ALSO READ:
Doubling Down: World’s First 16-λ Single Fiber Bidirectional Link for AI
The computational needs of Artificial Intelligence (AI) have pushed hardware to its absolute limits. One of the most significant bottlenecks in building a massive, scale-up AI system is interconnect I/O—specifically, the number of optical fibers you can connect to a GPU or a switch. Co-Packaged Optics (CPO) has emerged as a leading solution, but it still faces the physical constraint of fiber real estate.
The Passage 3D Silicon Photonics Engine supports from single-chip to multi-die complexes and all the way to wafer-scale—the world’s fastest interconnect.
Explore the Passage M1000 Reference System, a groundbreaking platform built around the Passage M1000 3D Photonic Superchip. Discover how this revolutionary photonic interconnect technology is changing the game for Artificial Intelligence (AI) infrastructure by enabling massive scale-up bandwidth and radix, connecting GPUs, TPUs and data center switches in the largest AI model training clusters.
3D Photonic Interconnect for AI
The Passage™ M1000 3D Photonic Superchip reference platform demonstrates record-breaking 114 Tbps total bandwidth. A 4000 mm2 photonic interposer for massive die complexes. M1000 has 256 optical fibers and supports 1.5kW+ power delivery and the world’s first built-in solid state optical circuit switching.
Unleash I/O anywhere within your chip complex. Eliminate energy-draining, latency-heavy network-on-chip journeys. Outperform shoreline-limited technologies like conventional CPO, NPO, and pluggables.