China successfully powered up its "artificial sun" nuclear fusion reactor for the first time, state media reported Friday, marking a great advance in the country's nuclear power research capabilities. Phys.Org reports: The HL-2M Tokamak reactor is China's largest and most advanced nuclear fusion experimental research device, and scientists hope that the device can potentially unlock a powerful clean energy source. It uses a powerful magnetic field to fuse hot plasma and can reach temperatures of over 150 million degrees Celsius, according to the People's Daily -- approximately ten times hotter than the core of the sun. Located in southwestern Sichuan province and completed late last year, the reactor is often called an "artificial sun" on account of the enormous heat and power it produces. They plan to use the device in collaboration with scientists working on the International Thermonuclear Experimental Reactor -- the world's largest nuclear fusion research project based in France, which is expected to be completed in 2025.

Hmmmmmm shares a report from Ars Technica: Micro Magic Inc. -- a small electronic design firm in Sunnyvale, California -- has produced a prototype CPU that is several times more efficient than world-leading competitors, while retaining reasonable raw performance. EE Times reported on the company's new prototype CPU, which appears to be the fastest RISC-V CPU in the world. Micro Magic adviser Andy Huang claimed the CPU could produce 13,000 CoreMarks (more on that later) at 5GHz and 1.1V while also putting out 11,000 CoreMarks at 4.25GHz -- the latter all while consuming only 200mW. Huang demonstrated the CPU -- running on an Odroid board -- to EE Times at 4.327GHz/0.8V and 5.19GHz/1.1V. Later the same week, Micro Magic announced the same CPU could produce over 8,000 CoreMarks at 3GHz while consuming only 69mW of power.

Part of the difficulty in evaluating Micro Magic's claim for its new CPU lies in figuring out just what a CoreMark is and how many of them are needed to make a fast CPU. It's a deliberately simplified CPU benchmarking tool released by the Embedded Microprocessor Benchmark Consortium, intended to be as platform-neutral and simple to build and use as possible. CoreMark focuses solely on the core pipeline functions of a CPU, including basic read/write, integer, and control operations. This specifically avoids most effects of system differences in memory, I/O, and so forth. [...] With that said, it's worth pointing out that -- if we take Micro Magic's numbers for granted -- they're already beating the performance of some solid mobile phone CPUs. Even at its efficiency-first 3GHz clockrate, the Micro Magic CPU outperformed a Qualcomm Snapdragon 820. The Snapdragon 820 isn't world-class anymore, but it's no slouch, either -- it was the processor in the U.S. version of Samsung's Galaxy S7.

What if your digital assistant could battle rap? That may sound far-fetched, but Gil Weinberg, a music technologist at the Georgia Institute of Technology, has adapted a musical robot called Shimon to compose lyrics and perform in real time. From a report: That means it can engage in rap "conversations" with humans, and maybe even help them compose their own lyrics. Shimon, which was intentionally designed to sound machinelike (listen here), is meant to be a one-of-a-kind musical collaborator -- or an inhuman rap-battle opponent. Computer-generated music dates back to the 1950s, when early computers used algorithms to compose melodies. Modern robots can use machine learning to ad-lib on instruments including the flute and drums. One such machine was an earlier version of Shimon, which could play the marimba and sing. The recently updated robot looks the same; it still consists of a ball-shaped "head," with saucy movable eyebrows above visor-covered eyes, perched at the end of a mechanical arm. But now Weinberg claims Shimon is the first improvising robot to foray into rap, with its distinct stylistic features that pose unique programming challenges.

The crowning glory of rap lies in the lyrics. On top of semantic content, the words need to adhere to an aesthetically pleasing beat and rhythm, all while delivering multiple layers of poetic complexity. In a recent paper, published in the proceedings of the 11th International Conference on Computational Creativity 2020, Weinberg's research team outlines the technical advances that brought a rapping Shimon to life. When Shimon battle raps, software converts its human opponent's spoken lyrics into text. The robot's system identifies keywords from this, and generates new lyrics based on several custom data sets of words that Shimon has been trained on (using deep-learning models). These data sets can come from any text: the work of Lil Wayne, JAY-Z or other rappers; lyrics from other genres; or even nonmusical literary works. Imagine how Shakespeare or Jane Austen might sound if they rapped; Shimon could simulate that for you.

An anonymous reader quotes a report from Scientific American: For the first time, a quantum computer made from photons -- particles of light -- has outperformed even the fastest classical supercomputers. Physicists led by Chao-Yang Lu and Jian-Wei Pan of the University of Science and Technology of China (USTC) in Shanghai performed a technique called Gaussian boson sampling with their quantum computer, named Jiuzhang. The result, reported in the journal Science, was 76 detected photons -- far above and beyond the previous record of five detected photons and the capabilities of classical supercomputers.

Unlike a traditional computer built from silicon processors, Jiuzhangis an elaborate tabletop setup of lasers, mirrors, prisms and photon detectors. It is not a universal computer that could one day send e-mails or store files, but it does demonstrate the potential of quantum computing. Last year, Google captured headlines when its quantum computer Sycamore took roughly three minutes to do what would take a supercomputer three days (or 10,000 years, depending on your estimation method). In their paper, the USTC team estimates that it would take the Sunway TaihuLight, the third most powerful supercomputer in the world, a staggering 2.5 billion years to perform the same calculation as Jiuzhang. [...] This latest demonstration of quantum computing's potential from the USTC group is critical because it differs dramatically from Google's approach. Sycamore uses superconducting loops of metal to form qubits; in Jiuzhang, the photons themselves are the qubits. Independent corroboration that quantum computing principles can lead to primacy even on totally different hardware "gives us confidence that in the long term, eventually, useful quantum simulators and a fault-tolerant quantum computer will become feasible," Lu says.

... [T]he USTC setup is dauntingly complicated. Jiuzhang begins with a laser that is split so it strikes 25 crystals made of potassium titanyl phosphate. After each crystal is hit, it reliably spits out two photons in opposite directions. The photons are then sent through 100 inputs, where they race through a track made of 300 prisms and 75 mirrors. Finally, the photons land in 100 slots where they are detected. Averaging over 200 seconds of runs, the USTC group detected about 43 photons per run. But in one run, they observed 76 photons -- more than enough to justify their quantum primacy claim. It is difficult to estimate just how much time would be needed for a supercomputer to solve a distribution with 76 detected photons -- in large part because it is not exactly feasible to spend 2.5 billion years running a supercomputer to directly check it. Instead, the researchers extrapolate from the time it takes to classically calculate for smaller numbers of detected photons. At best, solving for 50 photons, the researchers claim, would take a supercomputer two days, which is far slower than the 200-second run time of Jiuzhang.

sciencehabit writes: The U.K. government today invited communities around the country to volunteer a site for a prototype fusion reactor, which would be the first -- it is hoped -- to put electricity into the grid. The project, called Spherical Tokamak for Energy Production (STEP), began last year with an initial 222 million pounds over 5 years to develop a design. The U.K. Atomic Energy Authority, the government agency overseeing the effort, says construction could begin as soon as 2032, with operations by 2040.

Still, spherical tokamaks also come with drawbacks. The hot dense plasma in a smaller device is more punishing on materials, so components may need to be replaced more often. And STEP is unlikely to be capable of breeding tritium, one of two hydrogen isotopes that fuels the reactor. Tritium is radioactive with a half-life of 12 years and global supplies are low. A working reactor will have to breed its own tritium by surrounding the vessel with patches of lithium that produce tritium when bombarded by neutrons from the fusion reaction.

schwit1 shares a report from Autoblog, adding: "And CR decides to predict poor reliability on EVs it hasn't even evaluated yet." From the report: The latest auto survey from Consumer Reports shows several newer electric cars to be beset with problems, contradicting the conventional wisdom that EVs with their simpler powertrains should have fewer issues than gasoline- or diesel-powered cars. The CR reader survey harvested data on some 329,000 vehicles and specifically calls out the Audi E-Tron, the Kia Niro EV, and the Tesla Model Y.

The E-Tron is dinged for "drive-system electrical failures along with other power-equipment issues." The Niro EV's problems reportedly included electric-motor bearing failure. The Tesla suffers a panoply of build-quality issues include misaligned body panels and poor paint quality. Both Audi and Kia claimed to be aware of the issues. For now, though, CR has removed the E-Tron and the Niro EV from its Recommended list (which is based on vehicle test results as well as reliability). The Model Y was not on the Recommended list. CR notes that some older, less-complicated EVs did well in the reliability survey, including the Chevrolet Bolt and the Nissan Leaf. More controversially, as a result of this latest survey's findings, Consumer Reports has decided to downgrade the predicted reliability of several new EVs that were not even included in the survey, including the Ford Mustang Mach-E, the Mercedes-Benz EQC, and the Porsche Taycan.

"Often, it's not the EV tech that's problematic," says Anita Lam, CR's associate director of automotive data integration. "It's all the other new technology that could show up on any car -- new infotainment systems, more sophisticated power equipment and gadgets -- that often gets put on new EVs to feed a perception that they're supposed to be luxurious and high-tech."

Joe2020 writes: Famous developer Hector Martin who put Linux on the PS4 now wants to port Linux to the new Apple M1, and he wants to do it with the help of crowdfunding by making it his full-time job. One can find his official pledge for support here. "Since these devices are brand new and bespoke silicon, porting Linux to run on them is a huge undertaking. Well beyond a hobby project, it is a full-time job," the developer explains.

"The goal is to bring Linux support on Apple Silicon macs to the point where it is not merely a tech demo, but is actually an OS you would want to use on a daily driver device. To do this, there is a huge amount of work to be done. Running Linux on things is easy, but making it work well is hard. Drivers need to be written for all devices. The driver for the completely custom Apple GPU is the most complicated component, which is necessary to have a good desktop experience. Power management needs to work well too, for your battery life to be reasonable," the dev explains. Martin says he hopes to have enough donations to purchase the new Apple Silicon-powered devices and hire other people to help with the job.

Slashdot reader NoMoreACs also shared the news via Mac Rumors.

An anonymous reader quotes a report from Ars Technica: Amazon is rolling out cheap new tools that will allow factories everywhere to monitor their workers and machines, as the tech giant looks to boost its presence in the industrial sector. Launched by Amazon's cloud arm AWS, the new machine-learning-based services include hardware to monitor the health of heavy machinery and computer vision capable of detecting whether workers are complying with social distancing. Amazon said it had created a two-inch, low-cost sensor -- Monitron -- that can be attached to equipment to monitor abnormal vibrations or temperatures and predict future faults. AWS Panorama, meanwhile, is a service that uses computer vision to analyze footage gathered by cameras within facilities, automatically detecting safety and compliance issues such as workers not wearing PPE or vehicles being driven in unauthorized areas. Amazon said it had installed 1,000 Monitron sensors at its fulfillment centers near the German city of Monchengladbach, where they are used to monitor conveyor belts handling packages.

If successful, said analyst Brent Thill from Jefferies, the move would help Amazon cement its position as the dominant player in cloud computing, in the face of growing competition from Microsoft's Azure and Google Cloud as well as a prolonged run of slowed segment growth. "This idea of predictive analytics can go beyond a factory floor," Mr. Thill said. "It can go into a car, on to a bridge, or on to an oil rig. It can cross fertilize a lot of different industries." The new services, announced on Tuesday during the company's annual cloud computing conference, represent a step up in the tech giant's efforts to gather and crunch real-world data in areas it currently feels are underserved. "If you look at manufacturing and industrial generally, it's a space that has seen some innovations, but there's a lot of pieces that haven't been digitized and modernized," said Matt Garman, AWS's head of sales and marketing, speaking to the FT.

MojoKid writes: NVIDIA expanded its line-up of Ampere-based graphics cards today with a new lower cost GeForce RTX 3060 Ti. As its name suggests, the new $399 NVIDIA GPU supplants the previous-gen GeForce RTX 2060 / RTX 2060 Super, and slots in just behind the recently-released GeForce RTX 3070. The GeForce RTX 3060 Ti features 128 CUDA cores per SM, for a total of 4,864, 4 Third-Gen Tensor cores per SM (152 total), and 38 Second-Gen RT cores. The GPU has a typical boost clock of 1,665MHz and it is linked to 8GB of standard GDDR6 memory (not the GDDR6X of the RTX 3080/3090) via a 256-bit memory interface that offers up to 448GB/s of peak bandwidth. In terms of overall performance, the RTX 3060 Ti lands in the neighborhood of the GeForce RTX 2080 Super, and well ahead of cards like AMD's Radeon RX 5700 XT. The GeForce RTX 3060 Ti's 8GB frame buffer may give some users pause, but for 1080p and 1440p gaming, it shouldn't be a problem for the overwhelming majority of titles. It's also par for the course in this $399 price band. Cards are reported to be shipping in retail tomorrow.

The Raspberry Pi Foundation has released a tiny $5 fan combined with a small heatsink for the Raspberry Pi 4. TechCrunch reports: It works with the official case, below the top cover. That accessory should prevent the Raspberry Pi from overheating. According to the foundation, the tiny fan should be enough to prevent throttling. "It draws air in over the USB and Ethernet connectors, passes it over a small finned heatsink attached to the processor, and exhausts it through the SD card slot," the Raspberry Pi Foundation says. It's a cheap stopgap solution, but I hope the Foundation will prioritize heat dissipation for the next iteration of the Raspberry Pi.

Tasmania consists of the 26th-largest island in the world and its surrounding 334 islands — an island state of Australia with a population around 540,000 people, according to Wikipedia.

Friday the Tasmanian government "declared that it has become the first Australian state, and one of just a handful of jurisdictions worldwide, to be powered entirely by renewable electricity," according to one news report: Tasmania joins the Australian Capital Territory as the only two Australian jurisdictions sourcing all of their electricity from renewable energy sources, and places Tasmania alongside countries like Scotland, Iceland and Costa Rica which have also made the transition to 100 per cent renewable electricity. The milestone was welcomed by environmental groups, saying that it was another example of what is being achieved by state and territory governments that are stepping in to show leadership on energy policy in a vacuum left by ongoing conflict both between and within political parties at a federal level...

Tasmanian energy minister Guy Barnett added that the Tasmanian government would continue to support an expansion of the state's renewable energy capabilities, as the state looks to grow its role as a supplier of zero emissions energy to both mainland Australia and of green hydrogen into international export markets. "But there is more to do, which is why we have set a target to double our renewable generation to a global-leading target of 200 per cent of our current needs by 2040 — which we recently passed into law following the passing of legislation through both Houses of Parliament," Barnett added.

Programmer Abdullah Diaa has put together a website to help determine if your favorite apps work on Apple Silicon yet. An anonymous reader shares a report from The Next Web: ... [P]lease say hello to Is Apple silicon ready? The idea behind the site is simple: it shows you if specific apps will work on laptops and desktops with Apple's in-house chip. Easy to get your head around, right? It shows you a list of software and, if they have native M1 support, they're given a green tick.

Here's an image that shows you what's going on far clearer than lots of words could. As you can see, the site also shows you if the app you're after has Rosetta 2 support. Effectively, Rosetta 2 is an emulator, allowing a large number of apps designed for Intel machines to run on Apple Silicon. If this is supported, you will still be able to use that software on an M1-toting machine. Further reading: Linus Torvalds Would Like To Use An M1 Mac For Linux, But...

Yes, Torvalds said he'd love to have one of the new M1-powered Apple laptops, but it won't run Linux and, in an exclusive interview he explains why getting Linux to run well on it isn't worth the trouble. Steven J. Vaughan-Nichols writes via ZDNet: Recently, on the Real World Technologies forum, Linux's creator Linus Torvalds was asked what he thought of the new M1-powered Apple laptops. Torvalds replied, "I'd absolutely love to have one if it just ran Linux." You may think, "what's the problem? Doesn't Linux run on practically every processor on the planet from 80386s to IBM s390x to the ARM family of which Apple's M1 chip is a child?" Well, yes, yes it does. But it takes more than a processor to run a computer.

Torvalds would like to run Linux on these next-generation Macs. As he said, "I've been waiting for an ARM laptop that can run Linux for a long time. The new Air would be almost perfect, except for the OS. And I don't have the time to tinker with it, or the inclination to fight companies that don't want to help." Aye, there's the rub. In an exclusive interview, Torvalds expanded on why he can't see porting Linux to the M1-based Macs. "The main problem with the M1 for me is the GPU and other devices around it, because that's likely what would hold me off using it because it wouldn't have any Linux support unless Apple opens up."

Still, while Torvalds knows Apple opening up their chipsets "seems unlikely, but hey, you can always hope." Even if that "wasn't an issue," Torvalds continued, "My personal hope would be more cores. Even in a laptop, I don't care about 20-hour battery life (and I wouldn't get it building kernels anyway). I'd rather plug it in a bit more often, and have 8 big cores." As for the Mac's limited RAM -- no more than 16GBs on current models -- he can live with that. "16GBs is actually ok by me because I don't tend to do things that require a lot more RAM. All I do is read email, do git and kernel compiles. And yes, I have 64GB in my desktop, but that's because I have 32 cores and 64 threads, and I do hugely parallel builds. Honestly, even then 32GB would be sufficient for my loads." That said, other developers and power users may want more from the new Macs, Torvalds thinks. "The people who really want tons of memory are the ones doing multiple VMs or huge RAW file photography and video."

The European Union could produce enough batteries by 2025 to power its fast-growing fleet of electric vehicles without relying on imported cells, European Commission Vice President Maros Sefcovic said on Tuesday. Reuters reports: As part of its plan to become climate neutral by 2050, the EU wants to boost local production of the building blocks for green industries -- including hydrogen fuel to make low-carbon steel and batteries to power clean vehicles. "I am confident that by 2025, the EU will be able to produce enough battery cells to meet the needs of the European automotive industry, and even to build our export capacity," Sefcovic told the online European Conference on Batteries. Today, China hosts roughly 80% of the world's lithium-ion cell production, but Europe's capacity is set to expand fast.

Europe has 15 large-scale battery cell factories under construction, including Swedish company Northvolt's plants in Sweden and Germany, Chinese battery maker CATL's German facility, and South Korean firm SK Innovation's second plant in Hungary. Sefcovic said by 2025 planned European facilities would produce enough cells to power at least 6 million electric vehicles.

Elon Musk made rare comments about a new Tesla vehicle to be designed in Berlin, adding that the reason behind the new vehicle program is to attract new talent from Europe: "I think there's a lot of talent, talented designers and engineers, in Europe. And a lot of the best people, they want to work somewhere where they are doing original design work. They don't want to just be doing the European version of something that was designed in California. So, I think it's important in order to attract the best talent to do original design." Electrek reports: Tesla has been putting a lot of efforts into attracting top talent and it has been successful at it in its home country. Furthermore, Musk commented on the vehicle segment that Tesla plans to address with a locally designed vehicle: "In Europe, I think it would make sense to do I guess a compact car -- perhaps a hatchback or something like that. Something that answers "what do most people want?' in a given region. In the US, cars tend to be bigger for personal taste reasons and in Europe, it tends to be smaller. If you try to park in dense urban environments, having a car that fits in tight parking spaces is important."

Musk didn't offer a timeline for Tesla to design and build the new electric car in Germany, but it's not expected to hit the market for at least a few more years as Tesla focuses on bringing the European Model Y to production at Gigafactory Berlin next year. You can watch the interview where Musk makes the new comments here.

Long-time Slashdot reader 00_NOP is a software engineer (with a PhD in real-time computing) re-visits a historic research paper on the financial trade-offs between disk space (then costing about $20,000 per kilobyte) and (volatile) memory (costing about $5 per kilobyte): Thirty-five years ago that report for Tandem computers concluded that the cost balance between memory, disk and CPU on big iron favoured holding items in memory if they were needed every five minutes and using five bytes to save one instruction.

Update the analysis for today and what do you see?

Well my estimate is that we should aim to hold items that we have to access 10 times a second.
And needless to say, some techniques for saving data space are more efficient than they were 35 years ago, their article points out.

"The cost of an instruction per second and the cost of a byte of memory are approximately equivalent — that's tipped the balance somewhat towards data compression (eg., perhaps through using bit flags in a byte instead of a number of booleans for instance), though not by a huge amount."

According to a facebook post from the police department of Corvallis, Oregon, a Tesla Model 3 crashed at over 100mph, causing batteries from the Tesla to enter two different residences by breaking through the windows, one landing on a person's lap and the second landing on a bed, catching the bedding on fire. "A tire was ripped from the car during the collision and struck the second story siding of a nearby apartment complex with such force that it ruptured the water pipes within the wall, destroying the bathroom to the apartment and flooding the downstairs portion of the apartment as well," adds ExtremeTech. From the report: Tesla goes to some trouble to make certain that the battery cells in its vehicles don't go flying in the event of a collision. But the nature of this impact was obviously sufficient to break whatever solution the manufacturer has developed for dealing with the problem. Previous teardowns of the Model 3 battery pack have shown that the cells are sealed in place with high-strength epoxy.

With that said, there does appear to be a unique problem for BEVs in a situation like this. According to a follow-up post, the Model 3 battery cells can remain hot to the touch and might cause burns for up to 24 hours following involuntary dispersal. That kind of hazard -- specifically, the length of time you might be at risk from harm due to leftover detritus -- seems a potentially significant issue in certain situations. Tesla's epoxy solution shows it has considered the problem, but there may be reason to revisit things. It is unclear if individual cells remain at significant risk for secondary ignition after being separated from the main battery for any length of time or if the majority of fire risk is in the immediate period post-impact. The driver, incidentally, survived, which seems to say something good about Tesla's crash survival measures, at the least. The vehicle, needless to say, did not.

The Internet Archive is now emulating Flash animations, games and toys in our software collection. Jason Scott writes in a blog post: Utilizing an in-development Flash emulator called Ruffle, we have added Flash support to the Internet Archive's Emularity system, letting a subset of Flash items play in the browser as if you had a Flash plugin installed. While Ruffle's compatibility with Flash is less than 100%, it will play a very large portion of historical Flash animation in the browser, at both a smooth and accurate rate.

We have a showcase of the hand-picked best or representative Flash items in this collection. If you want to try your best at combing through a collection of over 1,000 flash items uploaded so far, here is the link. You will not need to have a flash plugin installed, and the system works in all browsers that support Webassembly. For many people: See you later! Enjoy the Flash stuff!

An anonymous reader quotes a report from VentureBeat: Cerebras Systems and the federal Department of Energy's National Energy Technology Laboratory today announced that the company's CS-1 system is more than 10,000 times faster than a graphics processing unit (GPU). On a practical level, this means AI neural networks that previously took months to train can now train in minutes on the Cerebras system.

Cerebras makes the world's largest computer chip, the WSE. Chipmakers normally slice a wafer from a 12-inch-diameter ingot of silicon to process in a chip factory. Once processed, the wafer is sliced into hundreds of separate chips that can be used in electronic hardware. But Cerebras, started by SeaMicro founder Andrew Feldman, takes that wafer and makes a single, massive chip out of it. Each piece of the chip, dubbed a core, is interconnected in a sophisticated way to other cores. The interconnections are designed to keep all the cores functioning at high speeds so the transistors can work together as one. [...] A single Cerebras CS-1 is 26 inches tall, fits in one-third of a rack, and is powered by the industry's only wafer-scale processing engine, Cerebras' WSE. It combines memory performance with massive bandwidth, low latency interprocessor communication, and an architecture optimized for high bandwidth computing.

Cerebras's CS-1 system uses the WSE wafer-size chip, which has 1.2 trillion transistors, the basic on-off electronic switches that are the building blocks of silicon chips. Intel's first 4004 processor in 1971 had 2,300 transistors, and the Nvidia A100 80GB chip, announced yesterday, has 54 billion transistors. Feldman said in an interview with VentureBeat that the CS-1 was also 200 times faster than the Joule Supercomputer, which is No. 82 on a list of the top 500 supercomputers in the world. [...] In this demo, the Joule Supercomputer used 16,384 cores, and the Cerebras computer was 200 times faster, according to energy lab director Brian Anderson. Cerebras costs several million dollars and uses 20 kilowatts of power.

MojoKid writes: AMD officially launched its Radeon RX 6800 and Radeon RX 6800 XT graphics cards today, previously known in the PC gaming community as Big Navi. The company claimed these high-end GPUs would compete with NVIDIA's best GeForce RTX 30 series and it appears AMD made good on its claims. AMD's new Radeon RX 6800 XT and Radeon 6800 are based on the company's RDNA 2 GPU architecture, with the former sporting 72 Compute Units (CUs) and 2250MHz boost clock, while the RX 6800 sports 60 CUs at a 2105MHz boost clock. Both cards come equipped with 16GB of GDDR6 memory and 128MB of on-die cache AMD calls Infinity Cache, that improves bandwidth and latency, feeding the GPU in front of its 256-bit GDDR6 memory interface.

In the benchmarks, it is fair to say the Radeon RX 6800 is typically faster than an NVIDIA GeForce RTX 3070 just as AMD suggested. Things are not as cut and dry for the Radeon RX 6800 XT though, as the GeForce RTX 3080 and Radeon RX 6800 XT trade victories depending on the game title or workload, but the RTX 3080 has an edge overall. In DXR Ray Tracing performance, NVIDIA has a distinct advantage at the high-end. Though the Radeon RX 6800 wasn't too far behind and RTX 3070, neither the Radeon RX 6800 XT or 6800 card came close the GeForce RTX 3080. Pricing is set at $649 and $579 for the AMD Radeon RX 6800 XT and Radeon RX 6800, respectively and the cards are on sale as of today. However, demand is likely to be fierce as this new crop of high-end graphics cards from both companies have been quickly evaporating from retail shelves.