Start-up plans to use terahertz radio frequencies for communication between servers instead of copper or optical connections — radio-based interconnections offer 1.6 TB/s using half the volume of copper

Alphawave
(Image credit: Alphawave)

Scale-up connectivity is crucial for the performance of rack-scale AI systems, but achieving high bandwidth and low latency for such interconnections using copper wires is becoming increasingly complicated with each generation. Using optical interconnections for scale-up connectivity is a possibility, but it may be an overkill, so start-ups Point2 and AttoTude propose to use radio-based interconnections operating at millimeter-wave and terahertz frequencies over waveguides that connect to systems using standard pluggable connectors, reports IEEE Spectrum.

Point2's implementation uses what it calls an 'active radio cable' built from eight 'e-Tube' waveguides. Each waveguide carries data using two frequencies — 90 GHz and 225 GHz — and plug-in modules at both ends convert digital signals directly into modulated millimeter-wave radio and back again. A full cable delivers 1.6 Tb/s, occupies 8.1mm, or about a half the volume of a comparable active copper cable, and can reach up to seven meters, more than enough for scale-up connectivity. Point2 says the design consumes roughly one-third the power of optical links, costs about one-third as much, and adds as little as one-thousandth the latency.

A notable aspect of Point2's approach is the relative maturity of its technology. The radio transceivers can be fabricated at standard semiconductor production facilities using well-known fabrication processes — the company has already demonstrated this approach using a 28nm chip with the Korea Advanced Institute of Science and Technology (KAIST). Also, its partners Molex and Foxconn Interconnect Technology have shown that the specialized cables can be produced on existing lines without major retooling.

AttoTude is pursuing a similar concept, but at even higher frequencies. Its system combines a digital interface, a terahertz signal generator, and a mixer that encodes data onto carriers between 300 and 3,000 GHz that feeds the signal into a narrow dielectric waveguide. Early versions used hollow copper tubes, while later generations rely on fibers measuring approximately 200 micrometers across with losses as low as 0.3 dB per meter (considerably lower than copper). The company has demonstrated 224 Gb/s transmission over four meters at 970 GHz and projects viable reaches of around 20 meters.

Both companies use waveguides instead of cables because, at millimeter-wave and terahertz frequencies cables fail. While at very high data rates copper cables can pass signals, they do so by becoming thicker, shorter, and more power-hungry. Furthermore, their losses and jitter rise so fast that the link budget collapses and breaks, so cables cannot be used for such applications. Meanwhile, waveguides are not an exotic choice, they are among a few viable option for interconnects with terabit/s-class bandwidth.

Google Preferred Source

Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds.

Anton Shilov
Contributing Writer

Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.

  • Zaranthos
    Wonder how shielding (or lack thereof) and external interference affect this? An optical cable would likely be far less subject to external interference apart from cable damage.
    Reply
  • Jame5
    The title of the article says TB/s and then the body of the article says Tb/s. Which is it actually?

    There is an 8x difference there.
    Reply
  • bit_user
    Zaranthos said:
    Wonder how shielding (or lack thereof) and external interference affect this?
    Given that Point2 bundles 8 waveguides within a single cable, it seems that the issue of cross-talk and interference is negligible. At least, for the distances concerned.

    Jame5 said:
    The title of the article says TB/s and then the body of the article says Tb/s. Which is it actually?
    Yeah, someone deserves a slap on the wrist for that. It's Terrabits/s, according to the PDF (linked from the article). That's actually the second generation, based on 224G serdes and 130/260 GHz carrier frequency.

    Here's the PDF (from more than a year ago, apparently):
    https://point2tech.com/wp-content/uploads/2024/08/240710-E-Tube-Whitepaper-clean-update-final.pdf
    Reply
  • cia1413
    Zaranthos said:
    Wonder how shielding (or lack thereof) and external interference affect this? An optical cable would likely be far less subject to external interference apart from cable damage.
    A wave guide is a solid hollow tube, so it is shielded, the signal bounces back and forth on the sides but the tube is grounded. The frequency makes it so the signal cant survive outside the tube so you cant really have cross talk. I used waveguides in the military so I might be wrong, but I have a little bit of experience using them in microwave and satcom gear.
    Reply
  • bill001g
    cia1413 said:
    A wave guide is a solid hollow tube, so it is shielded, the signal bounces back and forth on the sides but the tube is grounded. The frequency makes it so the signal cant survive outside the tube so you cant really have cross talk. I used waveguides in the military so I might be wrong, but I have a little bit of experience using them in microwave and satcom gear.
    That is how older cell towers used to work. Those huge cable going up the side of the tower were not cables they were hollow wave guide. Modern technology has allowed them to place even very high power radios in the antenna themselves rather than at the bottom of the tower.
    Reply
  • bit_user
    bill001g said:
    That is how older cell towers used to work. Those huge cable going up the side of the tower were not cables they were hollow wave guide.
    I've seen one of those, up close. I worked with a guy who had a short piece of one in his office.

    He said it was from a FM radio tower. The explanation I got was that high frequency signals stayed mostly at the surface of a wire and therefore you could economize by not using a solid cable and simply use a hollow one. Nothing about waveguides though. So, either he was wrong about how it worked, or it operated on a different principle than these do.
    Reply
  • usertests
    Consumes 1/3 the power of optical, but costs 1/3 more than optical
    Point2 says the design consumes roughly one-third the power of optical links, costs about one-third as much
    Huh?
    Reply
  • bit_user
    usertests said:
    Huh?
    I don't know where the first quote is from, but the Point2 PDF says that active optical cable (AOC/LPO - they don't spell out what LPO means) costs 3x as much as e-Tube cable.

    The article also cites a piece in IEEE spectrum. So, maybe the first quote is in reference to something it says? Perhaps the discrepancy could be explained by looking at cost overheads (i.e. transceivers, connectors, etc).
    Reply
  • MoxNix
    Zaranthos said:
    Wonder how shielding (or lack thereof) and external interference affect this? An optical cable would likely be far less subject to external interference apart from cable damage.
    Waveguides are inherently shielded by design. They are hollow tubes, the signal bounces around inside the tube, the tube walls are the shielding.
    Reply