Graphics Cards - Page 122

TSMC is seeing its 3 biggest customers revising their orders all at the same time: AMD, Apple, and NVIDIA for their next-gen RDNA 3, iPhone 14, and Ada Lovelace products, respectively.

NVIDIA is the big one that we'll tackle in this article because they're in a real precarious spot: NVIDIA has been bedding Samsung for a while now, leaving the South Korean arms for the arms of Taiwan and back to its old faithful: TSMC (Taiwan Semiconductor Manufacturing Company) for its next-gen Ada Lovelace GPU architecture and upcoming GeForce RTX 40 series graphics cards... well, they've hit a snag.

According to the latest report out of DigiTimes and translated by @RetiredEngineer on Twitter: "Faced with abrupt drop-off in PC demand and customers' inventory adjustment, AMD and NVIDIA has no choice by to reduce orders".

Arm has just announced its next-gen flagship GPU with a really interesting name that I like the sound of more and more as I see it: Immortalis.

The new Arm Immortalis-G715 GPU is the successor to Arm's super-successful Mali GPU -- which has shipped 8 billion GPUs to be precise -- packing hardware-based ray tracing (RT), variable rate shading (VRS), and more. Arm says that its new Immortalis-G715 GPU will support ray tracing and variable rate shading across all of its Immortalis GPUs.

Arm's new Immortalis-G715 GPU is the first Arm GPU to feature hardware-based ray tracing support, designed specifically for mobile. We have ray tracing on the PC and consoles and have had it for a while now, but Arm is wanting to get ray tracing support into smartphones and now it's on its way.

AYANEO has just teased its next-gen gaming handheld, which is also the world's first gaming handheld system that will include either Intel or AMD discrete graphics cards.

The new AYANEO NEXT 2 will include an Intel CPU and Intel GPU, or an AMD CPU and AMD GPU together, for the first time in history. AYANEO CEO Arther Zhang confirmed the news himself, with the AYANEO NEXT 2 being the first to use a non-integrated GPU -- a discrete GPU -- inside of one of its designs, giving gamers the choice between Intel and AMD.

AYANEO will be using an Intel Alder Lake CPU with an Intel DG2 Mobile GPU for its Intel-powered AYANEO NEXT 2 handheld gaming system, while the AMD-powered version will include an AMD "6000 series" CPU and an AMD 6000 series mobile GPU.

A fresh new rumor on AMD's next-gen RDNA 3 GPU architecture has floated up into the rumor mill, with AMD software engineers pushing out new patches for the new GFX11 architecture -- otherwise known as RDNA 3.

The new patch teases AMD is working on its own instructions that can operate on matrixes, with support for advanced artificial intelligence algorithms, to super-power their super-resolution technologies on RDNA 3-based graphics cards, spotted by @0x22h on Twitter. Effectively, this would be like Tensor cores on an NVIDIA GPU, hardware-based assistance for DLSS.

AMDGPU is a backend for AMD GPUs for LLVM compiler library, which gets updated by AMD employees, and if you're keen-eyed enough you can get a sneak into what next-gen GPU architectures will bring. In this case, the Wave Matrix Multiply-Accumulate was added to the new GFX11 architecture, GFX11 being the codename of AMD's next-gen RDNA 3-based Radeon RX 7000 series GPUs.

EVGA's new PowerLink 41s has been announced, acting as a next-gen cable management accessory for your EVGA GeForce RTX 3090 Ti FTW3 graphics card.

The new EVGA PowerLink 41s provides maximum stability, improved case airflow, and of course it glows with fully-customizable ARGB LED lighting. EVGA has designed its PowerLink 41s exclusively for its GeForce RTX 3090 Ti FTW3 series of GPUs, which rock the new 16-pin PCIe power connector... this is where PowerLink 41s helps.

PowerLink 41s connects to the end of your EVGA GeForce RTX 3090 Ti FTW3 graphics card, and turns the single 16-pin PCIe power connector into 4 x 8-pin PCIe power connectors, which then get connected individually to your power supply. You'll also get some beautiful RGB lighting on the back of it, so the EVGA PowerLink 41s connected to an EVGA GeForce RTX 3090 Ti FTW3 will look beautiful... cleaner, and has RGB lighting to boot.

The closer we get to AMD's next-gen RDNA 3 GPU launch, the more details that are leaking out: today, we have news that the rearchitected RDNA 3 GPU Compute Units will have "enhanced ray tracing" capabilities, and even faster GPU clocks.

AMD itself has confirmed the news of the boosted ray tracing capabilities and higher GPU clocks during its Financial Analyst Day 2022. AMD's SVP of Engineering at Radeon Technologies Group, David Wang, explained that the company has architectured the compute units inside of RDNA 3 that will increase ray tracing capabilities.

We don't know what these "enhanced ray tracing capabilities" are going to do, but it should be obvious that ray tracing performance and upgraded (and new) features inside of the next-gen AMD RDNA 3-based Radeon RX 7000 series GPUs will be plenty. AMD will better compete against NVIDIA in the ray tracing department, as NVIDIA is the clear dominating GPU in ray tracing, but RDNA 3 won't be messing around.

We only just heard about Intel's first Arc workstation GPU -- the Arc Pro A40 -- just yesterday, and now we're already hearing about the Intel Arc Pro A50 workstation GPU.

Intel recently launched its new desktop Arc GPUs in a China exclusive, with benchmarks and more being revealed over the last few days, then news of the Arc Pro GPUs started. First, we heard about the Intel Arc Pro A40 workstation GPU, and now news of the Arc Pro A50 workstation GPU is here.

In new listings on SiSoft Sandra, the Intel Arc Pro A40 and Arc Pro 40 workstation GPUs are found -- with the new Arc Pro A50 workstation featuring the full ACM-G11 GPU with 8 Xe-Cores (128 Execution Units and 1024 FP32 cores). Both the Intel Arc Pro A50 and Arc Pro A40 workstation GPUs seem to be packing 6GB of GDDR6 memory, which should be pumping through a 96-bit memory bus.

AMD isn't too far away now from launching its next-gen RDNA 3-based Radeon RX 7000 series GPUs, and now we're hearing about higher power consumption on the RDNA 3 chips... because NVIDIA is using more power.

The news is coming from Tom's Hardware, which spoke with AMD Senior VP Sam Naffziger, who was one of the minds behind AMD's revolutionary chiplet architecture. AMD has recently said that it would have a 50% projected performance-per-watt uplift with its new RDNA 3 GPUs over RDNA 2, but now those numbers are getting clearer.

Naffziger said that since NVIDIA is cranking up the power consumption on its next-gen Ada Lovelace-powered GeForce RTX 40 series GPUs, that it would be boosting the power consumption on its RDNA 3-based Radeon RX 7000 series GPUs.

NVIDIA's next-gen GeForce RTX 4090 Ti and GeForce RTX 4090 graphics cards -- in Founders Edition form -- have been teased in some new renders. Just remember, this could be completely fake, so I've got a link here to make sure this is safe.

The new renders are courtesy of Moore's Law is Dead, with the alleged NVIDIA GeForce RTX 4090 Ti Founders Edition, and NVIDIA GeForce RTX 4090 Founders Edition both shown off in their BFGPU goodness. NVIDIA will reportedly using a 3-slot, or 3.5-slot cooling design with more fins and more heat sink surface area with its new Ada Lovelace GPUs in the high-end RTX 4090 Ti and RTX 4090 designs.

In a new tweet about his video, Tom @ Moore's Law is Dead explains: "Tonight I share renders of the leaked #NVIDIA RTX 4090 Ti cooler, and break down what there is to learn about AD102 from said leak! 💚🧵 I also provide information about when you can expect decent Lovelace Volume this fall".

AMD is celebrating the first anniversary of the first-gen FidelityFX Super Resolution 1.0 (FSR 1.0) technology, by making its next-gen FSR 2.0 technology open source, and available to download right now.

AMD has now published the source code of FSR 2.0 on GitHub, which should see many more FSR 2.0-capable titles in the future. AMD explains that with the introduction of FSR 2 "our temporal upscaling solution earlier this year, there are now over 110 games that support FSR. The rate of uptake has been very impressive - FSR is AMD's fastest adopted software gaming technology to date".

With over 110 games supporting FSR 1.0, there is now a dedicated FSR 2.0 page that also includes the FSR 2.0 API, the full C++, and HLSL source code behind it, with AMD adding that you'll "also discover our Cauldron-based sample and comprehensive API documentation to help you with your integration".

NVIDIA looks to be making some changes to its upcoming GeForce RTX 40 series GPUs, with leaker "kopite7kimi" revealing "some updates" on the new Ada Lovelace graphics cards on Twitter.

In a new tweet, the leaker has provided some updated specs on NVIDIA's three first Ada GPUs: the second-flagship GeForce RTX 4090, the new GeForce RTX 4080, and the GeForce RTX 4070. Let's tackle the elephant in the room: the GeForce RTX 4090.

The updated specs for NVIDIA's flagship GeForce RTX 4090 see its CUDA core configuration tweaked, with kopite7kimi noting that the AD102-300 GPU will have 16384 CUDA cores (up from 16128 CUDA cores). The SMs (Streaming Multiprocessors) have changed slightly, with the leaker saying NVIDIA is using 128 SMs on the GeForce RTX 4090 (up from 126).

Intel's new Arc desktop GPUs are only just launching now... at least as an exclusive in China... but we're already seeing the first whispers of a new Intel desktop workstation GPU.

A new "Intel Arc Pro" graphics card has been spotted on the South Korean National Radio Research Agency (RRA), where the certification for Intel's new Arc Pro GPU is listed with certification number "RR-CPU-DG2IPC" on June 22, 2022 -- today.

Intel has changed its Arc GPU roadmap a bit over the last 6 months, but it did have Arc mobile GPUs in notebooks in Q1 2022 -- promised Arc desktop GPUs in Q1 2022, then Q2 2022 and barely made it with an exclusive, super-limited launch in China -- with Arc workstation GPUs teased for Q3 2022.

Intel's first foray back into the GPU space since its AGP-powered i740, the new Arc A380 desktop GPU is here... at least kinda... released in China as an exclusive for now.

The new custom GUNNIR A380 Photon OC graphics card is the first, and only (so far) custom Arc desktop graphics card, but that's something we already knew. What's new here is that we have the first benchmarks tested by Shenmedounengce benching the Core i5-12400 processor, mid-range B660 motherboard, and DDR4 memory.

Intel's new Arc A380 desktop GPU was benched against the NVIDIA GeForce RTX 3050 and GeForce GTX 1650, while AMD's Radeon RX 6500 XT and Radeon RX 6400 were also tested. These are all low- to mid-range graphics cards, against the Intel Arc A380 with its ACM-G11 GPU (up to 2.45GHz GPU boost clocks) with Xe-Cores and 6GB of GDDR6 memory on a 96-bit memory bus.

AMD is continuing to march towards its next-gen RDNA 3 GPU architecture, with the future Radeon RX 7000 series GPUs to use the flagship Navi 31 GPU... but now we're hearing about something faster, a dual-GCD masterpiece.

The rumors of a new Navi 3X GPU are coming from leaker "@Greymon55" on Twitter, who said: "there seems to be 16384SP 8SE Navi 3X, but I don't know if it really exists or if it's a gaming card". A follow-up tweet added that it will be a 2023 release, with "specifications to be determined".

The dual-GCD (Graphics Compute Die) is where the action will be happening, with the consumer and gaming side of the Navi 31 GPU offering 12288 GPU cores (at least according to the current rumors), the new Navi 3X GPU with 16384 GPU cores should power a next-gen Radeon PRO workstation GPU.

The totally next-gen PCI Express (PCIe) 7.0 specification has been announced today at the PCI-SIG Developers Conference 2022, ushering in yet another round of doubling the data rate: now up to 128GB/sec.

The new PCIe 7.0 x16 standard will offer up to 512GB/sec bi-directionally, and while your GPU would be sitting on its hands at that point -- graphics cards of today don't need the wicked fast upgraded speeds we're getting with PCIe 5.0, PCIe 6.0, and the just-announced PCIe 7.0 -- the new speeds will be a boon for HPC, AI, and supercomputers.

This means we're going to see next-gen PCIe 7.0 x4 NVMe M.2 SSD of the future pushing a huge 128GB/sec -- up from the 64GB/sec on PCIe 6.0 x4, the 32GB/sec on PCIe 5.0 x4, the 16GB/sec on PCIe 4.0 x4, and 8GB/sec on PCIe 3.0 x4. 128 gigabytes per second, transferring on that tiny M.2 SSD on your motherboard.

The first custom Intel Arc A380 desktop GPU has launched... well, in China at least... with GUNNIR's new Arc A380 Photon listed for $599.

GUNNIR's new custom Arc A380 Photon GPU is listed for 3999 RMB (around $595) on the official JD webstore, but it's unavailable because it's sold out (obviously). JD is waiting for its shipment, with all of the new Intel Arc A380 graphics cards shipping with slower GDDR6.

Intel updated its own Arc A380 website, detailing the 6GB of GDDR6 memory at 15.5Gbps bandwidth -- down from 16Gbps -- reducing the memory bandwidth down to 186GB/sec, down from 192GB/sec. Intel has also confirmed that its Arc A380 desktop GPUs launching in June are limited to pre-built PCs only, so the Chinese JD.com website is the only place allowed to sell the Arc A380 GPUs in China.

Intel's new Arc A380 desktop GPU has finally launched, at least in China, with its 6GB of GDDR6 memory being reduced in bandwidth silently.

GUNNIR launched its new custom Arc A380 Photon OC 6G graphics card last week with its 6GB of GDDR6 memory clocked at 15.5Gbps, down from 16Gbps. The 6GB of GDDR6 memory is on a 96-bit memory bus, with the 15.5Gbps bandwidth packing 186GB/sec bandwidth -- down from the 192GB/sec on the 16Gbps GDDR6.

The official Intel website and its Arc A380 GPU listing have 6GB of GDDR6 at 15.5Gbps bandwidth, with the company also clarifying some of the issues with what was happening with HDMI 2.1 on its Arc A380 graphics cards. Intel Arc A380 officially supports HDMI 2.1 but it is up to AIB partners to add it, partners... please use HDMI 2.1 and not HDMI 2.0 on ALL of your Arc GPUs.

I'm sure you've heard by now that the cryptocurrency market has had the arse fall out of it, with Bitcoin circling $20,000 or so -- leaving crypto miners, small, and big -- shuffling on the spot.

In a new report from Bloomberg, we're being told crypto miners across the world spent around $15 billion in 2021 alone... taking up more GPUs than gamers. Yes, crypto miners purchased more graphics cards than gamers, which should shock some, and not shock others that know crypto miners are buying 10s, 100s, or 1000s of graphics cards at once.

Bloomberg reported: "Ethereum miners have spent approximately $15 billion on graphics processing units (GPUs), according to Bitpro Consulting, and that doesn't include ancillary costs like wiring and transformers".

GALAX has just unveiled its new GALAX GeForce RTX 3060 Vegetables Fairy 'Cabbage Dog' special edition graphics card... which... well... I'll let you see it first:

What is this thing? The new card is based on the Vegetables Fairy concept by Japanese creator "PonkichiM" who envisions animals as foods and vegetables. Each of the animals are based on various foods, including: Garlic Cat, Shiitake Mushroom, Lotus Root, Vegetables Red Fox Radish, Vegetables Squirrel, and Cabbage Dog.

The GPU isn't any different, with GALAX using a custom PCB and shroud design for its new GALAX GeForce RTX 3060 Vegetables Fairy 'Cabbage Dog' special edition graphics card, but inside we have the GA106-302 GPU.

NVIDIA's next-gen AD102 GPU has been rumored to be a power-hungry monster since day one, with leaks suggesting between 600W and 900W of power consumption.

The new Ada Lovelace GPU architecture and its flagship AD102 GPU have a power limit of 800W according to leaker "kopite7kimi" but adds at the end of his tweet "I don't think we need to use the full power cap". I've said in previous articles that I think the 600-800W monster AD102 GPU we keep hearing about has to be a new TITAN RTX graphics card.

NVIDIA launching a new GeForce RTX 4090 Ti and or RTX 4090 with 800W of power sounds insane, but 600W doesn't... because the not-so-old GeForce RTX 3090 Ti uses 450W out of the gate. We keep hearing 600W+ but then these 800W rumors are just as common in the rumor mill. The leak includes that the AD102 GPU will use 450W, AD104 with 400W, and AD106 with 260W.