Kunlun: A 14nm High-Performance AI Processor for Diversified Workloads

📋 论文概要

本文介绍了百度自研的AI芯片Kunlun，采用三星14nm工艺，基于XPU架构，旨在灵活处理语音、图像、语言和自动驾驶等多样化AI工作负载。芯片实现了高可编程性和高性能，峰值性能达230TOPS@INT8，内存带宽512GB/s。

💡 主要创新点

• 采用XPU架构，兼顾高可编程性与高性能，支持多样化AI工作负载。
• 在14nm工艺下实现230TOPS@INT8的峰值性能，并通过动态频率提升至281TOPS。
• 提供512GB/s的高内存带宽，满足大规模AI模型的数据吞吐需求。

🏷 关键词

📄 原文摘要

In order to be able to handle a wide range of AI applications, such as for speech, image, language and autonomous driving, it is necessary that an AI accelerator be flexible enough to handle diversified workloads. Baidu Kunlun, an AI chip designed in-house by Baidu, achieves this capability with high programmability, flexibility and performance. Baidu Kunlun was inspired by the XPU architecture [1]. The chip is implemented in Samsung 14nm process technology. Its peak performance is 230TOPS@INT8 at 900MHz and up to 281TOPS@INT8 at 1.1GHz boost frequency. The memory bandwidth is 512GB/s and the peak power is 160W. Baidu Kunlun achieves good performance across various types of workloads. With 900MHz base frequency, the latencies of BERT, ResNet50, YOLOv3 are 1.7×, 1.2× and 2× less than an Nvidia T4 GPU, respectively, with optimizations from TensorRT. Recently, Baidu Kunlun has been deployed in data centers

👥 作者与机构

Jian Ouyang, Xueliang Du, Yin Ma, Jiaqiang Liu

Baidu, Beijing, China