Passage EVK100

Exascale Connectivity for AI

Passage EVK 100 represents a giant leap in photonic interconnect performance. Designed for the extreme demands of scale-up and scale-out AI networks, it delivers massive bandwidth density and unprecedented energy efficiency.

Aggregate I/O

3.2

Tbps aggregate bandwidth @ 112G PAM4

Efficiency

3.4

pJ/bit target link efficiency @ 112G PAM4

Innovation

The CPO Scaling Solution

Passage EVK100 is engineered to meet the bandwidth explosion of exascale AI superpods. By integrating advanced Photonic Integrated Circuits (PIC) with high-performance optical SerDes chiplets in a 2D multi-chip package, Passage EVK 100 de-risks the most aggressive roadmaps in the industry.

Architecture

Optimized for Bandwidth Density

Passage EVK100 uses a 16-wavelength 112G PAM4 DWDM architecture to maximize bandwidth per fiber. The system supports 1.6 Tbps unidirectional (separate Tx/Rx fibers) transmission on a single-mode optical fiber.

Designed for scale-up and scale-out AI networks, the platform leverages high baud rates to maximize link bandwidth density.

Link Architecture

1,600 Gbps per fiber enabled by a 16-channel DWDM O-band link architecture.

Technical Specifications

SerDes modulation formats
56G NRZ, 112G PAM4
Link architecture
16λ DWDM
Wavelength grid
200 GHz spacing centered at 1310 nm (O-band)
Throughput modes
1.6 Tbps UniDi
Port count
2 fibers
Efficiency
3.2 pJ/bit @112G PAM4 including laser
Pre-FEC BER target
< 1e-5
Chassis form factor
OCP-compliant rack integration
Operating temperature
25°C–105°C (validated)

The Future of Exascale

Passage EVK100 is the standard-bearer for AI infrastructure. Contact our sales team for a deep-dive on the technology and integration roadmaps.