性能

As the volume of data available from sensor-enabled devices such as vehicles expands, it is increasingly hard for companies to make informed decisions about the cost of capturing, processing, and storing the data from every device. Business…

Scheduling a stream of jobs whose holding cost changes over time is a classic and practical problem. Specifically, each job is associated with a holding cost (penalty), where a job's instantaneous holding cost is some increasing function of…

In recent years, the Internet has been dominated by content-rich platforms, employing recommendation systems to provide users with more appealing content (e.g., videos in YouTube, movies in Netflix). While traditional content…

The increasing use and cost of high performance computing (HPC) requires new easy-to-use tools to enable HPC users and HPC systems engineers to transparently understand the utilization of resources. The MIT Lincoln Laboratory Supercomputing…

In this paper, we use a machine learning approach to predict the stationary distributions of the number of customers in a single-staiton multi server system. We consider two systems, the first is $c$ homogeneous servers, namely the…

Recent advancements in large language models (LLMs) have prompted interest in deploying these models on mobile devices to enable new applications without relying on cloud connectivity. However, the efficiency constraints of deploying LLMs…

In this paper, we address the inherent limitations in traditional assembly line balancing, specifically the assumptions that task times are constant and no defective outputs occur. These assumptions often do not hold in practical scenarios,…

The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop…

The increasing complexity of embedded hardware platforms poses significant challenges for real-time workloads. Architectural features such as Intel RDT, Arm QoS, and Arm MPAM are either unavailable on commercial embedded platforms or…

Performance analysis is critical for GPU programs with data-dependent behavior, but models like Roofline are not very useful for them and interpreting raw performance counters is tedious. In this work, we present an analytical model for…

Magnetic Resonance Image (MRI) pre-processing is a critical step for neuroimaging analysis. However, the computational cost of MRI pre-processing pipelines is a major bottleneck for large cohort studies and some clinical applications. While…

Performance regressions in software systems can lead to significant financial losses and degraded user satisfaction, making their early detection and mitigation critical. Despite the importance of practices that capture performance…

As models become larger, ML accelerators are a scarce resource whose performance must be continually optimized to improve efficiency. Existing performance analysis tools are coarse grained, and fail to capture model performance at the…

The rapid adoption of AI-driven automation in IoT environments, particularly in smart cities and industrial systems, necessitates a standardized approach to quantify AIs computational workload. Existing methodologies lack a consistent…

We introduce preti, a novel framework for predicting software execution time during the early stages of development. preti leverages an LLVM-based simulation environment to extract timing-related runtime information, such as the count of…

Large Language Model (LLM) services such as ChatGPT, DALLE, and Cursor have quickly become essential for society, businesses, and individuals, empowering applications such as chatbots, image generation, and code assistance. The complexity…

People and businesses increasingly rely on public LLM services, such as ChatGPT, DALLE, and Claude. Understanding their outages, and particularly measuring their failure-recovery processes, is becoming a stringent problem. However, only…

Performance modeling, a pivotal domain in program cost analysis, currently relies on manually crafted models constrained by various program and hardware limitations, especially in the intricate landscape of GPGPU. Meanwhile, Large Language…

With the advancement of Large Language Models (LLMs), the importance of accelerators that efficiently process LLM computations has been increasing. This paper discusses the necessity of LLM accelerators and provides a comprehensive analysis…

Implementing Deep Neural Networks (DNNs) on resource-constrained edge devices is a challenging task that requires tailored hardware accelerator architectures and a clear understanding of their performance characteristics when executing the…