arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.08269cs.ET
收藏

量化感知的光子同向计算用于加速人工智能和科学模拟

Quantization-aware Photonic Homodyne computing for Accelerated Artificial Intelligence and Scientific Simulation

University of California, Berkeley(加州大学伯克利分校);Opticore Inc.(Opticore公司);University of Southern California(南加州大学);MIT(麻省理工学院);University of Maryland, College Park(马里兰大学帕克分校);Stanford University(斯坦福大学)
Lian Zhou, Kaiwen Xue, Amirhossein Fallah, Lijin Liu, Chun-Ho Lee, Kiwon Kwon, Clayton Cheung, Yuan Li, Yue Yu, Yun-Jhu Lee, Songlin Zhao, Ryan Hamerly, Edo Wak… 展开作者

Lian Zhou, Kaiwen Xue, Amirhossein Fallah, Lijin Liu, Chun-Ho Lee, Kiwon Kwon, Clayton Cheung, Yuan Li, Yue Yu, Yun-Jhu Lee, Songlin Zhao, Ryan Hamerly, Edo Waks, Dirk Englund, Constantine Sideris, Mengjie Yu, Zaijun Chen

AI总结:

本研究提出一种量化感知的光子同向计算框架,利用光子技术实现高精度、高速度的AI和物理模拟计算,显著提升计算效率和精度。

摘要:

现代高性能计算中的问题,从计算机视觉和语言模型中的深度学习模型训练和推理,到具有非线性耦合方程的复杂物理系统模拟,都需要计算资源呈指数增长。光子模拟系统正出现具有内在并行性、高带宽和低传播损耗的解决方案。然而,其应用受到低模拟精度的阻碍,这是由于电光畸变、材料非线性以及信噪比所致。在这里,我们通过跨芯片片的量化感知数字-光子混合精度框架克服了这一障碍,用于加速AI处理和物理模拟。利用掺锂铌酸盐光子学与通道均衡技术,我们展示了在同向光学逻辑中具有6位精度的线性乘法(9位幅度-相位解耦),在128十亿符号每秒(128 GS/s)的时钟速率下,使AI处理具有6纳秒延迟。硬件-算法协同设计,包括迭代求解器、稀疏-密集量化和位切分矩阵乘法,探索光子幅度和相位相干性以进行复值、受物理启发的计算。在电磁问题中,我们的方法为散射问题中的偏微分方程(PDEs)提供了12位解决方案,这通常需要高达32位甚至64位的精度。这些结果在保持数字级保真度的同时,利用了高速低能耗的光子硬件,为生成式人工智能、实时机器人、气候挑战和生物发现的精确模拟建立了通路。

英文摘要:

Modern problems in high-performance computing, ranging from training and inferencing deep learning models in computer vision and language models to simulating complex physical systems with nonlinearly-coupled equations, require exponential growth of computational resources. Photonic analog systems are emerging with solutions of intrinsic parallelism, high bandwidth, and low propagation loss. However, their application has been hindered by the low analog accuracy due to the electro-optic distortion, material nonlinearities, and signal-to-noise ratios. Here we overcome this barrier with a quantization-aware digital-photonic mixed-precision framework across chiplets for accelerated AI processing and physical simulation. Using Lithium Niobate photonics with channel equalization techniques, we demonstrate linear multiplication (9-bit amplitude-phase decoupling) in homodyne optical logics with 6-bit precision at the clock rate of 128 giga-symbol-per-second (128 GS/s), enabling AI processing with 6 ns latency. Codesign hardware-algorithms, including iterative solvers, sparse-dense quantization, and bit-sliced matrix multiplication, explore photonic amplitude and phase coherence for complex-valued, physics-inspired computation. In electromagnetic problems, our approach yields 12-bit solutions for partial differential equations (PDEs) in scattering problems that would conventionally require up to 32-bit and often even 64-bit precision. These results preserve digital-level fidelity while leveraging the high-speed low-energy photonic hardware, establishing a pathway toward general-purpose optical acceleration for generative artificial intelligence, real-time robotics, and accurate simulation for climate challenges and biological discoveries.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑