PCIe 6.0 Spec Release Date on Track, Version 0.5 Announced

Tom's Hardware | Feb. 21, 2020, 5:26 a.m. | Original

(Image credit: Shutterstock)

Although AMD has already implemented PCIe 4.0 across a range of mainstream products with its Ryzen 3000-series processors and latest graphics cards, Intel is still stuck on PCIe 3.0, having canceled its plans for PCIe 4.0 on Comet Lake . Meanwhile, PCI-SIG, which makes the PCIe specifications, announced version 0.5 of the upcoming PCIe 6.0 spec today, which features eight times the bandwidth of PCIe 3.0.

Even though we've yet to see products supporting PCIe 5.0, PCI-SIG first announced it'd be introducing a PCIe 6.0 spec in October . The spec's jump in bandwidth is no surprise, as each new generation of PCIe doubles the bandwidth of the previous. Where PCIe 3.0 has a bandwidth of 8 GTps per lane, PCIe 4.0 doubles that figure to 16 GTps, and PCIe 5.0 jumps to 32 GTps. Logically, PCIe 6.0 makes the jump to an impressive 64 GTps per lane.

(Image credit: PCI-SIG)

Those figures translate to about 8 GBps per lane of PCIe 6.0, which for a 16-lane slot would equate to nearly 128 GBps per slot. Consequently, it wouldn't come as a surprise if the eventual arrival of PCIe 6.0 devices meant the days of full-length PCIe slots were numbered. The first sign of this was AMD's Radeon RX 5500 XT graphics card, which only needs 8 lanes thanks to PCIe 4.0 support.

These figures are achieved by encoding with Pulse Amplitude Modulation with 4 levels (PAM-4). The specification also features low-latency Forward Error Correction (FEC) and will be compatible with all previous versions of PCIe.

According to PCI-SIG. the PCIe 6.0 spec is on track for delivery in 2021. That doesn't mean we'll be seeing products with it in 2021 though; it only means that hardware vendors will start developing supporting products.

The biggest areas that will benefit from faster PCIe, at least initially, are high-computing platforms, such as artificial intelligence and machine learning. It will likely take significantly longer before individual consumers start leveraging the increase in bandwidth.

PCI-SIG will share more details at its upcoming Developers Conference on June 3 and 4.

4 Comments Comment from the forums
  • TechLurker 21 February 2020 18:54
    Given that AMD and Intel both mentioned plans to jump to PCIe 5.0 in 2021 onwards, I wonder if they will stay with PCIe 5.0 or jump to 6.0 another year or two later.

    While it makes sense to futureproof hardware, I wonder if it's more convenient to just have their CPUs "PCIe 6.0 ready" but on motherboards, split the bandwidth across more PCIe 5.0 or even PCIe 4.0 lanes. Bringing back the age of having up to 7 x16-sized slots on XL-ATX motherboards or more staggered 4 x16-sized slot motherboards (like the TRX40 Aorus Extreme; requiring 8-9 slots) and NVMe drives between the slots.

    For one, I recall that PCIe 4.0 is already expensive due to needing to add whatever signal repeater chips are necessary to get full slot coverage, which was something that limited full PCIe 4.0 to X570 and TRX40 motherboards while B550A and B550s will supposedly only have the first M.2 and PCIe x16 slot at 4.0.

    For another, while AMD has ignited a fire under makers of PCIe-based add-on cards to innovate for PCIe 4.0, it's still going to be a long time before any can really make full use of that bandwidth, so downgrading CPU-based PCIe 5.0 or 6.0 to 4.0 but adding more slots seems like a reasonable middle ground.
    Reply
  • bit_user 22 February 2020 01:05
    TechLurker said:
    I wonder if it's more convenient to just have their CPUs "PCIe 6.0 ready" but on motherboards, split the bandwidth across more PCIe 5.0 or even PCIe 4.0 lanes.
    If they continue having a separate I/O die, then desktop CPUs won't just inherit PCIe 5.0+ "for free".

    As you rightly point out, faster interconnect speeds is a costly proposition. I don't see it coming to desktops, though it'd be interesting if they upgraded the CPU <-> chipset with a PCIe 5.0 or PCIe 6.0 link. As you point out, that could enable more/wider/faster chipset-connected slots.
    Reply
  • srimasis 22 February 2020 02:17
    So is it possible to have proper SLI or Crossfire with pcie 6.0 without any bridge since GDDR6 bandwidth is 72 GBps and pcie 6.0 bandwidth is 128 GBps. I hope to see proper dual gpu compatibility like having two 8gb GPUs combination would act as one 16gb GPU.
    Reply
  • InvalidError 22 February 2020 06:51
    srimasis said:
    So is it possible to have proper SLI or Crossfire with pcie 6.0 without any bridge since GDDR6 bandwidth is 72 GBps and pcie 6.0 bandwidth is 128 GBps.
    72GB/s for GDDR6? For a RX5700XT that's 16GT/s x 256bits = 512GB/s.

    Even if mainstream CPUs got PCIe6, it would still be split x8x8 so you lose half the bandwidth there. Then you also lose performance to the GPU-bus-host-bus-GPU-bus-host-GPU roundtrip and other overheads inherent to accessing remote memory pools.

    If you want to make multiple GPUs behave like a single larger one, you'll need even more bandwidth and lower latency than that to account for all of the other internal processes that require bandwidth too but never have to leave the die in single-GPU setups.
    Reply
EK-Loop Connect Lets You Control Your RGB, Fan, Pump and Sensors With One Device Logitech G332 SE Deal Lets You Ditch Your Old Gaming Headset for $25