The startup develops an optical interposer that utilizes light for energy-efficient die-to-die interconnects, enabling high-performance computing (HPC) processors to achieve full scalability with multi-chipset configurations. This technology addresses the limitations of traditional electrical interconnects, enhancing data transfer speeds while reducing power consumption.
Funding
$3.8M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Product
Problem
High-performance computing (HPC) and artificial intelligence (AI) applications are increasingly limited by the bandwidth and energy consumption of traditional electrical interconnects between dies in multi-chipset processors. Copper wires cannot scale to meet the demands of modern computing architectures, creating a bottleneck for data transfer.
Solution
NcodiN develops optical interposers that use light to enable ultra-fast and energy-efficient die-to-die interconnects, unlocking the full scalability of multi-chiplet-based HPC processors. Their NConnect technology features the world's smallest laser integrated on silicon, achieving unmatched efficiency and ultra-dense integration. This optical network-on-chip seamlessly integrates with existing chiplet architectures and advanced packaging, delivering high bandwidth and limitless scalability without disrupting existing infrastructure. NcodiN's solution overcomes the limitations of copper interconnects, enabling the next generation of AI computing with increased reach, low power consumption, and unprecedented bandwidth.
Target Audience
NcodiN's primary customers are chipmakers and system integrators in the high-performance computing (HPC), artificial intelligence (AI), telecommunications, and smart cities sectors.
Features
- Optical interposer technology for die-to-die interconnects
- NConnect: Optical network-on-chip
- World's smallest laser integrated on silicon
- Bandwidth density: ≥60 Tbps/mm²
- Energy efficiency: <0.1 pJ/bit
- Reach: ≥50 mm
- Seamless integration with existing chiplet architectures and advanced packaging