Related papers: DARTH-PUM: A Hybrid Processing-Using-Memory Archit…

Large Language Models (LLMs) have become essential in a variety of applications due to their advanced language understanding and generation capabilities. However, their computational and memory requirements pose significant challenges to…

The widespread adoption of cloud-based solutions introduces privacy and security concerns. Techniques such as homomorphic encryption (HE) mitigate this problem by allowing computation over encrypted data without the need for decryption.…

Training machine learning algorithms is a computationally intensive process, which is frequently memory-bound due to repeatedly accessing large training datasets. As a result, processor-centric systems (e.g., CPU, GPU) suffer from costly…

The effective use of parallel computing resources to speed up algorithms in current multi-core parallel architectures remains a difficult challenge, with ease of programming playing a key role in the eventual success of various parallel…

Computing-in-memory (CIM) has been demonstrated across various memory technologies, ranging from memristive crossbars performing analog dot-product computations to large-scale digital bitwise operations in commodity DRAM and other proposed…

Compute-in-memory (CIM) has shown significant potential in efficiently accelerating deep neural networks (DNNs) at the edge, particularly in speeding up quantized models for inference applications. Recently, there has been growing interest…

Processing-in-memory (PIM) has emerged as the go to solution for addressing the von Neumann bottleneck in edge AI accelerators. However, state-of-the-art (SoTA) digital PIM approaches suffer from low compute density, primarily due to the…

Today's systems are overwhelmingly designed to move data to computation. This design choice goes directly against at least three key trends in systems that cause performance, scalability and energy bottlenecks: (1) data access from memory…

The computing wall and data movement challenges of deep neural networks (DNNs) have exposed the limitations of conventional CMOS-based DNN accelerators. Furthermore, the deep structure and large model size will make DNNs prohibitive to…

In recent years, there is an increasing demand of big memory systems so to perform large scale data analytics. Since DRAM memories are expensive, some researchers are suggesting to use other memory systems such as non-volatile memory (NVM)…

In memory computing (IMC) architectures for deep learning (DL) accelerators leverage energy-efficient and highly parallel matrix vector multiplication (MVM) operations, implemented directly in memory arrays. Such IMC designs have been…

General matrix-vector multiplication (GeMV) remains a critical latency bottleneck in large language model (LLM) inference, even with quantized low-bit models. Processing-Using-DRAM (PUD), an analog in-DRAM computing technique, has the…

Applications with low data reuse and frequent irregular memory accesses, such as graph or sparse linear algebra workloads, fail to scale well due to memory bottlenecks and poor core utilization. While prior work with prefetching,…

PIM architectures aim to reduce data transfer costs between processors and memory by integrating processing units within memory layers. Prior PIM architectures have shown potential to improve energy efficiency and performance. However, such…

Deep learning hardware designs have been bottlenecked by conventional memories such as SRAM due to density, leakage and parallel computing challenges. Resistive devices can address the density and volatility issues, but have been limited by…

Phase-change memory (PCM) devices have multiple banks to serve memory requests in parallel. Unfortunately, if two requests go to the same bank, they have to be served one after another, leading to lower system performance. We observe that a…

In-memory analog matrix computing (AMC) with resistive random-access memory (RRAM) represents a highly promising solution that solves matrix problems in one step. However, the existing AMC circuits each have a specific connection topology…

Decoder-only Transformer models such as GPT have demonstrated exceptional performance in text generation, by autoregressively predicting the next token. However, the efficacy of running GPT on current hardware systems is bounded by low…

This work discusses memory-immersed collaborative digitization among compute-in-memory (CiM) arrays to minimize the area overheads of a conventional analog-to-digital converter (ADC) for deep learning inference. Thereby, using the proposed…

Computing on encrypted data is a promising approach to reduce data security and privacy risks, with homomorphic encryption serving as a facilitator in achieving this goal. In this work, we accelerate homomorphic operations using the…