Items tagged with NASDAQ:NVDA

In case there was any doubt that Arm could be switching hands in the near future, its parent company, SoftBank, confirmed it is shopping the semiconductor outfit around and is in talks with a specific bidder. While not mentioned by name, it has been widely reported that NVIDIA has interest in acquiring ARM, despite inevitable regulatory hurdles. A sale to NVIDIA or any other company is still not a foregone conclusion. SoftBank has options, and it is considering all of them. Should there not be a satisfying offer, SoftBank could retain Arm and take it public again. It could also sell a stake or multiple stakes in Arm, rather than offload the company outright to a single buyer, NVIDIA or otherwise.... Read more...
A brand new round of GeForce graphics cards looms just around the corner, and the countdown has begun. Well, TWO countdowns, actually. One is the Ultimate Countdown we wrote about yesterday, which we have a little more information to share. And the other is the countdown to September 1, 2020, the day NVIDIA will host a "GeForce Special Event." These two countdowns are intertwined (and are one in the same, really). The first one popped up yesterday in a vague Twitter post, from NVIDIA's verified GeForce account. It showed a short clip of a supernova, with the words, "21 Days. 21 Years." Turns out this is a 21-day celebration of the past 21 years in graphics, dating back to the introduction of... Read more...
The "Ultimate Countdown" has begun over on NVIDIA's official GeForce Twitter page, only we are not entirely sure to what. From the looks of things, it could be a big bang in the making, but let's hope not—despite all our problems, we've grown fond of this world as it exists. More likely, the Ultimate Countdown will take us to the unveiling of NVIDIA's next-generation GeForce RTX 3000 series, based on Ampere. Whether they will actually be branded as GeForce RTX 3000 cards remains to be seen as well. The only seemingly sure thing is that Ampere will power NVIDIA's next-gen cards. We can hardly wait, especially with so many leaks and rumors pointing to big gains in both rasterized rendering... Read more...
Look for NVIDIA to launch its next-generation GeForce RTX 3000 series of graphics cards around a month from now, if the latest leaked information is correct. These cards will feature the NVIDIA's Ampere GPU architecture. Ampere, of course, has already launched, though so far only in the machine learning sector with the A100 Tensor Core GPU. That part touts 54 billion transistors packed into a die that measures 826mm2. There are a total of 6,912 FP32 CUDA cores, 432 Tensor cores, and 108 streaming multiprocessors. It also wields 40GB of HBM2e memory with a maximum memory bandwidth of 1.6TB/s. FP32 compute performance checks in at 19.5 TFLOPs. Whatever emerges in the consumer sector will be a bit... Read more...
I would not say it has been a good, long run for the GeForce RTX 2070 Super, but it has certainly been a good run, albeit a short one. As in, the card is just under a year old, and there is already chatter that NVIDIA is discontinuing the SKU. The reason? To make room for a new generation of graphics cards based on Ampere, of course. To be perfectly clear, there is no official confirmation from NVIDIA that the GeForce RTX 2070 Super is getting the Old Yeller treatment. However, according MyDrivers, the SKU has been "completely discontinued," with the last batch of chips having gone out to NVIDIA's hardware partners. No new orders for the GeForce RTX will be accepted, the report states. The GeForce... Read more...
It is not a foregone conclusion that NVIDIA will end up acquiring Arm, a move that would send shockwaves through the technology industry. That's because NVIDIA may not be the only suitor. Samsung is reportedly interested in buying a stake in Arm as well, albeit a relatively small one (as opposed to acquiring the company outright). Arm's parent company, Softbank, is shopping the semiconductor designer around, and may have multiple suitors. And with good reason—Arm's intellectual property is found in a wide range of designs and hardware in almost every home. From smartphones to a growing base of Internet of Things (IoT) devices, and even computer servers, Arm's technology is practically everywhere... Read more...
Stop what you are doing, go into the kitchen, and grab your container of salt. We'll wait. Still waiting. Okay, now that you have gone and grabbed a whole bunch of grains of salt, lets get to the latest next-generation GeForce RTX rumor. According to the recent chatter, the GeForce RTX 3090 will be around 50 percent faster than the GeForce RTX 2080 Ti in 3DMark's Time Spy Extreme benchmark. What is that based on? Well, this is where the salt comes in handy. A pair of established leakers on Twitter posted the information, but without any links or graphs or...anything, really. It is basically banter, presumably on some kind of discovery or inside knowledge. Here is the interesting exchange... KatCorgi:... Read more...
For the third time in a row, NVIDIA ran a clean sweep of MLPerf's set of AI and machine learning performance benchmarking suite. This time, however, the distinction of fastest GPU went to NVIDIA's A100 Tensor Core graphics solution, which is based on the company's 7-nanometer Ampere architecture that was recently introduced. "The A100 Tensor Core GPU demonstrated the fastest performance per accelerator on all eight MLPerf benchmarks. For overall fastest time to solution at scale, the DGX SuperPOD system, a massive cluster of DGX A100 systems connected with HDR InfiniBand, also set eight new performance milestones," NVIDIA stated in a celebratory blog post. MLPerf is an industry benchmarking group... Read more...
Back in early June, we reported that AMD CEO Dr. Lisa Su quickly shot up the ranks to become the highest paid CEO among the S&P 500. Su, who has helmed AMD since 2014, made a number of bold decisions that have allowed the company to claw away market share from longtime rival Intel, not only in the mainstream processor market but also in the highly lucrative enterprise sector. AMD’s Rise Under The Leadership Of Dr. Lisa Su AMD's (and Su's) laser-like focus has greatly improved the company’s fortunes. In early trading this morning, AMD shares shot up over 12 percent to around $67/share. While AMD stock has been on an upward trajectory all year long, this particular... Read more...
There is already plenty of excitement in anticipation of NVIDIA porting its Ampere GPU architecture over to the consumer market with its next round of GeForce RTX graphics cards, and adding to the hype is an early look at some benchmarks, albeit for the machine learning version (A100). Compared to Turing, the benchmark data shows Ampere way out ahead. The benchmark data was shared on Twitter by Jules Urbach, CEO and co-founder of of OTOY, a cloud graphics company. He ran the Ampere GPU through a round of testing in OctaneBench, which is based on OTOY's OctaneRender application. Here is a look at the results... Source: OTOY "A record breaking week. The NVIDIA A100 has now become the fastest GPU... Read more...
NVIDIA has partnered with the University of Florida (UF) to build an artificial intelligence (AI) supercomputer that will be the fastest in all of academia. Or more specifically, it will be capable of a whopping 700 petaflops of AI performance, made possible by enhancing the university's existing HiPerGator supercomputer with NVIDIA's DGX SuperPod architecture. This essentially represents an infusion of NVIDIA's DGX A100 systems, each of which wields eight Tensor Core GPUs based on the company's 7-nanometer Ampere architecture. And each of those GPUs touts 54 billion transistors capable of delivering 5 petaflops of performance in a single node, along with the ability to handle 1.5TB of data per... Read more...
Turn out the lights, the party's over. The Turing GPU party, that is. Well, not officially, but you can assume the party is winding down to some degree, with NVIDIA getting ready to launch a new round of consumer graphics cards based on its Ampere GPU architecture. As it prepares for that day, rumor has it NVIDIA is discounting its GeForce RTX 2080 Ti and several other GeForce RTX 20-series graphics cards. NVIDIA's 7nm Ampere GPU has already arrived, of course, though so far only in high performance computing (HPC) form. A consumer launch is still around the corner. Leading up to the launch, there has been an avalanche of leaks and rumors pointing to next-gen GeForce RTX 3000 series cards, including... Read more...
One of the biggest things that happened this weekend was the Ubisoft Forward event, where the company talked about some of its future video games. One of the games that the company spoke about at the show was its new free-to-play battle royale shooter Hyper Scape. It was announced that the game is now in open beta for PC gamers during the event. In addition, gamers who have an NVIDIA GeForce NOW subscription can get in on the Hyper Scape open beta. As with all GeForce NOW games, Hyper Scape requires no downloads before allowing players to jump into the action in Neo Arcadia. There's been quite a bit of buzz surrounding the game since it was announced in late June. Free-to-play battle royale style... Read more...
I suspect that by the end of this summer, we will finally have some official clarity on what the next round of graphics cards will bring. Reinforcing that notion is a fresh rumor claiming NVIDIA has taped out a pair of mainstream Ampere cards headed for the consumer market, those being the GeForce RTX 3060 and Geforce RTX 3050. They are considered mainstream in the sense that they are not professional graphics cards, like the Quadro series, nor do they fall into that in-between category served by the Titan RTX. They will still cost a chunk of change, though. For reference, the GeForce RTX 2060 launched at $349. It remains to be seen if Ampere will represent a price bump at each model tier. We... Read more...
Now might not be the optimal time to invest in a new GPU—both NVIDIA and AMD have new graphics cards on the horizon, built around Ampere and RDNA 2 (Big Navi), respectively—but if you absolutely can't wait, you can score a nifty bonus. If you buy a GeForce RTX series graphics card, that is. Purchasing a qualifying card and you will receive Death Stranding at no additional cost. The bundle promotion arrives just a few days before Death Stranding releases to PC on next Tuesday, July 14. Death Stranding will come out of the gate with support for NVIDIA's second generation Deep Learning Super Sampling (DLSS 2.0) technology. Simply put, DLSS 2.0 works well, and is much improved over the... Read more...
NVIDIA has, for the first time, surpassed Intel to take the crown as the most valuable chipmaker in the United States. NVIDIA did this after its shares rose 2.3% in afternoon trading on Wednesday to reach $404 per share. When the stock hit that price per share, the company's market capitalization came in at $248 billion. On the same day, Intel's market capitalization was $246 billion. Intel was once the leading chipmaker in the entire world but has been on the decline amid fierce competition from NVIDIA and rival chipmaker AMD, among others. One move that has enabled NVIDIA to grow so much in recent years was its expansion outside of its traditional market of computer gaming chips into hardware... Read more...
It will probably be another month (hopefully) or two (hopefully sooner) before NVIDIA officially lifts the curtain on its next round of GeForce RTX graphics cards, based on its newest Ampere GPU architecture. In the meantime, the leak and rumor scene continues to buzz. The latest supposed leak claims to detail the specifications for two upcoming models, the GeForce RTX 3070 Ti and GeForce RTX 3070. Ampere itself is already official. NVIDIA formally introduced the part in May for the high-performance computing (HPC) market, in the form of the A100. That part boasts 54 billion transistors, 6,912 FP32 CUDA cores, 432 Tensor cores, and 108 streaming multiprocessors, along with 40GB of HMBe2 memory.... Read more...
Stop us if you heard this one already—over at Geekbench, performance results purporting to be from an unreleased Tiger Lake processor with Xe graphics have emerged and show...what's that, you have heard this before? Fair enough, but what makes this latest leak a little different (and interesting) is potentially seeing how the graphics portion compares with NVIDIA's discrete GeForce MX350 GPU. As many of you reading this already know, Tiger Lake is the codename for Intel's next round of mobile processors, which will succeed Ice Lake. They are being built on an enhanced 10-nanometer manufacturing process (10nm+), and feature graphics based on the same Xe architecture that will underpin Intel's... Read more...
It is confirmed, folks, go ahead and bet the farm on NVIDIA releasing a GeForce RTX 3080 Ti graphics card in the near future, it is definitely, without a doubt, for sure going to happen. Yep. Probably so. Well, it is certainly likely. Okay, maybe it will happen? Hmm, perhaps you should hold on to the deed to the farm a little longer. However, a supposedly leaked presentation slide seemingly indicates ASUS is working on a custom variant of the rumored part, as shown in the image above. So, there's that. In case it is not obvious by the watermark, the folks at Videocardz got their mitts on the photo. The site believes it was taken during an internal meeting at ASUS to discuss possible designs for... Read more...
It appears as though NVIDIA has silently added another Turing GPU option to its lineup, with at least one of its hardware partners already taking advantage of the new part. That would be Galax (also known as Galaxy), which is one of several brands owned by Palit Microsystems. Galaxy has begun advertising a new GeForce GTX 1650 Ultra. The "Ultra" could just be a custom model designation by Galax, similar to how EVGA sells "Ultra Gaming" variants, to offer one example. Or it could be a brand new tier in NVIDIA's GeForce GTX 16 series. As of this writing, however, here is how the GeForce GTX 16 series shakes out on NVIDIA's website... GeForce GTX 1660 Ti—TU116-400-A1 GPU GeForce GTX 1660 Super—TU116-300-A1... Read more...
One of NVIDIA's major selling points when it introduced its GeForce RTX graphics cards based on Turing was the presence of dedicated RT cores to handle ray-traced visuals. It has been somewhat of a slow march to ray-traced territory by developers, though things have certainly improved. And looking ahead, Cyberpunk 2077 will embrace ray tracing effects in a big way. Cyberpunk 2077 is one of the most anticipated games in recent history. We are optimistic it will live up to the hype. It should certainly look gorgeous, if nothing else, from what we have seen so far. "In addition to featuring CD Projekt Red’s fantastic open-ended gameplay, Cyberpunk 2077 is also blessed with jaw-droppingly beautiful,... Read more...
NVIDIA has over the years signed some big names in the automotive world for its DRIVE platform, and the company is making a big announcement in conjunction with one of the leaders in the premium sector: Mercedes-Benz. Next-generation Mercedes vehicles will leverage NVIDIA’s future DRIVE platform that is powered by the Orin SoC. Orin is based on 7nm Ampere architecture and can scale in implementation from as little as 5W in low-end configurations to as high as 800W for Level 5 autonomous robotaxis. Mercedes says that the hardware/software solution will provide Level 2 and Level 3 autonomy, along with automated parking functionality that scales up to Level 4. Using a combination... Read more...
1 2 3 4 5 Next ... Last