Related papers: LUNA-CIM: Lookup Table based Programmable Neural P…

Based on the analysis of the proportion of utility in the supporting transactions used in the field of data mining, high utility-occupancy pattern mining (HUOPM) has recently attracted widespread attention. Unlike high-utility pattern…

Large language model (LLM) inference performance is increasingly bottlenecked by the memory wall. While GPUs continue to scale raw compute throughput, they struggle to deliver scalable performance for memory bandwidth bound workloads. This…

We introduce Lookup-Table Language Models (LookupLM), a method for scaling up the size of RNN language models with only a constant increase in the floating point operations, by increasing the expressivity of the embedding table. In…

We describe a space-time optimized circuit for the table lookup subroutine from lattice-surgery surface code primitives respecting 2D grid connectivity. Table lookup circuits are ubiquitous in quantum computing, allowing the presented…

We present an algorithm to perform trust-region-based optimization for nonlinear unconstrained problems. The method selectively uses function and gradient evaluations at different floating-point precisions to reduce the overall energy…

Modern computing systems are limited in performance by the memory bandwidth available to processors, a problem known as the memory wall. Processing-in-Memory (PIM) promises to substantially improve this problem by moving processing closer…

Deploying Large Language Models (LLMs) on mobile devices faces the challenge of insufficient performance in smaller models and excessive resource consumption in larger ones. This paper highlights that mobile Neural Processing Units (NPUs)…

Many modern workloads such as neural network inference and graph processing are fundamentally memory-bound. For such workloads, data movement between memory and CPU cores imposes a significant overhead in terms of both latency and energy. A…

This paper investigates hardware-based memory compression designs to increase the memory bandwidth. When lines are compressible, the hardware can store multiple lines in a single memory location, and retrieve all these lines in a single…

Computing has a huge memory problem. The memory system, consisting of multiple technologies at different levels, is responsible for most of the energy consumption, performance bottlenecks, robustness problems, monetary cost, and hardware…

Efficient all-digital post-correction of low-resolution analog-to-digital converters can be achieved by using Look-Up Tables (LUTs). The performance of a LUT can be optimized by incorporating a parametric model for the expected input…

Large language models (LLMs) have garnered substantial attention due to their promising applications in diverse domains. Nevertheless, the increasing size of LLMs comes with a significant surge in the computational requirements for training…

We propose a quantized decoding algorithm for low- density parity-check codes where the variable node update rule of the standard min-sum algorithm is replaced with a look-up table (LUT) that is designed using an information-theoretic…

Parameter quantization for Large Language Models (LLMs) has attracted increasing attentions recently in reducing memory costs and improving computational efficiency. Early approaches have been widely adopted. However, the existing methods…

The resource requirements of neural networks can be significantly reduced through pruning - the removal of seemingly less important parameters. However, for LLMs, full retraining to recover pruning-induced performance degradation is often…

Processing large numbers of key/value lookups is an integral part of modern server databases and other "Big Data" applications. Prior work has shown that hash table based key/value lookups can benefit significantly from using a dedicated…

High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems.The…

Processing-in-memory (PIM) architectures bring computation closer to data, reducing the processor-memory transfer bottleneck in traditional processor-centric designs. Novel hardware solutions, such as UPMEM's in-memory processing…

The computational and memory challenges of large language models (LLMs) have sparked several optimization approaches towards their efficient implementation. While prior LLM-targeted quantization, and prior works on sparse acceleration have…

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…