Related papers: Context-aware Failure-oblivious Computing as a Mea…

Computer systems are designed to make resources available to users and users may be interested in some resources more than others, therefore, a coordination scheme is required to satisfy the users' requirements. This scheme may implement…

Computation in-memory is a promising non-von Neumann approach aiming at completely diminishing the data transfer to and from the memory subsystem. Although a lot of architectures have been proposed, compiler support for such architectures…

Recent rapid strides in memory safety tools and hardware have improved software quality and security. While coarse-grained memory safety has improved, achieving memory safety at the granularity of individual objects remains a challenge due…

Despite the deployment of preventive security mechanisms to protect the assets and computing platforms of users, intrusions eventually occur. We propose a novel intrusion survivability approach to withstand ongoing intrusions. Our approach…

Closed queuing networks with finite capacity buffers and skip-over policies are fundamental models in the performance evaluation of computer and communication systems. This technical report presents the details of computational algorithms…

The implementation of digital filters in processors based on fixed-point arithmetic can lead to problems related to the finite word-length. In particular, the processing of signals in such filters can produce overflows and unwanted noise…

Large language models (LLMs) can suggest missing elements from items listed in a prompt, which can be used for list completion or recommendations based on users' history. However, their performance degrades when presented with too many…

Debugging is an unavoidable and most crucial aspect of software development life cycle. Especially when it comes the turn of embedded one. Due to the requirements of low code size and less resource consumption, the embedded softwares need…

Large language models have been widely adopted across different tasks, but their auto-regressive generation nature often leads to inefficient resource utilization during inference. While batching is commonly used to increase throughput,…

The vast number of interleavings that a concurrent program can have is typically identified as the root cause of the difficulty of automatic analysis of concurrent software. Weak memory is generally believed to make this problem even…

CXL shared memory and persistent memory allow the contents of memory to persist beyond crashes. Stores to persistent or CXL memory are typically not immediately made persistent; developers must manually flush the corresponding cache lines…

Human error research on overconfidence supports the benefits of early visibility of defects and disciplined development. If risk to the enterprise is to be reduced, individuals need to become aware of the reality of the quality of their…

We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs). Specifically, we propose meta-buffer to store a series of…

Message passing programs commonly use buffers to avoid unnecessary synchronizations and to improve performance by overlapping communication with computation. Unfortunately, using buffers makes the program no longer portable, potentially…

We present DataFlow, a computational framework for building, testing, and deploying high-performance machine learning systems on unbounded time-series data. Traditional data science workflows assume finite datasets and require substantial…

In runtime verification, the central problem is to decide if a given program execution violates a given property. In online runtime verification, a monitor observes a program's execution as it happens. If the program being observed has hard…

In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of…

Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading…

A non-invasive, cloud-agnostic approach is demonstrated for extending existing cloud platforms to include checkpoint-restart capability. Most cloud platforms currently rely on each application to provide its own fault tolerance. A uniform…

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…