Graphics Cards - Page 240

When NVIDIA's founder and CEO Jen-Hsun Huang tease the world with the first GeForce GTX Titan X during the Epic Games GDC 2015 event, the world went crazy. We kind of knew it was coming, but were expecting it to be unveiled at NVIDIA's own GTC 2015 event starting on March 17.

Well, media samples are now spreading across the world with TechGage receiving their sample and taking some up close and personal shots. There's nothing new to tell you here, but we do have a much better look at the card itself. Sitting next to a GeForce GTX 980, we can see in the above shot that the Titan X looks virtually identical from the front (or top in the case of this photo), with the only difference being "GTX 980" and "TITAN" and of course the color scheme has been changed from silver, to a blackish color.

The Titan X has had its backplate removed, which I'm sure is because the GM200 GPU powering the Titan X and its 12GB of VRAM runs much hotter than the GTX 980. The GTX 980's backplate gets ridiculously hot as it is, so I think this is a great move by NVIDIA and something that needed to be done in order to keep the card from getting too hot.

GDC 2015 - Earlier today we were introduced to the GeForce GTX Titan X from NVIDIA, its Maxwell-based card that features a gigantic 12GB of VRAM. We don't know much else about it other than it featuring 12GB of framebuffer and 8 billion transistors, until now.

Legit Reviews spotted NVIDIA's soon to be dominant card at the NVIDIA booth at GDC, housed inside of the beautiful In Win Tou Tempered Glass chassis, where they got a closer look at the GTX Titan X. Thanks to the closer look, we can see that the GTX Titan X is a dual-slot card with a 6-pin and 8-pin PCIe power connectors, and two SLI connectors that mean you could have four of these bad boys in SLI. Yes, four GTX Titan X cards in SLI, for a total of 48GB of VRAM.

With the GeForce GTX Titan Z on the market being a dual-GPU solution, the Titan X is 100% confirmed as a single GPU card which means the single GPU is using all of that 12GB framebuffer. With four of these in SLI, we will be seeing 12GB of VRAM used in total which is much better than the Titan Z, or even the Titan Black Edition cards which have 6GB per GPU.

According to the latest report from Jon Peddie Research (JPR), NVIDIA is dominating the GPU market share game against AMD. JPR's data for Q3 2014 has NVIDIA securing a huge 76% of the GPU market share, leaving AMD with just 24%. Matrox and S3 are now out of the game, with Matrox losing its small 0.10% market share to NVIDIA.

JPR's estimated graphics add-in-board (AIB) shipments and suppliers' market share for the quarter tracks add-in graphics boards, which feature discrete GPUs. These AIBs are used in various devices, such as desktop PCs, workstations, servers, and other devices "such as scientific instruments". JPR's report has found that AIB shipments have decreased by 0.68% from the previous quarter with the total AIB shipments decreasing over the quarter to 12.4 million units.

AMD's quarter-to-quarter total desktop AIB unit shipment has decreased 16%, while NVIDIA's quarter-to-quarter unit shipments increased by 5.5%.

Tom's Hardware has quite the exclusive report, where they're saying that they have a "source with knowledge" on the matter of DirectX 12, that will see that the new API will combine the powers of competing GPUs. In order words, an NVIDIA GeForce GPU will work together in a multi-GPU set up with an AMD Radeon card.

This is something DirectX 12 has on its side with its Explicit Asynchronous Multi-GPU capabilities, which will throw all of the various graphics resources in a system, and into a single "bucket". From there, the game developers will have to work out where the workload will be split, which could see different hardware being used in specific tasks.

One of the major points of this new multi-GPU technology is that multi-GPU configurations will no longer have to mirror their frame buffers, or VRAM. In previous APIs, right up to DX11, you needed two cards of identical VRAM amounts to work in tandem, but only one lot of VRAM is utilized, it's not combined. This is a limitation of rendering an alternate frame (AFR), but DX12 is removing the 4 + 4 = 4 limitation of AFR, replacing it with a new frame method called SFR, or Split Frame Rendering.

We know to expect some big things from DirectX 12, but the more we hear about it, the more we want it now, now, now. AnandTech has completed a deep-dive into the upcoming API from Microsoft, noticing some huge improvements across a range of hardware.

We've written about Brad Wardell, the CEO of Stardock and his impressions of DX12, but he has said that using an "unreleased GPU" he was able to see a huge 100FPS difference between cards. He tweeted that he "did a test of DirectX 11 vs. DirectX 12 on an unreleased GPU with an 8core CPU. DX11: 13fps, DX12: 120fps. Lighting and lens effects".

When pressed, Wardell said he was using a Crossfire system, with an Intel Core i7 CPU. Since he's using an "unreleased GPU" we can gather he might be using the new Radeon R9 390X, which is another nice nugget of information, it means that they're out in the wild. Better yet, Wardell said that "one thing it does make it easy to treat multiple GPUs as a single identity". This is something we reported on not too long ago, where we reported that the VRAM on multi-GPU systems would be seen as one.

AMD is on the verge of announcing and releasing its new Radeon 300 series of cards, but according to a new report from Sweclockers, the codename Fiji GPU will be the only new chip in the Radeon 300 series family. The rest of the cards, will have the current GCN cores, with the GCN 1.1 and GCN 1.2 architecture powering them.

The Radeon R9 390 and R9 390X should feature the new Fiji architecture, with the R9 390 arriving with the Fiji Pro GPU, while the R9 390X will rock the Fiji XT core. When it comes to the Radeon R9 395X2, we don't know if we'll see two of the Fiji XT or Fiji PRO GPUs on it just yet. We do know that we should expect the Radeon R9 390X to feature 4096 cores, 4GB of 4096-bit (1024-bit per channel) HBM memory and hopefully, much more. These new cards will be the first video cards in the world to feature SK Hynix's HBM memory, as well as the first look at the latest GCN 1.3 architecture.

The biggest beast of the new cards will be 'Bermuda' which is the R9 395X2 dual-GPU offering, which should feature the new GCN 1.3 architecture and the super-fast new HBM memory. We don't know what else to expect, but I would like to see AMD make two versions of its R9 390X available: one with 4GB of HBM memory and the other with 8GB of VRAM. Another nice touch would be to have two versions of the R9 395X2: one with 8GB of VRAM (4GB per GPU) and another with 16GB of VRAM (8GB per GPU).

AMD must be so close to unveiling its next-generation range of GPUs, but the latest information on the Radeon R9 390X has it rocking an all-in-one (AIO) liquid cooler made by Cooler Master.

Cutting to the chase, AMD will reportedly ship its reference Radeon R9 390X with an AIO cooler but AIB partners like SAPPHIRE, XFX and so forth will ship their own coolers. WCCFTech is now reporting that the new Radeon 300 series, and more specifically the flagship Radeon R9 390X will launch in "four to six weeks", which should see it released in late March, or early April.

AMD has said that it's working on something "crazy" for the Game Developers Conference (GDC) 2015, which kicks off in early March. This new information could be true, with AMD showing off its new GPU at GDC 2015, which is incredibly exciting.

Many users are reportedly outraged due to NVIDIA's cancellation of overclocking capabilities for their 900M series - through the latest driver release. Although mobile video cards are not generally overclocked, customers who purchased systems containing GTX 980M GPU's were applying mild overclocks to get the most out of their system.

This driver update is the GeForce R347 (347.29), which has removed its overclocking tools and withdrew support for any third-party tools you may wish to install. Users have been issuing complaints on NVIDIA's official forums, which saw a response from NVIDIA staff. Manuel Guzman replied "unfortunately GeForce Notebooks were not designed to support overclocking. Overclocking is by no means a trivial feature, and depends on thoughtful design of thermal, electrical, and other considerations. By overclocking a notebook, a user risks serious damage to the system that could result in non-functional systems, reduced notebook life, or many other effects."

As seen on HotHardware, Guzman went on to express that allowing mobile GPU overclocking in the first place was a mistake made by his team and should have never been implemented.

It has been rumored that NVIDIA would slide out from under those warm cuddles that TSMC provide to manufacturer its GPUs, into the arms of Samsung or GlobalFoundries, but it looks like this won't be happening any time soon.

NVIDIA's CEO and co-founder Jen-Hsun Huang said during the company's recent conference call with investors and financial analysts during the week, where he said that TSMC will continue to be a big partner of theirs, but didn't confirm or deny that it could shift some of its production to another company. Huang said: "We always look at all foundries, and TSMC remains our most strategic [partner]. They are going to continue to be a very important partner for us for the foreseeable future".

TSMC will begin its 16nm FinFET production in the second half of the year, much later than the likes of its competitors in Samsung and GloFo. When it came to talking about the 16nm FinFET process, Huang said: "TSMC is a fabulous supplier, [...] their FinFET technology is excellent. [We have been] working with TSMC on FinFET now for a couple of years, and so we have quite a bit of confidence in their ability to deliver amazing FinFET transistors".

We don't normally see a behind the scenes look at the hardware powering a gigantic event like the Super Bowl, but we now know what powered the show. This year's Super Bowl half-time show was powered by MAINGEAR, with a system that packed quite a punch in the performance department.

According to 'Bulwerk' on the Octane forums, they needed to render animation at a huge 3780x3024, which requires a serious amount of number crunching power. So they asked MAINGEAR to construct an insane PC that featured four NVIDIA GeForce GTX Titan Z GPUs, which were all liquid cooled using EK Water Block products.

On top of that, we have an ASUS X-99E WS motherboard, Intel Core i7-5930K processor, 16GB of Corsair Vengeance DDR4 RAM, a Samsung 850 PRO 256GB SSD, and two Corsair AX 1200i PSUs.

It looks like Google Glass will soon be getting a major revamp under its new leadership, with Tony Fadell taking over the project. Various people familiar with the matter told The New York Times that Google Glass will be completely redesigned.

One of the sources has said that Fadell is a product person, so he won't be releasing the new version of Glass until it is near perfect. Fadell said in a statement to the Times that the early version of Glass broke ground, allowing the company to learn what is important for consumers and enterprise users when it came to their revolutionary wearable device.

Fadell added that he is excited to be working with fashion guru Ivy Ross, who will be providing direction and support for the new version of Glass, and other devices that will be rolled out in the future. This means that we most likely won't hear about a new version of Google Glass for a while yet, until the company is much closer to a final, consumer version.

We know it's coming, but AMD is beginning to acknowledge its forthcoming Radeon 300 series more and more. First, we had company CEO Lisa Su confirm the new GPUs for Q2 2015, but now the official AMD Facebook page has said they're coming.

In a response to someone asking about whether AMD would reveal its next-gen GPU shortly, they replaced with "We don't have an official date to share just yet but hte second we know, we will definitely announce it on Facebook". Another reply added "We're still putting the finishing touches on the 300 series to make sure they live up to expectation. Can't wait to reveal them though. We're pretty excited".

We should expect AMD to reveal the new GPUs in the near future, which should feature the exciting new High Bandwidth Memory (HBM) which should provide a huge memory bus. 4GB of RAM is expected, but I think we'll also see 8GB models coming thorugh, too.

NVIDIA caught headlines last week with its VRAM issues on the Maxwell-based GeForce GTX 970, but it's a new week, with new memory-related issues. This time, it's AMD and its Radeon GPUs and a very specific game, on a very specific OS.

Radeon users are seeing memory leak problems on Battlefield 4 with Windows 8.1, with WCCFTech confirming the issue with AMD's Head of Global Technical Marketing, Robert Hallock. Hallock acknowledged the issue in Battlefield 4, of which it only affects gamers running Windows 8.1. AMD is working directly with DICE on the issue, but with the game being over a year old and many DLC packs in, and the fact that AMD were and still are heavily partnered with DICE, this shouldn't be happening.

AMD will address the memory leak issues in a new beta driver that will arrive soon.

We know that AMD is currently preparing the launch of the Radeon R9 300 series, but between now and then what to add-in board (AIB) partners do? Do they continue ordering Radeon R9 290X, R9 290 and other 200 series GPUs from AMD? Well, that's where we are today.

DigiTimes is reporting from a source close tro them that some of AMD's AIB partners are reducing orders for current-gen Radeon GPUs as there is growing anticipation for the next-gen from AMD, as well as citing reduced demand for Radeon R9 200 series cards. DigiTimes has said: "Since AMD is already planning to unveil its next-generation GPUs in the second half, the sources believe the GPU vendor will have a chance to regain some of its lost market share in the second half of 2015".

The bigger tease is that AMD would reportedly launch its Radeon R9 380X as early as late this month, or early March according to VideoCardz. We might not see that happen, but with less Radeon R9 200 series cards on shelves around the world, AMD could surprise NVIDIA and the world by capitalizing on the GeForce GTX 970 VRAM issues.

We've been hearing the rumbles of an insane video card from EVGA for quite a while now, but here it is: the EVGA GeForce GTX 980 KINGPIN ACX 2.0. From the name alone, you can see that this is the top tier Maxwell-powered GTX 980 from NVIDIA, but the entire package is going to blow you away.

First and foremost, we have a custom designed PCB which has been tailor made to push things right to their breaking points. Under LN2, the new EVGA GeForce GTX 980 KINGPIN ACX 2.0 was capable of an insane 2.2GHz GPU clock, and 8.9GHz on the memory. Comparing this to the stock speeds of 1291MHz for the GPU and 7GHz for the GDDR5 RAM, this is an impressive result for EVGA and KINGPIN. The custom designed PCB is showing its strength here, but it'll be more interesting to see what it does with its ACX 2.0+ cooler.

Speaking of the custom designed PCB, we have a 14+3 Fully Digital VRM which will increase the stability, efficiency and the overall power capacity of the board, all while it runs at low temperatures of an average of 28C. The custom designed PCB has been made from 12 layers of copper, with two 8-pin PCIe power connectors backed up by a third, 6-pin PCIe power connector. All of this power will ensure that the EVGA GeForce GTX 980 KINGPIN ACX 2.0 has enough power when it is receiving a total thrashing in the overclocking department.

Just how is 4K gaming affecting AMD internally right now? According to Robert Hallock who is part of the Technical Communications division for AMD Radeon graphics, he said that gamers are adopting 4K gaming nicely, but the R&D department for AMD is already planning for the future.

For Hallock, the Radeon R9 290X was a major step in that direction, allowing for gamers to play at 4K with a single GPU. Lower-end parts of the market aren't quite there yet, so GamingBolt asked him some questions where he replied with the future of 4K gaming is an evolution of GPU horsepower, which is something AMD is working on. He said: "If you think back to the launch of the AMD Radeon R9 290X, our video card marked arguably the first time anyone could reasonably expect to play games at 4K on a single GPU. Sure, there were some games that needed two for peak image quality, but one was and is pretty solid for the majority of titles. We were also the first company to offer full support for 4K SST displays in our driver".

"4K adoption is very popular amongst the elite enthusiasts, but understandably slower being adopted in lower-end segments. I couldn't characterize the rates with hard numbers as that's not my area of expertise, but this is the sense I'm getting from interacting with the AMD community every day", he continued. Hallock added: "Ultimately, the evolution of GPU horsepower is the biggest factor in driving 4K forward. Graphics being such an important part of our business, of course, you can count on great progress on that front as the years wind on".

Colorful Technology has announced its latest GeForce GTX 960 video cards, with some truly great models being shown off by NVIDIA's biggest AIB partner in China.

We have four different models being unveiled, with the Colorful GTX960 CH which is a reference like card for entry users. Moving on, we have the Colorful GTX960 i-Cafe for System Integrators, the iGame GTX960Ymir-U for general users and for enthusiasts we have the iGame GTX960 Ymir-X. Starting with the GTX960 i-Cafe which features a longer PCB than the reference design, but features the same clocks as the GTX960 CH. The iCafe version provides consumers with better stability and a longer lifespan thanks to its more efficient cooler and higher quality electronic components.

Moving on to the iGame GTX960 Ymir-U which is targeting gamers and general users, which will have two clock models. The first is a power efficiency model which will have clock speeds of 1127/7010MHz while in performance mode it will crank up to 1203/7010MHz. The iGame GTX960 Ymir is the performance model of the Colorful GTX960 series, with triple fans, a steel back panel, breathing light and a longer PCB. We have two clock speeds on this card, with the default efficient mode coming in at 1127/7010MHz while the performance model cranks things up to an insane 1405MHz.

NVIDIA has been getting some flak for the VRAM issues on its GeForce GTX 970, quickly altering the official specifications of the Maxwell-powered card. Well now AMD is jumping on the chance to sell some of its Radeon R9 290X inventory, dropping the price to as low as $299 for the Hawaii-powered card.

AMD has hit back with a serious troll, statign "4GB means 4GB" somethign that blew up on our Facebook page yesterday. AMD emphasizes that its Radeon R9 290 and R9 290X video cards come with 4GB of VRAM, where all 4GB can be filled up to the very last megabyte. On top of this, they have a 512-bit memory bus which is spitting out 320GB/sec of memory bandwidth, something that the Maxwell-powered GeForce GTX 900 series can't do.

We know that AMD will be announcing and then launching its Radeon R9 300 series, but the latest video could be a very big tease of an imminent announcement, we hope. Take a look at AMD's 'The Fixer 3' teaser below.

It really is just a teaser, as it shows off absolutely nothing. A man is walking away from the camera holding a Radeon video card of some sort, with the "The FIX3R" showing up on the screen. We have already seen Fixer 1 and Fixer 2, so the Fixer 3 could be totally unrelated to the Radeon R9 300 series, but there's still hope.

We know that AMD will be launching its Radeon R9 300 series in Q2 2015, so we should expect AMD to begin its marketing machine in the coming weeks and months, for sure.

During AMD's Q4 earnings call, CEO Lisa Su teased that the company will have "very good" graphics products that will ship in Q2 2015. Su confirmed that AMD has multiple product launches to spread out over "the next couple of quarters", with those quarters being Q2 and Q3. Most of which will be released between April and June.

Su did explain what is happening with the GPU side of the business, in that AMD had a large quantity of its Hawaii-based R9 290 series GPUs, most of which are rapidly declining. The company then increased its inventory in the anticipation of continued demand, but it fell off very quickly - mostly because the cryptocurrency market began to shrink rapidly. Thanks, Bitcoin miners. During Q4, Su said that company took the required actions to get the inventory levels back to normal, and moving into Q1 2015, AMD took even more drastic actions. I would dare say that NVIDIA's Maxwell-based GeForce GTX 980 and GTX 970 video cards had something to do with that.

Su continued: "Think on the computing and graphics business, we can improve our execution and there is a lot of focus, at least from my standpoint, to ensure that our 2015 product launches are quite strong. So that's important for us to really stabilize that business, and that will certainly be key to our second half performance. I think from where I see it going forward, we are very focused on correcting the channel and normalizing that business. I think we have some good products that are coming out for it. So I do see opportunities for a return to a more healthy channel business going forward".