Items tagged with GPU

A little over a month ago, AMD launched the Navi-based Radeon RX 5700 series to mostly good reviews. The cards offered competitive performance at their respective price points, with power efficiency that was vastly superior to AMD’s previous-generation Vega-based Radeons. One of the things some folks took issue with in regard to AMD’s reference Radeon RX 5700 and RX 5700 XT cards, however, was their cooling. As we (and many others) mentioned in our initial reviews, the cards were noisier than their NVIDIA-made counterparts, and although temperatures were within spec, peak junction temps were relatively high, which could be a cause for concern in a poorly ventilated chassis. The general... Read more...
The final member of NVIDIA’s GeForce RTX Super-series officially arrives today, the GeForce RTX 2080 Super. In case you missed it, a couple of weeks back, NVIDIA launched the GeForce RTX 2060 Super and RTX 2070 Super, to preemptively zing AMD in the lead-up to the Radeon RX 5700 series launch. The GeForce RTX Super-series will supplant and eventually replace their original, “non-Super” counterparts once availability dries up. At the top and bottom of the stack, however, the GeForce RTX 2060 and GeForce RTX 2080 Ti will remain. It is in the meat of the 20-series where the Supers reside, with the new GeForce RTX 2080 Super we’ll be showing you here today leading the charge,... Read more...
AMD has been talking about its next-generation Navi GPU architecture for ages. It was over 3 years ago that we first mentioned Navi here on the HotHardware, and since then there has been a slow, steady stream of information disseminated to the public, leading up the last month’s big architecture disclosure at E3 and the official unveiling of the initial Radeon RX 5700 series line-up, which we will be showing you here. If you missed our coverage of AMD's  Navi GPU architecture and its newly-designed RDNA-infused microarchitecture and instruction set, you can find it right here. We strongly suggest checking that article out, because we cover a number of deep technical details, including... Read more...
NVIDIA dropped a hint that something “Super” was coming just prior to Computex and since then a handful of leaks have let the cat mostly out of the bag. Today, however, we can dispel the rumors, officially reveal what NVIDIA’s got coming down the pipeline, and show you exactly what NVIDIA’s Super branding is all about. NVIDIA is overhauling its Turing-based GeForce RTX line-up with an array of “Super” GPUs, specifically the GeForce RTX 2060 Super, RTX 2070 Super, and RTX 2080 Super. In the short term, like two days from now, the GeForce RTX 2060 Super and RTX 2070 Super will hit store shelves. The GeForce RTX 2080 Super is coming in a few weeks though, and... Read more...
AMD's upcoming Radeon RX 5700 series of graphics cards is based on the AMD’s new Navi GPU architecture, which features a totally new compute unit design infused with “RDNA”, or Radeon DNA. For the past few generations, AMD’s GPUs have leveraged GCN-based, or the company's Graphics Core Next, compute units. GCN served AMD well for a number of years and is well-suited for a variety of workloads, but with the Radeon RX 5700 series and Navi, AMD wanted to update is microarchitecture and GPU line-up with Compute Units that have been fully re-tooled for gamers. With RDNA, AMD wanted to create the fundamental building block of a CU that could scale from a few watts, all the way... Read more...
A couple of weeks back, NVIDIA launched the latest edition to its Turing-based GPU line-up, the GeForce GTX 1650. As its name suggests, the GeForce GTX 1650 is similar to the recently-released GeForce GTX 1660 and 1660 Ti, but it is powered by a different GPU with somewhat tamer specifications, which results in a lower price point as well. We’ll dig into the specifics in just a moment. As was the case with the GeForce GTX 1660 and 1660 Ti, there will be no Founder’s Edition version of the GeForce GTX 1650 arriving on store shelves. Instead, NVIDIA is relying on their add-in board partners to seed the market this time around. The card we’ll be looking at today is one the higher-end... Read more...
Intel made some interesting disclosures at the FMX conference currently underway in Stuttgart, Germany, which focuses on advanced animation, film effects, games, and other types of immersive media. At the conference, James Jeffers, Intel’s Senior Principal Engineer and Senior Director of Advanced Rendering and Visualization, held a workshop during which he announced that Intel’s Xe architecture roadmap includes support for hardware accelerated ray tracing, among a couple of other graphics and rendering-related news. There is some nuance to the ray tracing tid-bit, however. A blog post covering much of what Jeffers discussed during the workshop is live on Intel’s IT Peer Network... Read more...
Update, 4/1/2019: Intel Vice President Of Core And Visual Computing and GM of Visual Technologies team at Intel, Ari Rausch has confirmed Tom Petersen's arrival to their team in a recent tweet... So happy and thrilled to have @NVIDIA_tap the one and only Tom Petersen joining our Intel GPU team. We are going to have an awesome roadmap and oddesy ahead with @IntelGraphics — Ari Rauch (@arirauch) April 1, 2019 In addition, the Intel Graphics Twitter account is also officially welcoming TAP to the fold... We are excited and thrilled to have Tom Petersen “TAP” joining us as an Intel Fellow on our GPU team. pic.twitter.com/30f0TkPlXY — Intel Graphics (@IntelGraphics) April 1,... Read more...
Intel has been particularly focused on graphics late, more so than we can recall in recent years. Between hyping its first modern discrete GPU that is still scheduled to debut in 2020, revamping its Graphics Command Center, and sharing details about its upcoming integrated GPU refresh, it's clear where Intel's mind is at. A lot of details are still under lock and key, though. That said, a recent driver update may provide some clues about Intel's upcoming Gen11 graphics. Gen11 will make its debut later this year, complementing Intel's upcoming 10-nanometer Sunny Cove CPU architecture, which itself will form the basis for both Core (consumer) and Xeon (server) processors. A recent whitepaper published... Read more...
Chris Hook, Graphics and Visual Technologies Marketing Chief at Intel had the crowd whipped-up into a fine frenzy earlier this week in San Francisco, at an event location right across from one of the Moscone Center halls of Game Developers Conference. Hook and various company execs, including Intel CEO Bob Swan and Intel SVP, Core and Visual Computing Raja Koduri, took to the stage to talk a bit more about the company’s plans and vision to bring next generation discrete graphics products to market in 2020. Intel’s messaging and presentation was keenly focused on community. The event was entitled the Odyssey – referring to the journey Intel is inviting enthusiasts and gamers... Read more...
All of the buzz surrounding Intel's efforts in graphics right now is around the company's Odyssey towards its first modern discrete GPU, currently scheduled for release in 2020. That's understandable, but let's not forget that, in terms of market share, Intel's integrated graphics lead the pack. Intel's upcoming Gen11 graphics will keep things going, and interestingly, Intel has quietly released a white paper that describes Gen11 in some detail. Intel has already shared a few details about Gen11 during its Architecture Day last December. Gen11 will complement Intel's upcoming Sunny Cove CPU architecture, which itself will form the basis for both Core (consumer) and Xeon (server) processors. While... Read more...
We are only a couple of weeks removed from the launch of the GeForce GTX 1660 Ti and NVIDIA is already at it again. This time around, we have yet another affordably-priced, Turing-based GPU to show you all, the GeForce GTX 1660 – sans Ti. As its naming suggest, the new GeForce GTX 1660 is very similar to its more-powerful counterpart; they’re both based on the same GPU, but a few cores and other components have been disabled in the GTX 1660. A handful of other changes have been made with the GeForce GTX 1660 as well, which push the card down a rung in terms of performance, but also bring down the price. We have a couple of GeForce GTX 1660 cards on tap for you here, one from EVGA... Read more...
The NVIDIA Titan RTX is a GPU with somewhat of an identity crisis. The card is based on a fully-enabled Turing TU102 GPU, and is technically the most powerful graphics card in NVIDIA’s current line-up for gaming. If you hit NVIDIA’s site and check out the Titan RTX’s landing page, however, it isn’t being targeted at gamers. NVIDIA’s site makes statements like, “TITAN RTX frees you to work at the full speed of your creativity” and “[TITAN RTX] provides a fast and simple start to exploring GPU-accelerated data science workflows on your PC.” The words “game” or "gaming" do not even appear on the Titan RTX page. Although some folks... Read more...
Although the Turing-based GeForce RTX 2000 series hit store shelves first, it was about a week before their initial unveiling that NVIDIA CEO Jensen Huang took to the stage and announced the Quadro RTX family of workstation-class GPUs, targeting professional graphics applications. As of today, Quadro RTX series consists of four graphics cards, ranging from the monstrous Quadro RTX 8000 with its 48GB of GDDR6 to the Quadro RTX 4000, which targets more mainstream content creation professionals. It’s the later that we’ll be showing you here today. Looking at the Quadro RTX 4000 in light of some of NVIDIA’s other pro-graphics cards, it would appear to be a rather tame solutions.... Read more...
NVIDIA is expanding its Turing-based GPU lineup today and pushing its latest graphics architecture down into a more affordable price point. Although it does share some similarities with its predecessors, the NVIDIA GeForce GTX 1660 Ti we will be showing you here is unlike all of the other Turing-based GPUs that have launched to date in a few meaningful ways. The fact that the card is branded a GeForce GTX, rather than a GeForce RTX, hints at the biggest difference – the GeForce GTX 1660 Ti doesn’t support NVIDIA’s RTX real-time ray tracing technology. What the GeForce GTX 1660 Ti does do, however, is incorporate all of the architectural efficiencies of Turing into an affordable... Read more...
In case you didn't already know, Intel is working on a discrete graphics card that will be used to tackle a number of market sectors, including the ever-important gaming community. In keeping with the company's recent efforts to be more engaging with graphics card enthusiasts, Intel is inviting gamers to "Join the Odyssey." So, what exactly is this Odyssey that Intel speaks of? Intel says that it "is built around a passionate community, focused on improving graphics and visual computing for everyone, from gamers to content creators. "We’re committed to listening to the community, and in return you will get closer to the inner workings of visual technology development than ever... Read more...
It’s no secret that Intel is developing a discrete GPU family that it will use to take on many sectors in the graphics market. The company will put a primary focus on the gaming sector (where it will go toe-to-toe with AMD and NVIDIA) and also professional and enterprise markets. We’re learning today that Intel is hoping to bolster its efforts to create a discrete GPU with the acquisition of Ineda Systems. Financial details of the transaction are scare at the moment, but we do know that it was an all-cash deal. Ineda was founded in 2011 and is based in Hyderabad, the booming tech-centric capital city of India’s Telangana state.  Ineda is a fabless chip design... Read more...
AMD CEO Dr. Lisa Su unveiled the Radeon VII during a keynote address at the Consumer Electronics Show last month. Although the Radeon VII was billed as the first 7nm GPU, fundamentally it is similar to the Radeon Instinct MI50, which was announced late last year. Of course the Radeon Instinct MI50 is targeted at HPC and Deep Learning applications, while the Radeon VII is technically the first enthusiast-class gaming GPU for consumers. Regardless, the fact remains that the same 7nm Vega 20-based chip is at the heart of both cards. Although it is still based on the company’s Vega architecture, the GPU powering the Radeon VII isn’t a simply shrink of an existing design. There have been... Read more...
AMD CEO Dr. Lisa Su took the wraps off the company’s first 7nm GPU based on its Vega architecture at CES 2019 in Las Vegas last month. Dr. Su’s keynote underscored the company’s lead against its rivals with respect to silicon process technology, and AMD’s new Radeon VII is one of multiple new products in its graphics and processors portfolios that’s built on a cutting-edge 7nm manufacturing node. And while AMD’s Radeon VII is essentially a process shrink of the company's Radeon Vega architecture with a few tweaks and fixes, along with that process geometry optimization should come optimizations for power consumption, clock speed, performance and other fine... Read more...
In case you haven't been keeping up with the latest happenings in the PC graphics market, Intel is going full-bore with a discrete graphics card family. Intel will be [in part] targeting the PC gaming market with this new GPU, which is supposed to be officially unveiled in 2020. Although we've been able to get limited insight into Intel's plans through our conversations with key executives, the company is revealing more about the project in a rather unconventional way. Intel Graphics posted a video to Twitter which in effect serves as a recruitment tool for its budding graphics division. The video starts off with commentary from Raja Koduri, the former Radeon Technologies Group... Read more...
Shortly after NVIDIA initially launched the first wave of high-end Turing-based GeForce RTX cards, EVGA announced a dizzying array of new graphics cards featuring the new GPU. With that in mind, it should come as no surprise that EVGA did the same when NVIDIA expanded the GeForce RTX family with the more main-stream, GeForce RTX 2060. EVGA already has three RTX 2060s in its line-up, two short-board, single-fan offerings, and a larger, dual-fan model with a GPU that’s clocked significantly higher than NVIDIA’s reference specifications. We’ve got the card in the middle of the stack to show you here today, the EVGA GeForce RTX 2060 XC. This card has a somewhat uncommon form factor,... Read more...
There is no disputing that AMD has made some giant strides in the enthusiast market, especially with its Zen CPU architecture, though also with its Vega GPUs. The latest incarnation of the latter is the recently announced Radeon VII with a 7nm Vega GPU inside. It's a beastly card in its own right, though NVIDIA still has the edge in overall performance with its own Turing GPU architecture. Will AMD ever close the performance gap? That is an interesting question to mull, in light of recent patent applications that AMD filed. First let's talk about the performance of the Radeon VII. The only numbers we have to evaluate at the moment are AMD's own benchmark figures. If those are a proper representation... Read more...
Prev 1 2 3 4 5 Next ... Last