Skip to main content

AMD’s next superefficient GPUs could have Nvidia worried

Given the performance upgrades we’ve seen in recent years in regard to graphics cards, the battle between AMD and Nvidia’s upcoming next-gen GPUs is shaping up to be one of the most exciting times in tech in recent memory.

Lending credence to that theory is a new rumor outlining the technical differences between Team Red’s RTX 7000 cards and Nvidia’s RTX 4000-series.

An AMD RX 6500 XT with other graphics cards stacked up in the background.
Jacob Roach / Digital Trends

Efficiency and performance powerhouse?

Moore’s Law Is Dead, a technology YouTuber known for his insider information, revealed some interesting details regarding AMD and Nvidia’s next-gen plans in his video The Road to RDNA 3 & Lovelace.

Recommended Videos

The first segment of the video, titled The RDNA 3 lineup is unlike anything you’ve seen, suggests AMD “should just completely blow Lovelace out of the water when it comes to efficiency.” As a result, he speculates AMD’s upcoming video cards could even ultimately outperform Nvidia’s Ada series when it comes to overall performance.

Get your weekly teardown of the tech behind PC gaming
Check your inbox!

To that end, Moore’s Law Is Dead further adds that RDNA 2 versus Ampere (the architectures the current-gen AMD and Nvidia GPUs are based on, respectively) saw AMD offering generally more efficient products compared to its rival’s offerings. However, in the case of RDNA 3 versus Lovelace, he stresses that Nvidia is facing a “real, true efficiency problem coming up” in a way it hasn’t experienced before.

Elsewhere, he mentions that the technology community could be overestimating Lovelace’s performance expectations. Although he admits the Nvidia RTX 40-series will offer a huge performance increase, one that is markedly larger than Ampere over Turing, Moore’s Law Is Dead reiterates the initial target of a 66% to 80% increase, as opposed to other estimates that indicate an even higher jump.

With this in mind, Moore’s Law Is Dead’s sources suggest that the estimates for AMD’s RDNA 3 performance upgrade is apparently higher than the expectations for Nvidia’s Lovelace.

More to the story?

While we always stress to not take rumors as fact, there may be some truth behind these claims. And this is where things start to get interesting: As reported by Wccftech, a leaked LinkedIn description deriving from an AMD principal member of technical staff appears to confirm that the RX 7000 series is based on RDNA 3, with a certain model utilizing two separate processes (TSMC 5nm and 6nm). Wccftech points out that this could indicate AMD is adopting a multi-chip module (MCM) approach for its future GPUs.

Wccftech also highlights how AMD has reinvigorated the CPU market and given Intel a run for its money via its MCM Ryzen processors. Should the LinkedIn description prove to be real, and AMD is indeed integrating an MCM design for its GPUs as well, then it could very well edge out Nvidia’s Lovelace boards, at least in regard to power efficiency.

The battle of next-gen

An Nvidia GeForce RTX graphics card inside the Maingear Vybe.
Jacob Roach / Digital Trends

As for which next-gen GPUs will beat the other in terms of launch periods, Moore’s Law Is Dead reiterates the general consensus that Ada Lovelace (RTX 4000-series) is scheduled for a third-quarter release, while AMD is likely to introduce its RTX 7000 video cards a few months later during the fourth quarter.

Corroborating these claims when it comes to Team Green’s next-gen GPU road map is the fact that we’ve already heard that the RTX 4090 is on track to hit store shelves in September. Moore’s Law Is Dead has also heard from sources that Ada is “for the most part ready in its design now, but they’re not quite ready with the drivers and the segmentation to get it out there.”

Why the gap between the launch periods for both next-gen GPUs? Moore’s Law Is Dead stresses that RDNA 3 is “a more complex design, really a more ambitious design.”

Theoretically, those extra few months could therefore be enough to allow AMD to take the “efficiency and performance crown,” which is why the company “knows that this launch needs to be perfect.”

Before the battle of next-gen GPUs comes to fruition later in the year, we’ll see a taste of things to come in the form of Nvidia’s new flagship RTX 3090 Ti board going up against AMD’s Radeon RX 6950XT.

Nvidia may have edged out its main rival in 2021, but if the aforementioned video is anything to go by, AMD is adamant in its intention to make sure history doesn’t repeat itself moving forward.

Ultimately, regardless of whoever comes out on top, competition between these two technology titans makes one thing certain: Before the arrival of 2023, the GPU market will usher in the most advanced graphics card we’ve seen yet.

Zak Islam
Former Digital Trends Contributor
Zak Islam was a freelance writer at Digital Trends covering the latest news in the technology world, particularly the…
Your next gaming PC could be fully built by Nvidia
Nvidia's A100 data center GPU.

Nvidia might be at the heart of your next gaming PC, not just through a graphics card, but also through your processor. Team Green is working on an Arm-based PC platform that's built around a CPU and GPU designed by Nvidia and that is reportedly set to launch in September 2025, according to DigiTimes.

According to the report, Nvidia is planning on launching a high-end computing platform based on Arm instructions in September, with a commercial launch following in March 2026. This is the first we're hearing about a timeline for Arm-based chips designed by Nvidia, but it's not the first time we're hearing about it. About a year ago, Reuters reported that Nvidia began looking into Arm-based CPUs as "part of Microsoft's effort to help chip companies build Arm-based processors for Windows PCs."

Read more
AMD could swipe some of the best features of Nvidia GPUs
AMD logo on the RX 7800 XT graphics card.

Nvidia overwhelmingly dominates the list of the best graphics cards, and that largely comes down to its feature set that's been enabled through DLSS. AMD isn't sitting idly by, however. The company is researching new ways to leverage neural networks to enable real-time path tracing on AMD graphics cards -- something that, up to this point, has only really been possible on Nvidia GPUs.

AMD addressed the research in a blog post on GPUOpen, saying that the goal is "moving towards real-time path tracing on RDNA GPUs." Nvidia already uses AI accelerators on RTX graphics cards to upscale an image via DLSS, but AMD is focused on a slightly different angle of performance gains -- denoising.

Read more
AMD may completely dominate CES 2025
AMD presenting its new Turin CPUs.

AMD might really go all-out during CES 2025 this January. According to a known leaker on the Chiphell forums, AMD is readying a slew of consumer products, ranging from more X3D desktop CPUs to handheld chips and RDNA 4 graphics cards. Here's what we have to look forward to.

The tantalizing bit of gossip comes from Zhangzhonghao, a leaker who's been known to discuss new releases ahead of time. Starting with laptops, AMD is reportedly set to release next-gen Kraken (or "Krackan" as referred to by this leaker) Point APUs alongside Ryzen AI Max (or Strix Halo) and, lastly, Fire Range CPUs.

Read more