China’s optical chip breakthrough boosts AI speed 100-fold using fraction of compute power
Summary
Chinese researchers have developed an all-optical interconnect system that links standard electronic chips, boosting AI distributed inference speeds by over 100 times while using just one-ninth of typical computational resources. The breakthrough, published in National Science Review, uses silicon photonic transceiver chips and FPGAs to achieve dramatic efficiency gains.
View Cached Full Text
Cached at: 07/13/26, 07:52 AM
Similar Articles
Chinese chip stores data with a single electron, breaking AI memory bottleneck
Researchers at Fudan University have developed a two-dimensional flash memory chip that stores data using a single electron, achieving a tenfold voltage improvement and potentially enabling efficient AI on mobile devices.
Exploring 400 Gbps/λ and beyond with AI-accelerated silicon photonic slow-light technology
This paper explores using AI-accelerated silicon photonic slow-light technology to achieve data rates of 400 Gbps per wavelength and beyond, advancing optical communication capabilities.
Coherent Breaks Ground on Expanded Texas Facility, Scaling AI’s Optical Backbone
Coherent breaks ground on an expanded facility in Texas, backed by a $50 million CHIPS Act grant, to scale production of optical components and compound semiconductors essential for AI infrastructure. NVIDIA CEO Jensen Huang highlighted the critical role of optics in enabling large-scale AI systems.
@intel: As AI demands unprecedented brainpower, the semiconductor industry is moving beyond single, massive chips. Advanced pac…
Intel is advancing chip packaging technologies like Foveros and EMIB to enable multi-chip packages for AI workloads, scaling beyond traditional reticle limits.
@VraserX: China developing domestic AI chips while the US restricts access to its best hardware creates a fascinating possibility…
China's development of domestic AI chips in response to US restrictions could either slow its progress or accelerate its independence from foreign hardware like Nvidia.