Related papers: Efficient Page Migration in Hybrid Memory Systems

The complex nature of real-world problems calls for heterogeneity in both machine learning (ML) models and hardware systems. The heterogeneity in ML models comes from multi-sensor perceiving and multi-task learning, i.e., multi-modality…

Heterogeneous computing is the strategy of deploying multiple types of processing elements within a single workflow, and allowing each to perform the tasks to which is best suited. To fully harness the power of heterogeneity, we want to be…

PagedAttention is a popular approach for dynamic memory allocation in LLM serving systems. It enables on-demand allocation of GPU memory to mitigate KV cache fragmentation -- a phenomenon that crippled the batch size (and consequently…

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…

Storing tabular data to balance storage and query efficiency is a long-standing research question in the database community. In this work, we argue and show that a novel DeepMapping abstraction, which relies on the impressive memorization…

This paper summarizes our work on characterizing application memory error vulnerability to optimize datacenter cost via Heterogeneous-Reliability Memory (HRM), which was published in DSN 2014, and examines the work's significance and future…

In this paper, we present a SRAM-PCM hybrid cache design, along with a cache replacement policy, named dead fast block (DFB) to manage the hybrid cache. This design aims to leverage the best features of both SRAM and PCM devices. Compared…

As persistent memory (PM) technologies emerge, hybrid memory architectures combining DRAM with PM bring the potential to provide a tiered, byte-addressable main memory of unprecedented capacity. Nearly a decade after the first proposals for…

In modern systems, DRAM-based main memory is significantly slower than the processor. Consequently, processors spend a long time waiting to access data from main memory, making the long main memory access latency one of the most critical…

Large Language Models (LLMs) with Mixture-of-Expert (MoE) architectures achieve superior model performance with reduced computation costs, but at the cost of high memory capacity and bandwidth requirements. Near-Memory Processing (NMP)…

Reducing energy consumption is a challenge that is faced on a daily basis by teams from the High-Performance Computing as well as the Embedded domain. This issue is mostly attacked from an hardware perspective, by devising architectures…

In this paper, we conduct systematic measurement studies to show that the high memory bandwidth consumption of modern distributed applications can lead to a significant drop of network throughput and a large increase of tail latency in…

We present a lightweight tool for the analysis and tuning of application data placement in systems with heterogeneous memory pools. The tool allows non-intrusively identifying, analyzing, and controlling the placement of individual…

Wireless baseband processing (WBP) is a key element of wireless communications, with a series of signal processing modules to improve data throughput and counter channel fading. Conventional hardware solutions, such as digital signal…

Six-dimensional movable antenna (6DMA) is an effective solution for enhancing wireless network capacity through the adjustment of both 3D positions and 3D rotations of distributed antennas/antenna surfaces. Although freely…

Mixture-of-Experts (MoE) has emerged as a practical approach to scale up parameters for the Transformer model to achieve better generalization while maintaining a sub-linear increase in computation overhead. Current MoE models are mainly…

Memory disaggregation over RDMA can improve the performance of memory-constrained applications by replacing disk swapping with remote memory accesses. However, state-of-the-art memory disaggregation solutions still use data path components…

Modern high-performance computing (HPC) environments rely on hybrid storage systems (HSS) that combine multiple storage devices with diverse latency, bandwidth, endurance, and capacity characteristics to meet the performance, capacity, and…

Large Language Models (LLMs) increasingly require processing long text sequences, but GPU memory limitations force difficult trade-offs between memory capacity and bandwidth. While HBM-based acceleration offers high bandwidth, its capacity…

Large language models (LLMs) are widely used but expensive to run, especially as inference workloads grow. To lower costs, maximizing the request batch size by managing GPU memory efficiently is crucial. While PagedAttention has recently…