Graphics Cards - Page 119

Intel's new Arc A380 graphics card is kinda here, if you're in China... or spending oodles of money and going through the headache of getting a card across the border. Well, if you do for whatever reason... Bykski has a new water block for the Arc A380.

The new Bykski I-GNA380-X GPU BLOCK is a custom water block for the GUNNIR Arc A380 Photon OC graphics card, which is still mysterious: it's the first and only desktop Arc GPU for sale, and we don't know if the PCB that GUNNIR is using is a full custom design, or not. It's most likely an Intel reference design, so we don't know if you buy the Bykski I-GNA380-X GPU BLOCK if it'll fit on any other Arc A380 that's not from GUNNIR.

If you want a nice-and-tight single-slot GUNNIR Arc A380 Photon OC graphics card, the Bykski I-GNA380-X GPU BLOCK is what you want. Inside, the GUNNIR Arc A380 Photon OC graphics card has the Intel ACM-G11 GPU, 6GB of GDDR6 memory, a single 8-pin PCIe power connector that uses up to 92W of power. The reference Intel Arc A380 design has a 75W TDP, just FYI.

Intel's new Arc A-series desktop GPUs launched without even a whimper, with the new GPUs being an exclusive to China for many months... but it appears AIB partners are now getting some of that Arc silicon to make entry-level graphics cards for some upcoming pre-built PCs.

GUNNIR started it all with their custom Arc A380 Photon OC 6G graphics card, then ASRock, and now we have ASUS and MSI leaping into the game. The Intel Arc A380 cards from ASUS and MSI comes from leaker "momomo_us" on Twitter, where MSI lists its new PC with an Intel Core i5-12400 or Core i5-12400F for the lower-end SKU, while the higher-end system has an Intel Core i7-12700 or Core i7-12700F processor.

These systems can be configured with 3 different GPUs: a custom MSI GeForce GTX 1650, an MSI GeForce GT 1030, or Intel DG2 A380 or Intel DG2 A310 graphics card. We should expect to see 4GB of VRAM on each of the Arc A380 and Arc A310 graphics cards, but there's no details on that with MSI's upcoming PC.

NVIDIA's next-gen Ada Lovelace GPU architecture should be detailed in the coming weeks, with the GeForce RTX 4090 expected to launch first and be a powerhouse... but the GeForce RTX 4080 and GeForce RTX 4070 graphics cards will follow, and now we have some early 3DMark performance estimates.

The upcoming NVIDIA GeForce RTX 4080 and GeForce RTX 4070 graphics cards have had their 3DMark TimeSpy Extreme graphics scores revealed by leaker "kopite7kimi". The leaker says that the GeForce RTX 4080 has 15,000+ points in TimeSpy Extreme, while the GeForce RTX 4070 will have 10,000+ points in TimeSpy Extreme.

These scores are based on the previously known specs of the cards, with the GeForce RTX 4080 packing the AD103 GPU and 10240 CUDA cores, while the GeForce RTX 4070 is based on the AD104 GPU and 7168 CUDA cores.

AMD's next-gen Radeon RX 7900 series graphics cards will reportedly have 20Gbps memory bandwidth, while the 7x50 XT refresh will bump those numbers up again.

The next-gen RDNA 3-based Radeon RX 7900 series is in the news from leaker "Greymon55" on Twitter, who said, "7900 series is 20Gbps, I don't know about the rest" when pressed by VideoCardz about "anything on individual SKU specs" of the upcoming Radeon RX 7000 series graphics cards.

The leaker says that AMD will be launching its new Radeon RX 7000 series graphics cards -- not just the Radeon RX 7900 series to be specific -- in November. We were already kinda expecting that because AMD is about to unleash its new Zen 4-based Ryzen 7000 series CPUs... and in the weeks after that, we'll get the RDNA 3-based Radeon RX 7000 series GPUs... and we ALL can't wait.

I'm sure that by now you've heard about the mess that is the Intel Arc GPU launch, and that's because it's been such a disaster. Apart from YouTubers throwing up sponsored videos that only put the graphics cards in a good light, there's been no traditional tech press covering Intel Arc graphics cards, since they're still a China exclusive.

We've had a few European reviewers get their hands-on Intel Arc, likening Intel's big new GPU as "playing drunk, in a minefield". That same minefield must be where Intel GPU marketing plans their big launch, where leaker Moore's Law is Dead leaked that Intel is pulling back on its huge global launch of Arc for a much more watered-down positive-vibes-only round with YouTubers and select tech press.

But now... Intel Arc desktop GPUs will have a staggered launch according to Igor from Igor's Lab, who reports that Intel has "now internally decided on a narrower time frame" and that if they stick to this timeframe we should expect Intel Arc desktop GPUs to launch between August 5, and September 29.

I wouldn't want to be on the Intel GPU marketing team right now, or anywhere at Intel for that matter as it seems to be filled with issues... but the Intel Arc GPUs have been an utter disaster, and no matter how much sticky tape that Intel puts on it, it's not going to be good.

A new leaked internal roadmap from Intel sourced by Moore's Law is Dead shows that Intel had originally planned to have 4 different Arc graphics cards: Arc A770, Arc A750, Arc A580, Arc A380 to system integrators by... well... now, the end of July. But no OEMs that manufacture these graphics cards, or the system integrators that will have Arc GPUs inside, have announced custom Arc graphics cards or Arc GPU-powered PCs.

Intel could be saying one thing about Arc internally, and externally... we don't know, but it sounds like that is happening. Intel GPU marketing is a mess right now, with them out there being confident -- sending Ryan Shrout and Tom Peterson out to YouTubers -- meanwhile, it's a dumpster fire around them.

Intel is truly struggling with its GPU marketing team... with Arc being a total DOA POS, and now MLID is coming out for their throat... and rightfully so. I've been pushing against Intel and this "marketing" that htey're going, and it seems that I'm not the only one. Check out Tom's latest video, and a bunch of his comments below:

It looks like Intel could have a major "fundamental hardware flaw" inside of the Arc Alchemist GPU scheduler, which is causing issues (amongst the laundry list of things wrong with the Intel Arc GPU). Tom explains: "Igor has started to find, and from what I'm hearing behind the scenes... there's almost certainly a fundamental hardware flaw in the scheduler of Alchemist".

Tom continued: "Can they make things better... can there be mitigations in drivers that they will improve over time... yes... but it's never going to be perfect. It's already having problems above 90FPS consistently at super low resolutions with a weak card... how are they going to get a high-end card to game above 144Hz".

I don't think you could be in the dark about how much of a shit show the Intel Arc GPU has been so far, but I've been pretty damn critical of it... it deserves no defense, until Intel has proven itself in the GPU market, and it looks like they might not even get a chance.

In his latest video, Tom at Moore's Law is Dead says that Intel's new Arc Alchemist desktop GPUs could actually end up being cancelled and that they "may end up a waste of sand". I guess being a waste of sand for Intel is better than AIB partners telling NVIDIA to "pound sand" as it seems sand is in the headlines a lot when it comes to GPU rumors lately.

Tom said: "Intel may cancel Arc before Battlemage is even launched".

NVNDIA has announced it will be hosting a "Special Address" at SIGGRAPH 2022 in just over a weeks time.

The company announced its special address will give us a glimpse into the future of AI-infused virtual worlds, where NVIDIA CEO Jensen Huang and other NVIDIA senior leadership will appear for the special address on August 9. The next day, NVIDIA will talk more about the Omniverse, GTC, and more.

On August 9, the "Special Address" from NVIDIA won't see a next-gen GPU revealed like most people expect to see. Rather, we'll see NVIDIA kick off its Special Address between 9AM and 10AM on August 9, while starting at 10AM there's "The Future of Extended Reality: How Immersion Will Change Everything" and after that at 11AM we have "Buidling on NVDiffrec and Instant NeRT for production-ready free-viewpoint video of people and places".

Intel has its first graphics card since the Intel i740 and its benchmarking it with indoor environments of Death Stranding, which I'd say was a weird flex but not after reviewers calling the Intel Arc A380 graphics card like "sitting in a minefield, playing drunk".

Anyway, GPU marketing dude of Intel, Ryan Shrout, posted a new article and video on the official Intel Arc website and Intel YouTube channel. In the video, Shrout is using the Intel Arc A750 Limited Edition graphics card with VRR (Variable Refresh Rate), HDR (High Dynamic Range) and HDMI 2.1 technologies.

Shrout tested an Intel-marketed Death Stranding with indoor environments, where it said it was running at 80-100FPS. I don't know if you'd want to be testing that particular game, in that particular way, for your first graphics card since the Intel i740, but that's where we are here in July 2022. I get it, but there are far better games and tests that could've been run... Death Stranding and indoor environments? Aight.

AFOX is teasing both AMD's next-gen RDNA 3-based Radeon RX 7000 series graphics cards, and NVIDIA's next-gen Ada Lovelace-based GeForce RTX 40 series graphics cards, registering a laundry list filled with graphics cards to the EEC.

The company makes a bunch of PC hardware including graphics cards, motherboards, SSDs and PSUs but man, AFOX is truly preparing for a bloody lot of next-gen graphics cards. AFOX has submissions for the new flagship AMD Radeon RX 7900 XT and Radeon RX 7900 and NVIDIA GeForce RTX 4090 Ti and GeForce RTX 4090 graphics cards.

But it didn't stop there, it has filed submissions to the EEC (Eurasian Economic Commission) regulatory office for what seems like every possible model of next-gen graphics cards that both AMD and NVIDIA will be unleashing in the coming months. From the very top of the AMD Radeon RX 7900 XT down to the Radeon RX 7500, and the GeForce RTX 4090 Ti down to the GeForce RTX 4050.

NVIDIA is boxing up its next-gen GeForce RTX 40 series GPUs it seems, as we're now hearing that a Chinese GPU supplier is expecting their first batches of Ada Lovelace GPUs very, very soon.

In a recent PRO Hi-Tech tech news roundup, Ilya Korneychuk said that their Chinese GPU supplier is expecting to receive their first batch of GeForce RTX 40 series GPUs in less than a month. In some Google-powered translation from Russian, he explained: "our graphics card supplier in China has told us that it will receive the first batch of RTX 4000s in less than a month".

Pulling this all together: the last we heard is from a leaker that said that NVIDIA's next-gen GeForce RTX 4090 was actually really close, in that "we will see her soon". Before that, we heard that NVIDIA would be launching its higher-end GeForce RTX 4090 first in August, and then the GeForce RTX 4080 in September, and the GeForce RTX 4070 after that.

Innosilicon is going to unveil its next-gen Fantasy 2 graphics card family on August 3, with the Chinese GPU maker teasing its announcement ahead of the reveal.

The new Innosilicon Fantasy 2 graphics cards will act as the successor to the Fantasy No.1 series, where the previous Type-A graphics card offering 5 TFLOPs of compute performance, while the Type-B card was a dual-GPU affair offering 10 TFLOPs of compute performance.

We should see the new Innosilicon Fantasy 2 GPUs based on Imagination's IMG BXT architecture, where the Chinese GPU company is making GPU solutions for high-performance tasks in cloud computing. Innosilicon had goals of reaching similar performance to NVIDIA's mid-range GeForce RTX 3060 graphics card... but didn't compute with the gaming performance of the RTX 3060.

NVIDIA will be launching its next-gen GeForce RTX 4090 in the coming months, with a new rumor that the company will be launching a 450W and 600W variant of the GPU.

Not only that, but NVIDIA will reportedly be making its new GeForce RTX 4090 cheaper... yes, cheaper... than NVIDIA's current flagship GeForce RTX 3090 Ti graphics card. The rumor we're discussing right now is coming from the Chiphell forums, stating that the GeForce RTX 4090 will be the only next-gen GPU that we see this year.

The rumor continues that NVIDIA might not have the other GeForce RTX 40 series SKUs out until Q1 2023, which would be a very interesting way of Ada Lovelace being rolled out. But why, and how would that happen? Well, I've been reporting from leaker Tom @ Moore's Law is Dead that AIB partners told NVIDIA to "go pound sand" over their warehouses filled with Ampere and Turing GPU stock. The AIB source said, "we're even willing to risk Lovelace allocation if they threaten us".

It looks like AMD is close to revealing its AI-based noise suppression technology, "accidentally" publishing a video teaser to their upcoming NVIDIA RTX Audio competitor on YouTube.

Well, before it was pulled it was screenshotted by the internet of course, and now we know a little of what to expect. AMD's upcoming Noise Suppression technology should work similar to how NVIDIA RTX Audio technology works, using the wonders of AI to clean your audio.

During the pandemic, using a headset with a microphone became invaluable, with NVIDIA stepping in almost immediately with an answer in RTX Voice. AMD's upcoming AI-powered noise suppression technology shouldn't be too far away, with the new RDNA 3 GPU architecture coming in the months ahead.

ASRock has made custom AMD Radeon GPUs for years and years now, with some of the very best -- in fact, the very best custom Radeon RX 6950 XT on the market -- but now the Taiwanese giant is making a custom Intel Arc A380 graphics card.

The new ASRock Arc A380 Challenger graphics card has been spotted, joining the custom Arc A380 graphics card race with GUNNIR and its Arc A380 Photon OC 6G graphics card. ASRock is using 'Intel ARC' branding on the top of the card, just like we see on AMD Radeon and NVIDIA GeForce graphics cards from AIB partners.

We have a small, dual-slot, single-fan graphics card with a single 8-pin PCIe power connector for the custom ASRock Arc A380 Challenger graphics card. Inside, the Arc A380 has the full ACM-G11 GPU on the TSMC 6nm process node with 8 Xe-Cores or 1024 ALUs, with a max GPU clock of 2450MHz. 6GB of GDDR6 is here at 15.5Gbps on a 96-bit memory bus that pumps 186GB/sec of memory bandwidth, with a 92W TBP.

I only got up just over a couple of hours ago, and I'm already head-first into the very latest rumors on NVIDIA's next-gen Ada Lovelace GPU architecture and the new GeForce RTX 40 series graphics cards.

In a series of tweets, leaker "kopite7kimi" teased that NVIDIA is reportedly working on "the beast" which rocks the PG137-SKU0 board and AD102-450-A1 GPU. That GPU would feature an insane 18176 CUDA cores, 48GB of GDDR6X memory at 24Gbps, and a huge 800W of total board power.

But then there was the tweet right after that, where the leaker says that NVIDIA will unveil its next-gen GeForce RTX 4090 graphics card. Kopite7kimi tweeted: "about RTX 4090, we will see her soon. Nothing to say". There's nothing more to say here, but we have to know that the GeForce RTX 4090 is very, very close at this point... but "we will see her soon" sounds very exciting.

NVIDIA is closer than it appears to launching its next-gen Ada Lovelace GPU architecture, with a purported "the beast" GPU powered by the AD102 GPU and a new board design: PG137.

The new NVIDIA PG137 board design is different from the PG139 that will make up the GeForce RTX 4090, with leaker "kopite7kimi" teasing "the beast" GPU: PG137-SKU0. This is reportedly powered by the AD102-450-A1 GPU with 18176 CUDA cores, an insane 48GB of GDDR6X memory at 24Gbps, and around 800W of TBP.

NVIDIA's purported "the beast" GPU with the AD102-450-A1 GPU and its huge 800W of power should require dual 16-pin PCIe power connectors. Quite the insane power leap, but if NVIDIA is scared of AMD and its next-gen RDNA 3-based Navi 31 GPU and its chiplet design... NVIDIA is going to drive up to 800W to beat it.

GPU prices have been slowly coming back down from the stratosphere, where we're back to kinda-regular pricing... and now the GeForce RTX 3080 Ti can be had for $900.

The price of NVIDIA GeForce RTX 30 series GPUs has been coming down over the last month, with the flagship GeForce RTX 3090 Ti already started falling from its $2000+ price down to $1500... and now it can be found for around $1450.

NVIDIA's GeForce RTX 3080 Ti can be purchased for $899... down from $930 with a $30 rebate card at Newegg, but down a big chunk from its $1100+ price from just weeks ago. That's for the custom triple-fan MSI Ventus GeForce RTX 3080 Ti graphics card, while the GeForce RTX 3090 can be purchased for $1250. Not too bad at all, and you get the 24GB of GDDR6X (up from the 12GB GDDR6X on the RTX 3080 Ti).

Graphics chip and technology company NVIDIA has announced that they will be showcasing their latest innovations, as well as cutting-edge AI and CG in simulation, collaboration, and design at this the SIGGRAPH 2022 conference located this year in Vancouver, Canada. They have titled their weeklong event "Illuminating the Future of Graphics".

Jensen Huan, NVIDIA's CEO, as well as other special presenters will be giving attendees of the NVIDIA Special Address at SIGGRAPH 2022, a glimpse into the future of AI-infused virtual worlds. There are plans to cover the research and technology that power these worlds, and how they open new frontiers for artistic expression and creativity or perfectly replicate nature's systems.

NVIDIA will also be presenting it's latest academic collaborations in graphics research with 17 technical papers. These research papers span advancements in neural content creation tools, display and human perception, the mathematical foundations of computer graphics, and neural rendering. A few of the research papers have already been published for consumption, and are available online through the links below.