Related papers: Container Density Improvements with Dynamic Memory…
Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…
Poor DRAM technology scaling over the course of many years has caused DRAM-based main memory to increasingly become a larger system bottleneck. A major reason for the bottleneck is that data stored within DRAM must be moved across a…
Poor time predictability of multicore processors has been a long-standing challenge in the real-time systems community. In this paper, we make a case that a fundamental problem that prevents efficient and predictable real-time computing on…
Context: Virtual machines provide isolation of services at the cost of hypervisors and more resource usage. This spurred the growth of systems like Docker that enable single hosts to isolate several applications, similar to VMs, within a…
Content-Addressable Memory (CAM) is a powerful abstraction for building memory caches, routing tables and hazard detection logic. Without a native CAM structure available on FPGA devices, their functionality must be emulated using the…
As emerging deep neural network (DNN) models continue to grow in size, using large GPU clusters to train DNNs is becoming an essential requirement to achieving acceptable training times. In this paper, we consider the case where future…
Since emerging edge applications such as Internet of Things (IoT) analytics and augmented reality have tight latency constraints, hardware AI accelerators have been recently proposed to speed up deep neural network (DNN) inference run by…
Today, flash memory are strongly used in the embedded system domain. NAND flash memories are the building block of main secondary storage systems. Such memories present many benefits in terms of data density, I/O performance, shock…
Die-stacked DRAM is a promising solution for satisfying the ever-increasing memory bandwidth requirements of multi-core processors. Manufacturing technology has enabled stacking several gigabytes of DRAM modules on the active die, thereby…
The number of processing elements (PEs) in a fixed-sized systolic accelerator is well matched for large and compute-bound DNNs; whereas, memory-bound DNNs suffer from PE underutilization and fail to achieve peak performance and energy…
Serverless computing relies on extreme multi-tenancy to remain economically viable, driving providers to rely on virtual machines (VMs) that ensure strong isolation and seamless ecosystem compatibility with the FaaS programming model.…
Over the past decades, the relentless scaling and mass production of flash memory have underpinned the data-centric era. Yet charge-trap-based 3D NAND flash is now constrained by intrinsic physical and architectural limits, including…
Large persistent memories such as NVDIMM have been perceived as a disruptive memory technology, because they can maintain the state of a system even after a power failure and allow the system to recover quickly. However, overheads incurred…
Decentralized storage is still rarely used in an academic and educational environment, although it offers better availability than conventional systems. It still happens that data is not available at a certain time due to heavy load or…
Compute in-memory (CIM) is a promising technique that minimizes data transport, the primary performance bottleneck and energy cost of most data intensive applications. This has found wide-spread adoption in accelerating neural networks for…
Efficient and scalable 3D occupancy mapping is essential for autonomous robot applications in unknown environments. However, traditional occupancy grid representations suffer from two fundamental limitations. First, explicitly storing all…
Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML…
Our goal in this dissertation is to provide tools, programming models, and system support for PIM architectures (with a focus on DRAM-based solutions), to ease the adoption of PIM in current and future systems. To this end, we make at least…
Non-volatile memory (NVM) provides a scalable and power-efficient solution to replace DRAM as main memory. However, because of relatively high latency and low bandwidth of NVM, NVM is often paired with DRAM to build a heterogeneous memory…
The effectiveness of in-memory dynamic graph storage (DGS) for supporting concurrent graph read and write queries is crucial for real-time graph analytics and updates. Various methods have been proposed, for example, LLAMA, Aspen,…