

Components
Up to 8 XE cores and 6 GB of memory: the first information about the Intel Arc Pro A50/A40 graphics cards appeared
The database of the SiSoftware Sandra test package has fresh data on the upcoming Arc A40 Pro and Arc A50 Pro graphics cards. These are graphics accelerators for workstations that are designed for engineering tasks.
The A50 Pro has a full ACM-G11 GPU with 8 Xe cores (128 execution units/1024 FP32 cores), while the A40 Pro is likely to get a stripped-down version of the chip. The clock frequency is 2.45 GHz.
Both cards have 6 GB GDDR6 memory, indicating a 96-bit memory bus. In this regard, both models are similar to the Arc A380 mobile card, which has almost the same configuration.
Thus, the company continues to prepare its entry-level products. When high-performance gaming and professional solutions based on the ACM-G10 GPU will appear, it is not reported. It is also not yet clear whether the Arc A40 Pro and Arc A50 Pro cards will be available in retail or whether they will appear only as part of workstations.
Earlier, Intel introduced its first gaming graphics card for $150.

Components
But these new AMD processors already look much more interesting. AMD talked a little about Ryzen generation Strix Point

The Ryzen 8000U/H/HS processors may disappoint with the lack of any significant improvements, but these are not all the new products that AMD is preparing for the 2024 model year. The Strix Point line will be much more interesting.
According to AMD’s slides, this line will also be released next year. It is not yet clear under what name, but based on the principle of naming the company’s processors, it should be Ryzen 8050, where the eight will indicate 2024, and the five will represent the Zen 5 architecture.
Yes, these will be mobile processors based on the new Zen 5 architecture, which should already make them much faster than current APUs. In addition, the iGPU of such processors will be built on the RDNA 3+ (or RDNA 3.5) architecture, but it is not yet clear what improvements it will bring.
If the Ryzen 8000U/H/HS has increased performance by 60% relative to the Ryzen 7000U/H/HS, then the Strix Point will be three times faster.
According to early leaks, Strix Point, unlike the Ryzen 7040 and Ryzen 8040, will have up to 12 processor cores, and the Strix Halo line will offer up to 16 cores, but these will be APUs of a completely different level. Also, Strix Point processors were previously credited with iGPUs with 1024 stream processors versus 768 for the Radeon 780M. Strix Halo will supposedly have 2560 stream processors, which is more than a number of Radeon desktop video cards.
Components
One of the most senseless changes in processor generations, and this time from AMD. Mobile Ryzen 8000U/H/HS presented

AMD will present new Ryzen 8000 mobile processors today as part of the Advance AI event. Materials from the presentation have already appeared on the Internet, so the new products are fully revealed to us.
The new generation is called Hawk Point and, unfortunately, it is almost no different from the Ryzen 7040 line. In fact, models with the corresponding names, for example, Ryzen 7 8840HS and Ryzen 7 7840HS, either differ slightly in frequencies or do not differ at all in basic parameters . There are the same Zen 4 processor cores, the same iGPU based on the RDNA 3 architecture, the same number of cores, cache memory, and so on.
In fact, the only update worth mentioning is the new Ryzen AI core for working with artificial intelligence. If the Ryzen 7000 has such a unit with a performance of 10 TOPS, then the Ryzen 8000 has 16 TOPS. The increase is very large, but the problem is that so far there is absolutely no place to use it.
Thus, the transition from Ryzen 7000U/H/HS to Ryzen 8000U/H/HS can be called one of the most minor and insignificant in all recent years from AMD.
It remains to be added that laptops with new APUs will hit the market in the next quarter.
Components
The Chinese will receive a stripped-down RTX 4090 instead of the banned original version. Details of the GeForce RTX 4090D (Dragon) model began to appear

The GeForce RTX 4090D (Dragon) video card, created specifically for China, generally remains a mystery, but the first details have appeared on the Internet.
In particular, it is reported that the frequencies of this version will be slightly different from the usual one. More precisely, the GPU will operate at frequencies of 2280-2520 MHz versus 2235-2520 MHz.
Also, the MEGAsizeGPU insider says that the number of CUDA cores in the Chinese card will still be less. The RTX 4090D will receive the same AD102 GPU, but cut down. At the same time, the insider says that he already has the exact parameters and even images, but cannot share this yet.
Given that the frequency changes are minor, the main question is how much the GPU will be cut and whether the memory subsystem will be cut.
Insider MEGAsizeGPU previously spoke about the launch of the RTX 4060 and RTX 4060 Ti before the announcement, as well as the release dates for these models.
-
Components6 days ago
The old GeForce RTX 3060 will still fight. Nvidia is going to reduce the price of this video card and extend its lifespan to combat AMD
-
Components3 days ago
Gamer’s Lexus TX presented: with RGB lighting, powerful acoustics and a pair of large monitors in the cabin
-
Components6 days ago
GeForce RTX 4090 D (Dragon) will retain the same AD102 GPU as the original model
-
News4 days ago
Ten times weaker than Nvidia H100, but entirely our own development. Loongson introduced LG200 AI accelerator