Jacob Roach / Digital Trends
Nvidia CEO Jensen Huang defends the recently launched RTX 4060 Ti, specifically its 8GB of VRAM. The CEO talked about gaming and recent GPU releases in a roundtable interview with reporters at Computex 2023, where he faced questions about the limited VRAM on Nvidia’s latest GPU.
PCWorld shared a quote in which Huang defended the 8GB of VRAM and told gamers to focus more on managing that VRAM: “Remember that the framebuffer isn’t computer memory — it’s a cache. And how you manage the cache is a big deal. It’s like any other cache. And yes, the bigger the cache, the better. However, you trade with so many things.”
The RTX 4060 Ti has faced a lot of criticism for its 8GB of VRAM, especially as video memory requirements have increased in recent PC releases such as Resident Evil 4, Hogwarts Legacy, and The last of us part one. Huang’s answer seems defensive, but it doesn’t really address the VRAM issues in the RTX 4060 Ti.
As Huang says, VRAM is essentially a cache. Data is moved from your storage to your system memory and finally to VRAM. The problem is that the output to system memory is extremely slow, which is a big reason why we’ve seen major issues with freezing and crashing in games like The last of us part one and The legacy of Hogwarts. Huang says managing VRAM is like “kung fu,” and while that might be true in theory, we’ve seen the management fail in practice.
Huang also did not say what exactly gamers also trade in higher VRAM capacity. Maybe power, maybe price, or maybe some combination of several different factors; it’s hard to say. However, Nvidia seems to recognize that capacity is an issue and is releasing a variant of the RTX 4060 Ti with 16GB of VRAM in July. It’s the same GPU with the same performance, just with more VRAM and priced $100 more than the base model.
Nvidia
After its Computex keynote, Nvidia became the first chip designer ever to reach a valuation of over $1 trillion, joining only five other companies currently at that level. However, it rang hollow for many gamers, as Nvidia mostly focused on artificial intelligence during its keynote, aside from the new Nvidia ACE engine for generative AI in games.
In response to PCWorld, Huang said that gamers are still Nvidia’s top priority. “Without artificial intelligence, we wouldn’t be able to do real-time ray tracing. That was not even possible,” said Huang. “And the first AI project in our company — the number one focus on AI was Deep Learning Super Sampling (DLSS). Deep learning. That’s the pillar of RTX.”
However, it is only fair that players feel neglected. Nvidia’s last generation pushed GPU prices higher than they’ve ever been, and in Nvidia’s latest earnings call, its data center and artificial intelligence revenue was double what it made from gaming. Additionally, Nvidia’s public presentations have increasingly focused on AI, with supercomputers like the DGX GH200 taking center stage.
Editor’s recommendations
Categories: GAMING
Source: newstars.edu.vn