Both Intel and AMD usually have processor updates to announce at CES in January, but AMD isn’t waiting to introduce its next-generation flagship laptop chips: the Ryzen 8040 series is coming to laptops starting in early 2024, though at first blush these chips look awfully similar to the Ryzen 7040 processors that AMD announced just seven months ago.
Though the generational branding is jumping from 7000 to 8000, the CPU and GPU of the Ryzen 8040 series are nearly identical to the ones in the 7040 series. The chips AMD is announcing today use up to eight Zen 4 CPU cores and RDNA 3-based integrated GPUs (either a Radeon 780M with 12 compute units, or Radeon 760M or 740M GPUs with 8 or 4 CUs). The chips are manufactured using the same 4 nm TSMC process as the 7040 series.
There’s also an AI-accelerating neural processing unit (NPU) that AMD claims is about 1.4 times faster than the one in the Ryzen 7040 series in large language models like Llama 2 and ONNX vision models. Both NPUs are based on the same XDNA architecture and have the same amount of processing hardware—AMD says that the AI performance improvements come mostly from higher clock speeds.
Clock speeds across the board are pretty similar to the 7040 series, though AMD Technical Marketing Manager Donny Woligroski claims that optimizations to firmware and drivers should still result in a “real generational improvement.” There’s plenty of room to improve a laptop chip’s performance without increasing peak clock speeds, especially if you can improve the sustained clock speeds that the chips can hit when they’re busy for an extended period. But generation-over-generation performance comparisons for anything other than AI weren’t included in AMD’s presentation.
AMD’s briefing and slide deck spend most of their time talking about Ryzen AI and the dedicated NPU. Though Nvidia dominates the market for server-side AI chips, local NPU hardware from AMD, Intel, and various ARM chipmakers may make it easier to run some generative AI workloads locally. Depending on how those features are implemented, they could be better for privacy since the processing is happening on-device rather than sending data to a server somewhere—when Apple talks about privacy, it often talks about this kind of on-device processing since its chips have included NPUs for years longer than Intel’s or AMD’s.
The quick leap in generational branding is enabled by the new processor naming scheme that it started using late last year. Rather than denoting anything about the underlying hardware, the first digit of the four-digit model number now just tells you what year the processor was introduced. The second digit denotes the “market segment” (a 5 or 6 for Ryzen 5, a 7 for Ryzen 7, and so on), and the third digit is where you actually get technical information about the underlying CPU architecture. The final digit is another way to distinguish between lower- and higher-end chips, and a suffixed letter indicates the TDP range of the chip and the kinds of systems it can be used in.
Intel recently criticized this naming scheme, pointing out in a since-deleted slide deck that it allows AMD to rebrand older processors as newer ones while making minimal technical improvements. This is completely fair criticism (and Intel quoted Ars while making it), though Intel regularly does the same thing with its processor generations.
For now, this naming system only applies to AMD’s laptop processors. Its Ryzen desktop CPUs, at least so far, have only jumped numbers when AMD has actually changed CPU architectures. AMD didn’t have much to add about a true next-generation successor to the 7040/8040 series silicon, but it did briefly tease a processor codenamed “Strix Point” that will launch at some point in 2024 with a next-generation NPU based on the XDNA 2 architecture. AMD says Strix Point will feature three times faster generative AI performance than its current silicon.
Listing image by AMD