AMD has adopted a brand new "Ryzen AI HX" naming scheme for its upcoming Strix Point APUs which sounds very familiar to Intel's Core Ultra.
21.04.2024 - 07:00 / wccftech.com / Hassan Mujtaba
NVIDIA's early engineering sample of the RTX 2070, known as the GeForce GTX 2070, has been spotted and features lower cores than the original variant.
NVIDIA's GeForce "GTX" labeling was used up till the GeForce 10 and GeForce 16 series GPUs. Everything after these GPUs was labeled under the GeForce "RTX" series but it looks like the company had internally labeled the RTX 20 series as GTX 20 series as one such model has now surfaced online.
Pictures posted by @unnatural__log show a peculiar NVIDIA GeForce RTX 2070 GPU which is mentioned to be an engineering sample which explains why it doesn't use the "RTX" labeling.
In terms of design, the NVIDIA GeForce GTX 2070 Engineering Sample features the same design as the GeForce RTX 2070. It has the same dual axial fan cooler with the dual-slot design but the label on the sides reads "GeForce GTX" and there's no "GTX 2070" or "RTX 2070" on the front. The card has a few missing labels but besides that, there are no big differences. The display ports include the same HDMI, 2x DP, USB Type-C VirtualLink port, and a DVI output. The card should feature a standard 8-pin connector since this was before the time NVIDIA switched to the 12-pin or 16-pin interfaces.
The PCB of the NVIDIA GeForce GTX 2070 Engineering Sample also matches the reference design but its the specifications that are the biggest change. While the RTX 2070 featured 2304 cores, the GTX 2070 ES GPU features 2176 cores and is based on the TU106-400A-A1 GPU with the device ID being "10DE-1F07 - 10DE-12AD". This is the same core configuration used by the RTX 2060 SUPER which featured the TU106-410-A1 GPU.
Based on the testing done by the user, the NVIDIA GeForce GTX 2070 Engineering Sample GPU was flashed with the BIOS of an RTX 2070 "400A BIOS" which doesn't change the device ID nor unlock the extra cores but it does grants some extra power to the GPU core which can be used for manual tweaking. With OC, the GPU ended up with around 95% of the performance of the RTX 2070, or a 16 percent boost over its default profile. That's a pretty decent bump considering that we don't get to see such gain on modern-day GPUs anymore since they are already running at clock speeds way above their listed "peak boost" clock speeds.
Overall, this shows that there was a time when NVIDIA hadn't decided to use the "RTX" branding for its upcoming Turing GPUs which ended up becoming the first "RTX" GPUs, thus ending the reign of the GeForce "GTX" series. NVIDIA has also sized the production of the last GeForce GTX GPUs which means
AMD has adopted a brand new "Ryzen AI HX" naming scheme for its upcoming Strix Point APUs which sounds very familiar to Intel's Core Ultra.
NVIDIA's GeForce RTX 50 "Blackwell" GPU family should kick off with the RTX 5080 graphics card first & followed by the flagship RTX 5090, reports Kopite7kimi.
XFX has finally launched its ultra high-end Radeon RX 7900 XTX Phoenix Nirvana GPU which comes with a triple slot & triple fan cooling solution.
AMD has shared some interesting data regarding the capabilities of its RDNA 3 GPU & XDNA NPU hardware in consumer-centric AI workloads.
Video game workers in Quebec, under the Game Workers Unite Montreal banner, are partnering with Canadian trade union Confédération des syndicats nationaux (CSN) in an effort to shape the industry for the better. Together, they’re launching a union drive to form a provincewide union for Quebec-based video game workers. Quebec is home to nearly 15,000 workers, according to GWU Montreal, at studios like Behaviour Interactive, Ubisoft, Warner Bros. Games, Electronic Arts, and Gameloft, making it a hotbed for the industry and its workers.
Qualcomm is expected to officially unveil the Snapdragon 8 Gen 4 in October this year, so it is no surprise that the flagship’s engineering sample is being thoroughly tested and benchmarked to iron out the problems before commercial units are sent to the company’s phone partners. However, early results show that the chipset’s performance is beyond disappointing, with the performance cores said to be running at a significantly lower resolution than what previous reports suggested.
AMD's Ryzen 9 7900X3D CPU is currently available at an absolute steal of a price point for just $329.99 at US retailer, antOnline.
AMD Ryzen CPUs are leading in the Korean DIY sales charts against Intel's Core lineup with Ryzen 5 being the choice of gamers.
NVIDIA's GeForce RTX 40 GPUs, including the RTX 4060 Ti, are experiencing some major supply issues, leading to increased prices.
Ampere Computing is leveraging TSMC's 3nm process node for its AmpereOne-3 CPU, offering up to 256 cores, in the coming year.
MSI seems to be focusing more on NVIDIA's RTX GPUs than AMD's Radeon GPUs as the company focuses on products with higher user interest.
An engineering sample of AMD's Zen 5-based Strix Point "Ryzen 9" APU with 12 cores, 24 threads, and 24 MB of L3 cache has been spotted at Geekbench.