Related papers: Effective Cache Apportioning for Performance Isola…
Data-intensive applications often require exploratory analysis of large datasets. If analysis is performed on distributed resources, data locality can be crucial to high throughput and performance. We propose a "data diffusion" approach…
Computation-Enabled Object Storage (COS) systems, such as MinIO and Ceph, have recently emerged as promising storage solutions for post hoc, SQL-based analysis on large-scale datasets in High-Performance Computing (HPC) environments. By…
By offloading intensive computation tasks to the edge cloud located at the cellular base stations, mobile-edge computation offloading (MECO) has been regarded as a promising means to accomplish the ambitious millisecond-scale end-to-end…
Compound AI systems (CASs) that employ LLMs as agents to accomplish knowledge-intensive tasks via interactions with tools and data retrievers have garnered significant interest within database and AI communities. While these systems have…
Two key synchronization paradigms for the construction of scalable concurrent data-structures are software combining and elimination. Elimination-based concurrent data-structures allow operations with reverse semantics (such as push and pop…
Large Language Models (LLMs) such as GPT-4 and Llama have shown remarkable capabilities in a variety of software engineering tasks. Despite the advancements, their practical deployment faces challenges, including high financial costs, long…
This dissertation develops hardware that automatically reduces the effective latency of accessing memory in both single-core and multi-core systems. To accomplish this, the dissertation shows that all last level cache misses can be…
Test-time scaling has become a standard way to improve performance and boost reliability of neural network models. However, its behavior on agentic, multi-step tasks remains less well-understood: small per-step errors can compound over long…
The latest trends in high-performance computing systems show an increasing demand on the use of a large scale multicore systems in a efficient way, so that high compute-intensive applications can be executed reasonably well. However, the…
Cloud computing enables the dynamic provisioning of server resources. To exploit this opportunity, a policy is needed for dynamically allocating (and deallocating) servers in response to the current load conditions. In this paper we…
The performance and behavior of large-scale distributed applications is highly influenced by network properties such as latency, bandwidth, packet loss, and jitter. For instance, an engineer might need to answer questions such as: What is…
Deploying data- and computation-intensive applications such as large-scale AI into heterogeneous dispersed computing networks can significantly enhance application performance by mitigating bottlenecks caused by limited network resources,…
We study general techniques for implementing distributed data structures on top of future many-core architectures with non cache-coherent or partially cache-coherent memory. With the goal of contributing towards what might become, in the…
In this paper, we consider the coded-caching broadcast network with user cooperation, where a server connects with multiple users and the users can cooperate with each other through a cooperation network. We propose a centralized coded…
Performance isolation is a keystone for SLO guarantees with shared resources in cloud and datacenter environments. To meet SLO requirements, the state of the art relies on hardware QoS support (e.g., Intel RDT) to allocate shared resources…
We propose a novel strategy for energy-efficient dynamic computation offloading, in the context of edge-computing-aided beyond 5G networks. The goal is to minimize the energy consumption of the overall system, comprising multiple User…
KV Cache is commonly used to accelerate LLM inference with long contexts, yet its high memory demand drives the need for cache compression. Existing compression methods, however, are largely heuristic and lack dynamic budget allocation. To…
We make three observations in modern processors: (1) LLC capacity is getting larger (up to 1GB); (2) core counts are increasing (up to 128 cores), accumulating a more significant amount of private L2 cache capacity on the chip; and (3)…
We present a new unified framework for minimizing congestion-dependent network cost in information-centric networks by jointly optimizing forwarding and caching strategies. As caching variables are integer-constrained, the resulting…
Recent advances in Large Language Models (LLMs) have revolutionized web applications, enabling intelligent search, recommendation, and assistant services with natural language interfaces. Tool-calling extends LLMs with the ability to…