With an increasing demand for networking speed and throughput performance within the datacenter and high performance computing clusters, the newly rebranded Ethernet Technology Consortium has announced a new 800 Gigabit Ethernet technology. Based upon many of the existing technologies that power contemporary 400 Gigabit Ethernet, the 800GBASE-R standard is looking to double performance once again, to feed ever-hungrier datacenters.

The recently-finalized standard comes from the Ethernet Technology Consortium, the non-IEEE, tech industry-backed consortium formerly known as the 25 Gigabit Ethernet Consortium. The group was originally created to develop 25, 50, and 100 Gigabit Ethernet technology, and while IEEE Ethernet standards have since surpassed what the consortium achieved, the consortium has stayed formed to push even faster networking speeds, and changing its name to keep with the times. Some of the biggest contributors and supporters of the ETC include Broadcom, Cisco, Google, and Microsoft, with more than 40 companies listed as integrators of its work. 


800 Gigabit Ethernet Block Diagram

As for their new 800 Gigabit Ethernet standard, at a high level 800GbE can be thought of as essentially a wider version of 400GbE. The standard is primarily based around using existing 106.25G lanes, which were pioneered for 400GbE, but doubling the number of total lanes from 4 to 8. And while this is a conceptually simple change, there is a significant amount of work involved in bonding together additional lanes in this fashion, which is what the new 800GbE standard has to sort out.

Diving in, the new 800GBASE-R specification defines a new Media Access Control (MAC) and a Physical Coding Sublayer (PCS), which in turn is built on top of two 400 GbE 2xClause PCS's to create a single MAC which operates at a combined 800 Gb/s. Each 400 GbE PCS uses 4 x 106.25 GbE lanes, which when doubled brings the total to eight lanes, which has been used to create the new 800 GbE standard. And while the focus is on 106.25G lanes, it's not a hard requirement; the ETC states that this architecture could also allow for larger groupings of slower lanes, such as 16x53.125G, if manufacturers decided to pursue the matter.


The 800 GbE PCS Flow Diagram

Focusing on the MAC itself, the ETC claims that 800 Gb Ethernet will inherit all of the previous attributes of the 400 GbE standard, with full-duplex support between two terminals, and with a minimum interpacket gap of 8-bit times. The above diagram depicts each 400 GbE with 16 x 10 b lanes, with each 400 GbE data stream transcoding and scrambling packet data separately, with a bonding control which synchronizes and muxes both PCS's together.

All told, the 800GbE standard is the latest step for an industry as a whole that is moving to Terabit (and beyond) Ethernet. And while those future standards will ultimately require faster SerDes to drive the required individual lane speeds, for now 800GBASE-R can deliver 800GbE on current generation hardware. All of which should be a boon for the standard's intended hyperscaler and HPC operator customers, who are eager to get more bandwidth between systems.

The Ethernet Technology Consortium outlines the full specifications of the 800 GbE on its website in a PDF. There's no information when we might see 800GbE in products, but as its largely based on existing technology, it should be a relatively short wait by datacenter networking standards. Though datacenter operators will probably have to pay for the luxury; with even a Cisco Nexus 400 GbE 16-port switch costing upwards of $11,000, we don't expect 800GbE to come cheap.

Related Reading

Source: Ethernet Technology Consortium
QSFP-DD Image Courtesy Optomind

Comments Locked

75 Comments

View All Comments

  • mode_13h - Monday, April 13, 2020 - link

    Why are you even talking about that, here? This article has nothing to do with consumer or SOHO networking.

    You've clearly got some issues...
  • Deicidium369 - Wednesday, April 15, 2020 - link

    I have 10Gb/s internet access - direct peer on a fiber provider's access point on my property. Instead of taking the $ for long term lease of a 25'x25' portion of my property (I am sitting on 3000acres), I worked out a deal for bandwidth (had no option other than paying the local cable co over $100K to extend their network to my property edge, and then the privilege of paying them $100/mo for 30Mb/s dn and 5 up) Started out as 1Gb/s about 4 years ago, then moved to a 10Gb/s circuit with 2Gb/s and then later 2.5Gb/s - was at 2.5 for almost 2 years - and 4 or 5 weeks ago they sent a message that the 10Gb/s was fully turned up - honestly even at 2Gb/s it was next to impossible to saturate that link - only large downloads from Microsoft or someone's Google Drive could come close - and 10Gb/s is just a number - even the business can't come close to burning that.
  • Dug - Thursday, April 9, 2020 - link

    I agree with 2.5G for home machines and wish it was widely adopted.
    5G and 10G ethernet is a hit or miss with many different controllers, switches, drivers, power and heat, but especially cables.
    Most homes will have cat5e which works with 2.5G just fine and doesn't require any special equipment or power requirements.
  • Deicidium369 - Wednesday, April 15, 2020 - link

    Problem with the 2.5Gb/s and 5Gb/s - has slowed the adoption of 10Gb/s -

    And no, MOST CAT5e CANNOT support 2.5Gb/s over anything other than a couple meters.
  • Unashamed_unoriginal_username_x86 - Thursday, April 9, 2020 - link

    I agree it's stupid the prices stay up and OEMs act like it's a premium technology, but 99% of consumers just hook it up to internet, and 99% of them don't get above 500Mbps. In Australia, 100Mbps is a premium plan; on fibre!
  • MenhirMike - Thursday, April 9, 2020 - link

    I've just recently done some diving into 2.5 GBit/s, and right now it's just not worth it because of the lack of Switches that support it and the extra cost of transceivers in case of SFP+ switches.

    Plus, 10G cards are relatively cheap now (Less than $100) - still more expensive than 2.5 GBit NICs, but with a e.g., MikroTik CRS305-1G-4S+IN Switch, some Intel X520 NICs, and DAC Cables (If 7m length is enough, otherwise transceivers) you get 10G for a price that isn't completely crazy.

    Also, it's possible to use 10G for a server/nas and support multiple Gigabit clients.
  • Brane2 - Thursday, April 9, 2020 - link

    What's the point?
    used ConnectX2 can get you easily to 40G if you are willing to use SFP DAC cables instead of modules.
    Which also come cheap.
    Only snag is that they can reach only up to 15m. For more than that you need either active cables, which can be more expensive, or a pair of SFP+ modules and a fiber.

    Why f**k around with this slow, overpriced cr*p ?
  • drexnx - Thursday, April 9, 2020 - link

    don't blame the motherboard manufactures, there's no home switch/router infrastructure out there, at all.

    go ahead and price out a standard home router for 4+1 ports on RJ45 >1GbE. Doesn't exist.
  • TheinsanegamerN - Friday, April 10, 2020 - link

    There's no home router support because nothing you buy comes with it. Chicken and egg problem. Given the cost of 2.5GBe hardware is barely higher then 1GBe and uses the same cables theres really no reason most motherboards dont have it built in already. It cant be a hatred of Realtek given how many use Realtek hardware.
  • brucethemoose - Thursday, April 9, 2020 - link

    On top of other comments, ethernet is basically enthusiast only tech now. 99% of consumers are working on wifi... heck, most laptops dont even have an RJ45 port anymore. That 1G connection to the modem won't be a bottleneck for years, and they arent really doing stuff over LAN either.

    There are use cases for businesses, but they mind as well jump to something better than 2.5G at that point.

Log in

Don't have an account? Sign up now