Graphics Cards - Page 118

I really thought we'd see NVIDIA unveil its next-gen GeForce RTX 40 series graphics cards, and the new Ada Lovelace GPU architecture sporting an also next-gen display connectivity: DisplayPort 2.0 aka DP2.0, but nope.

NVIDIA's huge GeForce RTX 40 series GPU reveal came and went, and after it all happened one of the biggest disappointments was the lack of DisplayPort 2.0 connectivity. We've had DisplayPort 1.4 connectors forever now, and while HDMI 2.1 has joined the party that's really for big, high refresh rate TVs (HDMI 2.1 is capable of 4K120).

But, DisplayPort 2.0 is the future... people using GeForce RTX 4090s and GeForce RTX 4080s, and other GeForce RTX 40 series graphics cards in 2023, 2024, and 2025... all without DP2.0 connectivity. So DP2.0 starts taking off in 2023, more prevalent in 2024 and 2025, yet the biggest quantum leap in GPUs doesn't have the very latest display standard in the tail end of 2022, which sucks.

NVIDIA has provided more details on its next-gen GeForce RTX 40 series GPUs and their die sizes, transistor counts, and more for the upcoming AD102, AD103, and AD104 GPUs.

The company provided some more details on its flagship AD102 GPU, but some of the pieces of the AD103 and AD104 GPU puzzles weren't there. AnandTech's Ryan Smith reported the detailed specifications of the GPUs, where we now know that NVIDIA's next-gen AD102 GPU has a 608 mm² die, 76.3B transistors, AD103 has a 378.6 mm² die, 45.9B transistors, while AD104 has a 294.5 mm² die, 35.8B transistors.

We also know that the ROP count on Ada Lovelace is significantly higher, with AD102 rolling out with a huge 192 ROPs, AD103 with 112 ROPs, and AD104 with 80 ROPs. For comparison's sake, the current-gen GA102 "Ampere" GPU has 112 ROPs (so the same as AD103). Increased ROP count = higher rasterization performance in games.

Uh, so you're going to want to be real, real careful with the new 12VHPWR power connector... with ZOTAC warning users that the new GeForce RTX 4090 power cable has a limited service life of 30 connects and disconnects. Yeah, just thirty times. This isn't something super new, as current connectors can't just be connected and disconnected hundreds of times without damage.

NVIDIA's new GeForce RTX 4090 graphics card uses the new 16-pin PCIe Gen5 "12VHPWR" power connector, but if you don't have a new PSU ready with a native 16-pin connector... then you'll need the 4 x 8-pin to 12VHPWR cable which is limited to 30 connect/disconnects.

As for NVIDIA's new GeForce RTX 4090 graphics card, power consumption will be 450W while we're expecting up to 600W and above with custom RTX 4090 models, like the upcoming ZOTAC GAMING GeForce RTX 4090 AMP Extreme AIRO graphics card. You wouldn't want 450W to 600W or above flowing through a cable that could be damaged, so... be careful with your RTX 490 and PSU purchases.

NVIDIA unleashed its new GeForce RTX 4090 but now AIB partners are announcing their new custom RTX 4090 designs... and man... GIGABYTE's new custom AORUS GeForce RTX 4090 MASTER makes the word behemoth feel small.

The new AORUS GeForce RTX 4090 MASTER graphics card is one of the largest graphics cards that GIGABYTE has ever made, and I'm sure it's joined the club of one of the biggest graphics cards ever made, period.

We're talking about a card that is 35.8cm long -- not bad so far, but the AORUS RTX 4090 MASTER is 16.2cm wide making it a thick boi for sure. But when it comes to how tall the card is, that's where it's even chunkier: 75.1cm high.

NVIDIA showed off its next-gen GeForce RTX 4090 graphics card in a new test of Cyberpunk 2077 using a pre-release version of DLSS 3.

The performance improvement is absolutely astonishing with NVIDIA's new GeForce RTX 4090 powered with DLSS 3 enabled in Cyberpunk 2077, with performance skyrocketing from 60FPS average at 1440p maxed out, to an almost unbelievable 170FPS average (with DLSS 3 set to Quality, not to Performance mode to be specific).

If we compare this to the current-gen GeForce RTX 3090 Ti with DLSS 2 disabled, the RTX 3090 Ti spits out just 36FPS average (compared to 60FPS on the RTX 4090) while with DLSS 2 enabled on Quality mode performance bumps up just to 62FPS average.

NVIDIA has shown off its next-gen GeForce RTX 4090 Founders Edition graphics card during a recent demo, showing the GPU clocking close to 3.0GHz as Jensen promised.

The new GeForce RTX 4090 Founders Edition graphics card was powered by an Intel Core i9-12900K processor, running CD PROJEKT RED's visual showcase: Cyberpunk 2077. The game was run at 1440p using Ultra Ray Tracing and Psycho settings (maximum).

Cyberpunk 2077 running at the native 2560 x 1440 resolution on the GeForce RTX 4090 Founders Edition graphics card -- without DLSS enabled -- was running at 60FPS average. The AD102-300 GPU inside of the RTX 4090 was running at over 2.8GHz during this demo, sitting between 2810MHz and 2850MHz with cool temps of just 50-55C.

NVIDIA announced its huge upgrade in DLSS 3 upscaling technology with its Ada Lovelace GPU architecture reveal, where GeForce RTX 40 series GPU owners are in for a real, real huge performance leap with DLSS 3.

Cyberpunk 2077 is one of the best-looking games on PC, and it is super-powered with ray tracing enabled and then performance-boosted with DLSS 2.x but the new update coming for the game will insert DLSS 3 that will drive performance on RTX 40 series GPUs through the roof.

CD PROJEKT RED will push out a new update for Cyberpunk 2077 that will add a new Ray Tracing: Overdrive Mode that will boost the level of detail in the already beautifully-detailed game even higher. We have NVIDIA RTX Direct Illumination (RTXDI) which will make every single neon sign, street lamp, car headlight, LED billboard and TV accurate ray-traced lighting and shadows, bathing objects, walls, passing cars and pedestrians in accurate colored lighting.

NVIDIA has unleashed its next-gen Ada Lovelace GPU architecture, with 3 new GeForce RTX 40 series graphics cards announced... and monster performance teased.

During the recent GeForce Beyond broadcast, NVIDIA founder and CEO Jensen Huang said that the team has been testing Ada in the labs and have pushed it to some lofty limits. Jensen said: "we've overclocked Ada to past 3GHz in our labs".

NVIDIA's new GeForce RTX 4090 graphics card is a monster, where it's up to 2x faster than the GeForce RTX 3090 Ti thanks to Ada Lovelace's new DLSS 3-ready AI upscaling technology. The next-gen AD102-300 GPU features 16384 CUDA cores and a GPU boost clock of 2.52GHz with 24GB of GDDR6X memory clocked at 21Gbps bandwidth on a 384-bit memory bus for 1TB/sec+ memory bandwidth.

Inno3D has just unveiled a few new interesting GeForce RTX 40 series graphics cards, with the new flagship GeForce RTX 4090 iCHILL Frostbite graphics card.

The new Inno3D GeForce RTX 4090 iCHILL Frostbite features a tiny design that comes in at under a dual-slot, with the design of the cooled allows the components to be even closer by reducing the thickness of the thermal pads underneath.

Inno3D used software to simulate how water flowed, which provided the company with a more efficient design that also packs digital aRGB LEDs that will make for a sleek look inside of your gaming PC. The new GeForce RTX 4090 iCHILL Frostbite uses copper in its water coolers that are nickel-plated which boosts acid resistance and stops the nickel plating from peeling off, just like the previous-gen Frostbite card.

Now that the cat is out of the bag when it comes to NVIDIA's next-generation Ada Lovelace GPU architecture and new GeForce RTX 40 series graphics cards, ZOTAC is here with 9 new custom GeForce RTX 40 series graphics cards.

ZOTAC has three of each model: GeForce RTX 4090 24GB, RTX 4080 16GB, and RTX 4080 12GB graphics cards in AMP Extreme AIRO, Trinity OC, and Trinity variants. ZOTAC is using an all-new aerodynamic-inspired design for its new ZOTAC GAMING GeForce RTX 40 series graphics cards, as well as more key innovations that push the limit in gaming performance, cooling efficiency, noise levels, and durability.

The new flagship ZOTAC GAMING GeForce RTX 4090 AMP Extreme AIRO graphics card features a counter-rotating fan design that provides smooth airflow, extreme power phase design for stable power delivery and a strong metal die-cast backplate that provides improved durability.

NVIDIA might have unveiled its next-gen Ada Lovelace GPU architecture during its GeForce Beyond broadcast, where we were introduced to a trio of new GeForce RTX 40 series graphics cards, but now we are getting more details on the new flagship AD102 GPU.

The next-gen NVIDIA AD102 GPU will be at the center of the GeForce RTX 4090 graphics card, with AD102 packing up to 76.3 billion transistors, with a die size of 608.4 mm². NVIDIA's new Ada Lovelace GPUs are being made on TSMC's new 4N process node, with 2.78x the transistor density of its current-gen GA102 "Ampere" GPU made on Samsung's custom 8nm process node.

NVIDIA's new AD102 GPU has up to 18432 CUDA cores, up to 568 4th Gen Tensor Cores, and up to 142 3rd Gen RT cores while NVIDIA's new Ada Lovelace GPU architecture features Shader Execution Reordering (SER) which makes rasterization operations much, much faster: offering up to 25% more gaming performance.

NVIDIA has finally detailed its next-gen Ada Lovelace GPU architecture, with the new GeForce RTX 4090, RTX 4080 16GB and RTX 4080 12GB graphics cards... and now the RTX 6000 workstation GPU.

The new NVIDIA RTX 6000 workstation GPU is based on the Ada Lovelace GPU architecture, with up to 2x to 4x the performance of the previous generation RTX A6000 workstation card based on the Ampere GPU architecture. NVIDIA designed the new RTX 6000 for neural graphics and advanced virtual world simulation as well as Ada generation AI and programmable shader technology.

This makes the NVIDIA RTX 6000 workstation GPU the best choice if you're building for the metaverse and NVIDIA Omniverse Enterprice, with the very latest generations of render, AI, and shader technologies all spooled into a huge 48GB of GDDR6 ECC memory.

ASUS is asking us to "ascend to new heights" with the new GeForce RTX 4090 and GeForce RTX 4080 graphics cards, with the company detailing new ROG Strix and TUF Gaming designs.

The company has just unveiled new Ada Lovelace GPU-powered offerings in the form of GeForce RTX 4090, GeForce RTX 4080 16GB, and GeForce RTX 4080 12GB graphics cards. The new flagship ASUS ROG Strix GeForce RTX 4090 is here to topple your games and benchmark charts.

The new custom ASUS ROG Strix GeForce RTX 4090 graphics card features a 3.5-slot design, with ASUS going back to the drawing board for the heat sink design of its new ROG Strix GeForce RTX 4090. ASUS says there's a new vapor chamber, 30% more surface area for heat dissipation when compared to the ROG Strix GeForce RTX 3090.

MSI has unveiled its new fleet of custom GeForce RTX 4090 and GeForce RTX 4080 series graphics cards, with new members of the SUPRIM, SUPRIM LIQUID, GAMING TRIO, and VENTUS cards here to be detailed.

The new MSI GeForce RTX 4090 SUPRIM is the new flagship Ada Lovelace card from the company, cooled by the TRI FROZR 3S thermal solution, something MSI calls its "most advanced air cooling system". MSI cools the RTX 4090 SUPRIM by dissipating heat from critical board components with TORX FAN 5.0, up to 10 Core Pipes, Airflow Control finds featuring new Wave-curved 3.0 edges, and air antegrade fins.

MSI is outfitting its new custom RTX 4090 and RTX 4080 16GB graphics cards with a vapor chamber, while the RTX 4080 12GB gets a massive nickel-plated copper baseplate. MSI will be using its business-as-usual brushed aluminum on the exterior of the RTX 4090 and RTX 4080 16GB SUPRIM X graphics cards, while the backplate impart an armored aesthetic while reinforcing the length of the card.

NVIDIA has officially revealed its next-gen GeForce RTX 40 series "Ada Lovelace" GPUs with the introduction of the GeForce RTX 4090, and two new GeForce RTX 4080 (16GB + 12GB) graphics cards.

Now that the launch is out of the way, NVIDIA has detailed its upcoming GeForce RTX 40 series Founders Edition graphics cards, discussing the upgrades that are under the RTX 40 series FE hood, and so much more. NVIDIA says that they've further optimized the Dual Axial Flow Through system, increasing fan sizes and fin volume by 10%, and upgrading to a 23-phase power supply.

NVIDIA says that memory temperatures "are reduced", while the new, "substantially more powerful" Ada GPUs are "kept cool in ventilated cases, giving gamers excellent overclocking headroom". NVIDIA is reducing cable clutter once again, with the new GeForce RTX 40 series Founders Edition graphics cards featuring a next-gen ATX 3.0-capaple PCIe Gen5 16-pin power connector.

COLORFUL has just announced a bunch of new GeForce RTX 4090 and GeForce RTX 4080 16GB + RTX 4080 12GB graphics cards, so let's dive right into what the next-gen Ada Lovelace offerings have in store.

The company is introducing three different custom GeForce RTX 4090 graphics cards today, with COLORFUL announcing the iGame GeForce RTX® 4090 Vulcan OC-V, the iGame GeForce RTX® 4090 Neptune OC-V, and the GeForce RTX® 4090 NB EX-V graphics cards.

COLORFUL's new flagship iGame GeForce RTX® 4090 Vulcan OC-V features an updated look over its Ampere-based predecessor, with the new iGame RTX 4090 Vulcan OC-V featuring COLORFUL's new Hurricane Scythe Blade: a new and improved fan blade design that produces more airflow at lower noise levels compared to the previous-gen Storm Chaser fan design.

NVIDIA has just announced its next-gen Ada Lovelace GPU architecture and out of the box, we have the announcement of NVIDIA's next-gen AI upscaling technology: DLSS 3.

DLSS 3 launches with Ada Lovelace, with NVIDIA promising FPS boosts of up to 4x with DLSS 3 enabled. NVIDIA's new DLSS is the next evolution of neural graphics, which combines DLSS Super Resolution, all-new DLSS Frame Generation, and NVIDIA Reflex, running on the new hardware capabilities of GeForce RTX 40 Series GPUs.

NVIDIA's new DLSS 3 offers up to 4x performance "over brute-force rendering" with DLSS 3 already adopted into the gaming ecosystem, with over 35 games supporting DLSS 3 and much more on the way. DLSS 3 is powered by the 4th Gen Tensor Cores and Optical Flow Accelerator inside of the NVIDIA Ada Lovelace GPU architecture, which is inside of the new GeForce RTX 40 series graphics cards.

NVIDIA has finally announced its next-gen Ada Lovelace GPU architecture and with it three new GeForce RTX 40 series graphics cards: the flagship GeForce RTX 4090, and two new GeForce RTX 4080 graphics cards.

The new GeForce RTX 4080 is exactly as the rumors suggested: split into the RTX 4080 16GB and RTX 4080 12GB. NVIDIA's new GeForce RTX 4080 16GB features the AD103-300 GPU made on TSMC's new 4N process node, with 9728 CUDA cores, and a GPU boost clock of up to 2510MHz.

There's 16GB of GDDR6X memory on a 256-bit memory bus clocked at 22.5Gbps, offering up to 720GB/sec of memory bandwidth. NVIDIA's new GeForce RTX 4080 16GB graphics card has a default TGP of 320W.

NVIDIA has just announced its next-gen Ada Lovelace GPU architecture and three new GeForce RTX 40 series graphics cards, with the new flagship GeForce RTX 4090 finally detailed in all its next-gen GPU glory.

The new NVIDIA GeForce RTX 4090 graphics card features the AD102 GPU and made on TSMC's new 4nm process node, with a chunky 76 billion transistors inside of the RTX 4090. The new AD102-300 GPU has 16384 CUDA cores and a GPU boost clock of up to 2520MHz (just like all of the leaks have been saying, really).

NVIDIA has its 3rd Gen RT Cores and 4th Gen Tensor Cores inside of the Ada Lovelace GPU-powered GeForce RTX 40 series graphics cards, as well as support for NVIDIA's next-gen DLSS 3 upscaling technology. NVIDIA's next-gen GeForce RTX 4090 still rolls out with 24GB of GDDR6X memory clocked at 21Gbps (just like the RTX 3090 Ti), which will be on a 384-bit memory bus that will feature up to 1TB/sec+ of memory bandwidth.

I'm sitting in front of my PC at 11pm at night my time waiting with excitement for NVIDIA and its big next-gen GeForce reveal, and bam... AMD teases its next-gen RDNA 3 GPU reveal for November 3.

Just 2 hours away... 120 minutes and AMD is here to announce its next-gen Radeon RX 7000 series "RDNA 3" graphics card family will be unveiled on November 3. The news is coming directly from Scott Herkelmen, Senior Vice President and General Manager at AMD Radeon who tweeted out the news and told gamers to save the date for RDNA 3.

AMD is showing that it's a bit tougher this generation, after a very strong round with RDNA 2 the company is ready to strike again with RDNA 3 against Ada Lovelace. We've been hearing more and more about AMD's next-gen Radeon RX 7900 XT flagship GPU, rocking Navi 31 with AIB partners ready to clock the GPU "to the moon" as well as 24GB of GDDR6 memory (up from 16GB on the RX 6950 XT and 6900 XT cards).