Graphics Cards - Page 123

AMD and NVIDIA are both about to announce and release their next-gen graphics cards in the coming months, but before then we've seen pricing on both sides of the GPU camp drop significantly... thanking the GPU gods.

We've already seen EVGA slice and dice the price of its high-end GeForce RTX 3090 Ti FTW3 by $1000, dropping it from $2149 down to $1149... but now the AMD's second-fastest Radeon RX 6900 XT graphics card, and NVIDIA's third-fastest GeForce RTX 3080 Ti are both experiencing healthy price cuts which are now dipping their toes in -30% below MSRP territory.

Our friends at Wccftech have noticed that the ASRock Radeon RX 6900 XT Phantom Gaming D graphics card is now just $699, down -30% over its $999 MSRP. If you don't want to go with ASRock, Newegg has a listing for the GIGABYTE Radeon RX 6900 XT GAMING OC graphics card, also $699... down from its usual $899 pricing on the site. Not bad, not bad at all...

Intel kicked off its Xe HPG Scavenger Hunt in early 2021, and a rather large 18 months later we have no Arc graphics cards in the wild... meaning no Intel Arc graphics cards to give away to Arc Scavenger Hunt winners.

The company is now offering an alternative prize because there are simply no Intel Arc GPUs, so instead of an Intel Arc A7-series graphics card (Intel was giving Grand Prize winners an Intel Arc A770, while the first place prize was an Intel Arc A750) winners can now opt for an Intel Core i7-12700K and Core i5-12600K processor.

Intel sent an email to its winners, explaining to a Xe HPG Scavenger Hunt Top 300 prize winner that they would be provided with an alternative to the original hardware prize, in addition to the standard merchandise and swag prizing. The company confirms that the winners only have a few days to decide -- up to August 19 -- if you want to switch over your Arc GPU to an Intel 12th Gen Core "Alder Lake" CPU.

AMD's next-gen Radeon RX 7000 series graphics cards will begin their journey into our lives, benchmark charts, and hearts later this year... but in flagship Navi 31 GPU form first, and then comes Navi 32 aka "Wheat Nas".

The next-gen Navi 32 GPU is codenamed "Wheat Nas" with some new purported details on the smaller version of Navi 31, which will be re-using the same MCDs (Memory Chiplet Dies) as the Navi 31. AMD will be using its flagship RDNA 3-based Navi 31 GPU for desktop Radeon RX 7000 series graphics cards (Radeon RX 7900 XT, and others) while the Navi 32 GPU will be offered in mobile, and high-end desktop GPU form as well.

Angstronomics reports that Navi 32 was planned with 128MB Infinity Cache (as a 1-hi version) but AMD is reportedly going with just 64MB of Infinity Cache for Navi 32, down from the 128MB on the upcoming Navi 31 GPU. While the current-gen RDNA 2-based Navi 21 has 128MB of Infinity Cache, and Navi 22 has 96MB of Infinity Cache, meaning Navi 32 comes with less Infinity Cache than Navi 22... interesting.

A new report from Angstronomics says that AMD's next-gen RDNA 3-based Navi 3X GPUs were finished in 2019, finalized sometime in 2020, and have had "no changes since".

AMD's upcoming Navi 31 is the flagship GPU based on the RDNA 3 graphics architecture, which will reportedly feature 1 x GCD (Graphics Chiplet Die) and 6 x MCDs (Memory Chiplet Dies). Each of them will contain 16MB of Infinity Cache, joined by GDDR6 memory and 64-bit wide PHYs according to the report. Navi 31 is expected to rock out with 48 WGPs (Work Group Processors) and a 384-bit memory bus using GDDR6 memory.

According to this new information, Navi 31 will have a total of 96MB of Infinity Cache, which is actually lower than the current-gen RDNA 2-based Navi 21 GPU which has 128MB of Infinity Cache in total. Angstronomics adds that there will be a cut-down SKU that will be made available, packing 42 WGP and 5 x MCD (80MB of Infinity Cache in total, on a 320-bit memory bus using GDDR6 memory).

It was barely two weeks ago that I reported from leaks that Intel's Arc desktop GPU is so bad, it could be CANCELLED altogether... But now a major analyst has said that Intel could shut its GPU business because it's bleeding too much money: $3.5 billion so far.

In a new market research report from Jon Peddie Research, the firm estimates that Intel's Accelerated Computing Systems and Graphics (AXG) group has lost $3.5 billion SO FAR. Intel bleeding out $3.5 billion in a division that should be around for decades to come and pull hundreds of billions in that time, is not a good sign, and neither is one of the biggest analysts in the world saying Intel should shut the GPU department down because of it.

JPR founder Jon Peddie said: "So, the rumor mill has been hinting that the party is over and that AXG would be the next group to be jettisoned".

Exclusive: Intel has confirmed with TweakTown that its upcoming Intel Arc graphics cards will NOT support multi-GPU for gaming, which is not a surprise, but still disappointing to hear.

In the last 36 hours, it's been a whirlwind about Intel supporting multi-GPU for its upcoming Arc GPUs and their oneAPI software. Our own Rob Squires wrote: "software support for an Intel multi-GPU solution is here and almost made its debut at SIGGRAPH 2022".

But then this morning I woke up to emails from an Intel representative clearing it all up, with the Intel representative explaining: "Intel showed a Blender Cycles rendering demo at SIGGRAPH with Intel Arc graphics. Multi-GPU rendering support for Intel Arc and Intel Arc Pro graphics cards through oneAPI is supported starting in Blender 3.3. Intel Arc graphics does not support multi-GPU for gaming".

Intel is back again with another video detailing its Intel Arc A750 graphics card, which has been benchmarked in close to 50 games with both DX12 and Vulkan API-based games.

In a new video from Intel, we have Ryan Shrout and Tom Peterson benchmarking their lives away with the Arc A750 Limited Edition graphics card in 49 games at both 1080p and 1440p resolutions. Intel versed its own Arc A750 graphics card against NVIDIA's mid-range GeForce RTX 3060, where it beat the RTX 3060 by 3-5% on average.

Ryan explains on the official Intel website: "For games with dedicated benchmarks like Dirt 5 and Hitman 3, we used their benchmark modes. Other games without built-in benchmarks were run using repeatable scenarios, though other testers might come up with different results. And you'll see in our results disclosure that we had two different Intel labs with slightly different configurations contribute to this collection of data, but all measurements for both Intel Arc and competitive products on a per game basis were performed by the same labs. We're confident that the combined data tells the story of the type of performance you can expect when playing some of your favorite modern games".

NVIDIA has been playing with fire before the launch of its next-gen Ada Lovelace GPU architecture, which will power the new GeForce RTX 40 series graphics cards coming later this year.

But now we're hearing fresh news from Moore's Law is Dead, who reached out to his industry sources to find out what is going on with the current situation of warehouses filled with current-gen and even older-gen Ampere and Turing-based graphics cards.

MLID says that his sources have said that AIBs are being helped by NVIDIA to clear their reserve stockpiles of GA102 (GeForce RTX 3090 Ti, GeForce RTX 3090, GeForce RTX 3080 Ti, GeForce RTX 3080 12GB, GeForce RTX 3080). His sources state that this was "the compromise" of the "NVIDIA AIB Revolt" which is when AIBs told NVIDIA to "go pound sand" over their warehouses of older-gen GPUs before the next-gen Ada Lovelace cards arrive.

NVIDIA's next-gen GeForce RTX 4090 might get all the rumor limelight, but the GeForce RTX 4080 and GeForce RTX 4070 are going to be the real big sellers for gamers, and now we have the very latest rumors to continue driving up that hype train.

The next-gen GeForce RTX 4070 is rumored to have higher GPU clocks than the flagship GeForce RTX 4090, with leaker "kopite7kimi" tweeting last week that the RTX 4070 spec had been updated. NVIDIA's third-most powerful Ada Lovelace GPU in its upcoming GeForce RTX 40 series family will use the PG141-SKU331 GPU, with 7680 CUDA cores, and 12GB of GDDR6X memory clocked at 21Gbps which should provide 504GB/sec of memory bandwidth

The last we heard on the GeForce RTX 4070 and its memory system was that it would have 10GB of GDDR6X at 18Gbps, so we're looking at a decent upgrade: 12GB GDDR6X memory clocked at 21Gbps. Kopite7kimi also says that we should expect GPU boost clocks to be over 2800MHz+ which should result in custom AIB models of the GeForce RTX 4070 to hopefully breach 3000MHz+ which would be a very, very cool thing to see from NVIDIA.

UPDATE: Intel reached out to us to clarify some details, saying "Intel showed a Blender Cycles rendering demo at SIGGRAPH with Intel Arc graphics. Multi-GPU rendering support for Intel Arc and Intel Arc Pro graphics cards through oneAPI is supported starting in Blender 3.3. Intel Arc graphics does not support multi-GPU for gaming."

We learned something quite interesting at SIGGRAPH 2022 today: Intel is finalizing their oneAPi software for multi-GPU support. It turns out that it was only due to the inability to find the right chassis that prevented Intel from showing off a multi-GPU solution on the show floor this week.

Support for a multi-GPU solution could allow Intel to narrow the gap somewhat against NVIDIA and AMD on their entry-level cards for Arc discrete GPUs that are set to debut shortly, as we just reported.

Today, while wandering around the halls of SIGGRAPH 2022 in Vancouver, we caught up with someone from Intel who told us that discrete Arc graphics cards would launch a lot sooner than the end of the year.

Although we just reported yesterday that Intel formally announced product shipments before the end of the year, we were able to grease some wheels here at SIGGRAPH 2022.

Although our source would not give the exact date, they could confirm that the current plan would see product availability by the end of summer.

NVIDIA has released its new GeForce Game Ready 516.94 WHQL drivers, which provide the best day-0 gaming experience for Marvel's Spider-Man Remastered.

The new NVIDIA GeForce Game Ready 516.94 WHQL drivers will be ready for Marvel's Spider-Man Remastered, which packs NVIDIA technologies like NVIDIA DLSS, NVIDIA DLAA, NVIDIA HBAO+ and beefed-up ray tracing effects. The new GeForce Game Ready 516.94 WHQL drivers also support Madden NFL 23 and the beta of SUPER PEOPLE.

There's also a boat load of support for newly validated G-SYNC Compatible displays, including support for Corsair's new XENEON 32UHD144 gaming monitor which rocks out with a native 4K resolution and super-smooth 144Hz refresh rate. NVIDIA is supporting 18 newly validated G-SYNC Compatible displays in total, from ASUS, AOC, LG, and Philips.

NVIDIA is taking care of its staff with pay increases instead of lay offs during some hard financial times, not just for the company, but for the US economy and global economies.

In a new email picked up by Business Insider, NVIDIA is sticking to its guns with NVIDIA founder and CEO Jensen Huang keeping the can of whoop ass closed when it comes to hurting NVIDIA staffers during these hard times. Jensen explained in the email: "So what does this [THE REVENUE DROP] mean for us? Do we have a layoff? No. Instead, we have given raises to take care of your families as all of you are facing sky-high inflation".

He continued: "We will exercise extreme collaboration, a hallmark of our culture, finding every opportunity to leverage and reuse. We will find and eliminate all wasted time, process, and material. Take this opportunity to make NVIDIA even faster, leaner, and agile. So let's turn our alertness and agility to maximum, engines full-throttle, and fly through the challenges ahead while continuing to do our impactful work".

Chinese company Biren Technology has just unveiled its new GPGPU architecture for next-gen computing at its recent Biren Explore Summit 2022 event.

Biren's new BR100 GPU is built on the 7nm process node at TSMC using their TSMC 2.5D CoWoS packaging technology, featuring 77 billion transistors, 300MB of on-chip cache, and 64GB of super-fast HBM2e memory that pumps up to 2.3TB/sec of memory bandwidth. We have up to 256 TFLOPs of FP32 compute performance, with the GPU supporting both PCIe 5.0 and CXL interfaces.

The new BR100 GPGPU is based on Biren's own BiLiren architecture, but with the BR100 the company is also introducing the whole family of OAM-compatible cards, as well as the PCIe-based BR104 GPU. Biren is also unveiling their own software platform alongside the BR100 GPGPU launch, which is called BIRENSUPA, with support for mainstream deep learning frameworks like Baidu's PaddlePaddle.

NVIDIA's next-gen GeForce RTX 4080 graphics card is rumored to use up to 320W of power, which is down considerably from the previously rumored 420W of power.

The news on NVIDIA's next-gen Ada Lovelace GPU-powered GeForce RTX 4080 is from leaker "kopite7kimi" who tweeted: "We can expect RTX 4080 with 320W and RTX 4070 with 285W". The previous rumor for the RTX 4080 is that it would use 420W, so the drop to 320W is a lofty 100W... and that's a great thing.

NVIDIA has an additional 100W of power it can use for some monster overclocking on custom GeForce RTX 4080 graphics cards, something kopite7kimi addressed in a follow-up tweet, by saying: "Not much. The original power consumption limit is too loose which means great overclocking potential".

Intel is continuing its "marketing" for their upcoming Arc GPUs with something that leaker Moore's Law is Dead talked about: the Arc desktop GPU story. There's not much new here, but it's interesting that it's all playing out like this.

You can check out the "story" on Intel Arc GPUs on the official Intel website, where we find out that ex-PC Perspective owner and reviewer Ryan Shrout has a major hand in Arc. Shrout seems to be steering the Arc GPU ship, as the Intel website itself says that "Intel Gaming Access met with Ryan Shrout, Senior Director of Graphics and HPC Marketing at Intel".

Intel explains that "when it came to the creation of Intel Arc, Ryan and Intel's engineers had plenty of graphics experience to call on". Interesting, it seems that Ryan was integral to the entire Arc GPU process... so this marketing plan is his, and he's calling the shots.

Intel has officially entered the battlefield of professional graphics cards this week at SIGGRAPH 2022 in Vancouver, Canada. Today, Intel is showing off their upcoming professional discrete card offerings for the first time. They displayed their Arc Pro A40 and Arc Pro A50 video cards in their booth on the exposition floor.

Unfortunately, none of their demonstration systems used in the booth on the show floor are powered by their premier Arc Pro A50 solution. The Intel demo team was extremely proud and enthusiastic about the Arc Pro A40 and its current status.

One takeaway from seeing both cards next to each other is the physical size difference between the Arc Pro A40 and much larger Arc Pro A50 graphics cards. Although the smaller Arc Pro A40 card can fit in a small form factor solution, Intel likely will not be pushing their upcoming higher-end card into their smaller factor offerings in this generation of cards.

ASRock has posted a review of its new Intel Arc A380 Challenger ITX graphics card on Weibo, which is an interesting turn of events for the company.

Just weeks ago, ASRock only made AMD Radeon graphics cards and now the company has introduced its first Intel Arc graphics card, and then a review posted up on Chinese social networking site Weibo. ASRock's new Intel Arc A380 Challenger ITX is a small dual-slot, single-fan, single 8-pin PCIe power connector graphics card.

We knew most things we needed to know about the ASRock's new Intel Arc A380 Challenger ITX graphics card, but now we know that the fan hits 1700RPM or so under full load, while the ACM-G11 GPU hits 85C.

Micron is now making its ultra-fast 24Gbps GDDR6X memory, where it has entered production and is getting prepped for NVIDIA's next-gen Ada Lovelace-based GeForce RTX 40 series GPUs.

The new Micron GDDR6X modules at 24Gbps will arrive as 16Gb GDDR6X chips, which means we'll have 24GB of GDDR6X on flagship GeForce RTX 40 series GPUs with single-sided GDDR6X. This is what we want, as the 24GB of GDDR6X on the GeForce RTX 3090 was single-sided was a hot mess (literally) while the 24GB of GDDR6X on the GeForce RTX 3090 Ti was double-sided, and GDDR6X memory temperatures benefited greatly because of it.

Micron's new 24Gbps GDDR6X memory modules will also usher in 48GB of GDDR6X at 24Gbps, where the double-sided 24Gbps GDDR6X memory chips will be perfect for a new TITAN-class GPU, or workstation GPU powered by the next-gen Ada Lovelace GPU architecture from NVIDIA.

EVGA has just slashed a huge $1000 from its enthusiast-ready GeForce RTX 3090 Ti FTW3 graphics card, which cost $2149 just a week ago... and now it's down to $1149.

The custom EVGA GeForce RTX 3090 Ti FTW3 graphics card was introduced at $2149, with it being the cheapest of the three SKUs that EVGA has in its GeForce RTX 3090 Ti arsenal. As it stands, EVGA is selling its GeForce RTX 3090 Ti FTW3 graphics cards for between $1150 and $1400.

EVGA is discounting $1000 from its GeForce RTX 3090 Ti FTW3 ULTRA graphics card as well, down from $2199 to $1199 while the GeForce RTX 3090 Ti FTW3 BLACK is $600 discounted, down from $1999 to $1399. EVGA is still selling its higher-end GeForce RTX 3090 Ti HYDRO Copper and GeForce RTX 3090 Ti KINGPIN Hybrid graphics cards for $1500 and $2000, respectively.