Skip to main content

Why Nvidia’s brand new GPU performs worse than integrated graphics

Four Nvidia H100 HPC GPUs side by side.
Geekerwan

One might think that a GPU that costs over $40,000 is going to be the best graphics card for gaming, but the truth is a lot more complex than that. In fact, this Nvidia GPU can’t even keep up with integrated graphics solutions.

Now, before you get too upset, you should know I’m referring to Nvidia’s H100, which houses the GH100 chip (Grace Hopper). It’s a powerful data center GPU made to handle high-performance computing (HPC) tasks — not power PC games. It doesn’t have any display outputs, and despite its extensive capabilities, it also doesn’t have any coolers. This is because, again, you’d find this GPU in a data center or server setting, where it’d be cooled with powerful external fans.

While it “only” has 14,592 CUDA cores (which is fewer than the RTX 4090), it also has an insane amount of VRAM and a massive bus. In total, the GPU sports 80GB of HBM2e memory, split into five HBM stacks, each connected to a 1024-bit bus. Unlike Nvidia’s consumer GPUs, this card also still has NVLink, which means it can be connected to work seamlessly in multi-GPU systems.

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

The question remains: Why exactly is this type of GPU quite so bad at general usage and games?

To demonstrate the case, YouTuber Gamerwan was given four of these H100 graphics cards to test, and decided to put one in a regular Windows system to check out its performance. This was a PCIe 5.0 model, and it had to be paired with an RTX 4090 due to the lack of display outputs. Gamerwan also 3D-printed a custom-designed external cooler to keep the GPU running smoothly.

It takes a bit of work to even get the system to recognize the H100 as a proper GPU, but once Gamerwan managed to overcome the obstacles, he was also able to turn on ray tracing support. However, as we later find throughout the testing, there’s not much support for anything else on a non-data center platform.

In a standard 3DMark Time Spy test, the GPU only hit 2,681 points. For comparison, the average score for the RTX 4090 is 30,353 points. This score puts the H100 somewhere between the consumer GTX 1050 and GTX 1060. More importantly, it’s almost the same as AMD’s Radeon 680M, which is an integrated GPU.

The gaming tests also went poorly, with the graphics card hitting an average of 8 frames per second (fps) in Red Dead Redemption 2. The lack of software support rears its ugly head here — although the H100 can run at a maximum of 350 watts, the system can’t seem to push it past 100W, resulting in hugely throttled performance.

Comparison between the architecture of H100 and AD102 GPUs.
Gamerwan

There are a few different reasons for this poor show of gaming powers. For one, althoughrthe H100 is an ultra-strong graphics card on paper, it’s much different on an architectural level than the AD102 GPU that powers the RTX 4090. It only has 24 raster operating units (ROPs), which is a significant downgrade from the 160 ROPs that the RTX 4090 has. In addition, only four out of 112 texture processing clusters (TPC) can render graphics workloads.

Nvidia’s consumer GPUs receive a lot of support on the software side in order to run well. This includes drivers, but also system support from developers — both in games and in benchmark programs. There are no drivers that optimize the performance of this GPU for gameplay, and the result is, as you can see, extremely poor.

We’ve already seen the power of drivers with Intel Arc, where the hardware has remained the same, but improved driver support delivered performance gains that made Arc an acceptable choice if you’re buying a budget GPU. With no Nvidia Game Ready drivers and a lack of access to the rest of Nvidia’s software stack (including the ever-impressive DLSS 3), the H100 is a $40,000 GPU that has no business running any sort of game.

In essence, this is a computing GPU, and not a graphics card in the same way that most of us know them. It was made for all kinds of HPC tasks, with a strong focus on AI workloads. Nvidia maintains a strong lead over AMD where AI is concerned, and cards like the H100 play a big part in that.

Editors' Recommendations

Monica J. White
Monica is a UK-based freelance writer and self-proclaimed geek. A firm believer in the "PC building is just like expensive…
Why I’m feeling hopeful about Nvidia’s RTX 50-series GPUs
The RTX 4070 Super on a pink background.

I won't lie -- I was pretty scared of Nvidia's RTX 50-series, and I stand by the opinion that those fears were valid. They didn't come out of thin air; they were fueled by Nvidia's approach to GPU pricing and value for the money.

However, the RTX 40 Super refresh is a step in the right direction, and it's one I never expected to happen. Nvidia's most recent choices show that it may have learned an important lesson, and that's good news for future generations of graphics cards.
The price of performance
Nvidia really didn't hold back in the RTX 40 series. It introduced some of the best graphics cards we've seen in a while, but raw performance isn't the only thing to consider when estimating the value of a GPU. The price is the second major factor and weighing it against performance can often tip the scales from "great" to "disappointing." That was the case with several GPUs in the Ada generation.

Read more
CableMod’s adapters damaged up to $74K worth of Nvidia GPUs
Melted 12VHPWR connector made by CableMod for the RTX 4090.

CableMod's adapters were meant to fix the problem of melting connectors on Nvidia's top GPU, the RTX 4090, but it appears that things didn't go as planned. The Consumer Product Safety Commission has posted a notice that the CableMod 12VHPWR angled adapters are being recalled due to fire and burn hazards. More than 25,300 adapters are to be returned, and the affected customers are eligible for a full refund.

The connectors on the RTX 4090 have been melting ever since the GPU hit the shelves in late 2022, and so far, the only fix seems to lie in careful installation and picking the right PC case that can accommodate this monstrous card. CableMod's angled adapters showed a lot of promise, at least initially. Seeing as bending the cable can contribute to the overheating, an angled adapter should have been just the fix -- but unfortunately, the melting continued, even with the use of CableMod's solution.

Read more
The Nvidia RTX 4080 Super just trounced AMD
The Nvidia RTX 4080 Super on a pink background.

Whether you pick the RTX 4080 Super or the RX 7900 XTX, you're getting a powerful GPU that's capable of seamless gaming at 4K. But which one is better for the money? There used to be a clear answer to that question when we were only dealing with the RTX 4080, but the release of its Super successor made it a lot less straightforward.

Both the RTX 4080 Super and the RX 7900 XTX are among the best graphics cards that money can buy. While they're close in performance, they're not exactly the same, and the scales might now be tipping in an unexpected direction.
Pricing and availability

Read more