Related papers: Tearing Down the Memory Wall
Differentiable architecture search (DARTS) is successfully applied in many vision tasks. However, directly using DARTS for Transformers is memory-intensive, which renders the search process infeasible. To this end, we propose a multi-split…
In-memory computing is a promising alternative to traditional computer designs, as it helps overcome performance limits caused by the separation of memory and processing units. However, many current approaches struggle with unreliable…
The most important architectural problem in AI is not the size of the model but the absence of a layer that carries forward what the model has come to understand. Sessions end. Context windows fill. Memory APIs return flat facts that the…
This document presents a vision for a novel AI infrastructure design that has been initially validated through inference simulations on state-of-the-art large language models. Advancements in deep learning and specialized hardware have…
Today's computing systems require moving data back-and-forth between computing resources (e.g., CPUs, GPUs, accelerators) and off-chip main memory so that computation can take place on the data. Unfortunately, this data movement is a major…
This article presents an artificial intelligence (AI) architecture intended to simulate the iterative updating of the human working memory system. It features several interconnected neural networks designed to emulate the specialized…
In this paper we introduce "Federated Learning Utilities and Tools for Experimentation" (FLUTE), a high-performance open-source platform for federated learning research and offline simulations. The goal of FLUTE is to enable rapid…
Recent advancements in neural rendering technologies and their supporting devices have paved the way for immersive 3D experiences, significantly transforming human interaction with intelligent devices across diverse applications. However,…
In this thesis, I explore whether it is possible to build a unified Quantum Internet architecture that supports different types of quantum repeaters -- especially the two most distinct and seemingly incompatible ones: memory-based quantum…
This article features extended summaries and retrospectives of some of the recent research done by our group, SAFARI, on (1) understanding, characterizing, and modeling various critical properties of modern DRAM and NAND flash memory, the…
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…
Textual network embeddings aim to learn a low-dimensional representation for every node in the network so that both the structural and textual information from the networks can be well preserved in the representations. Traditionally, the…
Standard memory modules to store (and access) data are designed for use with a single system accessing it. More complicated memory modules would be accessed through a memory controller, which are also designed for one system. For multiple…
Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference. These architectures hold promise for streaming applications at the edge, but deployment in…
As DRAM scales to higher density and I/O speeds, ensuring data correctness becomes increasingly difficult. Industry has responded with a three-layer stack: on-die ECC (O-ECC), link ECC (L-ECC), and system ECC (S-ECC). However, these layers…
Heterogeneous systems appear as a viable design alternative for the dark silicon era. In this paradigm, a processor chip includes several different technological alternatives for implementing a certain logical block (e.g., core, on-chip…
Resistive random-access memory (RRAM) is gaining popularity due to its ability to offer computing within the memory and its non-volatile nature. The unique properties of RRAM, such as binary switching, multi-state switching, and device…
The needs of emerging applications, such as augmented and virtual reality, federated machine learning, and autonomous driving, have motivated edge computing--the push of computation capabilities to the edge. Various edge computing…
Many modern and emerging applications must process increasingly large volumes of data. Unfortunately, prevalent computing paradigms are not designed to efficiently handle such large-scale data: the energy and performance costs to move this…
We propose a self-organizing memory architecture for perceptual experience, capable of supporting autonomous learning and goal-directed problem solving in the absence of any prior information about the agent's environment. The architecture…