Current pluggable optics have stunted optical innovation for the last decade. So argues Chris Cole, industry veteran and an advisor at start-up Quintessent.
Chris Cole
Cole calls for a new form factor supporting hundreds of electrical and optical channels. In a workshop on massively parallel optics held at the recent ECOC conference and exhibition in Frankfurt, he outlined other important specifications such a module should have.
Cole, working with other interested parties in the new form factor, will present their proposal to the OIF industry body at its next meeting in November.
"I'm very optimistic it will be approved," says Cole.
Limitations
Pluggable optics require improvement in several areas.
One limitation is the large, limited number of gold-fingered interconnects on the edge of the printed circuit board (PCB) that fits inside the pluggable module. "This technology goes back 30 or 40 years," says Cole.
The high-speed OSFP (Octal Small Form-factor Pluggable) module has a row of eight transmit-receive pairs of gold-fingered edge interconnects. The OSFP interface supports 800 gigabits per second (Gbps), and 1.6 terabits per second (Tbps) if 200Gbps signalling is used. The industry can also double capacity to 3.2-terabit with 8x400Gbps signals.
In turn, the QSFP-XD has 16 such pairs arranged in two rows. That promises 3.2Tbps capacity using 16x200Gbps signals and 6.4Tbps with 16x400Gbps signals. However, Cole expects huge signal integrity issues using such a design.
Heat dissipation is another challenge with pluggables. Heat is extracted from a pluggable using a metal plate on the top, which Cole says limits power consumption to 50W.
It is is the low channel count, however, that is the biggest restriction, says Cole.
Meanwhile, yield and reliability have yet to advance. He cites the significant reliability performance achieved by Intel with its integrated laser technology. "It doesn't do any good because who cares?" he says. "You have a four-channel module, and something's wrong; you throw it away," says Cole.
Proposed form factor
The high-capacity form factor proposal calls for a dense, high-bandwidth design. Significant numbers of electrical and optical lanes are needed for that: hundreds rather than eight or 16. Moreover, hundreds of electrical interfaces is not a new concept: Cole cites the large 300-pin MSA used for early embedded coherent modems.
The new form factor would have 2D electrical connections with at least a 0.5mm lower pitch. A high-speed 256-lane count is envisaged, that would also enable many optical lanes and wavelength counts. Each electrical lane should have a bandwidth of 200GHz to support 448Gbps signalling. If implemented, the package's capacity would be 114Tbps.
"[200GHz lanes] is not very hard to do if you have a connection that is almost negligible height," says Cole.
Many optical connections are also required, says Cole. He suggests 512, where individual links are supported to ensure a high radix. "We can quibble about the correct number, but it's not eight or 16," says Cole. The design should also support liquid cooling to ensure a 100W power consumption.
Optical options
Cole says the design must be optics-agnostic. Nobody can predict the future, he says.
To support 12.8Tbps, for example, it could use 32 optical lanes each at 400Gbps or 16 lanes at 800Gbps both using a thin-film lithium niobate modulator. However, the design should also support many more slower optical channels.
One such 12.8Tbps optical transmission example is 256 channels, each a 50Gbps non-return-to-zero signal, making use of a compact ring-resonator modulators. It could even be 3,200x4Gbps MicroLED channels using an approach favoured by Avicena. It is not out of the question, says Cole.
Cole stresses that while 12.8-terabit and 25.6-terabit capacities may sound high compared to existing pluggable, but the numbers should be viewed as aggregate package capacities. "You would be breaking them out into many channels," he says.
Retaining features that work
Cole argues that the benefits of pluggable modules must be retained. These include front-plate access, testing, and easy replacement. Equally, the proposed form factor should preserve existing industry business models.
He is also adamant that conventional assembly must be replaced with process-based photonic integration to improve reliability. "The consistency you get in a fab versus what you get in a discrete assembly, there's an order of magnitude difference there," he says.