from the talk-to-me-again-of-Mendocino dept.
AMD unveiled its entry-level Mendocino series of laptop processors at Computex 2022. The company didn't provide much in the way of meaningful information and briefly talked about its power efficiency. Now, it has announced three new Mendocino processors, the Ryzen 5 7520U, Ryzen 3 7320U and Athlon Gold 7220U, manufactured on TSMC's 6 nm process node. They use a modified version of the Zen 2 cores and support LPDDR5 memory.
[...] The "U" Mendocino processors' names confirm that all three SKUs have a maximum TDP of 15 W, making them ideal for thin and light laptops. The Ryzen 5 7520U is a 4-core, 8-thread processor with base/boost clocks of 4.3/2.8 GHz. The Ryzen 3 7320U has the same configuration but reduces the base/boost clocks to 4.1/2.4 GHz. Lastly, the AMD Athlon Gold 7220U has 2 cores, 4 threads and a base/boost clock of 3.7/2.4 GHz.
Microsoft Pluton is confirmed to be in the 7020 series. All three of the APUs include Radeon 610M graphics with 2 RDNA2 compute units, one-third that of a Ryzen 5 6600U with 660M graphics. The 610M may be identical to the iGPU in Ryzen 7000 desktop CPUs, and it supports AV1 hardware decode and up to 4 display outputs (USB-C ports with DisplayPort capability could be used to get close to this number).
You can see AMD's new mobile naming scheme at work. The third digit of 7520U indicates that it uses Zen 2 cores. We could see Ryzen 3 7340U and Ryzen 5 7540U "Phoenix Point" APUs using Zen 4 cores surrounding that model.
Also at Tom's Hardware.
Previously: AMD Announces Mendocino APU at Computex, and More Details for Ryzen 7000 and Socket AM5
See Also: Nvidia Announces the RTX 4090, 4080 (16 GB and 12 GB), and More
Related Stories
AMD has announced "Mendocino", a mid-range chip for Windows and ChromeOS laptops that will launch in Q4 2022. The Mendocino die has a quad-core Zen 2 CPU and an unspecified amount of RDNA2 graphics cores, and uses LPDDR5 memory. It looks similar if not identical to the Van Gogh chip used in Valve's Steam Deck, except that it uses TSMC's "6nm" process instead of "7nm".
Seeing AMD planning to mint a new Zen 2-based APU in late 2022 is at first blush an unusual announcement, especially since the company is already two generations into mobile Zen 3. But for the low-end market it makes a fair bit of sense. Architecturally, Zen 3's CPU complexes (CCXes) are optimized for 8C designs; when AMD needs fewer cores than that (e.g. Ryzen 3 5400U), they've been using salvaged 8C dies. For Zen 2, on the other hand, the native CCX size is 4, which allows AMD to quickly (and cheaply) design an SoC based on existing IP blocks, as opposed to engineering a proper 4C Zen 3 CCX.
AMD's Ryzen 7000 series of desktop CPUs will launch this fall on a new AM5 socket, with a Land Grid Array (LGA) design. The heat spreader for the CPUs has cutouts on the top for capacitors, while the back is completely covered with pads (not pins like on AM4 CPUs). AM5 CPUs will only use dual-channel DDR5 memory, with no mixed DDR4/DDR5 support like Intel's latest Alder Lake CPUs.
Three new chipsets have been announced for the first AM5 motherboards: X670E (the 'E' is for "Extreme"), X670, and B650. These are differentiated primarily by the guaranteed level of support for PCIe 5.0 devices. X670E should support up to two PCIe 5.0 graphics card slots and multiple PCIe 5.0 SSDs, whereas B650 may only support a single PCIe 5.0 SSD, using PCIe 3/4 elsewhere. PCIe 5.0 x4 supports theoretical sequential read speeds of 16 GB/s, with SSDs in the real world likely reaching 14 GB/s.
There will be no more Pentium, Pentium Gold, Pentium Silver, Celeron, etc. branded mobile/laptop CPUs starting in 2023:
"Intel Processor" Replaces Pentium & Celeron Brands
The new "Intel Processor" branding is intended to "simplify" their offerings for users. Intel's premium Core, Evo, and vPro branding, among others will remain. But for the basic CPUs, they will now be known as Intel Procesor.
The change may also apply to desktop and embedded product lines, but Intel hasn't announced that yet.
Over at Team Red: AMD's new naming scheme for its mobile CPUs seems purposefully confusing
AMD has announced that next year's mobile processors will use a new naming scheme. The new system is difficult to understand and may confuse customers - maybe on purpose.
[...] So now, there will be the new Mendocino series, which are 2020's Zen2 chips brought back to life as Ryzen 7x20. Barcelo (Ryzen 7x30) and Rembrandt (Ryzen 7x35) will also continue on. Zen4, the hotly anticipated new CPUs, are relegated to the high-end as Ryzen 7x40 (Phoenix) and Ryzen 7x45 (Dragon Range).
The problem: The most important part of the model number, the CPU generation, is the third digit. Logically, the first two digits in a four digit number should be the most important ones.
AMD has not announced any concrete model numbers yet, but it is easy to imagine how confusing these number-games can be for regular consumers. For example, a customer may have the choice between a Ryzen 7 7730U and a Ryzen 7 7740U - one is based on Zen3 from 2021 and is still paired with old Vega-GPUs, while the other is a chip of the newest Zen4 generation, even though only the third digit of the model number is different. Transparent for customers? Not at all!
Some processor names had already leaked before the naming scheme announcement, such as the AMD Athlon Gold 7220U, which would be a "Mendocino" APU using the Zen 2 microarchitecture.
Nvidia Announces the RTX 4090, 4080 (16 GB and 12 GB), and More
At Nvidia's GPU Technology Conference (GTC), the company announced its first "Lovelace" GPUs for consumers: the RTX 4090 ($1600), RTX 4080 16 GB ($1120), and RTX 4080 12 GB ($900). The graphics cards are made with TSMC's N4 process, and support AV1 encoding and DLSS 3 upscaling.
The RTX 4090 comes with 24 GB of GDDR6X VRAM, and launches on October 12. Performance of the 4090 should be at least 60-70% higher than the RTX 3090 Ti, or higher in some cases (raytracing performance should be better than doubled). However, Nvidia is claiming up to quadruple the performance when using DLSS 3, which will not be made available on RTX 20/30-series GPUs due to an apparent requirement of fourth generation Tensor Cores and a newer version of "Optical Flow Accelerator". The new version of Deep Learning Super Sampling (DLSS) can generate entire frames, similar to video interpolation.
The RTX 4080 variants differ in both core counts and VRAM capacity, leading to a significant performance gap between them, and will launch sometime in November. The 4080 16 GB has nearly 27% more CUDA cores and 46% higher memory bandwidth than the 4080 12 GB. The GPUs also use different dies (AD103 and AD104). This could lead you to believe that Nvidia has turned the xx70-class card into a "4080" in order to sell it at a higher price.
