Related papers: Effectively Prefetching Remote Memory with Leap
Coalescing RDMA and Persistent Memory (PM) delivers high end-to-end performance for networked storage systems, which requires rethinking the design of efficient hash structures. In general, existing hashing schemes separately optimize RDMA…
Modern hardware systems are heavily underutilized when running large-scale graph applications. While many in-memory graph frameworks have made substantial progress in optimizing these applications, we show that it is still possible to…
Efficiently serving embedding-based recommendation (EMR) models remains a significant challenge due to their increasingly large memory requirements. Today's practice splits the model across many monolithic servers, where a mix of GPUs,…
Host-GPU data movement has become a latency-critical bottleneck in LLM serving, surfacing in common paths such as model-weight movement and KV cache offload/fetch. Today, each host-GPU copy is effectively confined to the PCIe path of the…
This paper evaluates the impact of using disaggregated servers in the near-edge of telecom networks (metro central offices, radio cell sites and enterprise branch office which form part of a Fog as a Service system) to minimize the number…
Flexibility at hardware level is the main driving force behind adaptive systems whose aim is to realise microarhitecture deconfiguration 'online'. This feature allows the software/hardware stack to tolerate drastic changes of the workload…
Retrieval-augmented generation (RAG) improves the service quality of large language models by retrieving relevant documents from credible literature and integrating them into the context of the user query. Recently, the rise of the cloud…
The promising applications of large language models are often limited by the constrained GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help address this issue by activating only a subset of the model's…
Storage disaggregation underlies today's cloud and is naturally complemented by pushing down some computation to storage, thus mitigating the potential network bottleneck between the storage and compute tiers. We show how ML training…
Tiered memory architectures have gained significant traction in the database community in recent years. In these architectures, the on-chip DRAM of the host processor is typically referred to as local memory, and forms the primary tier.…
Elastic computing enables dynamic scaling to meet workload demands, and Remote Direct Memory Access (RDMA) enhances this by providing high-throughput, low-latency network communication. However, integrating RDMA into elastic computing…
Page placement is a critical problem for memoryintensive applications running on a shared-memory multiprocessor with a non-uniform memory access (NUMA) architecture. State-of-the-art page placement mechanisms interleave pages evenly across…
A heterogeneous memory has a single address space with fast access to some addresses (a fast tier of DRAM) and slow access to other addresses (a capacity tier of CXL-attached memory or NVM). A tiered memory system aims to maximize the…
The integration of mobile edge computing (MEC) and wireless power transfer (WPT) technologies has recently emerged as an effective solution for extending battery life and increasing the computing power of wireless devices. In this paper, we…
To close the gap between memory and processors, and in turn improve performance, there has been an abundance of work in the area of data/instruction prefetcher designs. Prefetchers are deployed in each level of the memory hierarchy, but…
In this letter, we propose an enhanced Access Reservation Protocol (ARP) with a partial preamble transmission (PPT) mechanism for the narrow band Internet of Things (NB-IoT) systems. The proposed ARP can enhance the ARP performance by…
Main memory database systems aim to provide users with low latency and high throughput access to data. Most data resides in secondary storage, which is limited by the access speed of the technology. For hot content, data resides in DRAM,…
Adjoint algorithmic differentiation by operator and function overloading is based on the interpretation of directed acyclic graphs resulting from evaluations of numerical simulation programs. The size of the computer system memory required…
Remote Memory Access (RMA), also known as single sided communications, provides a way of accessing the memory of other processes without having to issue explicit message passing style communication calls. Previous studies have concluded…
We present a general, flexible modeling abstraction for building and working with distributed optimization problems called a RemoteOptiGraph. This abstraction extends the OptiGraph model in Plasmo$.$jl, where optimization problems are…