Aller au contenu principal

GeForce 40 series


GeForce 40 series


The GeForce 40 series is a family of graphics processing units developed by Nvidia, succeeding the GeForce 30 series. The series was announced on September 20, 2022, at the GPU Technology Conference (GTC) 2022 event.

The RTX 4090 was released as the first model of the series on October 12, 2022, launched for $1,599 US, and the 16GB RTX 4080 was released on November 16, 2022 for $1,199 US. An RTX 4080 12GB was announced in September 2022, originally to be priced at $899 US, however following some controversy in the media it was "unlaunched" by Nvidia. On January 5, 2023, that model would be released as the RTX 4070 Ti for $799 US. The RTX 4070 was then released on April 13, 2023 at $599 US MSRP. The RTX 4060 Ti was released on May 24, 2023 at $399 US, and the RTX 4060 on June 29, 2023, at $299 US. An RTX 4060 Ti 16GB followed on July 18, 2023, at $499 US. On January 8, 2024, Nvidia released the RTX 4070 SUPER at $599, RTX 4070 Ti SUPER at $799 and RTX 4080 SUPER at $999. These video cards were launched at higher specs and lower prices than their original counterparts. In the same vein, the production of the RTX 4080 and RTX 4070 Ti have stopped due to the SUPER series, but the 4070 will remain.

The cards are based on Nvidia's Ada Lovelace architecture and feature Nvidia's third-generation RT cores for hardware-accelerated ray tracing (RTX), and fourth-generation deep-learning-focused Tensor Cores.

Details

Architectural highlights of the Ada Lovelace architecture include the following:

  • CUDA Compute Capability 8.9
  • TSMC 4N process (5 nm custom designed for Nvidia) – not to be confused with N4
  • Fourth-generation Tensor Cores with FP8, FP16, bfloat16, TensorFloat-32 (TF32) and sparsity acceleration
  • Third-generation Ray Tracing Cores, along with concurrent ray tracing, shading and compute
  • Shader Execution Reordering – needs to be enabled by the developer
  • Dual NVENC with 8K 10-bit 60FPS AV1 fixed function hardware encoding
  • A new generation of Optical Flow Accelerator to aid DLSS 3.0 intermediate AI-based frame generation
  • No NVLink support
  • DisplayPort 1.4a and HDMI 2.1 display connections
  • Double-precision (FP64) performance of the Ada Lovelace chips are 1/64 of single-precision (FP32) performance.

Products

Desktop

  • RTX 4060 and RTX 4060 Ti use GDDR6 video memory. All other cards use GDDR6X video memory manufactured by Micron.
  • RTX 4060 and RTX 4060 Ti have a limited 8 lane PCI Express 4.0 bus interface. All other cards support the full 16 lanes.

Mobile

  • All models feature GDDR6 memory.

Controversies

RTX 4080 12GB

When the 12GB variant of the RTX 4080 was announced, numerous publications, prominent YouTubers, reviewers, and the community criticized Nvidia for marketing it as an RTX 4080, given the equivalent performance of previous xx80-class cards when compared with other cards of the same series, and the large gap in specifications and performance compared to the 16GB variant. The criticism focussed on Nvidia's naming scheme - two 4080 models were to be offered, an "RTX 4080 12GB" and an "RTX 4080 16GB" - the obvious interpretation was that the only difference between the two products would be a difference in VRAM capacity. However, unlike other examples of Nvidia GPUs with differing memory configurations within the same class which have typically been very close in processing performance, the RTX 4080 12GB uses a completely different processing unit and memory architecture: the 4080 12GB would use the AD104 chip, which features 27% fewer CUDA cores than the 16GB variant's AD103 chip. It would also have a reduced TDP (285W - the 16GB variant was configured to draw up to 320W), and a cut-down 192-bit memory bus. In prior generations (e.g. the GeForce 10, 20, 30 series), a 192-bit bus width had been reserved for xx60-class cards and below. These changes made the card up to 30% slower than the RTX 4080 16GB in memory-agnostic performance, while being priced significantly higher than previous xx70-class cards ($900 vs. $500 for the RTX 3070, approximately 80% more expensive).

On October 14, 2022, Nvidia announced that due to the confusion caused by the naming scheme, it would be "unlaunching"—i.e. postponing the launch of—the RTX 4080 12GB, with the RTX 4080 16GB's launch remaining unaffected.

On January 3, 2023, Nvidia reintroduced the RTX 4080 12GB as the RTX 4070 Ti during CES 2023 and reduced its list price by $100. The 4070 Ti's production was stopped with the introduction of the 4070 Ti SUPER.

12VHPWR connector failures

US Export restrictions on the RTX 4090

The United States Department of Commerce began enacting restrictions on the Nvidia RTX 4090 for export to certain countries in 2023. This was targeted mainly towards China as an attempt to halt its AI development. However as a result of this, the market price of the RTX 4090 rose by 25% as China began to stockpile 4090s. This led to Nvidia releasing a China specific model of the RTX 4090 called the RTX 4090D (D standing for "Dragon"). The RTX 4090D features a shaved down AD102 die with 14592 CUDA cores, down from 16384 cores of the original 4090.

The restrictions began on November 17th, 2023, effectively banning the RTX 4090 from China and other countries on the export restricted list.

Reception

RTX 4090

Upon release, the RTX 4090's performance received praise from reviewers with Tom's Hardware saying "it now ranks among the best graphics cards". A review by PC Gamer gave it 83/100, calling it "a hell of an introduction to the sort of extreme performance Ada can deliver when given a long leash". Tom Warren in a review for The Verge said that the RTX 4090 is "a beast of a graphics card that marks a new era for PC gaming". John Loeffler from GamesRadar wrote that the RTX 4090 offers "an incredible gen-on-gen performance improvement over the RTX 3090", "even putting the Nvidia GeForce RTX 3090 Ti to shame" and being "too powerful for a lot of gamers to really take advantage of." German online magazine golem.de described the RTX 4090 as the first GPU capable of native 4K gaming with ray tracing, as with the predecessor "one often preferred to forego ray tracing in favor of native resolution, especially in 4K." Aside from gaming performance, PCWorld's review highlighted the RTX 4090's benefits for content creators and streamers with its 24GB VRAM and AV1 encoding ability and was positive towards the Founders Edition's quiet operation and cooling ability.

However, it also received criticism for its value proposition given that it begins at $1,599. Analysis by TechSpot found that the RTX 4090's value at 1440p was worse than the RTX 3090 Ti and that the RTX 4090 did not make much sense for 1440p as it was limited by CPU bottlenecks. Power consumption was another point of criticism for the RTX 4090. The RTX 4090 has a TDP of 450W compared to the 350W of its last generation equivalent. However, Jarred Walton of Tom's Hardware noted that the RTX 4090 has the same 450W TDP as the RTX 3090 Ti while delivering much higher performance with that power consumption.

Aftermarket AIB RTX 4090 variants received criticism in particular for their massive cooler sizes with some models being 4 PCIe slots tall. This made it difficult to fit an RTX 4090 into many mainstream PC cases. YouTube reviewer JayzTwoCents showed an Asus ROG Strix RTX 4090 model being comparable in size to an entire PlayStation 5 console. Another comparison showed Nvidia's RTX 4090 Founders Edition next to the Xbox Series X for size. It was theorized that a reason for the massive coolers on some models is that the RTX 4090 was originally designed to have a TDP up to 600W before it was reduced to its official 450W TDP.

RTX 4080

The RTX 4080 received more mixed reviews when compared to the RTX 4090. TechSpot gave the RTX 4080 score of 80/100. Antony Leather of Forbes found that the RTX 4080 consistently performed better than the RTX 3090 Ti. The GPU's power efficiency was positively received with Digital Trends finding that the GPU had an average power draw of 271W despite its rated 320W TDP.

The RTX 4080's $1199 price received criticism for its dramatic increase from that of the RTX 3080. In his review for RockPaperShotgun, James Archer wrote that the RTX 4080 "produces sizeable gains on the RTX 3080, though they're not exactly proportional to the price rise". In another critique, RockPaperShotgun highlighted that AIB models can significantly exceed the base $1199 Founders Edition price, creating further value considerations. The Asus ROG Strix AIB model they reviewed came in at $1550 which is $50 less than the RTX 4090 Founders Edition. Tom Warren of The Verge recommended waiting to see what AMD could deliver in performance and value with their RDNA 3 GPUs. AMD's direct competitor, the Radeon RX 7900 XTX, comes in at $999 compared to the $1199 price of the RTX 4080.

The RTX 4080 received criticism for reusing the RTX 4090's massive 4-slot coolers which are not required to cool the RTX 4080's 320W TDP. A smaller cooler would have been sufficient. The RTX 3080 and RTX 3080 Ti with their respective 320W and 350W TDPs maintained 2-slot coolers while the 320W RTX 4080 has a 3-slot cooler on the Founders Edition and 4-slots on many AIB models.

It was reported that RTX 4080 sales were quite weak compared to the RTX 4090, which had shockingly sold out during its launch a month earlier. The global cost of living crisis and the RTX 4080's generational pricing increase have been suggested as major contributing factors for poor sales numbers.

RTX 4070 Ti

Following its relaunch as the RTX 4070 Ti, the GPU received mixed reviews. While its good thermal, 1080p, and 1440p performance were praised, its 4K performance is considered weak for the high $800 price tag.

Jacob Roach from Digital Trends gave the RTX 4070 Ti a 6/10, criticizing the lower memory bandwidth compared to the RTX 4080, its worse 4K performance, and the lack of a Founder's Edition model, with fears that the board partner cards would sell for over the $800 price tag, although he did praise the thermal performance and efficiency of his unit.

Michael Justin Allen Sexton from PCMag reviewed the ZOTAC RTX 4070 Ti Amp Extreme Airo model, giving it a 3.5/5, criticizing the large size of the card and it being only $100 less than AMD's direct competitor, the Radeon RX 7900 XT, which comes in at $899 compared to the $799 price of the RTX 4070 Ti.

It was reported that RTX 4070 Ti sales were quite weak, similar to the RTX 4080 at launch.

RTX 4070

At launch, Jacob Roach from Digital Trends gave the RTX 4070 a 4.5/5, praising its efficiency, the fact the Founder's Edition only took up two slots, and its good GPU performance at 1440p. However, following the launch of the AMD Radeon RX 7800 XT, AMD's direct competitor to the RTX 4070, Monica J. White from Digital Trends compared the latter to the RTX 4070, and said she would recommend the 7800 XT over the RTX 4070 because of better rasterization performance at 1440p, the fact that the 7800 XT had 16GB of VRAM compared to 12GB on the RTX 4070, and that the 7800 XT had a $100 cheaper price.

After the launch of AMD's Radeon RX 7800 XT, the direct competitor to the RTX 4070, which was released on September 6, 2023, the price of some RTX 4070 cards was lowered to $550 and the official MSRP was lowered to $550 following the launch of the SUPER series.

RTX 4060 Ti (8 GB & 16 GB)

The RTX 4060 Ti 8GB released in late May 2023. Many reviewers and customers denounced Nvidia for the lack of appropriate video memory for the release of the card, pointing that the RTX 3060 of the previous generation was released with 12GB of VRAM. Furthermore, many reviews mentioned that an 8GB card was simply not enough for modern standards, for example Digital Trends saying "It makes sense for the upcoming RTX 4060, which is launching in July with 8GB of VRAM for $300, but not for the $400 RTX 4060 Ti. At this price and performance, it should have 16GB of memory, or at the very least, a larger bus size." A few weeks later, prompted by consumers backlash, Nvidia announced they would release the RTX 4060 Ti 16GB in July 2023.

Despite that, the release of the 16GB variant itself was met with suspicion. Nvidia did not send samples for review, including to big names such as Gamers Nexus, Hardware Unboxed, and Linus Tech Tips. It was also later found out that AIBs were also prevented, presumably by Nvidia, to be allowed to give cards out for reviews. According to Gamesradar: "Coming in at $499, the Nvidia RTX 4060 Ti 16GB is arguably a hard sell. Normally, we’d test whether the GPU offers bang for buck, but it looks like reviews aren’t going to be a thing. In a way, that sort of makes sense, as it should perform fairly similarly to the existing 8GB model, with the added benefit of more VRAM."

YouTube reviewers Hardware Unboxed criticized both models of the RTX 4060 Ti, calling the 8GB of VRAM model "laughably bad at $400" and "frankly, we don't even need to test the RTX 4060 Ti 8GB to tell you it's a disgustingly poor value product...". They criticized its 8GB of VRAM, which led to poor 1% low frame rates at 1080p and unusable 1% low frame rates at 1440p in games such as The Last of Us Part I and The Callisto Protocol both using the ultra quality preset. A Plague Tale: Requiem was also unusable at 1080p not only using the ultra quality preset with ray tracing enabled, but using the high quality preset with ray tracing enabled as it suffered similar unusable 1% low performance. While Halo Infinite and Forspoken did not have poor 1% low performance at 1080p, they instead sometimes failed to load textures with the 8GB RTX 4060 Ti due to a lack of VRAM. These were not an issue with the 16GB RTX 4060 Ti, however, the 16GB RTX 4060 Ti was criticized for costing $500 to "fix" the issues with running out of VRAM, which was $100 more than the 8GB RTX 4060 Ti for otherwise identical performance outside of VRAM limitations.

RTX 4060

Jacob Roach from Digital Trends gave the RTX 4060 a 3/5, criticizing the poor performance of the GPU for the price, its low 8GB of VRAM capacity, the slow memory interface, and its performance at 1440p, although its efficiency was praised. He stated: "In the past, the RTX 4060 would have been classified as a workhorse GPU... The RTX 4060 falls short of filling that post, offering solid generational improvements but middling competitive performance, and relying on DLSS 3 and ray tracing to find its value."

See also

  • GeForce 10 series
  • GeForce 16 series
  • GeForce 20 series
  • GeForce 30 series
  • Ada Lovelace (microarchitecture)
  • Nvidia Workstation GPUs (formerly Quadro)
  • Nvidia Data Center GPUs (formerly Tesla)
  • List of Nvidia graphics processing units
  • Radeon RX 7000 series – competing AMD series released in a similar time-frame

References

External links

  • Official website
  • Nvidia GeForce RTX 40 series' announcement
  • NVIDIA ADA GPU ARCHITECTURE whitepaper
  • Media related to Nvidia GeForce 40 series video cards at Wikimedia Commons

Text submitted to CC-BY-SA license. Source: GeForce 40 series by Wikipedia (Historical)



INVESTIGATION