计算机科学
电子工程
计算机硬件
数字信号处理
收发机
延迟(音频)
信号处理
带宽(计算)
媒体处理器
可用的
数字信号处理器
游标尺
均衡(音频)
偏移量(计算机科学)
自适应均衡器
有限冲激响应
波分复用
隐藏物
符号间干扰
滤波器(信号处理)
串行解串
绘图
信号(编程语言)
数字滤波器
多路复用
均衡器
偏振模色散
功率消耗
能源消耗
实时计算
无线
吞吐量
高清电视
数字信号
脉冲整形
宽带
作者
Benshan Wang,Qiarong Xiao,Tengji Xu,F Li,Shaojie Liu,Qiuqiang Kong,Jianji Dong,Junwen Zhang,Chaoran Huang
出处
期刊:Science
[American Association for the Advancement of Science]
日期:2026-06-11
卷期号:392 (6803): eady5344-eady5344
标识
DOI:10.1126/science.ady5344
摘要
Large-scale artificial intelligence training demands ultralow-latency, energy-efficient interconnects for massive graphics processing unit clusters. In intensity-modulation/direct-detection links, digital signal processing (DSP) equalization is limited by nonideal equalization caused by phase loss as well as tight power and latency budgets. We present an integrated, programmable optical signal processor (OSP) that functions as a nonlinear universal equalizer and performs all-optical, DSP-free, real-time equalization. A deep reservoir with all-optical readout enables a Vernier scheme with ~1-picosecond (ps) sampling resolution and a tunable memory window. The OSP simultaneously equalizes eight wavelength-division-multiplexing (WDM) channels, delivering 1.6-terabits/second aggregate throughput with <60-picoseconds latency and tens of femtojoules/bit energy consumption. Operating before detection, it provides superior chromatic dispersion compensation, mitigates transceiver bandwidth limits and fiber nonlinearity, and expands the usable WDM window by a factor of 6.8.
科研通智能强力驱动
Strongly Powered by AbleSci AI