RIP apple M1

RIP apple M1 AMD won AGAIN with Ryzen 7940HS!!!
At SEC 2023 amd present as The new king AMD Ryzen 7940HS!

Ryzen Mobile 7040 Series: Zen 4 Phoenix Takes Flight

The only truly new silicon among today’s announcements, and arguably the marquee announcement among this evening’s mobile announcements, is AMD’s Ryzen Mobile 7040 series of chips. Codenamed Phoenix, this is AMD’s first mobile-centric Zen 4 CPU design, incorporating the new CPU cores, new RDNA 3 iGPU, and more into a new monolithic silicon die. AMD initially teased Phoenix back at their 2022 Financial Analyst Day, so while this evening’s announcement was hardly out of the blue, it’s been an eagerly anticipated one, as the Zen 4 CPU architecture was designed to shine in mobile just as much as it does the desktop.

Phoenix is AMD’s flagship mobile silicon, and the successor to the Zen3+/RDNA2 Rembrandt, which was the basis of the Ryzen Mobile 6000 series. Iterating on top of that design, Phoenix incorporates up to 8 of AMD’s new Zen 4 CPU cores, as well as a high-performance integrated GPU based on AMD’s new RDNA 3 architecture, with up to 12 CUs.

All of this, in turn, is being built on TSMC’s 4nm process, which makes it the single most advanced piece of silicon out of AMD yet, eclipsing even the 5nm-based Ryzen 7000 and Radeon RX 7000 families. Which is not to oversell 4nm here – TMSC’s 4nm nodes are all variants of their 5nm process, and we don’t know which specific variant AMD is using here – but it underscores that AMD has spared no expense here by using the best (and most expensive) process node they could get their hands on for their next generation mobile CPU.

Phoenix in the silicon flesh (Image Courtesy AMD)

Along with the new CPU and GPU architectures, Phoenix also marks one more first for an AMD processor: it is the first AMD CPU to incorporate an AI engine/neural networking processor.

Adopting their Xilinx-developed XDNA architecture, AMD has placed an XDNA processing block, which they’ve dubbed Ryzen AI, on Phoenix to accelerate the processing of AI workloads. As with other dedicated silicon blocks/domain specific accelerators, the inclusion of an AI engine is both to offer better throughput on a specific task, and to also execute that task in a far more power efficient manner. This, as AMD reasons, will give them an edge in performance, along with energy efficiency in tasks that can leverage the Ryzen AI block.

At this point AMD isn’t quoting performance figures for the AI engine, so we don’t have any hard numbers to use in comparison. But AMD has told us that the block can process up to 4 streams of AI workloads, and that it’s 20% faster than the neural engine on Apple’s M2 SoC. Obviously, any Apple comparisons are going to raise a few eyebrows as they’re the player to beat in the laptop space right now, so it will be interesting to see how these claims pan out once Phoenix starts shipping.

In any case, the Apple comparison is apt, as AMD is clearly taking a page from the mobile (handset) market playbook with the inclusion of a neural network processor. These AI processors have proven highly effective in mobile devices, and with Moore’s Law slowing down, the tech industry as a whole is drifting towards using more DSAs to keep performance and performance efficiency growing. So for a while now, it’s been clear that it would only be a matter of time; and in 2023, AMD is in a great position to do so thanks to their Xilinx acquisition.

With that said, this is clearly the very early days for an AI engine on a PC (Windows) laptop. The software ecosystem to make use of the hardware is not yet in place – especially in the consumer space – so AMD is taking the first step by providing hardware for developers to start coding against. AMD considers the Ryzen AI engine to be a long-term investment, and we should expect to see it appear in more AMD products over the coming years, as well as receiving hardware upgrades of its own. In the meantime, it’s going to be more of a conversational feature until consumer software is ready.

Moving on, AMD is initially launching 3 SKUs based on Phoenix, which per the new naming system, are all part of the Ryzen Mobile 7040 series. These are all HS-series parts, meaning they have TDPs of 35W to 45W, and while the 7040 series is slated to eventually come in U-series parts as well, AMD is going to be pushing their first Phoenix chips into the most visible (and profitable) segment of the notebook market.

AMD Ryzen 7040 Mobile CPUs 'Phoenix' on 4nm
AnandTech	C/T	Base Freq	Turbo Freq	GPU	GPU Freq	L3 Cache (MB)	TDP
HS-Series 35W - 54W
Ryzen 9 7940HS	8/16	4000	5200	RDNA 3 12 CUs	3000	16	35W - 54W
Ryzen 7 7840HS	8/16	3800	5100	RDNA 3 12 CUs	2900	16	35W - 54W
Ryzen 5 7640HS	6/12	4300	5000	RDNA 3 8 CUs	2800	16	35W - 54W

For the 7040 launch, there is an SKU each for the Ryzen 9, Ryzen 7, and Ryzen 5 segments. The Ryzen 9 7940HS and Ryzen 7 7840HS have all 8 CPU cores enabled, and differ only in terms of their clockspeeds. Meanwhile the Ryzen 5 part, the 7640HS, drops down to 6 CPU cores, and we’re still waiting to hear from AMD about how many RDNA 3 CUs are enabled (R5 parts typically have a half-enabled GPU).

At the high end, the 7940HS will be able to turbo as high as 5.2GHz, which is 200MHz higher than the fastest Ryzen Mobile 6000 chip. So the 7040 series will be enjoying both slightly higher CPU clockspeeds and a higher IPC rate than their predecessors. This does end up being a bit lower than the clockspeeds on the desktop-derived HX series parts, which go as high as 5.4GHz, which is part of the reason why AMD is offering the HX series as well – for buyers who need the very highest in CPU performance.

Notably, the 7040 series supports DDR5-5600 memory along with LPDDR5x-7500. Given that the HX series exists for peak performance needs, it’s somewhat difficult to imagine laptop vendors going with DDR5 on 7040 series laptops given the power efficiency hit. But the option is there, especially if they need to be able to offer removable DIMMs.

With regards to performance expectations, AMD is not offered us much in the way of useful comparisons (at least not in advance). So it’s not clear just how much faster these parts are going to be in CPU or GPU workloads compared to the existing Ryzen 6000 (Rembrandt) parts. AMD tells us that they do expect to compare favorably to Intel, who also announced new mobile parts this week. However unlike AMD, Intel doesn’t have a new CPU architecture or process node to take advantage of for this generation, so Intel’s position in the 45W market is fairly stagnant. That means the 7040 series gives AMD an opportunity to move ahead of Intel’s Alder Lake-derived parts, both from the 12^th and 13^th Core generations. If ever there was a time AMD was going to clearly and convincingly beat Intel in the 45W segment, this is it.

AMD has told us that the new Ryzen Mobile 7040 parts will also offer battery life improvements over their earlier parts (and Intel’s, as well). But AMD is not offering any specific performance figures here. So we’ll have to see how things shake out once 7040 series laptops start shipping.

And shipping dates are the one downbeat piece of news this evening; the first 7040 laptops won’t be shipping until March, a couple of months down the line. And we would be remiss to not point out that AMD’s mobile CPU shipment dates tend to be overly optimistic to begin with – often it’s a couple of months later before you can find laptops based on new AMD silicon in volume. So while we hope that AMD has some of the kinks worked out on their mobile product pipeline, there’s a genuine risk that 7040 series laptops may not be readily available until later in the spring.

Looking farther down the line, 7040/Phoenix is also slated to become available in 15 – 28 Watt U-series SKUs at some point. AMD has not offered any timeline for this, but it’s something for AMD laptop aficionados to look forward to later on in 2023.

Ryzen Mobile 7035 Series: Rembrandt Rides Again For HS and U

Go to our source to read more .