NVIDIA Issues Statement On RTX 5080 And 5070 As More ROPs Go Missing
It's official—following the first user report of a GeForce RTX 5080 Founders Edition graphics card to display missing render operation pipeline (ROP) hardware in the popular GPU-Z utility, NVIDIA has confirmed that it too is affected by a rare "production anomaly" affecting half a percent (0.5%) of all GeForce RTX 50 series cards. The confirmation came after NVIDIA originally stated that only the GeForce RTX 5090 / 5090D and GeForce RTX 5070 Ti were affected.
NVIDIA's original statement following reports of missing ROPs made no mention of the GeForce RTX 5080 or the upcoming GeForce RTX 5070 (non-Ti variant). According to NVIDIA, affected models have one fewer ROP than they're supposed to have, which gets identified as eight missing ROPs in GPU-Z due to how they operate (each ROP can generate eight pixels per clock cycle).
The company also said that the average impact on graphics performance for the missing ROP is 4%, with AI and compute workloads unaffected. In other words, it's a largely an annoyance with gaming. Now in an updated statement provided to TechPowerUp, which originally reported seeing GPUs with missing ROPs, NVIDIA confirmed it found the same production anomaly exists on GeForce RTX 5080 models as well.
"Upon further investigation, we’ve identified that an early production build of GeForce RTX 5080 GPUs were also affected by the same issue. Affected consumers can contact the board manufacturer for a replacement," NVIDIA's GeForce global PR director, Ben Berraondo, told the site.
What about the upcoming GeForce RTX 5070 (non-Ti)? When asked by The Verge, Berraondo went on record saying "no other NVIDIA GPUs have been affected," including the GeForce RTX 5070 or any cards that are part of a more recent production run. He also told the site that NVIDIA was unaware of the missing ROPs issue prior to launch.
Taking into account recent developments, NVIDIA has amended its original statement.
"We have identified a rare issue affecting less than 0.5% (half a percent) of GeForce RTX 5090 / 5090D, RTX 5080, and 5070 Ti GPUs which have one fewer ROP than specified. The average graphical performance impact is 4%, with no impact on AI and Compute workloads. Affected consumers can contact the board manufacturer for a replacement. The production anomaly has been corrected," Berraondo said.
It's a wonky situation to say the least, and it's curious how a hardware defect like this could go unnoticed before launch. Multiple checks in the validation process should have caught something like this, though we suppose if the real number really is less than half a percent of cards, it could be a little more difficult to detect.
The other challenge for NVIDIA is that this isn't the only issue affecting its GeForce RTX 50 series launch. Complaints of melting connectors, not enough supply to meet demand, and partner pricing rising hundreds of dollars above NVIDIA's baseline MSRPs have all dampened a much-anticipated launch.
Hopefully most, if not all of these issues will be corrected in time.
