Graphics Cards - Page 180

NVIDIA was ramping up to reveal its next-gen Ampere GPU architecture at its GPU Technology Conference (GTC) in a few days time, but in the end the company moved to an all-digital event over the COVID-19 coronavirus outbreak, then outright cancelled it.

But now, NVIDIA has taken to its official blog with a new post titled 'GTC News Can Wait' to explain it is delaying the announcement oif its exciting new products. The company explains: "We have exciting products and news to share with you. But this isn't the right time. We're going to hold off on sharing our GTC news for now".

NVIDIA continued: "That way, our employees, partners, the media and analysts who follow us, and our customers around the world can focus on staying safe and reducing the spread of the virus. We will still stream tons of great content from researchers and developers who have prepared great talks. This is a time to focus on our family, our friends, our community. Our employees are working from home. Many hourly workers will not need to work but they'll all be fully paid. Stay safe everyone. We will get through this together".

NVIDIA's next-generation Ampere GPU architecture should be announced in the coming months, and was meant to be unveiled at its GPU Technology Conference -- which was made all-digital, then canceled altogether.

But now, we have a juicy new rumor on Ampere and some delicious specs to salivate over. NVIDIA is reportedly using TSMC's fresh 7nm node for its HPC (High Performance Computing) products (think Tesla GPUs) while the GA10x GPUs will be made on Samsung's new 10nm node.

KittyCorgi on Twitter has tweeted that there will be 5 different Ampere GPUs on offer, with the GA102 sitting at the top of the heap -- the GA102 will succeed the Turing-based GA102 GPU that powers the GeForce RTX 2080 Ti and TITAN RTX. Following that is the GA103 (which doesn't succeed any Turing GPU), then GA104, and then GA106 and GA107.

NVIDIA has some fresh new GeForce drivers released that are Game Ready for Call of Duty: Warzone, the new battle royale focused game mode that sees up to 150 players battling it out in Call of Duty's usual signature gameplay.

The new GeForce Game Ready 442.59 drivers have day one optimizations not just for Call of Duty: Warzone, but they also fix some issues with NBA 2K20 and others. There are some issues included with these drivers that I'm sure will be ironed out with the next release, but for now you'll want to grab them if you're wanting to jump into Call of Duty: Warzone.

You can grab NVIDIA's new GeForce Game Ready 442.59 WHQL drivers here.

AMD revealed more details about its next-gen RDNA 2 architecture during its recent Financial Analyst Day, where we now (unfortunately) need to call "Big Navi" something else: RDNA 2, or Navi 2X.

The next-gen RDNA 2-based Radeon RX reference graphics cards from AMD have been confirmed to not use blower-style designs, with ex-NVIDIA and now current Vice President and General Manager for Radeon, Scott Herkelman, explaining that "there will be no blower reference fans for gamers on next gen".

AMD will however, not be stopping AIB partners from making blower design coolers on their cards if they so wish -- but AMD has been listening to feedback in a big way. Herkelman added: "Our AIBs may choose to do a "blower" design on any of the next gen GPUs, however, the majority of feedback we received from the community at the launch of 5700 XT on AMD reference designs has guided us towards dual/tri-axial designs. I'm excited for you all to see them when the time is right!"

NVIDIA is in full preparation for its now digital-only GPU Technology Conference (GTC), which kicks off on March 22 -- but between now and then we have some very super-juicy rumored specs on the Ampere GA100 GPU.

There is only a single source for this leak from a Chinese forum, with the folks at Wccftech picking it up and running with it. The Ampere GA100 GPU in question looks like an absolute beast, with this rumor concentrating on the full-fat GA100 GPU with a huge 8192 CUDA cores (at 2GHz which is crazy), 1024 Tensor Cores, 130 RT cores, and a whopping 48GB of HBM2e memory at 1.2GHz.

We're looking at a huge 36 TFLOPs of performance from GA100, with NVIDIA using TSMC's current 7nm+ node, and a huge 300W TDP. This is not a GeForce RTX 3080 Ti or next-gen Ampere-based TITAN RTX, but it would rather be the flagship Tesla card for HPC/servers. We should expect a cut down version of this to arrive in the form of the GA102 -- and power the next-gen GeForce RTX 3080 Ti and hopefully, a monster new TITAN RTX based on Ampere.

AMD has finally talked about its next generation "Big Navi" graphics cards, which from now on in will be called RDNA 2 or "Navi 2X" -- I kinda liked the name Big Navi, though. AMD CEO Dr. Lisa Su did say that AMD was preparing Big Navi to compete with NVIDIA, as the high-end GPU market is "very important" to the company.

During its recent Financial Analyst Day, AMD came out swinging talking about its warpath against its competitors in Intel and NVIDIA -- where it revealed that its next-gen discrete graphics cards will be based on the RDNA 2 architecture.

The company is referring to RDNA 2 as "Navi 2X" which will arrive on the 7nm node, but it also teased RDNA 3 or "Navi 3X" on an "Advanced Node", too. RDNA 3 / Navi 3X should be on the 7nm+ node, or the 5nm node -- something I'm going to need to clarify.

Just as we're all enjoying the weekend, rumors of NVIDIA's next generation Ampere GPU have surfaced -- this time, teasing some basic specifications, purported performance, and more.

We know that NVIDIA's next-gen GPU architecture after Turing will be Ampere, and then Hopper -- with Ampere finding a new home on the 7nm node and offering some truly kick ass performance improvements as well as power efficiency. Pascal and Turing were already quite power efficient GPUs, but Ampere really amps things up... pun intended.

This is where Twitter user '_roggame' comes in, where he has discovered some Geekbench results for "two unknown NVIDIA GPUs". The first of which packs 7552 CUDA (so Ampere) cores, 118 compute units (CUs), GPU clock speeds of 1.11GHz and 24GB of memory. We could be looking at GDDR6 or HBM2/2e, that is not confirmed. The next one has 6912 CUDA cores, 180 compute units, and a GPU clock of 1.01GHz while it packs much more memory at 48GB.

NVIDIA has just dropped their latest GeForce 442.50 WHQL drivers, which are Game Ready for a bunch of just-released updates to some of the largest games on the market. You can download NVIDIA's new GeForce 442.50 WHQL drivers right here.

The new drivers have Game Ready optimizations for Respawn's just-launched Apex Legends: Season 4, Tom Clancy's The Division 2 - Warlords of New York expansion, as well as ARK: Genesis Part 1. Not only that, but NVIDIA has added in some new security features into the GeForce 442.50 WHQL drivers.

NVIDIA has also added in a bunch of VRSS profiles for VR games, fixes on a bunch of other games, and added in some new monitors to the G-SYNC compatible list, which include:

AMD is hard at work on its new Big Navi GPU, and now we have a fresh new rumor that is very exciting -- as it teases some truly monster specs that could really shake up the camp at Team Green, at least until Ampere is here.

The new report is coming from 'CyberPunkCat' on Twitter that reportedly has sources at SK Hynix that have provided him with an information sheet on the specifications of Big Navi -- including an insane 24GB of HBM2e memory that has an even-more-insane 2GB/sec+ of memory bandwidth.

The new spec sheet teases Big Navi with a much larger 5120 shading units, 320 TMUs, 96 ROPs, 80 compute units and 12MB of L2 cache. But it's the gigantic 24GB of new HBM2e memory on a 4096-bit memory bus spitting out a huge 2048GB/sec (2TB/sec) of memory bandwidth.

NVIDIA launched its game streaming service GeForce NOW just a couple of weeks ago and the company has already seen over 1 million gamers sign up for it. With games like Cyberpunk 2077, and Google Stadia sucking in comparison (and GeForce NOW being much cheaper), it's no wonder NVIDIA is seeing success.

GeForce NOW supports over 400 games, while another 1000 are available for single-session installations -- all taking place on NVIDIA's servers. You can play your own games through your own accounts on Steam, the Epic Games Store, or Uplay -- while there's a free tier, NVIDIA also offers the premium Founders tier.

NVIDIA's premium Founders tier for GeForce NOW offers up longer play sessions, while both the free and premium tiers have RTX on (ray tracing) but the free version of GeForce NOW only has it for a 90-day introductory period. NVIDIA also announced that they have 1500 more games coming to GeForce NOW in the near future.

We all know AMD is cooking up Big Navi right now, with CEO Dr. Lisa Su herself confirming it is in the oven and coming out in 2020 -- but it looks like Big Navi might have just turned up somewhere new. AMD's new Big Navi is meant to disrupt 4K gaming with NVIDIA, like its Ryzen CPUs did with Intel.

The Korean RRA has just listed a couple of AMD graphics cards for certification, which is perfect timing for AMD's upcoming Financial Analyst Day which takes place on March 5. AMD will be talking about its next-gen RDNA2 architecture at this event on March 5, where we're all hoping to hear about Big Navi.

But when it comes to the two new Korean RRA certification entries, we're looking at D32310 and D30201 -- listed on February 3, and February 19, respectively. Perfect timing for AMD's upcoming Financial Analyst Day on March 5 -- and previously, we've had around one month between Korean RRA certification, and product releases from AMD.

NVIDIA teased something breathtaking yesterday, but today has made it official -- the GeForce RTX 2080 Ti Cyberpunk 2077 Edition graphics card. Check it out in all its glory in the video below:

NVIDIA has teamed with Cyberpunk 2077 developer CD Projekt RED on the new GeForce RTX 2080 Ti Cyberpunk 2077 Edition graphics card, with just 200 made -- but NVIDIA is giving 77 of them away in their 2020 #RTXOn sweepstakes. The 2020 #RTXOn sweepstakes run through to February 28, 2020. In order to win yourself one, all you have to do is:

So something amazing is about to happen, with Cyberpunk 2077 developer CD Projekt RED using its official Cyberpunk 2077 Twitter account to ask about making a limited edition Cyberpunk 2077 GPU... to which NVIDIA replied "stay tuned...".

I don't think this tease is about NVIDIA's next-gen Ampere GPU architecture that is right around the corner, something that should be detailed at its own GPU Technology Conference (GTC) 2020 that takes place between March 22-26. If it is, I'm all booked and ready to go and will deliver you guys the news from the show floor and GTC key note with NVIDIA founder and CEO Jensen Huang.

What we are probably looking at is a GeForce RTX 2080 SUPER graphics card themed like Cyberpunk 2077, as NVIDIA is the technology partner for CD Projekt RED and its recently-delayed Cyberpunk 2077. NVIDIA is no stranger to themed graphics cards, where just a couple of years ago it released the TITAN Xp Star Wars Collectors Edition graphics cards in both Galactic Empire and Jedi Order goodness.

NVIDIA completely pulled out of Mobile World Congress before the MWC organizers GSMA canceled the event, all over coronavirus.

The coronavirus outbreak and fears globally have also pushed NVIDIA to reduce its revenue outlook for the first quarter of fiscal year 2021 by $100 million over the disease outbreak. NVIDIA's earnings reports for fiscal year 2020 were stellar, with revenues of $10.92 billion -- down 7% from the previous year.

Still, NVIDIA's recent Q4 2019 revenue ended on January 26, 2020 saw them pull in $3.11 billion -- up a huge 41% from the previous year with its $2.1 billion. This is all thanks to its gaming technologies like GeForce graphics cards and NVIDIA's big push into AI.

It looks like NVIDIA is up to something a little sneaky here, with a new listing submitted to the Eurasian Economic Commission which teases what looks like a new GeForce GTX 1650 model.

The new listing is by MSI and teases the GeForce GTX 1650 which right now, packs GDDR5 memory, while the GeForce GTX 1650 SUPER is faster GDDR6 memory. The new models would see the GeForce GTX 1650 packing GDDR6 memory, but they wouldn't be a cluster f**k like the recent jebaiting to themselves that AMD did with the Radeon RX 5600 XT and last-minute BIOS changes.

We could see NVIDIA seeing AIB partners phasing out the older GDDR5-based GeForce GTX 1650 graphics cards with the newer GDDR6-based ones, but that's something we'll have to wait and see about over the coming weeks.

Intel is hard at work on its Xe GPU architecture, but a new rumor teases a tile-based architecture approach will be an interesting path as a new report suggests the datacenter variant of Xe could ramp up to 500W of power.

We now have more of an idea on the power consumption across the tile-design approach, where the 1-tile 'DG1' would come in with 96 execution units, 768 cores, and up to 75W TDP -- this is the entry-level Xe GPU. Up from there is the 128 execution unit / 1024 core version with up to 150W of power in the mid-range Xe.

The 2-tile GPU will have the same 128 EUs per tile but since there are two tiles we have 256 total EUs and up to 2048 cores with a TDP of 300W. This will be the high-end gaming card that we should see in 2021 or so, while the 4-tile 'Arctic Sound' is the beast with 4 tiles adding up to a huge 512 EUs, up to 4096 cores, and a huge 400-500W of power -- this is for the datacenter, and not gamers.

Raijintek has just unveiled its Samos AD5700 RBW, which is a new full-cover water block for AMD's Radeon RX 5700 series graphics cards. Check it out:

Raijintek designed the new Samos AD5700 RBW to fit onto AMD's own reference Radeon RX 5700 and Radeon RX 5700 XT graphics cards, packing a nickel-copper thermal plate, and translucent acrylic top cover. The full-cover cold plate will provide water cooling goodness to the most important parts of your Navi-powered graphics card: the GPU itself, GDDR6 modules, and the VRM power delivery MOSFET.

We have a 12mm thick clear acrylic top cover that features built-in G1/4" inlets/outlets, RGB lighting (which looks awesome) and is completely customization through motherboard manufacturer RGB lighting apps through a 4-pin 5V ARGB header. On the back, Raijintek offers up a black-themed aluminum backplate with passive cooling to the VRMs on the back of the card.

AMD is set to unleash its 'Big Navi' GPU this year, something AMD CEO Dr. Lisa Su herself has teased and confirmed, but a new rumor could see it unveiled as soon as March 5 at AMD's upcoming Financial Analyst Day. AMD wants to disrupt 4K gaming with Big Navi like it did to the CPU market with Intel.

This is where you should have an entire container of salt and not just a pinch, because I really don't think that's going to happen -- but, if AMD were to surprise unveil Big Navi, it would make serious waves. Maybe AMD will come out of nowhere and detail Big Navi at a financial event, but given it's a gaming card that would be a very left field move to make. But at this point of the game, AMD needs to do just that.

Big Navi should have performance that will equal, and in some games/resolutions beat NVIDIA's flagship GeForce RTX 2080 Ti. AMD's upcoming Big Navi will utilize the newer 7nm+ node but according to my personal sources they weren't able to squeeze as much from 7nm+ as they thought, and on top of that NVIDIA is close to launching its new Ampere-based GeForce RTX 3080 and GeForce RTX 3070 which Big Navi will not be able to come close to.

ASUS has just joined GALAX in the white graphics card market with its new GeForce RTX 2080 SUPER ROG STRIX White OC, with a super slick style that you just need to feast your eyes on below:

As you can see the entire graphics card and its cooling shroud is white, while underneath the PCB is black. So ASUS isn't going full-white here but it's pretty damn close. ASUS straps on its triple-fan cooler while keeping its thick 2.7-slot design, while the black PCB underneath is a full-custom job that requires dual 8-pin PCIe power connectors.

ASUS will be clocking the GeForce RTX 2080 SUPER ROG STRIX White OC at up to 1890MHz Boost, while the 8GB of GDDR6 will be clocked at 15.5Gbps. There's no clue on pricing just yet, but expect it to be a little more expensive than a traditional ROG STRIX member of the RTX 2080 SUPER family from ASUS.

NVIDIA's next-gen Ampere GPU is shaping up to be a monster, and could be NVIDIA's craziest GPU yet -- with new rumors suggesting it will be up to 75% more powerful than the current-gen GPUs. We've already heard that Ampere would offer 50% more performance at half the power of Turing, which sent the hairs on my neck standing up. Better yet, you can read about the leaked specs on the purported Ampere-based GeForce RTX 3080 and GeForce RTX 3070 right here.

The new tease is coming from the new Big Red 200 supercomputer, which will reportedly pack NVIDIA's next-gen Ampere GPUs. The new Big Red 200 supercomputer will pack an insane 672 dual-socket nodes thanks to AMD's kick ass EPYC 7742 processors (each with 64 cores and 128 threads) for a total of a mind-bending 86,016 cores and 172,032 threads -- will also be powered by NVIDIA's next-gen Ampere GPUs.

The new Big Red 200 supercomputer is being made in two phases with the first phase operational, but Indiana University was originally going to use NVIDIA's current-gen Tesla V100 GPUs but thought they'd wait for NVIDIA's next-gen Ampere GPUs. The new Big Red 200 supercomputer will use less GPUs but thanks to Ampere it will be more powerful -- where it has "also mentioned that Big Red 200 gained an additional 2 petaflops of performance even though it uses a smaller number of GPUs than the Volta V100 based design. The reason for going with a smaller number of next-generation GPUs is simply because they offer 70-75% better performance than existing parts".