It looks like NVIDIA’s next-generation gaming GPUs will finally catch up to AMD’s in the display connectivity department.
Per the latest rumors from kopite7kimi, NVIDIA GeForce RTX 50 Series graphics cards will supposedly launch with support for DisplayPort 2.1, a new version of the digital display interface standard from VESA that was introduced by the group in October last year.
This is a pretty big deal for NVIDIA users, as the current GeForce RTX 40 Series is limited to DisplayPort 1.4a and HDMI 2.1 display connections, the former of which features slower transmission speeds (25.92 vs. 77.36 Gbps) and a less impressive bit-rate class (HBR3 vs. UHBR) than DisplayPort 2.0 and its derivatives.
DisplayPort 2.1 is also pretty neat because it can do 8K resolution at 60 Hz without the need for Digital Stream Compression (DSC), which, as the name might suggest, could mean a worse picture, although VESA has described it as being “visually lossless.”
AMD’s Radeon RX 7000 Series are notable in that they already include support for DisplayPort 2.1, as the company explained during their launch last November:
The industry’s only high-end gaming graphics cards to support DisplayPort 2.1 technology with UHBR 13.5, offering up to 54Gbps of display link bandwidth and enabling high-refresh 4K (up to 480Hz) or 8K (up to 165Hz) gaming on next-gen displays.
NVIDIA revealed why its GeForce RTX 40 Series GPUs didn’t support DisplayPort 2.0 in a Q&A roundup from September, explaining that the “current DisplayPort 1.4 standard already supports 8K at 60Hz. Support for DisplayPort 2.0 in consumer gaming displays are still a ways away in the future.”
And here’s what VESA had to say about DisplayPort 2.1’s new features during its launch in October 2022:
…DisplayPort 2.1 has tightened its alignment with the USB Type-C specification as well as the USB4 PHY specification to facilitate a common PHY servicing both DisplayPort and USB4. In addition, DisplayPort 2.1 has added a new DisplayPort bandwidth management feature to enable DisplayPort tunneling to coexist with other I/O data traffic more efficiently over the USB4 link. This increased efficiency is on top of mandated support for VESA’s visually lossless Display Stream Compression (DSC) codec and VESA’s Panel Replay capability. DSC bitstream support can reduce DisplayPort transport bandwidth in excess of 67 percent without visual artifacts, while VESA’s Panel Replay capability can reduce DisplayPort tunneling packet transport bandwidth in excess of 99 percent when Panel Replay operation is taking place.
kopite7kimi has also claimed that NVIDIA’s GeForce RTX 50 Series GPUs will be built on TSMC’s 3-nanometer process.
The GeForce RTX 40 Series uses GPUs built on TSMC’s 4N technology, which, despite the name, appears to actually be a 5-nanometer process.
√
— kopite7kimi (@kopite7kimi) November 15, 2023
TSMC3
— kopite7kimi (@kopite7kimi) November 15, 2023