Lower Energy, High Performance LLM on FPGA Without Matrix Multiplication


A new technical paper titled "Scalable MatMul-free Language Modeling" was published by UC Santa Cruz, Soochow University, UC Davis, and LuxiTech. Abstract "Matrix multiplication (MatMul) typically dominates the overall computational cost of large language models (LLMs). This cost only grows as LLMs scale to larger embedding dimensions and context lengths. In this work, we show that MatMul... » read more

Rotating neurons for all-analog implementation of cyclic reservoir computing


Abstract "Hardware implementation in resource-efficient reservoir computing is of great interest for neuromorphic engineering. Recently, various devices have been explored to implement hardware-based reservoirs. However, most studies were mainly focused on the reservoir layer, whereas an end-to-end reservoir architecture has yet to be developed. Here, we propose a versatile method for implemen... » read more

Power/Performance Bits: Nov. 16


Light-emitting memory Researchers from Kyushu University and National Taiwan Normal University propose a 'light-emitting memory' based on a perovskite that can simultaneously store and visually transmit data. The team used the idea in conjunction with resistive RAM (RRAM), in which states of high and low resistance represent ones and zeros. "The electrical measurements needed to check the r... » read more