Categories
Computing

TSMC focuses on power and efficiency with the new 2nm node

The Taiwan Semiconductor Manufacturing Co. (TSMC) has just officially unveiled its 2nm node, dubbed the N2. Set to release sometime in 2025, the new process will introduce a new manufacturing technology.

According to TSMC’s teaser, the 2nm process will either provide an uplift in pure performance compared to its predecessor, or, when used at the same power levels, will be much more power-efficient.

TSMC

TSMC talked about the new 2N technology at great length, explaining the inner workings of its architecture. The 2N is going to be TSMC’s first node to use gate-all-around field-effect transistors (GAAFETs) and will increase the chip density over the N3E node by 1.1 times. Before the 2N is ever released, TSMC will launch 3nm chips, which have also been teased at the 2022 TSMC Technology Symposium.

The 3nm node is going to come in five different tiers, and with each new release, the transistor count will go up, therefore increasing the chip’s performance and efficiency. Starting with the N3, TSMC will later release the N3E (Enhanced), N3P (Performance Enhanced), N3S (Density Enhanced), and lastly, the “Ultra-High Performance” N3X. The first 3nm chips are said to hit launch in the second half of this year.

While the 3nm process is nearer to us in terms of the launch date, it’s the 2nm that’s slightly more interesting, even though it’s still a couple of years away. TSMC’s goal with the 2nm node seems to be clear — increasing the performance-per-watt to enable both higher levels of output and efficiency. The architecture as a whole has a lot to recommend it. Let’s take the GAA nanosheet transistors as an example. They have channels surrounded by gates on all sides. This will reduce leakage, but the channels can also be widened, and that brings a performance boost. Alternatively, the channels can be shrunk to optimize the power cost.

Both the N3 and the N2 will offer considerable performance increases compared to the current N5, and all of them give the choice of balancing power consumption with performance-per-watt. As an example (first shared by Tom’s Hardware), comparing the N3 to the N5 nets an up to 15% gain in raw performance, and an up to 30% power reduction when used at the same frequency. The N3E will bring those numbers even further, up to 18% and 34%, respectively.

TSMC's wafer.
TSMC

Now, the N2 is where things start to get exciting. We can expect to see an up to 15% performance boost when used at the same power draw as the N3E node, and if the frequency is brought down to the levels provided by the N3E, the N2 will deliver an up to 30% lower power consumption.

Where will the N2 be used? It will likely find its way into all kinds of chips, ranging from mobile system-on-a-chips (SoCs), advanced graphics cards, and equally advanced processors. TSMC has mentioned that one of the features of the 2nm process is “chiplet integration.” This implies that many manufacturers may use the N2 to utilize multi-chiplet packages to pack even more power into their chips.

Smaller process nodes are never a bad thing. The N2, once it’s here, will deliver high performance to all manner of hardware, including the best CPUs and GPUs, while optimizing the power consumption and thermals. However, until that happens, we’ll have to wait. TSMC won’t start mass production until 2025, so realistically, we are unlikely to see 2nm-based devices entering the market before 2026.

Editors’ Choice




Repost: Original Source and Author Link

Categories
Computing

Intel Meteor Lake will pack more punch for the same power

Intel has just given us a much larger glimpse into its future Meteor Lake lineup. At the 2022 IEEE VLSI Symposium, the company talked about the 14th generation of its processors, detailing the future process node and the improvements the new Intel 4 process should bring.

The teaser certainly sounds promising. Intel claims that Meteor Lake CPUs will provide 20% higher clock speeds than the previous generations, all while maintaining the same power requirements.

Intel

Intel Meteor Lake is still quite far off — the company confirms that the new chips are on track to meet the 2023 launch deadline, although no specifics have been given at this time. Before we ever see Meteor Lake, we will see the launch of Intel Raptor Lake in the fall. However, unsurprisingly, both Intel and the tech world at large are looking to the future — and as far as the 14th generation of Intel chips goes, the future looks pretty exciting.

During the 2022 IEEE VLSI Symposium, Intel took the public on a deep dive into the upcoming Intel 4 process node, which is what Meteor Lake is based on. As a successor to the Intel 7 (used for Alder Lake and Raptor Lake), it will require a new socket, and it will feature a new architecture. Intel claims that the changes introduced in that generation will deliver huge performance gains while keeping the power consumption at a similar level to what we’ve grown used to with 12th-gen CPUs.

The company teased that Meteor Lake will deliver up to 21.5% higher frequencies at the same power requirements as the Intel 7 process. Similarly, when scaled down to the same frequency as Intel 7, Meteor Lake will sport an up to 40% power reduction. This is going to be achieved through various changes in the chip’s architecture, such as a 2x improvement in area scaling. This means that it has doubled transistor density compared to the Intel 7, at least for the high-performance libraries.

With the new process node, Intel will largely use extreme ultraviolet (EUV) lithography as a way to simplify manufacturing. Simply put, this reduces the number of steps needed to manufacture the node by a significant amount. It should result in higher yields and reduce production errors. As a result of EUV, Intel noted a 5% reduction in process steps and a 20% lower total mask count.

The Intel 4 name is a code name for Intel’s 7nm process node, which means a switch from 10nm to 7nm for Intel. The new chips will utilize Intel’s Foveros 3D packaging technology and will feature a four-die setup joined by TSV (through silicon-via) connections. These four tiles will be split into the input/output tile (I/O), the system-on-a-chip tile, the compute tile, and the graphics tile.

Intel Meteor Lake slide, part two.
Intel

Intel has shared a blown-up image of the compute die for Meteor Lake, complete with six blue-colored performance cores (Redwood Cove) and two clusters of four Crestmont efficiency cores, colored in purple. In the middle of the chip, you can see the L3 cache and the interconnect circuitry. The company has yet to divulge the exact description of the I/O and the SOC tiles.

In addition to teasing the Intel 4 process, the manufacturer also talked about what comes next — moving on to Intel 3. Intel 3 will come with enhanced transistors and interconnects, and it’s worth noting that I4 will be forward compatible with I3, so it won’t require a full redesign. Intel will stay true to the EUV technology, with more EUV layers that simplify the design even further. According to the current estimations, the I3 node will be around 18% faster than the I4. Once Intel is done with I3, it will move on to the 20A and 18A nodes and even more exciting technologies.

All in all, Intel’s sneak peek is very detailed and quite technical, so if you’re a fan of that, make sure you read the full write-up prepared by Tom’s Hardware. Although Meteor Lake is a while off, there’s still plenty to be hyped for this year. We’ve got the Intel Raptor Lake coming up, and around the same time, AMD is slated to launch the Ryzen 7000 series of CPUs.

Editors’ Choice




Repost: Original Source and Author Link

Categories
Security

Ukraine says it stopped a Russian cyberattack on its power grid

An attack on Ukraine’s power grid was foiled by cybersecurity analysts and officials, as reported by Reuters. After investigating the methods and software used by the attackers, cybersecurity firm ESET says that it was likely carried out by a hacking group called Sandworm, which The Record reports allegedly has ties to the Russian government.

The group planned to shut down computers that controlled substations and infrastructure belonging to a particular power company, according to the Computer Emergency Response Team of Ukraine (or CERT-UA). The hackers meant to cut off power on April 8th while also wiping the computers that would be used to try and get the grid back online.

This attempted attack involved a wide variety of malware, according to ESET, including the recently discovered CaddyWiper. ESET also found a new piece of malware, which it calls Industroyer2. The original Industroyer was used in a successful 2016 cyberattack that cut off power in parts of Kyiv, according to the security firm, probably by the same group behind this month’s foiled attack. Industroyer isn’t widely used by hackers — ESET notes that it’s only seen it used twice (earlier this month and in 2016), which implies that it’s written for very specific uses.

CERT-UA says that the hackers were biding their time, initially breaching the company’s systems before March. ESET’s analysis shows that one of the main pieces of malware was compiled over two weeks before the attack was supposed to take place.

It’s unclear how the hackers initially got into the company’s network or how they gained access to the network that controls industrial equipment like the targeted substations. The analysis does show, however, that the hackers were planning on covering their tracks after the attack.

Ukraine and its infrastructure have been targeted by hackers since before the Russian invasion began. It’s likely that this won’t be the last attack on its power grid, but the country’s response to this incident shows that its cybersecurity defense strategy is capable of warding off complex attacks.

Repost: Original Source and Author Link

Categories
Security

Not even your PC’s power supply is safe from hackers

Hackers have managed to find a way to successfully gain access to uninterruptable power supply (UPS) computer systems, according to a report from The Cybersecurity and Infrastructure Security Agency (CISA).

As reported by Bleeping Computer and Tom’s Hardware, both the Department of Energy and CISA issued a warning to organizations based in the U.S. that malicious threat actors have started to focus on infiltrating UPS devices, which are used by data centers, server rooms, and hospitals.

UPS devices allow companies to rely on emergency power when the central source of power is cut off for any given reason. If the attacks concentrated on these systems come to fruition, the consequences could prove to be catastrophic. In fact, it could cause PCs or their power supplies to burn up, potentially leading to fires breaking out at data centers and even homes.

Both federal agencies confirmed that hackers have found entry points to several internet-connected UPS devices predominantly via unchanged default usernames and passwords.

“Organizations can mitigate attacks against their UPS devices, which provide emergency power in a variety of applications when normal power sources are lost, by removing management interfaces from the internet,” the report stated.

Other mitigation responses the agencies recommended putting in place include safeguarding devices and systems by protecting them through a virtual private network, applying multi-factor authentication, and making use of effective passwords or passphrases that can’t be easily deciphered.

To this end, it stresses that organizations change UPS’s usernames and passwords that have remained on the factory default settings. CISA also mentioned that login timeout and lockout features should be applied as well for further protection.

Severe consequences

The report highlights how UPS vendors have increasingly incorporated a connection between these devices and the internet for power monitoring and routine maintenance purposes. This practice has made these systems vulnerable to potential attacks.

A prime example of hackers targeting UPS systems is the recently discovered APC UPS zero-day bugs exploit. Known as TLStorm, three critical zero-day vulnerabilities opened the door for hackers to obtain admin access to devices belonging to APC, a subsidiary of an electrical company.

If successful, these attacks could severely impact governmental agencies, as well as health care and IT organizations, by burning out the devices and disabling the power source remotely.

The number of cyberattacks against crucial services has been trending upwards in recent years as cybercriminals progressively identify exploits. For example, cyberattacks against health care facilities almost doubled in 2020 compared to 2019.

It’s not just large organizations that are being targeted — online criminals stole nearly $7 billion from individuals in 2021 alone.

Editors’ Choice




Repost: Original Source and Author Link

Categories
Game

Halo Infinite’s Surprise Launch is a Power Play for Xbox

For once, a seemingly ridiculous video game rumor turned out to be true: Halo Infinite’s multiplayer released nearly one month early. Leaks indicated that the surprise could happen, but it still seemed too good to be true. But the fact is that players are enjoying Halo Infinite’s first season much sooner than anticipated.

In an age where video game release dates only get moved back, not forward, the news came as a straight-up shock. Shooter fans were just sitting down with Call of Duty: Vanguard and waiting for Battlefield 2042’s full release. Xbox Game Pass subscribers had just begun digging into the recently released Forza Horizon 5. If you had a strict plan for tackling all the games launching this holiday season, go ahead and toss it in the fire.

The decision to drop Halo Infinite early isn’t just a sweet “thank you” to fans for their support. It’s the sneakiest power play a video game company has pulled since Sony’s infamous “$299” mic drop at E3 1995.

Un-freakin’ believable

Before the surprise drop, Microsoft was in something of an awkward position. Halo Infinite was set to be its big holiday game, but its planned December 8 release date wasn’t ideal. A December date meant that the game wouldn’t be out in time for Black Friday and Cyber Monday, when many people buy holiday gifts or hunt for discounted games. Battlefield 2042 and Call of Duty: Vanguard would headline sales events, putting those shooters in the spotlight heading into the holidays. Even if Halo Infinite got positive buzz at launch, it would be late to the party.

Getting good word of mouth was going to be a challenge, too. December releases also tend to miss the Game of the Year season as many sites publish their lists by the end of November. While Digital Trends planned to hold our GOTY decision until we played Halo, others likely would have left it out of contention and saved it for their 2022 lists. Similarly, the game would be ineligible for The Game Awards this year and would be considered for the following year’s show instead, much like what happened to Super Smash Bros. Ultimate when it dropped in mid-December 2018. Any critical acclaim would come late, making it hard for Microsoft to capitalize heading into the holidays.

By dropping the multiplayer mode early, Microsoft has rewritten the rules. While the game isn’t fully out (single-player is still coming in December), the conversation around it is now in full swing. Players will start posting clips all over social media, it’ll dominate Twitch charts, and media will start kicking out impressions way earlier than planned (ourselves included). And all of that will happen before people start putting together their holiday wish lists.

It’s a bombshell move and one that might tick the competition off. Battlefield 2042 was supposed to be the most high-profile game launching this month (especially after tepid Call of Duty: Vanguard reviews), but Halo Infinite just crashed a Warthog full of banana peels on its clear runway. Now it’ll have to share the spotlight with the biggest shooter of the year — one that’s totally free to play and has the element of surprise behind it.

Halo Infinite is no longer at risk of getting lost in the mix; it’s the competition who should be worrying.

A sneaky beta

The sneakiest part of the whole early launch is the clever use of a “beta” label. Fans aren’t experiencing the final version of Halo Infinite right now. Microsoft is strategically calling the multiplayer mode a “beta.” That gives the company a fair bit of flexibility. Players are more likely to forgive any technical issues when they know they’re playing a non-final version of a game. EA won’t get the same good will when Battlefield 2042 launches in full later this week. In fact, the game is already getting “review bombed” by early access players who are bumping into stability issues in a game they paid $60 or more for.

What remains to be seen is whether or not the multiplayer mode actually leaves beta once the game’s release date rolls around. There’s a good chance that Microsoft will just leave the label on — an admission that the long-delayed game still wasn’t ready for launch. Had Microsoft fully released the multiplayer on December 8 as a beta, fans would have been outraged. The company would be under scrutiny for releasing an unfinished game (it will already lack campaign co-op and Forge mode at launch, which has drawn criticism from fans). Instead, fans are simply delighted they’re getting to play it weeks early.

New Halo Infinite Map Behemoth.

Messaging is everything in video games and Microsoft seems acutely aware of that. By positioning the launch as a “gift,” players are going to approach the game much differently than they would have in December. Microsoft now looks like a good guy kindly giving fans a surprise, rather than a giant company rushing out a game to pump up its fourth quarter financial earnings at any cost. It’s a devilishly clever move that could change the way companies roll out their games moving forward.

I’m not sure if that’s good for players in the long term, but that’s unimportant at the moment. Microsoft has delivered a rare shock in an industry that’s usually predictable. Rule-breaking power plays like this are scarce, but they tend to be turning points for the industry. Don’t be surprised if the Xbox Series X suddenly usurps PS5 as this holiday’s hottest console as a result.

Halo Infinite’s multiplayer is now free to download and play on PC, Xbox One, and Xbox Series X/S. The full game, including its single-player mode, launches on December 8.

Editors’ Choice




Repost: Original Source and Author Link

Categories
Computing

Nvidia Ada Lovelace GPUs Are Twice As Fast and Power Hungry

As many people still struggle to get their hands on one of Nvidia’s RTX 30-Series graphics cards, preparations for the next generation of GPUs are well underway. The next line of Nvidia graphics, code-named Ada Lovelace, is said to release in 2022.

According to rumors, the new cards may turn out to be twice as fast as the current generation, placing them firmly at the top of any list of the best graphics cards. The dramatic increase in performance comes at a price, though: Nvidia 40-Series graphics cards may also be twice as power-hungry as the current models.

Nvidia

The rumor comes from a well-known leaker on Twitter, @Greymon55, who has a long track record for revealing information about the upcoming releases of both Nvidia and AMD. Previous rumors about the upcoming Nvidia release also come from Greymon55 and Kopite7kimi. Put together, all the leaks are starting to form a fairly clear picture that shows us what to expect from Ada Lovelace GPUs.

According to various rumors, GeForce RTX 40-Series GPUs will run on the new AD102 chip, also referred to as ADA GPU. The new cards may offer a massive step-up in terms of the number of CUDA cores. Rumored to have 18,432 CUDA cores, Ada Lovelace GPUs will have almost twice as many as the current generation of Ampere cards.

According to Kopite7kimi, the new RTX GPUs will run on TSMC’s 5nm process node and might have an astounding clock speed of up to 2.2GHz. There may also be a serious jump in teraflops (TFLOPs). Nvidia’s top card, the RTX 3090, currently has 36 TFLOPs of FP32 compute power. Ada Lovelace cards are rumored to pack up to 81 TFLOPs, which is over twice as much as the RTX 3090.

A black EVGA RTX 3090 graphics card with pastel RGB lighting on top.

Some users were wondering whether Nvidia will utilize a multi-chip module (MCM) architecture in Ada Lovelace. Nvidia’s upcoming Hopper GPU, made for data centers and working with AI, is supposed to release fairly soon, and it will feature MCM. However, it’s more likely that Nvidia will not use MCM in Ada Lovelace GPUs and will stick to the traditional design.

Although the cards are almost certain to be massive upgrades to the current generation, the power comes at a certain price. Nvidia’s current RTX 3090 is already a power-hungry card, and the rumored RTX 3090 Ti is said to have a TGP of 450W. This means that Ada Lovelace cards may have a TDP of up to 600W. Such high-power requirements will force the use of the best power supply units available.

No release date for Ada Lovelace GPUs has been confirmed yet, but all signs point to 2022. With the ongoing graphics card shortage, it’s possible that many users won’t get their hands on the new cards right away.

Editors’ Choice






Repost: Original Source and Author Link

Categories
Game

Fortnite Power Leveling weekend is live: Get Supercharged XP bonus

Epic Games has announced the arrival of Power Leveling weekend in its hit battle royale game Fortnite. Today through early Sunday morning, players can log into the game to unlock a Supercharged XP perk, helping them rake in more points during gameplay to unlock Battle Pass items at a faster rate.

Fortnite Power Leveling weekends are exactly what they sound like: multi-day events during which players can add a supercharged multiplier to their XP, making it possible to rake in a large number of points during regular gameplay, particularly when completing punchcards and other quests. This can result in earning a considerable number of Battle Stars in a short period of time.

The Power Leveling weekend is a welcomed addition to Season 8, which had been criticized early on due to the slow rate at which players earned XP. There were concerns the season would require excessive grinding to complete the Battle Pass, but Epic addressed these complaints with an adjustment in late September.

Players can get the Supercharged XP bonus simply by logging into the game like usual. You’ll know you have the bonus when the small, glowing “Supercharged XP” identifier appears above the left-hand side of the XP bar found at the bottom of the screen during gameplay. Epic says Fortnite players have until 4 AM PT / 7 AM ET to unlock the bonus.

Fortnite Chapter 2 – Season 8 features a total of 9 Battle Pass pages, each filled with items that can be unlocked using Battle Stars earned during gameplay. In addition, the game now allows players to ‘superlevel,’ which means exceeding the standard Battle Pass levels to unlock additional rewards like style variants and weapon wraps.



Repost: Original Source and Author Link

Categories
Computing

Apple Confirms High Power Mode On M1 Max MacBook Pro

Apple has just confirmed that the 16-inch version of the latest MacBook Pro will support the new High Power mode. This applies only to models that run on the M1 Max chip. High Power mode is Apple’s new invention made to maximize performance during periods of intense workloads, such as color grading an 8K ProRes video.

In order to enable the new High Power mode, users will likely need the 16-inch version of the new MacBook Pro, equipped with an M1 Max chip and running MacOS Monterey. According to Apple, the new mode will be enabled through System Preferences and will not be on by default.

It’s still somewhat unclear what the new High Power setting will fully entail. It’s clear that it’s meant to let the MacBook Pro handle periods of highly intensive workloads. Such tasks can involve working with 4K or 8K videos, video editing, design work, and more.

Although this feature should let the 16-inch MacBook Pro run smoothly during resource-intensive tasks, code-level references that were previously found indicate that this will make the fans louder. Whether the temperatures will rise beyond what’s acceptable remains to be seen, but Apple did optimize these new Macs to offer better airflow. Battery life reduction is also to be expected during High Power mode usage.

The first references to the new feature were discovered last month by Filipe Espósito of 9to5Mac in the beta of MacOS Monterey. Prior to this, in 2020, references to “Pro Mode” were found in MacOS Catalina 10.15.3. At that time, the internal code that was found suggested this option will make apps run faster while quickly exhausting the Mac’s battery.

Lifestyle image of someone using the new Macbook Pro 2021.

Apple hasn’t made a statement as to whether the feature will be enabled on the M1 Pro chip or whether it will be available on the 14-inch MacBook Pro at all. For now, it’s safe to assume that High Power mode will remain reserved for the 16-inch MacBook. This marks a difference compared to the previous assumptions that the 14-inch and 16-inch MacBook Pros will offer the exact same performance, but it still remains to be seen whether this is true.

Pre-orders for the new 14-inch and 16-inch MacBook Pros, equipped with the new-and-improved M1 Pro and M1 Max chips, have already started rolling in. The first units are set to be shipped soon and will arrive on October 26. At that point, we can expect more reviews of High Power mode, which should clarify the extent of the performance increase provided by this setting. Regardless of the final outcome, it’s already clear that the new notebooks are swiftly topping the ranks of the best MacBooks out there due to the new M1 Pro and M1 Max chips installed inside.

Editors’ Choice




Repost: Original Source and Author Link

Categories
Game

Power Up Pokestops in Pokemon GO: What do I get?

Today we get our first look at Power Up Pokestops, a new game mechanic in Pokemon GO. This system delivers bonus items and features based on the leveling up of each individual stop. TO BE CLEAR: This might not all work right this minute – Niantic JUST launched the feature, so it may need some work!

Level 0 is the basic level at which all Pokestops begin. This sort of Pokestop appears (according to the game code) to be exactly the same as a standard Pokestop as far as drops and bonuses. Once we start to level up, things get better!

After 50 points, a Pokestop moves to Level 1. That’ll last approximately 48 hours, and it’ll give players “Bonus Items on Spin.” Once the timer is up, the stop returns to level 0.

Other Pokestop levels last approximately 12 hours, then move back to a non-powered level 0 stop. It’ll be interesting to see if this system sticks, or if Niantic will move to a system where levels move down one at a time (3 for 12 hours, then 2 for 12 hours, etc).

Level 2 requires 100 points. The duraction of a Level 2 Power Up Pokestop is 12 hours, and it gives the spinner both Bonus Items on Spin and a Buddy Bonus Heart!

After 250 points, a Pokestop moves to level 3. At level 3, a Power Up Pokestop will last 12 hours and deliver four different sorts of bonuses. It’ll give Bonus Items on Spin, Buddy Bonus Heart, Bonus Spawns, and Bonus Raid Premier Balls.

Bonus Spawns likely only activate on Pokestops and NOT on Pokemon Gym locations, while the opposite is likely true for Bonus Raid Premier Balls. Your Buddy Pokemon can benefit from ONE Power Up Pokestop per day, and will gain 4 “emotion points” when a Powered Up Pokestop or Gym is visited.

It’s important to note that everything we’re seeing here was part of the game’s code, and won’t necessarily stick to the live game forever. Niantic is known to change game mechanics with some frequency – especially if something in Pokemon GO is broken. We might get more, might get less – we shall see!

Repost: Original Source and Author Link

Categories
Computing

Nvidia RTX 40 Series GPUs Might Be Even More Power Hungry

A flurry of recent rumors suggests that Nvidia’s upcoming RTX 40-series graphics cards will be even more power-hungry than what’s currently available. Leakers peg the power consumption in the range of 400W to 500W for the flagship card, which is higher than even the obscenely powerful RTX 3090.

3DCenter, who has previously covered the roller coaster of GPU prices in Europe, nailed down multiple leakers claiming the card will use at least 400W of power. That’s certainly not out of the question, as the RTX 3090 already requires 350W of power. Assuming Nvidia wants to push even more power out of the upcoming range, a 400W+ power requirement could be possible.

Nvidia hasn’t announced anything about the RTX 40-series yet, so it’s likely that developers are still tweaking the final design. Kopite7kimi, one of the leakers who claimed a 400W+ power limit and is known for Nvidia leaks, said the upcoming range will be built on chipmaker TSMC’s 5nm node, breaking from the 8nm Samsung process Nvidia used on RTX 30-series graphics cards.

The next-generation architecture, tentatively named Lovelace, is rumored to arrive in late 2022 or early 2023. The rumor mill suggests that the graphics core powering the range will be capable of housing up to 18,432 CUDA cores, which is nearly 8,000 more than the RTX 3090.

AMD’s upcoming cards are rumored to require equally as much power. The RDNA 3 range is also rumored to consume between 400W and 500W of power with TSMC’s 5nm process. During a recent investors call, AMD CEO Lisa Su confirmed that 5nm is the goal and that the GPUs are on track for a 2022 launch.

Unlike Lovelace, RDNA 3 cards are rumored to use a multi-chip-module (MCM) GPU package. Essentially, the upcoming range is rumored to utilize multiple dies on the same package, unlike the RTX 40-series’ traditional monolithic design.

A diagram of an MCM on RDNA 3.

Nvidia is rumored to be working on its own MCM design, currently named Hopper. Originally, rumors pegged Hopper as the successor to the current Ampere range, though recent speculation suggests Nvidia is locked on delivering Lovelace sooner.

Both new generations are rumored to offer up to a 2.5x improvement over the current generation. As for where they’ll fall in relation to each other, it’s too soon to say.

As is the case with all early rumors and speculation, you shouldn’t take this information as law. We’re still far out from launch, so AMD and Nvidia are more than likely still finalizing the design and tweaking specs to meet their price, power, and performance targets.

Based on what we know so far, however, a higher power draw will likely be something PC builders need to deal with. Nvidia pushed past the 250W ceiling with the RTX 3080, RTX 3080 Ti, and RTX 3090, surpassing even the most powerful cards from the generations that proceeded them. It’s too soon to say for sure, but you might need to invest in a new power supply when these cards finally arrive.

Editors’ Choice






Repost: Original Source and Author Link