When AMD showed off the new RX 480 at Computex a couple of weeks ago, we all knew that wouldn’t be the only card in its new lineup. Now, after the PC Gaming Show at E3, we have confirmation of that suspicion, with the official announcement of the RX 470 and RX 460. Details are still scarce on the two new cards, but it does expand our understanding of the RX series and the Polaris architecture.
Importantly, AMD is the first brand to make the move to the 14nm FinFET die size. The smaller silicon means better power and performance efficiency, while still providing a decent performance boost, if the RX 480 benchmarks (from AMD) are any indication.
There are improvements to the software and feature side to, and they happen at the API level. Like the RX 480, the new cards are DX12 compatible, with a higher feature level than Nvidia’s previous generation cards. That’s allowed the $200 RX 480 to slide past the much more expensive GTX options in benchmarks like Ashes of the Singularity. It even competes with the GTX 1070 and 1080, although there are other factors at play there.
It’s a similar story with Asychronous Compute, which works pretty much exactly like it sounds. The GPU is able to run more background calculations while rendering, which can result in better framerates and lower latency. Nvidia made some strides with Async Compute in the GTX 1070 and 1080, but AMD is still ahead, and part of that is thanks to the red team’s improved support for new APIs, like Vulkan and DirectX 12. Nvidia also supports these — but AMD seems have more experience coding for the newer APIs, perhaps due to its early promotion of its own Mantel API.
Vulkan follows up Mantle as AMD’s open source graphics API of choice. Developed by Khronos, the same team that created the widely used OpenGL standard, Vulkan is designed to cut out the distance between software and hardware, increasing performance and efficiency, and it leverages some of AMD’s tech to get there. Unlike Nvidia’s GPU tech, which includes proprietary features like PhysX and HairWorks, Vulkan is designed with enough hardware abstraction to run on non-AMD devices.
But these new GPUs aren’t just for desktop gaming PCs, and AMD is acutely aware of its own lacking market share in the mobile department. The new cards will be targeted at budget laptops as well, and if their target price point is any indication, they could end up turning cheap laptops in gaming whiz-kids.
The focus beyond gaming continues with suppoert for HDMI 2.0b, DisplayPort 1.3/1.4, and acelerated H.265 encoding. All of this ensures that gamers can take advantage of 4K video thanks to support for the latest connection standards and lower CPU overheading when playing UltraHD video.
Like the specifications of the new cards, the price is still a mystery, but AMD stated in no uncertain terms it would be targeting the sub-$300 price point with the line. Considering the RX 480 is priced at $200 even, the two lower numbers are certain to be budget build leaders.
After five years with Apple silicon, from the original M1 MacBook Air to the M5 MacBook Air released earlier this year, I've watched these chips mature not just on the spec sheet, but in real-world workflows and overall efficiency.
The new M6 chip might sound like a routine generational upgrade, but it's the company's first chip built on a 2nm manufacturing process, which brings meaningful improvements over previous Apple chips.
Gemini Notebook’s mobile app now has a built-in recorder for capturing lectures and meetings as sources. You can record directly where you’ll use the material, skipping the separate recording app and the file upload afterward.
Google announced the feature on X, highlighting classroom lectures and team meetings as potential uses. It also works for capturing your own thoughts, so you can talk through an idea and bring that explanation into your notebook while it’s still fresh.
In 1950, Alan Turing asked whether machines can think. Rather than argue over definitions, he turned the question into a party game, where an interrogator trades typed messages with hidden players and tries to work out who is who. Since then, chatbots have gotten so good that they have already fooled humans in modern versions of the test.
So, four researchers from Paris Cité University asked the obvious follow-up question in a new study published in Computers in Human Behavior Reports: can AI at least catch its own kind?