Jump to content

Search the Community

Showing results for tags 'nvidia'.

  • Search By Tags

    Type tags separated by commas.
  • Search By Author

Content Type


Forums

  • Site Related
    • News & Updates
    • Site / Forum Feedback
    • Member Introduction
  • News
    • General News
    • FileSharing News
    • Mobile News
    • Software News
    • Security & Privacy News
    • Technology News
  • Downloads
    • nsane.down
  • General Discussions & Support
    • Filesharing Chat
    • Security & Privacy Center
    • Software Chat
    • Mobile Mania
    • Technology Talk
    • Entertainment Exchange
    • Guides & Tutorials
  • Off-Topic Chat
    • The Chat Bar
    • Jokes & Funny Stuff
    • Polling Station

Categories

  • Drivers
  • Filesharing
    • BitTorrent
    • eDonkey & Direct Connect (DC)
    • NewsReaders (Usenet)
    • Other P2P Clients & Tools
  • Internet
    • Download Managers & FTP Clients
    • Messengers
    • Web Browsers
    • Other Internet Tools
  • Multimedia
    • Codecs & Converters
    • Image Viewers & Editors
    • Media Players
    • Other Multimedia Software
  • Security
    • Anti-Malware
    • Firewalls
    • Other Security Tools
  • System
    • Benchmarking & System Info
    • Customization
    • Defrag Tools
    • Disc & Registry Cleaners
    • Management Suites
    • Other System Tools
  • Other Apps
    • Burning & Imaging
    • Document Viewers & Editors
    • File Managers & Archivers
    • Miscellaneous Applications
  • Linux Distributions

Categories

  • General News
  • File Sharing News
  • Mobile News
  • Software News
  • Security & Privacy News
  • Technology News

Find results in...

Find results that contain...


Date Created

  • Start

    End


Last Updated

  • Start

    End


Filter by number of...

  1. Nvidia today has launched its latest GeForce Game Ready 471.96 WHQL driver. Interestingly, however, the new driver - unlike most launches - isn't optimized specifically for any new game. Of course, the 471.96 driver carries all game-related optimizations that Nvidia has added in its recent updates, plus it also includes Windows 11 support. And there is new stuff with the latest driver too. For example, it adds support for six new G-SYNC Compatible displays. They are: EVE Spectrum ES07D03 Lenovo G27Q-20 MSI MAG321QR Philips OLED806 ViewSonic XG250 Xiaomi O77M8-MAS In relation to G-SYNC, Nvidia has noted that the feature is disabled for those games and other applications that are meant to run at a fixed framerate. Also, 24 new games have been added to the list of titles for GeForce Experience’s one-click optimal settings. These are: Aliens: Fireteam Elite Bless Unleashed Blood of Heroes Car Mechanic Simulator 2021 Doki Doki Literature Club Plus! Draw & Guess Faraday Protocol Final Fantasy Final Fantasy III Ghost Hunters Corp Golf With Your Friends GrandChase Humankind King's Bounty II Madden NFL 22 Mini Motorways Psychonauts 2 Quake Remastered SAMURAI WARRIORS 5 Supraland The Great Ace Attorney Chronicles The Walking Dead: Onslaught Yakuza 4 Remastered Yakuza 5 Remastered As usual, the new 471.96 driver also fixes some bugs: DPC latency is higher when color mode is set to 8-bit color compared to 10-bit color. [3316424] Unable to detect supported display modes for the Samsung Odyssey G9 display [3332327] Blue-screen crash/reboot loop occurs when two Samsung Odyssey G9 displays @ 240Hz are connected. [3256732] NVDisplay.Container.exe constantly writes data to C:\ProgramData\NVIDIA Corporation\nvtopps\nvtopps.db3. [3350171] [Windows 11][Notebook]: With the graphics mode set to Hybrid, the GPU frequently wakes up while idle. [3345922] [CUDA][Turing/Volta GPUs]: Stability issues with Topaz Denoise AI. [200755368] There are also some unresolved issues that remain: [Deathloop][HDR]:TDR/corruption occurs in the game with Windows HDR enabled. If this issue occurs, toggle the Windows HDR setting. [NVIDIA Control Panel]: After overinstalling the driver using express install when GPU scaling is enabled, the 0.59x upscaling factor is missing from the NVIDIA Control Panel scaling resolution list (Display > Change Resolution page). To work around, disable and then re-enable GPU scaling. Alternatively, perform a clean driver installation. [Battlefield V][DirectX 12]: The game may crash with HDR enabled. [3353767] To work around, enable HDR from the Windows display settings before launching the game. [YouTube]: Video playback stutters while scrolling down the YouTube page. [3129705] Tom Clancy's The Division 2 may display graphical artifacts. [200754013] Sonic & All-Stars Racing Transformed may crash on courses where players drive through water. [3338967] The 471.96 Game Ready driver is now available for download on the GeForce Experience app. Those looking for the official standalone installation links can find them below: Desktop GPUs: Download: Windows 7, 8, 8.1 | Windows 11, 10 – Standard / DCH Notebook GPUs: Download: Windows 7, 8, 8.1 | Windows 11, 10 - Standard / DCH You may find more details on the official blog post here. Nvidia Game Ready 471.96 driver adds support for six new G-SYNC compatible displays
  2. Delays have Nvidia facing down the end-of-2022 deadline to complete the deal. Nvidia's purchase of ARM sure is taking a while, and today the company told the Financial Times it is unlikely to meet the 18-month regulatory window it initially laid out. The blockbuster $40 billion deal was announced in September 2020, and it would give Nvidia control of the world's most popular architecture, used by Apple, Samsung, Qualcomm, Huawei, Google, Amazon, Microsoft, and a ton of other companies. Nvidia CEO Jensen Huang told the Financial Times, "Our discussions with regulators are taking longer than initially thought, so it’s pushing out the timetable... It’s not one particular regulator, but we’re confident in the deal, we’re confident regulators should recognize the benefits of the acquisition." Nvidia is facing several problems with regulators. First up, regulators in ARM's home country, the UK, have national security concerns. Bloomberg spoke with a "person familiar with the matter" and reports that "the UK is currently inclined to reject the takeover" as it currently stands. Of course, Nvidia could make some concessions to push the deal through, but Bloomberg quotes one analyst as saying investors have "low expectations" that the deal will go through. FT also notes in the UK that "the deal has become a politically charged symbol of the country’s loss of corporate influence in the face of foreign takeovers." Neither this nor the "national security" concerns make a whole lot of sense because the "foreign takeover" has already happened, though. ARM has been owned by the Japanese company Softbank since 2016, and now Softbank is selling ARM to Nvidia, an American company. Does China want another major pillar of technology in the US? A country that will probably have serious concerns is China, which is still reeling from the US export ban on Huawei, one of China's biggest companies. In the smartphone market, Huawei has plummeted from a first-place perch down to the "other" category in most marketshare charts thanks to the ban. Huawei also is the world's No. 1 telecom equipment manufacturer, and it's finally starting to see some losses in that market, too. Nvidia buying ARM would represent even more US control over the smartphone and wider technology market. Part of the delay with Chinese regulators is apparently Nvidia's fault: the company only submitted an application to Chinese regulators in June 2021, eight months after the announcement of the deal. The company now has to wait as long as 18 months from that date for the investigation to complete, which would push things to December 2022. Nvidia basically ended up waiting until the last minute—the deal with Softbank will be void if Nvidia can't close by the end of 2022. Nvidia wouldn't be the first company to have a huge tech deal shut down by Chinese regulators. Back in 2016, Qualcomm tried to buy NXP for $47 billion, but the company failed to secure Chinese regulatory approval in time and ended up abandoning the deal in 2018. ARM licenses the ARM chip architecture and pre-made CPU designs to many huge companies in tech, and these licenses underpin major products for many companies. Under Softbank, ARM was seen as a neutral party, since Softbank doesn't compete with ARM licensees and Japan isn't currently engaged in a trade war with China. Nvidia has a reputation of being hard to work with, and it's unclear how well "Nvidia ARM" would work with others. It's also not clear how the company would inevitably try to connect ARM licensing with its GPU business (ARM also designs mobile GPUs to pair with its CPUs). Nvidia insists it will keep ARM "neutral," and the company has a whole website dedicated to pitching the merger to the world. Specific pages detail Nvidia's "vision" for ARM in the UK, Europe, and China—so, there's a page for each regulatory body that has raised concerns about the deal. If Nvidia doesn't live up to all of its promises, the industry is side-eyeing the open source RISC-V architecture as a possible escape hatch, although that would take a massive, coordinated industry-wide effort to replace ARM. If the deal with Nvidia doesn't go through, Softbank might opt to list ARM on the stock market rather than sell it outright. For now, time's ticking. Approval for Nvidia’s ARM acquisition might come down to the wire
  3. Nvidia RTX 4000 ‘Lovelace’ GPUs design finalized, could arrive end 2022 Set to be built on TMSC 5nm, or maybe even 5nm enhanced Nvidia’s next-gen GeForce graphics cards, presumably RTX 4000 models, are codenamed ‘Lovelace’ (we’ve heard that name before, of course) and have now been finalized, according to the rumor mill. This comes from leaker Greymon on Twitter, who also reckons that the GPUs will be built by TSMC on 5nm – and in a further tweet, the leaker explains that Lovelace products could be made using either TSMC’s straight 5nm process, or perhaps ‘N5P’ (theoretically an enhanced 5nm with better performance). Greymon isn’t sure yet which of these routes Nvidia might travel, and of course, we have to take everything shared here with a good deal of caution, as with anything from the grapevine. There has been some confusion about whether Nvidia might tailor its next-gen graphics cards in reaction to AMD’s RDNA 3 efforts, as VideoCardz, which spotted the above tweet, points out. Switching tack? Renown leaker Kopite7kimi has suggested Nvidia could switch tack, from Lovelace to Hopper GPUs – or AD102 to GH202 respectively – depending on how AMD’s MCM architecture shapes up (remember, the rumor mill has suggested it’s going to be employed with RDNA 3 products). MCM or multi-chip module is a chiplet design, as opposed to monolithic (one single chip). Nvidia could still go the MCM route itself, depending on how powerful it looks like the rival RDNA 3 GPUs might be, or that was the suggestion from Kopite7kimi. While spec rumors are definitely pushing it at this stage, Kopite7kimi has also floated the idea that the flagship RTX 4000 card will run with 144 streaming multiprocessors for a maximum of 18,432 CUDA cores. Greymon, however, seems to pretty firmly believe that Lovelace is now locked in for Nvidia as the next-gen range of desktop graphics cards. As for the release date, Greymon tweeted that it will be ‘no earlier’ than the end of 2022, perhaps indicating there’s even a chance it could slip to early 2023. Analysis All of this must be treated with a lot more skepticism than normal because it’s very early days for Nvidia’s next-gen GPUs, and as we know, when rumors come far in advance, they are a lot more, shall we say, variable in quality and potential accuracy. Even what Nvidia is currently planning could well change, although Greymon’s main contention here is that the RTX 4000 series has now been finalized, of course. Nvidia purportedly going with TSMC to produce these cards, either on 5nm, or maybe even enhanced 5nm, will be quite a leap, especially with the latter; so the performance boosts coming should be very impressive. Team Green may well be wise to look at pulling all the stops out, though, if AMD’s RDNA 3, due also at the end of 2022 in theory (and on TSMC 5nm), fulfils its promise as outlined on the GPU grapevine. Namely that the low-end next-gen AMD cards will be as good as the most powerful current RDNA 2 cards (like the flagship RX 6900 XT). When you further consider that Intel is entering the graphics card arena, maybe later this year, or earlier on in 2022, with a potentially promising high-end GPU, then it’s easy to see how Nvidia might want to push hard to maintain its undoubted dominance in the desktop market. Nvidia RTX 4000 ‘Lovelace’ GPUs design finalized, could arrive end 2022
  4. Nvidia's latest 471.41 driver makes Red Dead Redemption 2 DLSS ready, and more Nvidia today has launched its latest WHQL-certified display driver version 471.41. The new driver adds support for Nvidia's DLSS technology in a couple of titles. As the company had promised, today Rockstar's Red Dead Redemption 2 (RDR 2) gets support for the update. Alongside RDR 2, survival-horror title, Chernobylite - that's still in early access - has also gained support for the image upscaling technology. With the help of DLSS, Nvidia says RDR 2 gets a performance boost of up to 45%. Meanwhile, with Chernobylite, the performance has close to doubled in certain circumstances according to Nvidia's own numbers. The driver also adds support for two new G-Sync Compatible monitors from Samsung, namely: LS28AG700N, a 28" 4K panel, LC27G50A, a 27" 1440p model. As usual, the new driver also fixes several problems which are: [Capture One]: Hardware acceleration stops working. [3338552] Disabled NOHud/RemoveHud filter from the game Valorant. [3332516] [Doom Eternal]: The game may freeze during gameplay. [3331270] [League of Legends]: The game may fail to launch. [200744747] [HDR]: Mouse cursor color may shift when connected to certain DSC monitors in HDR mode [200741796] Ansel DOF filter blurs the entire screen in some games. [3288883] Some displays screen resolution limited to 640x480 after driver update. [3330750] [HDMI 2.1][8K] HDMI audio playback may become distorted after changing display modes [3268312] [RDP] Remote desktop connection to PC with color set to 10-bit will result in corrupted picture. [3332787] GPU HDMI audio dropouts may occur when connected to an LG C9 OLED TV [3316495] And here are the issues that still remain on Windows 10 although a couple of them have a temporary workaround: [Batman Arkham Knight][GeForce 10 Series]: The game may crash when turbulence smoke is used. [3202250] To work around, disable "INTERACTIVE SMOKE/FOG" from the in-game graphics options [YouTube]: Video playback stutters while scrolling down the YouTube page. [3129705] [Hitman 3]: The game may display random flickering when V-SYNC is disabled [200742415] [Monster Hunter World]: The game displays flashing glitches after extended gameplay. [3336071] Sonic & All-Stars Racing Transformed may crash on courses where players drive through water. [3338967] DPC latency is higher when color mode is set to 8-bit color compared to 10-bit color. [3316424] To work around, disable MPO using the registry key found in the KB article: https://nvidia.custhelp.com/app/answers/detail/a_id/5157/ Unable to detect supported display modes for the Samsung Odyssey G9 display [3332327] The new 471.41 Game Ready driver is available for download on the GeForce Experience app and via the links below for standalone installations: Desktop GPUs: Download: Windows 7, 8, 8.1 | Windows 10 – Standard / DCH Notebook GPUs: Download: Windows 7, 8, 8.1| Windows 10 – Standard / DCH And for those wondering, these drivers are Windows 11 ready too. Nvidia has urged users who find any issue with the 471.41 driver to report the problem in the official feedback thread which you can find here. You can view Nvidia's official press release here. Nvidia's latest 471.41 driver makes Red Dead Redemption 2 DLSS ready, and more
  5. Nvidia's 466.79 Hotfix driver adds RTX 3070 Ti support, fixes a BSOD error, and more Nvidia's newest graphics card, the GeForce RTX 3070 Ti, launches today and alongside it team green has released the Game Ready WHQL driver version 466.77 which adds support for the new card. The driver carries over most of the same game optimizations that were added with the previous version 466.63. But it does carry support for The Persistence, which recently gained Nvidia's DLSS upgrade. The driver claims to fix a blue screen of death (BSOD) related to error causeds by DPC Watchdog violation in older Kepler and last-gen Turing GPUs. There are also a few more fixes and all of them have been listed below: [Crossfire HD]: Freestyle is not supported for the game. [200734448] [Kepler/Turing GPUs]: Blue-screen crash with DPC Watchdog Violation error may occur. [3321668/3321735] [VR]: If the GPU is connected to a 4K UHD TV, the system may freeze when launching a VR game. [3313315] [RTX 20 series][GTX 16/10 series][HDMI]: 4K @ 120Hz display mode is not available from display settings. [3312401] The known issues related to Windows 10 are the same as the earlier version. They are: [NVIDIA Ampere GPU]: Colors may appear incorrect in games if sharpen Freestyle filter is used with HDR enabled. [200658208] This issue will be resolved in the next NVIDIA driver release. [HDR]: Some specific HDMI displays might show some flickering in HDR mode. [200729987] If you experiencing flickering issues, reboot the system. [World of Warcraft: Shadowlands]: Random flicker may occur in certain locations in the game [3206341] [Batman Arkham Knight]: The game crashes when turbulence smoke is enabled. [3202250] [Steam VR game]: Stuttering and lagging occur upon launching a game while any GPU hardware monitoring tool is running in the background. [3152190] [YouTube]: Video playback stutters while scrolling down the YouTube page. [3129705] Display may flicker or lose signal when launching a game on an adaptive-sync VRR monitor in multi-monitor configuration when sharing the same display mode [3314055] The new 466.77 Game Ready driver is now available for download via the GeForce Experience app, but those wanting a standalone installation can use the links below. For those interested, you can view the release notes here. Desktop GPUs: Download: Windows 7, 8, 8.1 | Windows 10 – Standard / DCH Notebook GPUs: Download: Windows 7, 8, 8.1 | Windows 10 - Standard / DCH Update: A previous version of this article reported on the 466.77 driver, but soon after releasing the 466.77 driver today, Nvidia hurriedly launched a hotfix driver version 466.79. The new hotfix is completely based on the previous driver which means it contains those earlier optimizations and also adds a fix to resolve the display flickering issue. The problem is noted in the list of known bugs section highlighted by code number 3314055. Users, on desktops and notebooks, who are experiencing this flickering problem can download the 466.79 hotfix driver from the following links: Download: Windows 10 - Standard / DCH Nvidia's 466.79 Hotfix driver adds RTX 3070 Ti support, fixes a BSOD error, and more
  6. How good is Nvidia's GeForce RTX 3070 Ti video card? Late last month, NVIDIA announced two additions to its graphic cards portfolio. The new "gaming flagship" GeForce RTX 3080 Ti, and the GeForce RTX 3070 Ti. The flagship model launched on June 3rd, 2021 officially, the GeForce RTX 3070 Ti a week later on June 10th, 2021. If you know your way around video cards, you know that it is quite difficult to obtain reasonably priced cards due to the current market situation. The RTX 3070 Ti is priced at $599 by NVIDIA, $100 more than last year's NVIDIA RTX 3070 card, which NVIDIA priced at $499. According to NVIDIA's announcement, the GeForce RTX 3070 Ti "boosts performance with more CUDA Cores and our super speed GDDR6X memory". While that sounds good on paper, it is less than 5% of an increase over the $100 cheaper RTX 3070 video card. RAM on the other hand has been improved significantly, as NVIDIA decided to use GDDR6X memory in the new card, which was only used in 3080 and 3090 cards up until now. PC Gamer ran benchmarks and RAM performance saw an impressive boost (608GB/s over 448GB/s). Memory performance improves significantly, but the card has only 8 Gigabytes of it. That's fine compared to NVIDIA's own GeForce 3070 card, but not when you look at AMD's Radeon RX 6800 card, which comes with 16 Gigabytes. AMD's card was a bit on the pricey side when compared to the 3070, as it retails for $579, but it fares better against NVIDIA's new card as it is cheaper and comes with more RAM. Memory is not everything though, as performance is what ultimately matters for gamers. Benchmarks by PC Gamer show very similar performance for NVIDIA's card and AMD's card. Performance differed slightly in the 4K benchmarks, e.g. 56 to 57 average FPS in Metro Exodus, or 67 to 62 average FPS in Horizon Zero Dawn. Benchmarks by The Verge paint a similar picture at 1440P and 4K. Compared to the 3070, the 3070 Ti does better in most benchmarks, but not by much. In some, its performance was worse. NVIDIA claims that the 3070 Ti delivers a 1.5x performance improvement over the RTX 2070 Super, and a 2x improvement over the GTX 1070 Ti. Gamers who run older video cards will see higher performance improvements. The 3070 Ti is not designed as a replacement for the 3070, but likely released by Nvidia to have a competing model for AMD's RX 6800 card (which offers better performance than the regular 3070 version, but comes with a higher price tag). NVIDIA customers who run older video cards can now select NVIDIA's latest model over AMD's. NVIDIA's GeForce RTX 3070 Ti closes the gap to AMD's RX 6800, but it has a slightly higher price and less RAM. Chance is high that you won't be able to buy the new video card anytime soon, as demand is much higher than what is actually available. To answer the title question: it is quite a good card, but not convincing enough to send out a strong "buy me instead of AMD" signal to gamers. Now You: do you pay attention to video card releases? Which card do you favor? How good is Nvidia's GeForce RTX 3070 Ti video card?
  7. Nvidia RTX 3080 Ti is here, more expensive than previously rumored At Computex today, as the company had promised, Nvidia has announced its newest GeForce RTX offerings, the RTX 3080 Ti and the RTX 3070 Ti GPUs. The former will be available to purchase worldwide in a couple of days on June 3 and it is priced at $1,199, which is 20% higher than what rumors had earlier suggested. For this asking price, the new RTX 3080 Ti, Nvidia says, delivers twice the performance of the GTX 1080 Ti even in traditional rasterization situations. The gap naturally extends further when newer technologies like DLSS or real-time ray tracing are added into the mix. Moving on, the 3080 Ti's smaller sibling the RTX 3070 Ti is a much more affordable product coming in for half the price of the former at $599. It will be available for purchase next week. Similar to the performance claims of the 3080 Ti, Nvidia says that the new RTX 3070 Ti offers double the performance of the GeForce GTX 1070 Ti. It is also said to offer around 50% more performance than the RTX 2070 SUPER. In terms of cooling, both the RTX 3080 Ti and the 3070 Ti seem to be equipped with the same cooler design that came with the RTX 3090 and the RTX 3080. Both the coolers are 2-slot wide. The hardware specifications of the two new GPUs are given below: RTX 3080 Ti RTX 3070 Ti Architecture Ampere Ampere CUDA Cores 10,240 6,144 Base clock (GHz) 1.37 1.58 Boost clock (GHz) 1.67 1.77 Memory config. 12GB GDDR6X 8GB GDDR6X Memory interface 384-bit 256-bit Check out some gameplay footage of DOOM Eternal at 4K on the new RTX 3080 Ti provided by Nvidia. (YouTube sign-in required). You can read more about the RTX 3080 Ti and the 3070 Ti here. Nvidia RTX 3080 Ti is here, more expensive than previously rumored
  8. Nvidia teases GeForce RTX 3080 Ti announcement for May 31st A new RTX 3070 Ti is expected, too Nvidia is teasing a GeForce event for May 31st, the same day the company is rumored to be launching its new GeForce RTX 3080 Ti graphics card. A mysterious 11-second teaser video has appeared on Twitter today, simply revealing a GeForce event for 10PM PT on May 31st, or 1AM ET on June 1st. Recent rumors have suggested the GeForce RTX 3080 Ti will be revealed alongside the RTX 3070 Ti on May 31st. The RTX 3080 Ti will reportedly include 12GB of GDDR6X memory, a 2GB increase over what’s found on the existing RTX 3080. A wider 384-bit bus is also rumored, matching the RTX 3090 — and an increase to the memory bandwidth over the RTX 3080. Get Ready. pic.twitter.com/VuDCcKXrry — NVIDIA GeForce (@NVIDIAGeForce) May 26, 2021 The new RTX 3080 Ti and RTX 3070 Ti will undoubtedly include a hash limit for Ethereum cryptocurrency mining. Nvidia introduced this limit on newly manufactured RTX 3080 and RTX 3070 cards recently, branding new cards with a “Lite Hash Rate” or “LHR” identifier. Leaked specs appear to suggest the RTX 3080 Ti will sit between the RTX 3080 and RTX 3090, offering performance somewhere between the two. Since the RTX 3090 retails (on paper at least) at $1,499, it’s possible we’ll see RTX 3080 Ti pricing at around the $1,000 mark. Not that retail pricing really matters, as the street prices of new GPUs are utterly out of control. A global chip shortage has pushed GPU prices up, and demand is still incredibly high during ongoing supply constraints. Nvidia has already warned these supply issues will continue throughout 2021, so launching a new RTX 3080 Ti isn’t going to help here. Source: Nvidia teases GeForce RTX 3080 Ti announcement for May 31st
  9. NVIDIA announced today that it's halving the hash rate for Etehereum cryptocurrency mining on the new GeForce RTX 3080, 3070, and 3060 Ti graphics cards to make them less desirable for miners. The company will add "Lite Hash Rate" or "LHR" identifiers to retail product listings and boxes for all these new nerfed graphics cards that will start shipping later this month. "Today, we're taking additional measures by applying a reduced ETH hash rate to newly manufactured GeForce RTX 3080, RTX 3070 and RTX 3060 Ti graphics cards," said Matt Wuebbling, NVIDIA's Global Head of GeForce Marketing. "This reduced hash rate only applies to newly manufactured cards with the LHR identifier and not to cards already purchased." According to Wuebbling, this decision was taken to make sure that more of these cards will be used by gamers worldwide instead of stacked in cryptocurrency mining farms. RTX 3060 cards' hash rate also halved in February This announcement comes after NVIDIA also nerfed the Ethereum hash rate for all shipped GeForce RTX 3060 cards shipped starting February. "To help get GeForce GPUs in the hands of gamers, we announced in February that all GeForce RTX 3060 graphics cards shipped with a reduced Ethereum hash rate," Wuebbling added. NVIDIA is also hoping to push professional mining operations towards its new range of CMP dedicated mining GPUs by deliberately reducing the new GeForce RTX's mining performance by 50%. The specs for the company's dedicated GPU for professional mining are available in the table embedded below. 30HX 40HX 50HX 90HX Ethereum Hash Rate 26 MH/s 36 MH/s 45 MH/s 86 MH/s Rated Power 125 W 185 W 250 W 320 W Power Connectors 1x 8-pin 1x 8-pin 2x 8-pin 2x 8-pin Memory Size 6GB 8GB 10GB 10GB Starting Availability Q1 Q1 Q2 Q2 "Our RTX 30 Series is built on our second-generation RTX architecture, with dedicated RT Cores and Tensor Cores, delivering amazing visuals and performance to gamers and creators," Wuebbling concluded. "We believe this additional step will get more GeForce cards at better prices into the hands of gamers everywhere." Source
  10. NVIDIA brings its performance-enhancing DLSS to VR games 'No Man's Sky' is among the three virtual reality titles getting the upgrade this month. NVIDIA/Hello Games NVIDIA's Deep Learning Super Sampling (DLSS) tech is coming to nine more games this month, including three virtual reality titles. It'll be the first time that VR games have supported the upscaling technology, which boosts performance and improves visuals. No Man's Sky is one of the more notable games to get a DLSS upgrade in May. NVIDIA says an update that will arrive later this month will improve desktop performance by up to 70 percent when playing in 4K and make gameplay smoother and more responsive. NVIDIA claims DLSS doubles the VR performance of No Man's Sky when the Ultra graphics preset is used. If you have an Oculus Quest 2 and a GeForce RTX 3080, the tech should keep the framerate at 90 fps. The other two VR games to get DLSS support this month are Wrench (which now supports ray-tracing on both VR and desktop modes) and Into The Radius. DLSS will be also enabled in Metro Exodus PC Enhanced Edition, Scavengers, Everspace 2, Amid Evil, Aron’s Adventure and Redout: Space Assault by the end of the month, though some support the tech already. Meanwhile, NVIDIA has rolled out a Game Ready Driver for Days Gone, a PlayStation Studios game that arrived on PC today. Source: NVIDIA brings its performance-enhancing DLSS to VR games
  11. Nvidia 466.47 WHQL driver has support for Days Gone and Knockout City Bend Studios' Days Gone launched on PC earlier today, bringing the PlayStation exclusive open-world title to another platform for the first time. Nvidia has now released a graphics driver that provides official support for the game, mirroring the very recent AMD driver. The WHQL-certified 466.47 Game Ready release also ships with support for Knockout City, the upcoming team-based competitive game based on Dodgeball. Developed by Velan Studios and using the EA Originals label, the game has a May 21 launch date attached to it. Nvidia hasn't said anything about what kind of improvements do these two games receive when the new driver is powering them. This is also the driver Nvidia wants users to install if they are picking up a GeForce RTX 3080, RTX 3070, or RTX 3060 Ti with the new Lite Hash Rate identifier. Every newly manufactured Nvidia graphics card going forward will have a reduced Ethereum hash rate, and the company says the 466.47 driver is "required" for using those cards. Two issues have also been fixed in this driver: [Tom Clancy's Ghost Recon Breakpoint]: The game experiences low performance / low frame rate when launched with Bar1 enabled in the SBIOS. [200721940] [Starbase][GeForce RTX 20/GTX 16 Series]: The game may crash. [3293977] The known issues being worked on by the company are these: [NVIDIA Ampere GPU]: Colors may appear incorrect in games if sharpen Freestyle filter is used with HDR enabled. [200658208] This issue will be resolved in the next NVIDIA driver release. [HDR]: Some specific HDMI displays might show some flickering in HDR mode. [200729987] If you experiencing flickering issues, reboot the system. [World of Warcraft: Shadowlands]: Random flicker may occur in certain locations in the game [3206341] [Batman Arkham Knight]: The game crashes when turbulence smoke is enabled. [3202250] [Steam VR game]: Stuttering and lagging occur upon launching a game while any GPU hardware monitoring tool is running in the background. [3152190] [YouTube]: Video playback stutters while scrolling down the YouTube page. [3129705] The 466.47 Game Ready driver is available for download on the GeForce Experience app. Those wanting a standalone installation experience can use the links below. Here are the release notes. Desktop GPUs: Download: Windows 7, 8, 8.1 | Windows 10 – Standard / DCH Notebook GPUs: Download: Windows 7, 8, 8.1 | Windows 10 - Standard / DCH Source: Nvidia 466.47 WHQL driver has support for Days Gone and Knockout City
  12. NVIDIA Launches GeForce RTX 3050 and RTX 3050 Ti for Laptops Coinciding with today’s launch of Intel’s Tiger Lake-H CPUs for high performance laptops, NVIDIA is also using the occasion to launch their latest lineup of laptop video cards, the GeForce RTX 3050 and RTX 3050 Ti For Laptops. Based on NVIDIA’s newest and smallest Ampere GPU, GA107, the RTX 3050 series finally rounds out the rest of NVIDIA’s laptop offering, introducing a mobile video card that’s better suited for mid-power systems, and cheaper than RTX 3060 to boot. Laptops featuring the new RTX 3050 video adapters will be available today, with all of the major vendors set to ship laptops using NVIDIA’s latest laptop adapter in short order. NVIDIA’s xx50 tier of laptop video cards has traditionally been the company’s high-volume/low-price products for laptops, and the RTX 3050 family is no different. Laptops with the new adapters will start at $799, and will frequently crop up as a baseline option in Tiger Lake-H laptops. With Intel only shipping 32 EUs in Tiger Lake’s integrated GPU – just a third of how many are in Tiger Lake-U – Intel isn’t setting the bar for graphics performance particularly high in this generation of H-series CPUs. As a result, there’s a wide-open market for NVIDIA’s latest low-end graphics adapter to give these machines a boost in graphics performance. And, like the RTX 3060 For Laptops launch back at the start of the year, it’s actually the laptop market that is getting the newest silicon first. For the RTX 3050 series, NVIDIA is rolling out their new GA107 GPU. Cut from the same cloth as the rest of the Ampere family, NVIDIA’s 5th Ampere chip is the smallest and cheapest yet, fulfilling the company’s traditional waterfall launch strategy of rolling out successively cheaper and lower-power/lower-performing chips for additional markets. As an added kicker, these are the first xx50 tier products to have ray tracing – and thus qualify for the RTX moniker – so expect to see NVIDIA promoting that aspect rather hard. NVIDIA GeForce RTX 30 Series Laptop Specifications RTX 3070 Laptop GPU RTX 3060 Laptop GPU RTX 3050 Ti Laptop GPU RTX 3050 Laptop GPU CUDA Cores 5120 3840 2560 2048 ROPs 80 48 32? 32? Boost Clock 1290 - 1620MHz 1283 - 1703MHz 1035 - 1695MHz 1057 - 1740MHz Memory Clock 14Gbps GDDR6 14Gbps GDDR6 12Gbps? GDDR6 12Gbps? GDDR6 Memory Bus Width 256-bit 192-bit 128-bit 128-bit VRAM 8GB 6GB 4GB 4GB TDP Range 80 - 125W 60 - 115W 35 - 80W 35 - 80W GPU GA104 GA106 GA107 GA107 Architecture Ampere Ampere Ampere Ampere Manufacturing Process Samsung 8nm Samsung 8nm Samsung 8nm Samsung 8nm Launch Date 01/26/2021 01/26/2021 05/11/2021 05/11/2021 NVIDIA normally launches two parts at the xx50 tier for laptops, and for this generation NVIDIA has stuck squarely with tradition. At the top is the RTX 3050 Ti, a full-fat (or close to it) GA107 implementation with 20 SMs, for a total of 2560 CUDA cores. Below it is the RTX 3050 (vanilla), with has 16 SMs for 2048 CUDA cores. As these are Ampere family parts, NVIDIA has kept the basic GPU functional blocks proportional across the lineup, so we’re looking at 80/64 tensor cores and 20/16 ray tracing cores for the RTX 3050 Ti and RTX 3050 respectively. Past that, NVIDIA isn’t sharing too much about GA107 in particular. We’re still waiting to find out the die size and transistor count (just how much smaller is it than the 276mm2 GA106?), as well as a few details like ROP counts. As for clockspeeds, both RTX 3050 laptop parts are a bit more modestly clocked, owing to their lower TDP options. Officially, the boost clock for the RTX 3050 Ti for laptops is anywhere between 1035MHz and 1695MHz, depending on what the OEM dials in. Meanwhile the vanilla RTX 3050 for laptops lands between 1057MHz and 1740MHz; a bit higher than the Ti version, owing to the fewer enabled SMs in the lower-end part. Meanwhile, both adapters will ship with 4GB of GDDR6 memory. We’re still awaiting confirmation from NVIDIA on the clockspeed, but 12Gbps is a reasonable bet for both power and cost reasons. Both cards come with a 128-bit memory bus – another typical design choice for xx50 tier parts – so this puts the cards’ memory bandwidth at or above 192GB/sec. Finally, both parts offer the same 35 Watt to 80 Watt TDP window. This very wide range allows for the RTX 3050 parts to be suitable for use in everything from 13-inch gaming laptops to 17-inch workstation laptops. Though it also underscores the fact that the cards’ performance will vary pretty widely from OEM to OEM, since power and cooling allowances are such a critical element of performance. Overall, the new RTX 3050 parts come in at a lower TDP than the RTX 3060 – which started at 60 Watts – which opens the door for use in a bunch more designs, though I fully expect RTX 3060 to be more efficient where the parts overlap in power consumption. Performance Expectations & 140 Wins For better or worse, NVIDIA doesn’t spend a lot of time talking about the actual performance of their low-end laptop adapters, and the RTX 3050 series is no exception. The company’s promotional focus is more on features and how it compares to Intel’s integrated graphics, so we don’t have a lot of performance guidance to work with. Not helping matters again is the wide TDP range, which means different laptop designs can end up being quite far apart in performance. For the games where NVIDIA does provide GTX 1650 Ti data as a comparison point, they have the RTX 3050 Ti at roughly 60% faster. But with a sample size of two games, this should be taken as a very rough estimate. If nothing else, expect to see NVIDIA push DLSS harder here than they have on any other RTX 30 series part thus far. As these are the lowest performing Ampere parts (to date), they have little performance to spare for ray tracing and other resource-intensive effects at native (1080p) resolution, so NVIDIA will be relying on DLSS to make these advanced features viable on this entry-level hardware. Otherwise, as Ampere family parts, the new RTX 3050 for laptop accelerators offer the usual suite of NVIDIA features, including those laptop features rolled out back at the RTX 3060 For Laptops launch earlier this year. So this includes HDMI 2.1 output support and Dynamic Boost 2.0. As well, even these entry-level parts support PCI Express 4.0 connectivity and resizable PCIe base address register (reBAR) support to maximize performance there. Overall, NVIDIA is touting 140 wins across the consumer and professional (Studio) markets, underscoring the fact that the RTX 3050 series will be NVIDIA’s highest volume parts for the laptop market. Over the years NVIDIA has established a rather cozy symbiotic relationship with Intel’s H-series laptop CPUs – with xx50 tier parts being the de facto choice for laptops that include a discrete GPU as a baseline option – and it looks like that will once again be the case for Tiger Lake -H. Already NVIDIA has wins in 15-inch and 17-inch laptops from Dell, Lenovo, HP, and ASUS, and there will be more to come as OEMs continue to launch their next-generation H-series laptops. Finally, according to NVIDIA, the first RTX 3050-equipped laptops will be released as soon as today, depending on the shipping schedule of each OEM. Laptops with the new adapters will start at $799. Source: NVIDIA Launches GeForce RTX 3050 and RTX 3050 Ti for Laptops
  13. Nvidia GeForce RTX 3080 stock is coming — with a crypto mining limiter Galax Nvidia GeForce RTX 3080 and GeForce RTX 3070 will feature Nvidia's upgraded Ethereum limiter Image credit: Nvidia ) We’ve known for a while that Nvidia wants to fit its entire GeForce RTX 30-series range with an Ethereum cryptocurrency mining limiter, after trying it out on just the GeForce RTX 3060. Now we have our first look at partner versions of these anti-mining cards, starting with the Nvidia GeForce RTX 3080 and GeForce RTX 3070. As spotted by VideoCardz, Galax has revealed new “LHR” (Lower Hash Rate) versions of its GeForce RTX 3080 and GeForce RTX 3070 cards. These should make the GPUs only about half as effective at mining Ethereum, without affecting gaming performance. The idea, as with Nvidia’s hash-rate-lowering efforts on other GPUs, is to discourage miners from snapping up what previous little stock will be available, thanks to production problems caused by an underlying semiconductor shortage. Ordinary PC owners, who’ve likely been struggling to find where to buy the Nvidia GeForce RTX 3080, could therefore have a better chance of buying one. For its part, Galax is making it clear that these new models are mining-limited by adding a new “FG” suffix. It’s not clear what this stands for, though. “For Gaming” perhaps. Or “Finally, GPUs” for anyone who’s spent months unsuccessfully chasing restocks. Nvidia’s first attempt to slap an Ethereum mining limiter on the GeForce RTX 3060 didn’t exactly go to plan: its own beta drivers were found to disable it. And more enterprising miners eventually managed to crack it anyway. This second attempt is supposedly more secure, and is tipped to feature on the upcoming Nvidia GeForce RTX 3080 Ti in addition to these existing GPUs. However, the new limiters’ effectiveness remains to be seen, both in terms of how tough it is to crack and how well it actually helps get in-demand graphics cards into PC gamers’ hands. In any case, available stock is practically guaranteed to be low, so you’ll still need to be quick when the LHR cards launch. Source: Nvidia GeForce RTX 3080 stock is coming — with a crypto mining limiter
  14. Nvidia reportedly preparing RTX 3000 "Lite Hash Rate" series featuring new mining limiter Back in February, when Nvidia launched its RTX 3060 graphics card, the company also made a couple of major announcements related to GPU mining. First, the company introduced a mining limiter via driver that cripples the Ethereum mining output of the RTX 3060, and secondly, Nvidia also launched an all-new series of dedicated mining GPUs called the 'Cryptocurrency Mining Processors' (CMP) HX series. However, there may be more to come still. Citing sources close to it, VideoCardz alleges that Team Green is preparing a new lineup of the RTX 30-series cards. The new series is allegedly named the RTX 3000 Lite Hash Rate (LHR) series, and it will come with a new crypto mining limiter baked in for the 30-series SKUs. So, essentially, we may expect a brand new version of the RTX 3080, the 3070, the 3060 Ti, and the 3060. There might be an RTX 3090 version too but one of VideoCardz' sources says it's unlikely Nvidia will release it as the 3090 is already very expensive. The site adds that Nvidia won't be naming the final retail versions of the new cards as the LHR series and it will merely be used to help AIB partners differentiate them from the previous batches of non-LHR cards when they receive the new chips from Nvidia. Speaking of the chips, the GPU IDs of the new LHR chips as well as their non-LHR counterparts are listed below: non-LHR version GPU ID LHR version GPU ID RTX 3090 GA102-300-A1 GA102-302 RTX 3080 GA102-200-KD-A1 GA102-202 RTX 3070 GA104-300 GA104-302 RTX 3060 Ti GA104-200-A1 N/A RTX 3060 GA106-300 GA106-302 The new LHR-based cards are reportedly launching in mid-May which may coincide with the company's upcoming RTX 3080 Ti launch. As we have stated in our previous reports, the 3080 Ti and the 3070 Ti are said to feature the mining limiter as well. The new LHR cards will also come pre-installed with the latest VBIOS that enables PCIe Resizable BAR support. Source: VideoCardz Source: Nvidia reportedly preparing RTX 3000 "Lite Hash Rate" series featuring new mining limiter
  15. Alleged RTX 3080 Ti, RTX 3070 Ti launch dates have leaked A report emerged from Hong Kong-based site HKEPC last week that said Nvidia's upcoming GeForce RTX 3080 Ti will be allegedly be priced at $999 and launch sometime next month in May. Today, the same site has said that it has now obtained the exact date of the launch. The site says that it received this information courtesy of the Taiwan-based AIB vendors who will apparently be launching their own variants on the 26th of the month and the official launch of RTX 3080 Ti will be a day before that on May 25. But that's not all. Nvidia is also allegedly launching the RTX 3070 Ti soon after that. While this time no exact dates have been mentioned, the unveil is said to happen sometime in early June, which means within a few weeks of the rumored 3080 Ti reveal. The RTX 3080 Ti which, as we know of, has seemed to have gone through multiple revisions before Nvidia settled on its final specification. The information on the RTX 3070 Ti, however, had managed to elude us for a long time. But last month, VideoCardz managed to get some of the purported details on the RTX 3070 Ti as well as the final form of the 3080 Ti. The RTX 3070 Ti will allegedly offer the full GA104 GPU die with 6,144 CUDA Cores and feature faster GDDR6X memory compared to the non-Ti version. The full rumored hardware specifications of the two upcoming GPUs have been listed below. Specs of the RTX 3090, 3080 and 3070 have also been provided for comparison: RTX 3090 RTX 3080 TI RTX 3080 RTX 3070 Ti RTX 3070 GPU ID GA102-300-A1 GA102-225 GA102-200-KD-A1 GA104-400 GA104-300 CUDA Cores 10,496 10,240 8,704 6,144 5,888 Memory Interface 384-bit 384-bit 320-bit 256-bit 256-bit Memory Capacity 24GB GDDR6X 12GB GDDR6X 10GB GDDR6X 8GB GDDR6X 8GB GDDR6 Memory Clock 19.5Gbps N/A 19Gbps N/A 14Gbps It is being said that all of Nvidia's future GPUs will come pre-installed with the mining-limiter in their drivers so we may expect the same with the upcoming RTX 3080 Ti and the RTX 3070 Ti as well. Source: HKEPC Source: Alleged RTX 3080 Ti, RTX 3070 Ti launch dates have leaked
  16. Nvidia Warns: Severe Security Bugs in GPU Driver, vGPU Software The gaming- and AI-friendly graphics accelerators can open the door to a range of cyberattacks. Nvidia has disclosed a group of security vulnerabilities in the Nvidia graphics processing unit (GPU) display driver, which could subject gamers and others to privilege-escalation attacks, arbitrary code execution, denial of service (DoS) and information disclosure. Meanwhile, the Nvidia virtual GPU (vGPU) software also has a group of bugs that could lead to a range of similar attacks. 5 GPU Display Driver Security Bugs The most severe of the five bugs in the GPU display driver is tracked as CVE-2021-1074, which rates 7.5 out of 10 on the CVSS vulnerability scale, making it high-severity. It exists in the display driver’s installer, and allows an attacker with local system access to replace an application resource with malicious files. Such an attack may lead to code execution, escalation of privileges, denial of service, or information disclosure. Another high-severity bug, CVE-2021-1075, rates 7.3 on the CVSS scale. NVIDIA Windows GPU Display Driver for Windows, all versions, contains a vulnerability in the kernel mode layer (nvlddmkm.sys) handler for DxgkDdiEscape where the program dereferences a pointer that contains a location for memory that is no longer valid, which may lead to code execution, denial of service, or escalation of privileges. Two medium-severity flaws, CVE-2021-1076 and CVE-2021-1077, both rate 6.6 on the CVSS scale. The former NVIDIA GPU Display Driver for Windows and Linux, all versions, contains a vulnerability in the kernel mode layer (nvlddmkm.sys or nvidia.ko) where improper access control may lead to denial of service, information disclosure, or data corruption. The latter NVIDIA GPU Display Driver for Windows and Linux, R450 and R460 driver branch, contains a vulnerability where the software uses a reference count to manage a resource that is incorrectly updated, which may lead to denial of service. And finally, the medium-severity CVE-2021-1078 rates 5.5 on the CVSS scale and NVIDIA Windows GPU Display Driver for Windows, all versions, contains a vulnerability in the kernel driver (nvlddmkm.sys) where a NULL pointer dereference may lead to system crash. 8 Nvidia vGPU Software Vulnerabilities Meanwhile, Nvidia’s vGPU software has eight different security holes. The virtualized GPU allows computing acceleration tailored for resource-intensive workloads like graphics-rich virtual workstations, data science and artificial intelligence. The first four bugs are high-severity input-validation bugs that can lead to information disclosure, data tampering or DoS. These are: CVE‑2021‑1080 (7.8 on the CVSS scale): A vulnerability in the vGPU Manager (vGPU plugin), in which certain input data is not validated; CVE‑2021‑1081 (7.8): A vulnerability in the guest kernel mode driver and vGPU manager (vGPU plugin), in which an input length is not validated; CVE‑2021‑1082 (7.8): A vulnerability in the vGPU Manager (vGPU plugin), stemming from an input length not being validated; CVE‑2021‑1083 (7.8): A vulnerability in the guest kernel-mode driver and vGPU Manager (vGPU plugin), also arising from an input length not being validated. The other four could lead to a variety of outcomes if exploited: CVE‑2021‑1084 (7.8): A vulnerability in the guest kernel-mode driver and vGPU Manager (vGPU plugin), in which an input length is not validated, which may lead to data tampering or DoS; CVE‑2021‑1085 (7.3): A vulnerability in the vGPU Manager (vGPU plugin) could allow an attacker to write to a shared-memory location and manipulate the data after the data has been validated, which may lead to denial of service and escalation of privileges; CVE‑2021‑1086 (7.1): A vulnerability in the vGPU Manager (vGPU plugin) allows guests to control unauthorized resources, which may lead to integrity and confidentiality loss, or information disclosure; CVE‑2021‑1087 (5.5): A vulnerability in the vGPU Manager (vGPU plugin), could allow an attacker to retrieve information that could lead to an address space layout randomization (ASLR) bypass, which in turn could crack open the door to memory-corruption bug exploitation. Nvidia has released patches to mitigate all of the bugs, which uses can download at through the Nvidia Driver Downloads page or, for the vGPU software update, through the Nvidia Licensing Portal. Affected version tables are available in Nvidia’s advisory, released Friday. Nvidia continues to address security bugs on a regular basis. In January, it released fixes tied to 16 CVEs across its graphics drivers and vGPU software, in its first security update of 2021. And soon after, it issued patches for its Tesla-based GPUs and its Shield TV lineup. Source: Nvidia Warns: Severe Security Bugs in GPU Driver, vGPU Software
  17. Nvidia suggests uninstalling latest Windows 10 updates to fix gaming issues This month’s first mandatory cumulative updates were released in the second week with the promise of fixing problems that had been plaguing many users. However, despite the changelog says there are no critical issues, the list of issues in Windows 10 KB5001330 is growing steadily longer, with Nvidia now looking into the reports. A lot of users have reported that having installed Windows 10 KB5001330 cumulative update, they have also experienced some bad stuttering and FPS drop when playing games. “Previously ran Warcraft on a solid 140 FPS, now it’s stuttering occasionally and FPS has dropped to about 90 FPS,” one user wrote in the Feedback Hub. “Call of Duty Cold War and Warzone dropped down to 1 FPS and are completely unplayable. When running other games in fullscreen windowed the performance in Chrome on my secondary monitor is taking a massive hit too,” another user noted. Others have observed issues with Windows 10’s general performance and various crashes, but Microsoft has yet to acknowledge the reports. In a forum post, Nvidia employee has now recommended uninstalling the latest Windows Updates if you have gaming issues. “If you are seeing lower performance in games, check if rolling back Windows 10 Update KB5000842 solves the issue,” Nvidia said. To be clear, issues were first spotted in Windows 10’s March optional update KB5000842, but the bug appeared to have somehow slipped through the gaps to also appear in KB5001330 (April Patch Tuesday Update), which was pushed to users as a mandatory update this month. In short, April 2021 Patch Tuesday release seems like an odd update with some pretty wide-ranging problems. Some users have also reported that they cannot access the documents, pictures and other user folders because the operating systems boots with a temporary user profile. How to fix gaming issues after the update The only certain cure for the gaming and other issues reported in the cumulative update seems to be rolling back to the older version. Obviously, that’s far from an ideal solution, especially when we consider the important security fixes included in the latest update. If you’ve performance issues after the latest updates, you’ve two options – uninstall the patch or wait for next month’s update. To uninstall the updates, click the Start button, then click the Settings cog. Click Update & Security. On the next window, click “View update history,” then “Uninstall updates” in the top-left corner and look for the update in Control Panel that you want to remove. Source: Nvidia suggests uninstalling latest Windows 10 updates to fix gaming issues
  18. Nvidia's $40 Billion Arm Acquisition Is Under Scrutiny Photo: Justin Sullivan (Getty Images) As expected, Nvidia’s $40 billion acquisition of Arm is nowhere near a done deal. The EU and UK are ready to start investigating the merger, reports The Irish Times. Sources familiar with the matter told the publication that the deal will be thoroughly investigated, and could either be passed unconditionally or with concessions. The investigation comes in response to concerns that the deal will give Nvidia monopolistic power over current Arm licensees. Sources say the investigation is just beginning, as paperwork has not been filed in Brussels yet. The UK Competition and Markets Authority is currently collecting statements from various companies about their views of the acquisition. In the past, Nvidia’s rivals have called for the deal to be blocked, so it seems likely those statements will contain the same or similar sentiments. Arm co-founder Hermann Hauser wrote in a letter last year to the UK Foreign Affairs Committee that allowing Nvidia to acquire ARM would “give Nvidia a dominant position in all processor segments and create another U.S. technology monopoly.” If the acquisition were to be approved, it would only further exacerbate Britain’s worries about tech giants like Google, Facebook, Netflix and Amazon’s influence over the UK, said Hauser. Nvidia is one of 500 Arm licensees worldwide. Should Nvidia acquire Arm, it would become the licenser of those contracts. Nivida’s rivals have called for the deal to be blocked. Nvidia CEO Jensen Huang had previously told the Financial Times that “Nvidia will maintain Arm’s open licensing model,” and that it has “no intention to ‘throttle’ or ‘deny’ Arm’s supply to any customer.” An Nvidia spokesperson told Fortune, “The regulatory process is proceeding as we had planned,” and that the company “fully understand[s] that the relevant governments and regulators will review this transaction in detail, as they should, given the significance of the deal.” Nvidia remains confident that it will receive the necessary regulatory approvals to complete the acquisition. Huang told the Financial Times that Nvidia would be happy to retain Arm’s open licensing model if that was a stipulation of the acquisition. But it’s understandable if you don’t quite buy that, because tech giants have in the past agreed to conditions as part of a merger, only to disregard them later. Facebook, for instance, said it would not match WhatsApp and Facebook user accounts when it acquired the messaging platform in 2014, but it later went back on its promise. The deal is also facing scrutiny in the U.S. and China, so it looks like Nvidia has a long road ahead. Source: Nvidia's $40 Billion Arm Acquisition Is Under Scrutiny
  19. GeForce RTX 3080 Ti shipment spotted in the wild before alleged May 2021 launch An eagle-eyed Facebook user has photographed what appears to be a mother lode of MSI GeForce RTX 3080 Ti Ventus 3X OC graphics cards. An entire pallet of said hardware is en route to the U.S., where it is expected to hit shelves after its tentative launch sometime in mid-May. The Nvidia GeForce RTX 3080 Ti could be launched soon (image via MSI) The last time we heard about Nvidia's GeForce 3080 Ti was when its tentative launch date was pushed back a second time to mid-May. That date appears to be accurate if a new sketchy-looking photo from Facebook (via Videocardz) is anything to go by. A Hong Kong resident has posted what appears to be a pallet of GeForce RTX 3080 Ti graphics cards ready to be shipped to the U.S. It also reconfirms several leaks from earlier which said that the GeForce 3080 Ti would ship with 12GB of VRAM. The variant in question here is the MSI GeForce 3080 Ti Ventus 3X OC. It takes anywhere between 30 to 40 days for a cargo ship to reach the U.S. from Hong Kong. Therefore, the graphics card should make it to the market just in time for launch. Those looking for restocks of existing Ampere cards can breathe a sigh of relief too. There is an entire lot of GeForce RTX 3090 cards alongside the RTX 3080 Ti. However, there is no sign of its lower-specced cousin- the GeForce RTX 3070 Ti anywhere, but that is understandable, given that its launch date also got delayed by a few weeks. Then again, we can rest easy knowing that the GeForce 3080 Ti is real and will hit stores at some point. The problem, however, is availability. If Nvidia's recent statement about the graphics card shortage persisting through 2021 is true, then it will very likely end up like its peers. Buy the ASUS GeForce GT 1030 on Amazon An entire lot of GeForce RTX 3080 Ti graphics cards en route to the U.S. (image via Facebook) Source(s) Facebook via Videocardz Source: GeForce RTX 3080 Ti shipment spotted in the wild before alleged May 2021 launch
  20. Nvidia’s GeForce Experience now optimizes settings for creative apps Lightroom, AutoCAD, and DaVinci Resolve are all supported Nvidia has released a new feature for its GeForce Experience software that helps users of creative applications make sure they’re getting the best performance out of their GPUs. GeForce Experience can now tell you whether you have the best settings enabled for more than 30 creative apps including DaVinci Resolve, Adobe’s Lightroom and Illustrator, and Autodesk’s AutoCAD. If certain GPU features aren’t active, you can turn them on from within GeForce Experience itself “with a single button press.” For example, DaVinci Resolve users can automatically optimize settings for GPU acceleration in various modes, which may or may not have been switched on already. The idea is that GeForce Experience can now be a central hub for creative apps that helps you maximize performance. Nvidia isn’t doing anything specific here to actually improve how the apps work — though it is also releasing a new Studio Driver today for creative software — this is just a convenient way to make sure that you’ve set them up in the best way possible. GeForce Experience is an application for Nvidia GPU owners that’s usually associated with gaming-related functionality. For example, Nvidia releases “Game Ready Drivers” through GeForce Experience that optimizes new games for its GPUs, and the application can serve as a launcher for those games. With this move, the software is further expanding its focus to encompass creative users as well, which is an area that Nvidia continues to concentrate on. Earlier today the company announced that its RTX-powered audio noise removal feature would be directly integrated into Open Broadcaster Software (OBS), the popular streaming software. Source: Nvidia’s GeForce Experience now optimizes settings for creative apps
  21. Unity will add native NVIDIA DLSS support to its game engine The tech boost performance and visual acuity in games with little work needed for developers. Unity/NVIDIA Unity, one of the biggest game engines around, will soon offer support for NVIDIA’s Deep Learning Super Sampling (DLSS) tech. It should be available to Unity developers by the end of this year, allowing them to switch on DLSS in their games in just a few clicks. Unreal Engine also has DLSS support via a plugin that Epic Games rolled out this year. DLSS is a type of upscaling that both boosts performance and improves how games look. It uses AI-powered antialiasing to display images that are similar to native resolution quality (and sometimes even better than that), even though systems only actually render a fraction of the pixels. It lightens the load on hardware while allowing for better-looking games. In addition, DLSS boosts performance for rasterized graphics. The tech is often used alongside ray-traced reflections to produce realistic-looking environments at high resolutions and frame rates on NVIDIA's recent GTX graphics cards. Nintendo's rumored Switch Pro (or Super Switch or whatever it’ll be called) is expected to support DLSS as well. While the next Switch should be more powerful than the current models, it won’t have quite as much muscle as a PlayStation 5 or Xbox Series X/S. Expanded support for DLSS on the engine side should lead to better performance in more games, which should come in handy for the Switch Pro, especially given that it's likely to support 4K gameplay while in docked mode. Source: Unity will add native NVIDIA DLSS support to its game engine
  22. Nvidia 466.11 WHQL driver lands with support for Mortal Shell RTX and DLSS Nvidia is back with another driver update for graphics card owners on the green team. This latest WHQL-certified 466.11 Game Ready release comes with support for Mortal Shell’s RTX update, Valorant's Nvidia Reflex Boost improvements, Nvidia Noise Removal for OBS, and more. Mortal Shell, last year's indie Souls-like developed by Cold Symmetry, is finally receiving its long-promised RTX update, featuring both ray-traced shadows and DLSS capabilities. According to Nvidia, the DLSS implementation can improve framerates by up to 130% at 4K resolution. Meanwhile, Valorant players who are CPU-bound can now enable Boost Mode in the latency-reducing Nvidia Reflex technology. According to Nvidia, enabling Boost Mode while in a CPU-bound scenario can further reduce latency by up to 16% in the competitive title. Open Broadcaster Software (OBS) also received additional support in this driver. The popular software's new OBS Studio 27 beta version now touts Nvidia Noise Removal as a native feature, allowing creators to automatically remove any unwanted background sounds. Previously, this was only available via the company's Nvidia Broadcast companion app. Nvidia also validated six more monitors and televisions as G-Sync Compatible Displays with the release of this driver. The updated list now includes the LG displays 27GP950, 2021 B1 4K Series, 2021 C1 4K Series, 2021 G1 4K Series, 2021 Z1 8K Series, and MSI's MAG301RF. The handful of bug fixes included in this driver are as follows: [Supreme Commander/Supreme Commander 2]: The games experience low FPS. [3231218/ 3230880] [Adobe Camera RAW 12.x]: RAW files may show up black in Adobe Lightroom. [3266883/ 200717265] [VR]: Microsoft Flight Simulator 2020 VR may stutter if Hardware-accelerated GPU scheduling is disabled. [3246674] Some displays may show incorrect color levels after booting into Windows. [3285148/3287063] Here are the currently known issues to keep an eye out for: [World of Warcraft: Shadowlands]: Random flicker may occur in certain locations in the game [3206341] [Batman Arkham Knight]: The game crashes when turbulence smoke is enabled. [3202250] [Steam VR game]: Stuttering and lagging occur upon launching a game while any GPUhardware monitoring tool is running in the background. [3152190] [Prepar3D]: The application crashes to desktop after launched. [3285067] [YouTube]: Video playback stutters while scrolling down the YouTube page. [3129705] [Notebook]: Some Pascal-based notebooks w/ high refresh rate displays may randomly drop to 60Hz during gameplay. [3009452] The 466.11 WHQL-certified Game Ready driver can now be downloaded through the links below or via the GeForce Experience app. The release notes are here. Desktop GPUs: Download: Windows 7, 8, 8.1 | Windows 10 – Standard / DCH Notebook GPUs: Download: Windows 7, 8, 8.1 | Windows 10 - Standard / DCH Source: Nvidia 466.11 WHQL driver lands with support for Mortal Shell RTX and DLSS
  23. NVIDIA's Drive Atlan chip is headed to cars in 2025 NVIDIA claims the chip is capable of more than 1,000 trillion operations per second. Steve Marcus / reuters While we still have to wait until next year to see NVIDA's Orin chip start making its way to consumer cars, the company is already working on its next-generation Drive processor. It's called Atlan, and NVIDIA currently plans to roll it out with model year 2025 cars. Since it's so far out, the company didn't share too many details on the chipset, but what it did say is that it will feature its next-generation GPU architecture and new ARM CPU cores. It will also include a BlueField data processing unit, which NVIDIA says will assist the chip in completing the complex AI workloads necessary to enable autonomous vehicles. Those disparate parts will come together in a chip that will deliver data center-like performance, with NVIDIA claiming Atlan will be capable of more than 1,000 trillion operations per second. To put that in perspective, Orin, the Drive chip that's making its way to consumer cars next year, can complete 254 trillion operations per second. According to NVIDIA, all that power will allow automakers to build "software-defined" vehicles that they'll be able to upgrade in perpetuity with the help of OTA updates. And to help make those updates easier, Atlan will use the same CUDA and TensorRT APIs and libraries as its existing Drive chips. Source: NVIDIA's Drive Atlan chip is headed to cars in 2025
  24. Nvidia unveils Grace ARM-based CPU for giant-scale AI and HPC apps Nvidia's Grace CPU for datacenters. Image Credit: Nvidia Nvidia unveiled its Grace processor today. It’s an ARM-based central processing unit (CPU) for giant-scale artificial intelligence and high-performance computing applications. It’s Nvidia’s first datacenter CPU, purpose-built for applications that are operating on a giant scale, Nvidia CEO Jensen Huang said in a keynote speech at Nvidia’s GTC 2021 event. Grace delivers 10 times the performance leap for systems training giant AI models, using energy-efficient ARM cores. And Nvidia said the Swiss Supercomputing Center and the U.S. Department of Energy’s Los Alamos National Laboratory will be the first to use Grace, which is named for Grace Hopper, who pioneered computer programming in the 1950s. The CPU is expected to be available in early 2023. “Grace is a breakthrough CPU. It’s purpose-built for accelerated computing applications of giant scale for AI and HPC,” said Paresh Kharya, senior director of product management and marketing at Nvidia, in a press briefing. Huang said, “It’s the world’s first CPU designed for terabyte scale computing.” Above: Grace is the result of 10,000 engineering years of work. Image Credit: Nvidia The CPU is the result of more than 10,000 engineering years of work. Nvidia said the chip will address the computing requirements for the world’s most advanced applications — including natural language processing, recommender systems, and AI supercomputing — that analyze enormous datasets requiring both ultra-fast compute performance and massive memory. Grace combines energy-efficient ARM CPU cores with an innovative low-power memory subsystem to deliver high performance with great efficiency. The chip will use a future ARM core dubbed Neoverse. “Leading-edge AI and data science are pushing today’s computer architecture beyond its limits — processing unthinkable amounts of data,” Huang said in his speech. “Using licensed ARM IP, Nvidia has designed Grace as a CPU specifically for giant-scale AI and HPC. Coupled with the GPU and DPU, Grace gives us the third foundational technology for computing and the ability to re-architect the datacenter to advance AI. Nvidia is now a three-chip company.” Grace is a highly specialized processor targeting workloads such as training next-generation NLP models that have more than 1 trillion parameters. When tightly coupled with Nvidia GPUs, a Grace-based system will deliver 10 times faster performance than today’s Nvidia DGX-based systems, which run on x86 CPUs. In a press briefing, someone asked if Nvidia will compete with x86 chips from Intel and AMD. Kharya said, “We are not competing with x86 … we continue to work very well with x86 CPUs.” Above: The Alps supercomputer will use Grace CPUs from Nvidia. Image Credit: Nvidia Grace is designed for AI and HPC applications, but Nvidia isn’t disclosing additional information about where Grace will be used today. Nvidia also declined to disclose the number of transistors in the Grace chip. Nvidia is introducing Grace as the volume of data and size of AI models grow exponentially. Today’s largest AI models include billions of parameters and are doubling every two and a half months. Training them requires a new CPU that can be tightly coupled with a GPU to eliminate system bottlenecks. “The biggest announcement of GTC 21 was Grace, a tightly integrated CPU for over a trillion parameter AI models,” said Patrick Moorhead, an analyst at Moor Insights & Strategies. “It’s hard to address those with classic x86 CPUs and GPUs connected over PCIe. Grace is focused on IO and memory bandwidth, shares main memory with the GPU and shouldn’t be confused with general purpose datacenter CPUs from AMD or Intel.” Underlying Grace’s performance is 4th-gen Nvidia NVLink interconnect technology, which provides 900 gigabyte-per-second connections between Grace and Nvidia graphics processing units (GPUs) to enable 30 times higher aggregate bandwidth compared to today’s leading servers. Grace will also utilize an innovative LPDDR5x memory subsystem that will deliver twice the bandwidth and 10 times better energy efficiency compared with DDR4 memory. In addition, the new architecture provides unified cache coherence with a single memory address space, combining system and HBM GPU memory to simplify programmability. “The Grace platform and its Arm CPU is a big new step for Nvidia,” said Kevin Krewell, an analyst at Tirias Research, in an email. “The new design of one custom CPU attached to the GPU with coherent NVlinks is Nvidia’s new design to scale to ultra-large AI models that now take days to run. The key to Grace is that using the custom Arm CPU, it will be possible to scale to large LPDDR5 DRAM arrays far larger than possible with high-bandwidth memory directly attached to the GPUs.” Above: The Los Alamos National Laboratory will use Grace CPUs. Image Credit: Nvidia Grace will power the world’s fastest supercomputer for the Swiss organization. Dubbed Alps, the machine will feature 20 exaflops of AI processing. (This refers to the amount of computing available for AI applications.) That’s about 7 times more computation than is available with the 2.8-exaflop Nvidia Seline supercomputer, the leading AI supercomputer today. HP Enterprise will be building the Alps system. Alps will work on problems in areas ranging from climate and weather to materials sciences, astrophysics, computational fluid dynamics, life sciences, molecular dynamics, quantum chemistry, and particle physics, as well as domains like economics and social sciences, and will come online in 2023. Alps will do quantum chemistry and physics calculations for the Hadron collider, as well as weather models. Above: Jensen Huang, CEO of Nvidia, at GTC 21. Image Credit: Nvidia “This is a very balanced architecture with Grace and a future Nvidia GPU, which we have not announced yet, to enable breakthrough research on a wide range of fields,” Kharya said. Meanwhile, Nvidia also said that it would make its graphics chips available with Amazon Web Services’ Graviton2 ARM-based CPU for datacenters for cloud computing. With Grace, Nvidia will embark on a mult-year pattern of creating graphics processing units, CPUs, and data processing units (CPUs), and it will alternate between Arm and x86 architecture designs, Huang said. Source: Nvidia unveils Grace ARM-based CPU for giant-scale AI and HPC apps
  25. The GTX 1080 Ti could be next in line for a comeback Is Pascal's consumer flagship being resurrected? Rumor mill: Is Nvidia digging up more of its back catalog to ease the graphics card shortage crisis? If a recent rumor turns out to be accurate, the next product in line for a revival is a former consumer flagship: the GTX 1080 Ti. The rumor, and that’s all it is right now, comes from regular leaker Harukaze5719 (via PCGamesN). They spotted a post on Korean hardware forum Quasarzone suggesting the card, launched in March 2017, could be given a new lease of life. A forum member writes that they returned their old card for an RMA as it was still in the three-year warranty. Nothing unusual there, but the EVGA GeForce GTX 1080 Ti they received in return was brand-new, with a manufacturing date of 2021. How the GTX 1080 Ti stacks up against the Maxwell and Turing equivalents This doesn’t mean that the Pascal card is definitely being resurrected; it could be that these new cards are a small batch made for warranty replacements, and the internet does have a bit of a reputation for fakery. However, history tells us that a GTX 1080 Ti re-release is a strong possibility. The global chip shortage, cryptominers, and scalpers have created a perfect storm in which buying a new graphics card has become a near-impossible and costly task. The situation has led to Nvidia resuming production of the GTX 1050 Ti, GTX 1650, and RTX 2060 in the hope of getting more cards into the hands of gamers. The GTX 1080 Ti remains popular today. If a relaunch does happen, expect the card to move up from its current 18th position on the Steam Hardware Survey. It still stacks up well against recent releases—check out our feature last year that compared it against the RTX 2070 and Radeon 5700 XT, where it offered similar performance to the Turing GPU. And see how the GTX 1080 Ti fares against the GTX 980 Ti and RTX 2080 Ti. Source: The GTX 1080 Ti could be next in line for a comeback
×
×
  • Create New...