---
title: "NIFA：面向高效ML推理的非线性IMC增强型FPGA架构"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.15123v1"
permalink: "https://feed.astralor.com/items/itm_aaf87fdd1ed942b733545049"
published: "2026-07-16T15:32:44.000Z"
score: 79
channel: "tech"
tags: ["ACAM","FPGA","IMC","ReRAM","Transformer推理","能效优化"]
---

# NIFA：面向高效ML推理的非线性IMC增强型FPGA架构

## AI 点评

> 这篇NIFA论文让我眼前一亮——它不仅解决了ADC功耗瓶颈，更关键的是把IMC的适用范围从卷积网络扩展到了Transformer。对于想在FPGA上跑大模型推理的团队，这个方向值得深挖。硬件领域的突破往往比软件优化更有根本性影响。

## 速览

传统FPGA的模拟内存计算（IMC）块仅支持静态权重向量矩阵乘法（VMM），无法高效处理Transformer模型所需的非线性和动态矩阵乘法（DIMM），且ADC功耗面积占比超70%。本文提出NIFA架构：用模拟内容寻址存储器（ACAM）替换ADC，在块内原生支持非线性操作；通过FPGA感知的设计空间探索优化交叉阵列维度，并利用ACAM映射DIMM操作以支持注意力计算。实验表明，在CNN和Transformer基准上，能效分别提升40倍和1.9倍，面积效率分别提升4.1倍和2.5倍。

## 关键点

- 用ACAM替换ADC，消除IMC块中功耗和面积最大的组件，同时实现块内原生非线性运算。
- 首次将IMC扩展到动态矩阵乘法（DIMM），使Transformer注意力计算能从IMC获益。
- FPGA感知的设计空间探索平衡面积、灵活性和深度学习性能。
- 整体能效与面积效率在CNN和Transformer上均有显著提升，长序列下鲁棒性更强。

## 全文

Recent FPGAs have improved deep learning (DL) inference efficiency through dedicated tensor blocks and in-BRAM computation. ReRAM-based analog in-memory computing (IMC) pushes efficiency further, offering an order-of-magnitude improvement in compute density and energy efficiency over conventional digital logic by performing vector-matrix multiplication (VMM) directly within the ReRAM crossbar; prior work has integrated such IMC blocks into FPGAs for DL inference. However, conventional IMC designs support only static-weight VMM, leaving nonlinear operations and dynamic matrix-matrix multiplication (DIMM) to the FPGA fabric. As a result, the benefits of IMC are largely confined to static-weight models, whereas Transformer-based models, which rely on frequent nonlinear and DIMM operations, gain only limited improvement. Moreover, the ADCs within each IMC block consume more than 70% of its area and power, further limiting system efficiency and scalability. To address these limitations, we propose a novel FPGA architecture that integrates an ADC-free IMC block, replacing the conventional ADC with analog content-addressable memories (ACAMs) that natively perform nonlinear operations inside the block. To fully exploit this block, we conduct an FPGA-aware design-space exploration that determines optimal crossbar dimensions while balancing FPGA area, flexibility, and DL performance, and we develop an efficient mapping that leverages ACAMs to carry out DIMM operations, extending the applicability of IMC to attention computation. On CNN and Transformer-based benchmarks, the proposed architecture achieves up to 40x and 1.9x higher energy efficiency and 4.1x and 2.5x higher area efficiency, respectively. Overall, it significantly improves FPGA DL inference efficiency and sustains robust gains on Transformer-based workloads across long input sequences, advancing domain-specialized FPGA design.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_aaf87fdd1ed942b733545049