernels. Current benchmarks focus on the translation of high-level languages into CUDA, overlooking the more general and challenging task of…

Large language model (LLM) agents increasingly rely on external memory systems to remain consistent across long-horizon interactions, but little empirical work has been done to understand the specific failure modes and design choices that…

Large Language Models (LLMs) for code have gained significant attention recently. They can generate code in different programming languages based on provided prompts, fulfilling a long-lasting dream in Software Engineering (SE), i.e.,…

GPUs have gained significant popularity over the past decade, extending beyond their original role in graphics rendering. This evolution has brought GPU security and reliability to the forefront of concerns. Prior research has shown that…

Large Language Models (LLMs) exhibit pronounced memory-bound characteristics during inference due to High Bandwidth Memory (HBM) bandwidth constraints. In this paper, we propose an L2 Cache-oriented asynchronous KV Cache prefetching method…

The memory consistency model is a fundamental system property characterizing a multiprocessor. The relative merits of strict versus relaxed memory models have been widely debated in terms of their impact on performance, hardware complexity…

Mapping parallel threads onto non-box-shaped domains is a known challenge in GPU computing; efficient mapping prevents performance penalties from unnecessary resource allocation. Currently, achieving this requires significant analytical…

On-device inference for Large Language Models (LLMs), driven by increasing privacy concerns and advancements of mobile-sized models, has gained significant interest. However, even mobile-sized LLMs (e.g., Gemma-2B) encounter unacceptably…

Large Multimodal Models (LMMs) have witnessed remarkable growth, showcasing formidable capabilities in handling intricate multimodal tasks with exceptional performance. Recent research has underscored the inclination of large language…

Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to…

Traditional machine learning techniques are prone to generating inaccurate predictions when confronted with shifts in the distribution of data between the training and testing phases. This vulnerability can lead to severe consequences,…

We propose an axiomatic generic framework for modelling weak memory. We show how to instantiate this framework for SC, TSO, C++ restricted to release-acquire atomics, and Power. For Power, we compare our model to a preceding operational…

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…

Malicious software, or malware, presents a continuously evolving challenge in computer security. These embedded snippets of code in the form of malicious files or hidden within legitimate files cause a major risk to systems with their…

Large language models (LLMs) are becoming increasingly capable at small parameter scales. At the same time, conventional cloud-centric deployment introduces challenges around data privacy, latency, and cost that are acute in operational…

Although LLMs have shown promising potential in vulnerability detection, this study reveals their limitations in distinguishing between vulnerable and similar-but-benign patched code (only 0.06 - 0.14 accuracy). It shows that LLMs struggle…

With the expansion of the software scale and complexity of smart grid systems, the detection of smart grid software defects has become a research hotspot. Because of the large scale of the existing smart grid software code, the efficiency…

Large language models (LLMs) have grown beyond the memory capacity of single GPU devices, necessitating quantization techniques for practical deployment. While NF4 (4-bit NormalFloat) quantization enables 4$\times$ memory reduction,…

We propose a symbolic execution method for analyzing the safety of software under fault attacks both accurately and efficiently. Fault attacks leverage physically injected hardware faults in an embedded system to break the safety of a…