Partner Nintendo 3DS Central Social

NVIDIA's RTX 4000 Series

cm2

cm2

Well-Known Member
Full GL Member
20,796
2018
1,639
Awards
25
Credits
157
Nintendo $20 EShop
Nintendo $20 EShop
Mature Board Viewing
PSN Gift Card $20
PSN Gift Card $20
Read from Hardwaretimes:

NVIDIA’s next-gen GeForce RTX 4080/4090 GPUs are now being tested and evaluated, indicating that early engineering/production samples have already reached Santa Clara. According to the source (below), the AD102 GPU core is now being tested internally for early performance and specification targets. This means that we should soon start seeing leaks and benchmarks of these engineering samples, giving us a first glance at NVIDIA’s upcoming graphics architecture.

The GeForce RTX 4090 is going to come with 24GB of 24Gbps GDDR6X memory paired with 96MB of L2 cache across a 384-bit bus. The RTX 4080 is expected to feature 12 or 16GB of GDDR6X memory across a 320-bit bus and 80-88MB of L2 cache. This GPU will feature around 14,000 FP32 cores, a slight cut from the 15-16K shaders on the RTX 4090, and a total of 18,432 on the AD102 die. As for the RTX 4070, we’re looking at 12 or 16GB of GDDR6 memory across a 256-bit bus. It will be based on the AD104-400 die and pack up to 10,000 FP32 cores. Finally, the RTX 4070, 4080, and 4090 will have a TGP of 400W, 500W, and 600W, respectively.
 
Read more from spearblade :

RTX 4090 and RTX 4080 will both be rocking the flagship AD102 die. The AD102 cards can be compared to the GA102 cards – the most powerful video card architecture right now. GA102 cards include RTX 3080 and 3090, RTX A6000, and A40 (data center GPU).

Key features of the GA102 architecture such as high FP32 processing, second-generation RT cores, third-generation Tensor cores, third-generation NVLink, and PCIe Gen 4 might become a thing of the past with the release of the AD102. The only thing that will remain relevant is the GDDR6X memory – as Lovelace is going to be using the same memory type as Ampere.

TechPowerUp has a detailed overview of the AD102 architecture. The die size is 600 sq. mm. which is large but smaller than GA102 (628 sq. mm.). The chip will also support (like GA102) DirectX 12 Ultimate (12_2), OpenCL 3.0, OpenGL 4.6, Vulkan 1.2, Shader Model 6.6, and PureVideo HD VP12. It will support CUDA 9.0 (vs. RTX 3090 that supports up until 8.6).

Compared to the GA102, the AD102 will have:
  • 7,680 more CUDA cores (10752 vs. 18432)
  • 30+ more teraflops (35.6 vs. 66) – doubtful, as other leaks suggest 90+ tflops
  • 60 more RT cores (84 vs. 144)
  • 5 more graphics processing clusters (7 vs. 12)
  • 30 more texture processing clusters (42 vs. 72)
  • 90MB more L2 cache (6MB vs. 96MB)
L2 cache is surely a monstrous jump. Nvidia is about to give all 40 series cards a beefy L2 cache. This means that the lower-end ones will get 32MB of it. In comparison, RTX 3060 right now only has 3MB of it. The RTX 4060, in effect, will have more L2 cache than RTX 3090 (6MB).

All this will demand significantly more power, of course. We are looking at a TDP of 450-600W for the RTX 4090. More on that in the power consumption section.

Of course, with higher specs and performance come higher thermals. Unless you want to invest heavily in liquid nitrogen or a submerged build, a quad-slot cooling solution such as the AORUS RTX 3090 Xtreme is likely the only option.
 
NVIDIA'S RTX 4000 looks like a very fast videocard for PC Gaming in 4K video resolution, and at high frame rates.
 
Got some inside footage of the testing process here. Haters will say it's fake.

 
Seeing specs like these makes me wonder if I should encourage my husband to upgrade our gaming PC ...but when we replace one thing it usually means we have to replace another. It's been a decade since we last built our PC so a lot of it is outdated now...
 
Sharon said:
Seeing specs like these makes me wonder if I should encourage my husband to upgrade our gaming PC ...but when we replace one thing it usually means we have to replace another. It's been a decade since we last built our PC so a lot of it is outdated now...
Click to expand...

Generally if you get 7 years out of a custom built, it is time to start thinking of upgrades or a new build.
 
7 years? Yeah that sounds about right. I generally go at least 6 before even thinking about upgrading my computer.
 
Read from tweaktown:

The new GeForce RTX 4070 Ti should be the graphics card that the "full-fat AD104" GPU will be powering, with 12GB of GDDR6X memory clocked at 21Gbps, according to leaker "kopite7kimi". The leaker adds that the performance of the full-fat AD104 GPU will "easily match" the GeForce RTX 3090 Ti.

Rewinding the leaks back to March 2022, Moore's Law is Dead teased that the AD103-based GeForce RTX 4070 "should offer another 10-30% performance over the current flagship RTX 3090". Remember, that was before NVIDIA unleashed the RTX 3090 Ti. So we should expect to see the AD103-based RTX 4070 beating the RTX 3090, while the "full-fat AD104" based RTX 4070 Ti beating the RTX 3090 Ti.
 
Read GeForce RTX 4090s catching fire from tweaktown:

NVIDIA is in some serious hot water over the 16-pin "12VHPWR" power adapter with its new flagship GeForce RTX 4090 graphics card, with multiple reports of cards catching fire and the "12VHPWR" power adapter melting, or worse.

The story gets juicier now with Igor's Lab reporting that NVIDIA reportedly notified all of its AIB partners that all damaged cards that they receive back from consumers, need to be sent directly to NVIDIA HQ for "failure analysis".

This news lines up with NVIDIA CEO Jensen Huang flying out to Taiwan to meet with TSMC (Taiwan Semiconductor Manufacturing Company) to nail 3nm wafers for its next-gen Blackwell GPUs... but maybe Uncle Jensen was calming AIB partners down as they're about to get reamed with returns, bad reviews from customers, and more.

"NVIDIA just notified all AIC this morning... All damaged cards need to be sent directly to HQ for failure analysis, this is first time... Even a few years ago when 2080 Ti got issue with Micron, they didn't do this".
 
cm2 said:
Read GeForce RTX 4090s catching fire from tweaktown:

NVIDIA is in some serious hot water over the 16-pin "12VHPWR" power adapter with its new flagship GeForce RTX 4090 graphics card, with multiple reports of cards catching fire and the "12VHPWR" power adapter melting, or worse.

The story gets juicier now with Igor's Lab reporting that NVIDIA reportedly notified all of its AIB partners that all damaged cards that they receive back from consumers, need to be sent directly to NVIDIA HQ for "failure analysis".

This news lines up with NVIDIA CEO Jensen Huang flying out to Taiwan to meet with TSMC (Taiwan Semiconductor Manufacturing Company) to nail 3nm wafers for its next-gen Blackwell GPUs... but maybe Uncle Jensen was calming AIB partners down as they're about to get reamed with returns, bad reviews from customers, and more.

"NVIDIA just notified all AIC this morning... All damaged cards need to be sent directly to HQ for failure analysis, this is first time... Even a few years ago when 2080 Ti got issue with Micron, they didn't do this".
Click to expand...

Sounds like they rushed that card out too fast.
 
Saw MaxSun's anime PLOT GeForce RTX 4080 more expensive than RTX 4090 lol from tweaktown:
89573_04_maxsuns-anime-themed-geforce-rtx-4080-icraft-costs-more-than-4090_full.jpg

89573_02_maxsuns-anime-themed-geforce-rtx-4080-icraft-costs-more-than-4090_full.png
 
boiling RTX 4090 video lol
 
Nvidia's Official Response on the boiling RTX 4090:
 
NVIDIA just announced RTX 4070 Ti as the new name for the RTX 4080 with 12GB VRAM, 3 times more powerful than the RTX 3090 Ti and the price is $799. Basically the new sweet spot for PC Gaming imo. Read from TechRaptor:

It'll release on January 5 for $799 and it'll support the company's new DLSS 3 technology.

Speaking of specs, you're getting 40 Shader TFLOPs, 93 RT TFLOPs, and 641 Tensor TFLOPs thanks to the new Ada Lovelace architecture introduced with the RTX 4090 and 4080 a few months ago.

According to the manufacturer, the RTX 4070 Ti is designed to maximize gaming at 1440p resolution, and it's up to three times faster than the RTX 3090 Ti while being much kinder on your PSU (and the environment, I suppose), utilizing nearly half the power footprint.
 
Saw RTX 4080 Super review:
 
You must log in or register to reply here.
Back
Top