Tuesday, September 24th 2024
NVIDIA RTX 5090 "Blackwell" Could Feature Two 16-pin Power Connectors
NVIDIA CEO Jensen Huang never misses an opportunity to remind us that Moore's Law is cooked, and that future generations of logic hardware will only get larger and hotter, or hungrier for power. NVIDIA's next generation "Blackwell" graphics architecture promises to bring certain architecture-level performance/Watt improvements, coupled with the node-level performance/Watt improvements from the switch to the TSMC 4NP (4 nm-class) node. Even so, the GeForce RTX 5090, or the part that succeeds the current RTX 4090, will be a power hungry GPU, with rumors suggesting the need for two 16-pin power inputs.
TweakTown reports that the RTX 5090 could come with two 16-pin power connectors, which should give the card the theoretical ability to pull 1200 W (continuous). This doesn't mean that the GPU's total graphics power (TGP) is 1200 W, but a number close to or greater than 600 W, which calls for two of these connectors. Even if the TGP is exactly 600 W, NVIDIA would want to deploy two inputs, to spread the load among two connectors, and improve physical resilience of the connector. It's likely that both connectors will have 600 W input capability, so end-users don't mix up connectors should one of them be 600 W and the other keyed to 150 W or 300 W.Above is a quick Photoshop job by TweakTown of how such a card could look like. The requirement of two 16-pin connectors should rule out older PSU types, and NVIDIA will likely only include one adapter that converts two or three 8-pin PCIe power connectors to a 16-pin, with the other input expected to be a native 600 W input from an ATX 3.0 or ATX 3.1 PSU. Most of the newer generation ATX 3.0 or ATX 3.1 PSUs in the market only have one native 16-pin connector, and three or four additional 8-pin PCIe power connectors. As for the connector itself, this could very likely be a 12V-2x6 with compatibility for 12VHPWR.
Some PSU manufacturers are beginning to release high-Wattage models with two native 12V-2x6 connectors. These would typically have a Wattage of over 1300 W. The Seasonic Prime PX-2200 W, released earlier this week, is an extreme example of this trend. Besides its high Wattage, this PSU puts out as many as four 12V-2x6 connectors. Another recent example would be the MSI MEG AI1600T PCIE5 (1600 W), with two native 600 W 12V-2x6.
Source:
TweakTown
TweakTown reports that the RTX 5090 could come with two 16-pin power connectors, which should give the card the theoretical ability to pull 1200 W (continuous). This doesn't mean that the GPU's total graphics power (TGP) is 1200 W, but a number close to or greater than 600 W, which calls for two of these connectors. Even if the TGP is exactly 600 W, NVIDIA would want to deploy two inputs, to spread the load among two connectors, and improve physical resilience of the connector. It's likely that both connectors will have 600 W input capability, so end-users don't mix up connectors should one of them be 600 W and the other keyed to 150 W or 300 W.Above is a quick Photoshop job by TweakTown of how such a card could look like. The requirement of two 16-pin connectors should rule out older PSU types, and NVIDIA will likely only include one adapter that converts two or three 8-pin PCIe power connectors to a 16-pin, with the other input expected to be a native 600 W input from an ATX 3.0 or ATX 3.1 PSU. Most of the newer generation ATX 3.0 or ATX 3.1 PSUs in the market only have one native 16-pin connector, and three or four additional 8-pin PCIe power connectors. As for the connector itself, this could very likely be a 12V-2x6 with compatibility for 12VHPWR.
Some PSU manufacturers are beginning to release high-Wattage models with two native 12V-2x6 connectors. These would typically have a Wattage of over 1300 W. The Seasonic Prime PX-2200 W, released earlier this week, is an extreme example of this trend. Besides its high Wattage, this PSU puts out as many as four 12V-2x6 connectors. Another recent example would be the MSI MEG AI1600T PCIE5 (1600 W), with two native 600 W 12V-2x6.
109 Comments on NVIDIA RTX 5090 "Blackwell" Could Feature Two 16-pin Power Connectors
Because using PCIe riser cables have been nothing but problems for many people, often requiring them to choose lower PCIe gen level ("You only loose a couple percent of performance")?
As well as it is your problem of higher confidence in reliability of your cheap PSU over the reliability of the power section of your GPU card.
RTX 3090 was also able to be powered by 650-700W PSU, but then a power draw spike happens and the whole card shuts down for a moment. That's why they recommended high class 850W PSUs and even higher.
Jokes aside, it was inevitable, but I don't think it would happen so soon if Nvidia didn't aim for a massive AI accelerator card. This has very little to do with gaming, perhaps the architecture won't even be optimised for rasterized output that most games still use - and reviewers will be "encouraged" to talk almost exclusively about performance increase in RTX, AI assisted DLSS etc ..
And I dont see reasons why they couldnt be designed and offered as consumers grade accelerators.
If 800W hair dryer can be labeled as a consumer product so why not PC add on card ?
edit
Also keep in mind present EUV scanners will be cheaper over the course of time and installed and used scanners will be even cheaper than.
As a result we will have access to literally tons of consumer grade power hungry silicon way cheaper than can be offered now.
Similiar things happened in PV industry over the course of last 20 years.
If anything now with this i believe there are going to be overclocking competitions to see who can achieve the highest GPU power usage lol.
But i see mentioning such obvious things for designers is a futile effort in your case. Mechanical constraints related to mass mounting position and amount of heat dissipated is a one part but electricals constaints are separate part.
Using more connectors is a simple solution but dumbest one. Especially if coupled with really expensive card.
So going up to higher voltage is the right direction but it means small revolution along power supply path.
But industry is conservative and dont like revolutions until last minute.
edit
There are also marketing constraints too - more connectors means the card looks beefier so the price could be higher. But aware users will know it is pathological solution after all which will be obsolete relatively soon.
Also Just think that's 1200 watts for a video card that needs software of DLSS 4.0 to render video games from a low res to a high res. Still waiting for a NON AI software Pure hardware card.
As the only option in high-end, the bet will be: Can we release a >600W >2000€ gaming-card and people will still buy it? Well... technically we have 3*230VAC. If you connect a load between two of those lines, you get 400V over that load.
"Nvidia today announced the 9090, you're basically buying a self sufficient house for your GPU, and you live next to it under a cardboard box. It also charges your car when idling"
BTW I'm living in my home almost half century old and have all 3 AC phases in my garage. But in inhabitated part of my home I have access to 230V AC fused by 10A or 16A internal fuse and 25A fuse outdoor.
We are not used to using clothes dryers but we definitely have some spare of power for using in near future for different purposes.
So frankly speaking it is not sound good if you are admitting - average Joe in leading world economy is limited to 1800 W in his/her flat.