Top Qs
Timeline
Chat
Perspective
12VHPWR
Standard for connecting GPUs to power supplies From Wikipedia, the free encyclopedia
Remove ads
The 16-pin 12VHPWR connector is a standard for connecting graphics processing units (GPUs) to computer power supplies for up to 600 W power delivery. It was introduced by Nvidia in 2022 to supersede the previous 6- and 8-pin power connectors for GPUs. The stated aim was to cater to the increasing power requirements of Nvidia GPUs. The connector was formally adopted as part of PCI Express 5.[1]
.jpg)
The connector was replaced by a minor revision called 12V-2x6 (H++), introduced in 2023,[2][3] which changed the GPU- and PSU-side sockets to ensure that the sense pins only make contact if the power pins are seated properly. The cables and their plugs remained unchanged.[4]
Remove ads
Overview
The connector first appeared in the Nvidia RTX 40 GPUs.[5][6] The prior Nvidia RTX 30 series introduced a similar, proprietary connector in the "Founder's Edition" cards, which also uses an arrangement of twelve pins for power, but did not have the sense pins, except for the connector on the founders edition RTX 3090 Ti (though not present on the adapter supplied with those cards.)[7]
The 16-pin 12VHPWR connector, where HPWR stands for "High Power," supports higher power delivery to GPUs, up to 600 watts, a significant increase from the 150 watts of the 8-pin connector and the 75 watts of the 6-pin connector.[8][9]
Adapters converting multiple 8-pin to a single 16-pin connector are available.[10]
The 16-pin connector comprises twelve power pins arranged in two parallel rows, and four auxiliary sense pins that communicate the maximum allowable power draw.[8]
Remove ads
Reliability and design changes
Summarize
Perspective
Nvidia RTX 4090
Some buyers of the Nvidia RTX 4090, the first GPU to use the new connector, reported that the connectors of their RTX 4090 were melting,[11] which sparked several theories to explain it. After investigation, several sources reported that the main cause was the 12VHPWR connector not being fully seated while being put under load that resulted in overheating of the connector's pins, which in turn caused the melting of the plastic housing.[12][8]
PCI-SIG, the standards organization responsible for the creation of the 12VHPWR connector, has decided to make changes to the connector's specifications following the failures.[13]
A class-action lawsuit has been filed against Nvidia over melting 12VHPWR cables which the lawsuit states is "a dangerous product that should not have been sold in its current state."[14] The plaintiff who brought the suit claims that Nvidia unjustly enriched itself, violated the product's warranty and engaged in fraud and they are demanding that Nvidia pay damages to affected customers as compensation.[15] However, this lawsuit was voluntarily dismissed with prejudice by the plaintiff on March 10, 2023. No reason is provided as to why the case was dismissed.[16]
Following its own investigation and testing, Nvidia officially offered a statement on the melting connectors. They determined that the melting connectors are caused by user error from not inserting the 12VHPWR connector properly, causing partial contact. They have offered an expedited RMA process for any RTX 4090 affected by the melting connectors.[17][18][19] PCI-SIG later said in a statement that Nvidia and their partners were still responsible for testing their products to account for user error.[20]
Despite these claims of user error, a revised connector design intended to address these issues was introduced under the new name 12V-2x6.[21]
In February 2024, the U.S. Consumer Product Safety Commission announced a voluntary recall of 12VHPWR adapters made by Cablemod. According to the recall filing, 272 reports were filed with about 25,300 units shipped. The recall covers adapters using both the initial and the revised 12V-2x6 (CEM 5.1) design.[22]
It was also reported that the new connectors have a limited lifespan of around 30–40 mating cycles before contact potentially becoming unreliable.[23]
It has been noted that the older 6- and 8-pin connectors had substantially larger manufacturer-specified current-carrying capacity in relation to the power limits specified by PCI SIG:[24][8]
- Notes
Nvidia RTX 5090
The 12VHPWR has come under criticism again after the release of the GeForce RTX 50 series due to the cable melting in the high end RTX 5090 graphics card. These flaws are currently only confirmed on the RTX 5090 FE, but the removal of shunt resistors means the new re-design of the Nvidia cards exposes all cards to this flaw. Asus cards and some other brands add additional shunt resistors to detect potential overheating and warn the user, but without the ability to dynamically current balance and prevent overheating.[28]
Analysis of hardware design of the flagship Nvidia GPUs of the last few generations showed a crucial change. The earlier GPU models with 6- or 8-pin power connectors usually had a separate current sensor per each connector. It allowed the GPU to monitor whether the load is distributed evenly among the connectors. The Nvidia RTX 30 series achieved the same by splitting the six 12V pins of the 12VHPWR connector into three groups and also monitor them independently. Starting from the Nvidia RTX 40 series, all the 12V pins of the 12VHPWR connector are internally tied together, so the GPU does not know whether all the pins are making good contact. In this case, it is possible that the GPU may try to sink a lot of current through as little as a single pin, which would lead to excessive heat dissipation and melted connectors and wires as the result.[29] The same issue has also been spotted on the Sapphire Radeon RX 9070 XT Nitro+.[30][31]
Remove ads
See also
References
Wikiwand - on
Seamless Wikipedia browsing. On steroids.
Remove ads