Graphics Cards - Page 191

Intel has been slowly building out the Justice League of GPU marketing teams leading into its future graphics card launches, with yet another member of Team Red joining Team Blue.

I can exclusively report that Heather Lennon, who built the awesome AMD social and community strategy for the company over 10 years has now joined the ranks of Intel. Heather build up the Team Red community and won herself PR Week honors for Campaign of the Year, as well as Top 30 Under 30 from PR News in 2014.

Lennon secured a huge 40 awards for marketing and digital marketing for AMD before leading their North American marketing for AMD's own Best Buy account which handled both Radeon and Ryzen products for the company.

The world of 5nm is one step closer to reality with TSMC announcing it has completed the infrastructure design of its upcoming 5nm node.

TSMC's new 5nm node will roll out with the second generation of its extreme ultraviolet (EUV) as well as deep ultraviolet (DUV) lithography. The new 5nm node will see chips made for next-gen SoC designs, 5G devices, AI, and high-performance computing.

We are told to expect, from early numbers on an ARM Cortex-A72 core that TSMC's new 5nm process will have 1.8x the density of 7nm, and a nice 15% increase in clock speeds. Not bad at all.

The latest version of HWiNFO has preliminary support for AMD's next-gen Navi GPU architecture, but also a new mysterious CPU architecture from Intel teased as Emmitsburg.

HWiNFO v6.04 also features added support for Intel's new Cooper Lake and Snow Ridge, as well as full monitoring support for AMD's still-kinda-new Radeon VII graphics card. There is also 'improved' Zen 2 support with the latest version of HWiNFO and a bunch of other things tweaked, added, and now supported. You can grab HWiNFO v6.04 right here.

A few people replied to the original tweet, including Ashraf Eassa who is a Senior Technology Specialist with The Motley Fool, where he said Emmitsburg is "probably CPL/ICX PCH", meaning that Emmitsburg will be the chipset codename for the upcoming Cooper Lake/Ice Lake-X platform on LGA4189. He added that he feels like this "will be the last PCH before SPR. Then I/O will just be another chiplet on the package".

We knew it was going to happen, but now AMD itself has confirmed that it will be unveiling 7nm products at Computex 2019 that will include both next-gen Zen 2 processors and Navi GPUs.

A just-released Computex Taipei 2019 press release says that AMD will host a keynote called "The Next Generation of High-Performance Computing" at Computex 2019 on May 27, 2019. The company said it will be detailing new 7nm AMD EPYC 'Rome' CPUs, 3rd-gen Ryzen CPUs which will be based on the new Zen 2 architecture on the 7nm nodew as well as "graphics cards based on the next-generation Navi architecture".

The company says that all of these new products have been designed to "create exceptional experiences for gamers and creators as well as help solve many of the toughest challenges in our lives".

AMD have squished a bunch of bugs in its new Radeon Adrenalin Edition 19.4.1 drivers, with Radeon VII and Radeon RX Vega series graphics card owners with more than 3 monitors shouldn't have any more problems.

The full list of fixed issues include World of Warcraft patch 8.1.5 or later having issues when MSAA is enabled, Radeon WattMan auto overclocking not raising the engine clocks past default levels on Radeon RX vega graphics cards, and more. The full list of fixed issues, known issues, and important notes is below. You can grab the new Radeon Adrenalin 19.4.1 drivers here.

Fixed Issues

NVIDIA announced the Turing-based GeForce GTX 16 series graphics cards with the surprise launch of the GeForce GTX 1660 and GTX 1660 Ti which will soon be joined by the GTX 1650 and GTX 1650 TI according to the latest rumors.

The new GeForce GTX 1650 will reportedly roll out on the Turing TU117 GPU, compared to the Turing TU116 chip used on the GTX 1660/1660 Ti. The memory will be knocked down to GDDR5 on the GTX 1650 while the GTX 1650 Ti will reportedly debut with GDDR6, both with 4GB.

I haven't heard a peep about these new cards in official form, but have heard lots about them from various sources. We should expect a launch on April 22 for the GTX 1650 according to VideoCardz, and that's not too far away at all.

NVIDIA has just lost a major player on its team with director of technical marketing Tom Peterson leaving the company after nearly 15 years with Team Green.

Petersen announced the news on his personal Facebook account, where he said: "Today was my last day as an NVIDIA employee. I'll miss them. They carried me through some tough times and I am eternally grateful".

Rumor has it that Petersen has left for Intel, which has been vacuuming up talent with no remorse. WCCFTech is reporting from their own sources that Petersen is joining Intel as an Engineering Fellow and will be "reporting to Ari Rauch". Their report continues saying that Petersen will be responsible for "defining and delivering on the quintessential gaming experience - something Intel is going to be very particular about going forward".

NVIDIA didn't unveil a new GPU ar chitecture during its GPU Technology Conference last week, where I had some ponderings on whether we'd see the next-gen Ampere GPU architecture on 7nm unveiled, ultimately we didn't.

Jensen Huang, CEO and founder of NVIDIA, addressed this during GTC 2019 where he sad the company isn't in any rush to get mass produced 7nm GPUs because of the confidence he has in Turing. Turing is on the 12nm node and is more efficienct than AMD on 14nm (Vega 10 = Radeon RX Vega 64) and 7nm (Vega 20 = Radeon VII). He said: "What makes us special is we can create the most energy-efficient GPU in the world at anytime, and we should use the most affordable technology. Look at Turing. The energy-efficiency is so good even compared to somebody else's 7nm".

AMD was the first to reach the 7nm node with its new Vega 20 GPU powering the Radeon VII, but even on the exciting new node the Vega architecture can't begin to touch the efficiency and raw power of NVIDIA's Turing GPU architecture. Hell, even the previous-gen Pascal GPUs on 14nm are more power efficient than the 7nm Vega 20. NVIDIA has been absolutely nailing power efficiency on the last few generations of GPUs, learning and making huge leaps and bounds from the Fermi GPU fiasco.

Team Green is leading right into April with a window of opportunity for its marketing department: April 20 is right around the corner, so how better to celebrate 4/20 with a new GeForce 420.00 driver. Right?!

If you're not up with all the hipster lingo, 420 is a reference to - as the dictionary states it "used to refer to cannabis or to the act of smoking cannabis" and that "20th April (abbreviated 4/20 in the US), considered as an occasion for smoking or celebrating the smoking of cannabis".

Then also consider that NVIDIA is often referred to as Team Green (Team Red = AMD, Team Blue = Intel) and that green is the color of weed, 'green' is also another term for marijuana so the references and connections just keep piling up. Team Green releasing GeForce 420.00 drivers on 4/20 is too good to pass up, NVIDIA. You know what to do.

NVIDIA has just released a new batch of Game Ready GeForce drivers with the new GeForce 419.67 drivers dropping, with optimizations for Battlefield V's new battle royale mode Firestorm. You can download the new GeForce 419.67 drivers right here.

Not only that, but we have optimizations for the new Shadow of the Tomb Raider update that offers RTX features like ray-traced shadows and DLSS. There's also optimizations for Sekiro: Shadows Die Twice, and support for two more G-Sync compatible monitors in the ASUS VG278QR and ASUS VG258.

NVIDIA users can enable NVIDIA Surround with G-Sync compatible displays, if you do the following:

Samsung had some interesting things to show at NVIDIA's GTC 2019 this year, with the latest version of High Bandwidth Memory in something called Flashpoint, which offers a 33% increase in memory performance over HBM2.

We're looking at 3.2Gbps of bandwidth per pin, with double the density to 16Gb per die in stacks of 8. This means we're looking at a single package that can pack 16GB of HBM2E with up to 410GB/sec of memory bandwidth, but in a 4 stacks of HBM2E we're looking at an insane 64GB at 1.64TB/sec of memory bandwidth. The current 4x 4-Hi stacks of HBM2 on the AMD Radeon VII has 16GB with 1TB/sec of memory bandwidth, so this is quite the increase in bandwidth.

Jinman Han, Senior Vice President of Memory Product Planning and Application Engineering Team at Samsung Electronics explains: "Flashbolt's industry-leading performance will enable enhanced solutions for next-generation datacenters, artificial intelligence, machine learning, and graphics applications. We will continue to expand our premium DRAM offering, and improve our 'high-performance, high capacity, and low power' memory segment to meet market demand".

AMD paved the way for much better looking UI for its graphics control panel, but it is not perfect. But when you compare it to the years-old NVIDIA Control Panel for GeForce graphics cards, AMD is in the future.

Intel has previously teased its upcoming Graphics Command Center, and now we have our first official looks at what to expect. Oh, and it's been released and is on the Microsoft Store right now. You can see in the above shot that the Graphics Command Center starts off by just looking great, with a bunch of different areas to click into from the left hand panel: home, display, video, system, support and preferences.

In the display menu you'll find everything you need to know about the native resolution, refresh rate, scale, and rotation of your display. I'm using the Dell UP3218K monitor which is a native 8K panel at 60Hz here in this shot.

Intel hosted some members of a newly-formed graphics card community, a group of people surfing the hype wave of Intel's upcoming launch of graphics card for both the professional and gaming markets.

The Odyssey event was held during GDC 2019 in San Francisco, with a few different concept designs teased that fans have submitted. Intel being this confident showing off concept designs leads me to hoping that they actually use them, even if we get a launch of a few different SKUs, the same card/specs but different designs would be cool.

They look very similar to the shown-off-but-never-released Radeon Vega Nano, which Chris Hook showed off leading up to the launch of Vega. Hook is now working at Intel in pretty much the same role he held at RTG, and now we're seeing Vega Nano-like designs from Intel's upcoming graphics cards. Funny that.

NVIDIA has released some interesting stats on their GPU adoption, with new numbers releasing during their recent Investor Day event detailing Turing, Pascal, and older-gen GPU adoption.

The company has said that Turing GPUs have sold 45% more than Pascal GPUs in the first 8 weeks of launch, and considering the harsh reception and huge prices of the GeForce RTX cards, it hasn't stopped NVIDIA from selling a bunch of them. But how much penetration has Turing had into gamers' PCs?

According to NVIDIA's own graph we can see that just 2% of NVIDIA's consumers have upgraded to a Turing GPU, while 50% are using Pascal (GTX 10/16 series) and 48% are using older-gen GeForce cards. Close to 90% of GeForce GTX 10 series owners that are upgrading are grabbing higher-end Turing-based GPU offerings, too. You can see that most people that have a GTX 1080 or GTX 1080 Ti are upgrading to a new RTX 2080 or RTX 2080 Ti, which is interesting to see.

GTC 2019 - NVIDIA CEO and founder Jensen Huang had some big things to talk about during his opening keynote at GTC 2019, with one of them being the announcement of the latest RTX servers that will be hot pieces of tech for Hollywood studios working on VFX.

The new RTX server pods pack a huge 1280 Turing GPUs across 32 RTX blade servers, with 40 GPUs per server, each server consumes an 8U space in a rack. The GPUs inside are NVIDIA's new Quadro RTX 4000 and 6000 graphics cards, depending on the configuration and budgets of their customers.

NVIDIA said in its announcement: "NVIDIA RTX Servers - which include fully optimized software stacks available for Optix RTX rendering, gaming, VR and AR, and professional visualization applications - can now deliver cinematic-quality graphics enhanced by ray tracing for far less than just the cost of electricity for a CPU-based rendering cluster with the same performance".

GTC 2019 - NVIDIA unveiled a cute little AI computer today at its own GPU Technology Conference, with the introduction of the Jetson Nano.

The new Jetson Nano is an entry-level AI computer that NVIDIA will sell to developers for just $99, where inside NVIDIA is using an 128-core Maxwell GPU and quad-core ARM A57 processor that is capable of 472 gigaflops of processing power for neural networks, high-res sensors, and other robotic features.

It'll be a power-sipping PC requiring just 5W of power, can run Linux out of the box, and supports a bunch of different AI frameworks. It'll also house 4GB of RAM, 1GbE port, and I/O that you'll need to attach cameras and other devices to it.

GTC 2019 - NVIDIA showed off something very close to my heart at GTC 2019 this year, with a real-time ray tracing powered version of Quake II demoed.

The company has created a demo of Quake II that uses NVIDIA's RTX technology as well as HDR, something else NVIDIA inserted into id Software's iconic shooter. NVIDIA explained that the original lighting in Quake II was baked and static, but when ray tracing is enabled the entire environment comes alive and looks completely different from the work id Software did in the 90s.

We have beautiful dyanmic lighting that creates realistic reflections and shadows, all of which are visible across the envrionment in the game be it walls, floors, or windows. NVIDIA explains: "We've introduced real-time, controllable time of day lighting, with accurate sunlight and indirect illumination; refraction on water and glass; emissive, reflective and transparent surfaces; normal and roughness maps for added surface detail; particle and laser effects for weapons; procedural environment maps featuring mountains, sky and clouds, which are updated when the time of day is changed; a flare gun for illuminating dark corners where enemies lurk; an improved denoiser; SLI support (hands-up if you rolled with Voodoo 2 SLI back in the day); Quake 2 XP high-detail weapons, models and textures; optional NVIDIA Flow fire, smoke and particle effects, and much more!"

NVIDIA is unleashing the world of ray tracing onto millions of graphics cards on the market, with the company announcing 'basic RT effects' and 'low ray count' abilities for a bunch of GeForce GTX series graphics cards.

You'll need a GeForce GTX 1060 6GB minimum, with all Pascal GPUs through to the TITAN Xp working with the basic RT abilities, as well as the new Turing-based GeForce GTX 1660 and GTX 1660 Ti graphics cards. For complex and multiple RT effects with high ray counts, this is where the Turing RTX cards come into play with the GeForce RTX 2060, 2070, 2080, 2080 Ti, and TITAN RTX come into play.

NVIDIA will push out an April GeForce driver that will unlock the new ray tracing support in the GTX 10 and GTX 16 series graphics cards. This is huge news, as it shows the adoption of GeForce RTX has been low enough that NVIDIA is unlocking ray tracing abilities on its previous-gen Pascal GPU graphics cards which, some of them at least, are nearly three years old now.

Unity has just announced today at NVIDIA's own GTC 2019 that it has teamed with the GPU leader where it will integrate NVIDIA's RTX real-time ray tracing technology into its future platforms.

The company announced that NVIDIA's beautiful RTX real-time ray tracing technology is officially arriving in Unity's High Definition Render Pipeline (HDRP) today in preview form. It will officially be deployed out in a more optimized state to Unity customers in 2H 2019, so we should begin to see the flow-on effects of this in 2H 2019 and more so in 2020 and beyond.

Natalya Tatarchuk, Vice President of Graphics at Unity Technologies explained in a statement: "As part of our commitment to best-in-class visual fidelity graphics, we rolled out the preview of the High Definition Render Pipeline (HDRP) last year - a highly-optimized, state-of-the-art raster-based solution capable of achieving stunning graphics in real-time on consumer hardware. We built HDRP with the future in mind and today we're excited to announce that we are working with NVIDIA to adopt its RTX real-time ray tracing capabilities so we could bring this technology to all. Real-time ray tracing moves real-time graphics significantly closer to realism, opening the gates to global rendering effects never before possible in the real-time domain".

NVIDIA still owns the crown for the fastest gaming graphics card in the world with its GeForce RTX 2080 Ti and it has plenty of room to move with overclocking, but the company puts some major restrictions on it or else we would see the card being magnitudes faster than it already is.

Well, now we have legendary overclocker 'KINGPIN' overclocking his custom-made EVGA GeForce RTX 2080 Ti KINGPIN Hybrid graphics card, pushing the Turing GPU up to the dizzying heights of 2.7GHz. The 11GB of GDDR6 memory was also cranked up from its stock 14Gbps to 17Gbps, offering up 750GB/sec of memory bandwidth.

KINGPIN had the EVGA GeForce RTX 2080 Ti KINGPIN Hybrid graphics card at its max power target (+7%) and used LN2 cooling to keep the OC at its limits. He used an Intel Core i9-9980XE processor also cooled with LN2 overclocked to 5.6GHz on all 18 cores on top of an EVGA X299 DARK motherboard, and 32GB of G.SKILL TridentZ DDR4 RAM at 4000MHz. The results? World record score in 3DMark's new Port Royal benchmark.