Graphics Cards - Page 142

NVIDIA has just released its new GeForce Game Ready 497.09 WHQL drivers, which offer the best day one experience in ICARUS.

ICARUS will feature NVIDIA DLSS and NVIDIA RTX Global Illumination (RTXGI) technologies, with the new GeForce Game Ready 497.09 WHQL drivers able to rock and roll from the start. Not only do we have Game Ready support for ICARUS, but also the just-released Halo Infinite.

On top of that, we have support for NVIDIA's just-announced GeForce RTX 2060 12GB graphics card, which is a refreshed Turing TU106-based GPU with 12GB of GDDR6 memory launching on December 7. There's also support for 6 new G-SYNC Compatible displays from ASUS, Dell, LG, and MSI.

NVIDIA has announced its new GeForce RTX 2060 12GB graphics card, with it appearing on the official NVIDIA website in all its refreshed glory.

The "new" GeForce RTX 2060 12GB will be powered by the Turing TU106 GPU made on the same 12nm process, with GPU clocks at 1470MHz and 1650MHz for base and boost, respectively. The RTX 2060 12GB packs 12GB of GDDR6 memory on a 192-bit memory bus, with up to 336GB/sec of memory bandwidth.

Comparatively, the GeForce RTX 2060 SUPER has 12GB of GDDR6 on a wider 256-bit memory bus and a heftier 448GB/sec of memory bandwidth. NVIDIA is making the new GeForce RTX 2060 12GB graphics card in Founders Edition, too -- so it won't just be overclocked, custom AIB models of the RTX 2060 12GB but a new FE card as well.

SAPPHIRE has just introduced its new GearBox 500 Thunderbolt GPU enclosure, which can transform any PC or Mac with a Thunderbolt 3/4 connection into a desktop-class PC.

Inside, the new external GPU solution from SAPPHIRE packs their own PULSE Radeon RX 6600 XT 8GB graphics card which offers plenty of performance for the desktop, and some sneaky 1080p 60FPS+ gaming on the side.

SAPPHIRE has updated the chassis design inside of the new GearBox 500 Thunderbolt 3 eGFX enclosure, with improved airflow that keeps the GPU inside of it cooler than before. SAPPHIRE says you can run some pretty powerful GPUs inside of the enclosure, from something as the Radeon RX 570 through to the Radeon RX 6700 XT, and from the NVIDIA GeForce GTX 1060 to the GeForce RTX 3060 Ti.

NVIDIA is preparing its partners in Taiwan for a "major" GeForce RTX 40 series "Ada Lovelace" GPU launch in 2022, with next-gen gaming GPUs tapping TSMC's new 5nm process node.

DigiTimes has a new article behind a paywall that RetiredEngineer shed a light on in a tweet: "NVIDIA gaming GPUs getting major refresh next year, Taiwan factories all-out to support 5nm RTX40 generation. NVIDIA's biennial GPU refresh coming in 2022, riding on metaverse and gaming. Following H100, based on Hopper architecture, using TSMC's 5nm + CoWoS, aimed at datacenter/AI, gaming GPU RTX40 series, based on Ada Lovelace architecture, will also tap TSMC's 5nm....".

NVIDIA's next-gen Ada Lovelace GPU architecture is expected to deliver some truly gigantic performance improvements, as well as a shift away from Samsung's 8nm node process and back into the warm fuzzy fabricating arms of TSMC and its new 5nm process node for the next-gen GeForce RTX 40 series GPUs.

Innosilicon has just held its "Fantasy One GPU Product Press Conference" where it unveiled the new Fantasy One GPU family, and a few interesting new graphics cards.

Starting with the Innosilicon Fantasy One GPU itself, which is based on a multi-chip (chiplet) design and flagship dual-GPU graphics card in the form of the new "Type-B" dual-GPU solution uses 2 x Fantasy One GPUs and are connected using Innosilicon's just-announced Innolink interface.

Innosilicon's dual-GPU card has up to 10 TFLOPs of compute performance, and can handle 32 simultaneous 1080p 60FPS streams, or up to 64 streams at 720p 30FPS. The dual-GPU beast packs 32GB of GDDR6X memory, but they're super limited by the 128-bit memory bus on each of the respective Fantasy One GPUs.

Palit has just unleashed its beautiful and very unique new ColorPOP graphics card series, with the introduction of the new Palit GeForce RTX 3060 Ti ColorPOP graphics card.

The new Palit GeForce RTX 3060 Ti ColorPOP is a full-custom design with a 2.7-slot cooling solution, with Palit changing things up by rebranding their GamingPro series to the new ColorPOP series. The changes are extensive: new colors, new stickers, and of course; new packaging.

What is special here with the Palit GeForce RTX 3060 Ti ColorPOP is that it features beautiful color-shifting paint dabbed on its shroud and backplate, where the card will flex between different colors including green, violet, and blue when you look at it from different angles and lighting conditions.

NVIDIA is currently preparing another flagship graphics card for a big unveiling in January 2022, with the purported GeForce RTX 3090 Ti graphics card that will rock Micron's even-more-ultra-fast 21Gbps GDDR6X memory.

The current flagship NVIDIA GeForce RTX 3090 arrives with 24GB of GDDR6X memory clocked at 19.5Gbps, but it easily overclocks to 21Gbps and barely offers any perceivable performance difference. But, the new GeForce RTX 3090 Ti will not only have upgraded GDDR6X memory (21Gbps vs 19.5Gbps) but with it, it'll have slightly more memory bandwidth at 1008GB/sec (1TB/sec) compared to 936GB/sec on the RTX 3090.

Inside, NVIDIA is expected to use the GA102-350 GPU which bumps up everything across the board: 84 GPU clusters (versus 82 on the GA102-300 inside of the RTX 3090) while there's 10752 CUDA cores (up from 10496 CUDA cores), 84 RT Cores (up from 82 RT Cores) and finally: 336 Tensors/TMUs (up from 328 Tensors/TMUs).

We've been hearing more and more about NVIDIA's new GeForce RTX 2060 12GB graphics card, a refreshed Turing-based RTX 2060 with 12GB of GDDR6 memory (up from the 6GB GDDR6 on the regular RTX 2060).

But it looks like it'll be more than just double the VRAM of a regular GeForce RTX 2060, as the new GeForce RTX 2060 12GB will reportedly have a higher TDP of 184W (with the RTX 2060 SUPER having a 175W TDP). This means that the RTX 2060 12GB will actually be around the same performance as the RTX 2060 SUPER.

The 12GB of GDDR6 memory on the new GeForce RTX 2060 12GB will be on a 192-bit memory bus, while the RTX 2060 SUPER has its 12GB of GDDR6 on a wider 256-bit memory bus. Not only that, but the overclocked AIB variants of the new GeForce RTX 2060 12GB could see GPU boost clocks at default 1650MHz and up to 1690MHz and beyond with OC.

NVIDIA is reportedly hearing up for the launch of the lower-end GeForce RTX 3050 graphics card in Q2 2022 according to the same rumors.

The rumors are coming from the same source that first broke that NVIDIA is working on a new GeForce RTX 2060 with 12GB of GDDR6 memory, while in between we've been hearing plenty of rumors about the new mobile-focused GeForce RTX 3050 Ti.

VideoCardz is reporting that the non-Ti desktop GeForce RTX 3050 should come with 8GB of memory, but this could change -- we could see a 4GB variant as well. As for performance, NVIDIA's purported GeForce RTX 3050 would be faster than the GeForce GTX 1660 SUPER but slower than the GeForce RTX 2060 12GB (which isn't here yet).

Intel has laid out its GPU roadmap right into 2025 and beyond, with what will start with the Intel 1st Gen Arc "Alchemist" GPU launching in Q2 2022 for the desktop and Q1 2022 for mobile.

But in a few years, we're going to see the Intel 4th Gen Arc "Druid" GPU arrive and that should be sometime in 2025. In a new tweet, Intel Arc Community Advocate and Driver Guru, @theBryceIsRt, replied to @Freeman2352 who joked and tweeted "2025: RTX 6090 Super | 800W".

Bryce replied, tweeting: "If all goes well, that could be when Intel ARC 'Druid' cards comes out" and ends it with adding "game on" with a controller emoticon and nice little wink tease. Interestingly, he used "ARC" in all caps which was recently noted to be "Arc" without the all-caps -- OCD to the side, the 4th Gen Arc "Druid" GPU should drop in 2025 which isn't tooooo far away.

AMD has unleashed its highest-end Radeon RX 6900 XT Liquid Cooled Edition graphics card for the DIY market in Europe.

The Radeon RX 6900 XT Liquid Cooled Edition graphics card sees AMD using a pre-binned Navi 21 XTXH GPU, with some of the very highest RDNA 2 GPU clocks in the wild. AMD explains: "AMD will be making a limited number of Radeon RX 6900 XT liquid-cooled reference design graphics cards available to select system integrators".

"System integrators are a critical part of the gaming ecosystem and offering this model through their channels helps ensure that as many of these products as possible get into gamers hands".

GPU shipments are a bit funny right now and we all know it, with analyst firm JPR (Jon Peddie Research) posting a new report that details the global GPU market has hit a milestone of 101 million units in Q3 2021 alone.

JPR also notes that GPU shipments increased by 9% year-over-year while discrete GPU numbers inside of PCs is expected to hit 31% over the next 5 years leading up to 3.24 billion GPUs by the end of 2025. AMD had its GPU market share increase by 1.4% in the three-month period, while NVIDIA GPU market share increased by 4.86% in the same quarter.

AMD GPU shipments dropped by a decent chunk, by 11.4% in Q3 2021 while NVIDIA had its GPU shipments increased by 8% for the quarter. The latest numbers have AMD with 17% of the discrete GPU shipment market share, and NVIDIA with 83% of the dGPU shipment market share.

The price of AMD Radeon RX 6000 series GPUs is about to be a little worse, with AMD reportedly ramping up prices of its RDNA 2 cards by 10%.

AMD's increased pricing on Radeon RX 6000 series GPUs is reportedly starting with the next batch of GPU shipments from AMD to its AIB (add-in board) partners. We should expect the new pricing to be reflected online and in-store in the coming weeks, right as we lead into the holidays.

There was a 9% increase in pricing of AMD's new Radeon RX 6000 series GPUs in November 2021 over October 2021, and now we have another 10% increase moving into December. TSMC wafer costs increasing are being blamed, so AMD has got no other move to make other than take the hit -- which isn't nice -- or boost pricing (also not nice).

NVIDIA has just announced its new RTX A4500 workstation GPU, which uses the GA102 GPU with 7168 CUDA cores and 20GB of GDDR6 memory.

The introduction of the new NVIDIA RTX A4500 workstation GPU offers its 7168 CUDA cores alongside 224 Tensor Cores, and 20GB of GDDR6 memory clocked at 16Gbps on a 320-bit memory bus which will deliver up to 640GB/sec of memory bandwidth.

NVIDIA says the new RTX A4500 workstation GPU will have 23.7 TFLOPs of FP32 compute performance, while it has 46.2 TFLOPs of RT performance. NVIDIA's new RTX A4500 workstation GPU has a 200W TDP, which is 15% lower than the RTX A5000 and 17% slower.

NVIDIA is reportedly preparing a beefed-up GeForce RTX 2060 release in January 2022, which will see the card be released with 12GB of VRAM -- an upgrade from the 6GB of RAM by default.

But before its announcement or release, Russian YouTuber and modder VIK-on has upgraded his GeForce RTX 2060 6GB to a GeForce RTX 2060 12GB. The original GeForce RTX 2060 launched with the cut-down Turing-based TU106 GPU, rocking 1920 CUDA cores, and 6GB of GDDR5 memory on a 192-bit memory bus, clocked at 14Gbps.

NVIDIA is expected to make the GeForce RTX 2060 with 12GB official on December 7, with VIK-on testing the modded RTX 2060 with 12GB of VRAM in crypto mining and Unigine Superposition at first with roughly the same performance as the 6GB model -- duh. We should expect more official news and benchmarks in the coming weeks.

GALAX has just introduced the new GeForce RTX 3060 Metaltop Mini [FG] graphics card, a new GeForce RTX 3060-based graphics card on the super-small Mini-ITX form factor.

The new GALAX GeForce RTX 3060 Metaltop Mini [FG] graphics card rocks a single-fan design, while the "FG" in the name stands for "For Gamers". GALAX thinks by adding "FG" and it being "For Gamers" that the big bad crypto miners won't buy these... hah.

As for the measurements, we're looking at the card measuring in at just 16.8cm in length, 11.6cm in width, and 4cm in height. The single-fan design means it is nice and small and supports 0dB technology which means the single fan will disable when the GPU load is low enough (not gaming).

Meta today announced that the Mercenaries DLC package for Resident Evil 4 is officially in development for the Meta Quest. Along with that announcement, the company revealed that RE4 is the fastest-selling game on the platform. It's almost as if people really want AAA games in VR.

Capcom and Oculus (now Meta) released the Quest version of Resident Evil 4 on October 21st, and in just over a month, the game has become the fastest-selling title in the Quest platform's history. Meta has never released sales numbers for any of its headsets or games, but we know several titles have made millions of dollars in profits. Resident Evil isn't likely in the top-selling ranks yet, but it will be if the high sales volume continues. Beat Saber and Population: One have big head starts, though.

To keep the excitement about RE4 VR going, Capcom is working on a DLC expansion for the Quest title. The Mercenaries expansion will launch next year and let you experience more of Resident Evil in terrifying first-person VR. The Mercenaries expansion adds a hoard-mode experience to the game, where you need to fight off a never-ending hoard of Ganados until your rescue helicopter arrives.

AMD has a couple of new graphics cards are coming: the Radeon RX 6500M and Radeon RX 6300M, which will both feature the Navi 24 GPU.

We have heard about the Navi 24-powered GPUs before from Tom @ Moore's Law is Dead, with the entry-level Navi 24 GPU taking care of at least 6 new graphics cards from AMD. We should see the Radeon PRO W6500M, Radeon PRO 6300M, and then gaming SKUs in the Radeon RX 6500M and Radeon RX 6300M.

These 4 graphics cards are expected to join the already-known Radeon RX 6500 XT and Radeon RX 6400 series desktop graphics cards -- also powered by the same Navi 24 GPU. What we do know about the Navi 24 GPU is that it has a PCI Device ID of 7420-743F which has been spotted in Linux kernel/driver leaks previously.

It's been a couple of hot weeks of rumors and news about Intel's new Arc Alchemist family of GPUs, with Tom @ Moore's Law is Dead has unveiled new details about the Intel DG2-128EU GPU.

We should see Intel's new DG2-128EU GPU in desktop form with the Arc Alchemist, so expect 6GB of GDDR6 memory and a 96-bit memory bus. This beats out previous rumors of a 64-bit memory bus, but Tom also notes that we could see a 4GB GDDR6 variant, as well as a 64-bit mobile Arc Alchemist SKU in the future.

Tom expects the DG2-128EU GPU will have GPU clocks of between 2.2GHz and 2.5GHz, with a 75W TDP while Tom "can't promise they won't overclock it for desktop like Navi 24, but so far everything is low power". With the notes on power consumption, Tom continues: "with such low power, and 6GB of VRAM instead of 8GB, this thing can cost $179 or less with decent margins".

Intel's new flagship Arc Alchemist GPU has been spotted flexing some benchmark muscle on Geekbench, but with low GPU clocks and nowhere near a final driver, this isn't going to beat AMD or NVIDIA right now.

The GPU was spotted with detailed JSON data with 4 benchmark runs, with the GPU itself described as "OpenCL HD Graphics" or "Intel Xe Graphics". This GPU has 512 Execution Units and 12.7GB of VRAM, while the GPU was clocked at 1329MHz which from its max GPU clock of 2.1GHz is 63% lower.

Intel looks like it was testing the Arc Alchemist on an Intel Coffee Lake CPU, with an Intel Core i5-9600K processor, and not their latest 12th Gen Core "Alder Lake" CPU. But rather multiple generations old CPU and motherboard hardware are being used to test the very latest GPU.