One area of AMD's portfolio that perhaps doesn't garner the same levels of attention as its desktop, mobile, and server products is its embedded business. In early 2020, AMD unveiled its Ryzen Embedded R1000 platform for the commercial and industrial sectors and the ever-growing IoT market, with low-powered processors designed for low-profile systems to satisfy the mid-range of the market.

At Embedded World 2022 in Nuremberg, Germany, AMD has announced its next-generation of Ryzen Embedded SoCs, the R2000 series. Offering four different SKUs ranging from 2C/4T up to 4C/8T, which is double the core count of the previous generation, AMD claims that the R2000 series features up to 81% higher CPU and graphics performance.

The AMD Ryzen Embedded R2000 Series compared to the previous generation (R1000), now has double the core count, with a generational swing from Zen to the more efficient and higher performance Zen+ cores. All four SKUs announced feature a configurable TDP, with the top SKU, the R2544, operating at between 35 and 54 W. More in line with the lower power target of these SoCs, the bottom SKU (R2312) has a configurable TDP of between 12 and 35 W.

AMD Ryzen Embedded R2000-Series APUs
AnandTech Core/
Thread
Base
Freq (MHz)
1T Boost
Freq (MHz)
Memory
Support
L2
Cache
L3
Cache
GPU
CU's
TDP
Range
(W)
Launch
 (Expected)  
R2544 4 8 3350 3700 DDR4-3200 2 MB 4 MB 8 35-54 October 22
R2514 4 8 2100 3700 DDR4-2667 2 MB 4 MB 8 12-35 October 22
R2314 4 4 2100 3500 DDR4-2667 2 MB 4 MB 6 12-35 In Production
R2312 2 4 2700 3500 DDR4-2400 1 MB 2 MB 3 12-25 In Production

Another element delivering additional performance compared to the previous generation is better iGPU performance via increasing the number of Radeon Vega graphics compute units. The entry R2312 SKU comes with 3 CUs, while the R2544 comes with 8 CUs. The Ryzen Embedded R2000 series also benefits from newer video decode and display processor blocks, bringing support for decoding 4Kp60 video and driving up to three 4K displays.

AMD has also equipped the SoCs with 16 PCIe Gen 3 lanes on the R2314, R2514, and R2544 SKUs, while the R2312 gets eight. The R2000 series has support for two SATA 3.0 ports, up to six USB ports with a mixture of USB 3.2 G2 and USB 2.0, and OS support for Microsoft Windows 11/10 and Linux Ubuntu LTS. 

The application benefits of AMD's Ryzen Embedded R2000 series include the commercial and industrial sectors, as well as robotics, with a planned product availability of up to 10 years, ensuring a long life cycle for each product. Some of AMD's Ryzen Embedded R2000's Ecosystem partners include Advantech for its gaming and gambling machines, as well as DFI, IBASE, and Sapphire, so these new SoCs are already being adopted and planned into existing thin-client and small form factor systems.

AMD states that the Ryzen Embedded R2544 (4C/8T) and R2514 (4C/8T) will be available sometime in October 22, while the R2314 and R2312 SKUs are currently in production.

Source: AMD

POST A COMMENT

21 Comments

View All Comments

  • kpb321 - Wednesday, June 22, 2022 - link

    So are these just Binnings of the existing laptop/desktop APUs? The top end SKU seems to be pretty close to the 2600H or 2800H. Has a bit high CPU clocks than the 2600H but the 2800H has 11 CUs. The lowest end one seems to be pretty close to the Ryzen 3 3200U. Seems strange to not have the 2 higher end models if they are just reusing stuff that was released several years ago. Reply
  • PeachNCream - Thursday, June 23, 2022 - link

    Its common to reuse existing designs under different branding. In this case, it probably took a bit of time for AMD to finish the necessary validation to sell these as embedded processors for industrial usage. Better to test out chips in the consumer market and let stupid end users absorb the first few silicon revs before risking those same designs in longer lifespan hardware that will reside in places like assembly line control systems or thin clients. Reply
  • Rudde - Friday, June 24, 2022 - link

    The R1000 Banded Kestrel (2019) family has very similar specs to what was released as Athlon 3000 Dalì (2020). Both top out at 2 cpu cores and 3 gpu compute units. When compared to Ryzen 3000U Picasso (2019), the R2000 family has similar cpu core count (up to 4), but a little lower gpu compute unit count with only 8 compared to 11 (still close). What I found most interesting is that R2000 supports faster memory speeds at 3200 MHz, with Ryzen 3000U only supporting 2400 MHz. Another reason to move to the larger die is the 16 PCIe 3.0 lanes, up from 12.

    When comparing SKUs: The top R2544 is essentially a Ryzen 3550H and R2514 is like Ryzen 3500U. The R2314 is similar to the Ryzen 3300U. The R2312 is an odd one, having half of most resources compared to the other R2000s. When compared to the old R1000 family, it has less L3 cache (and PCIe lanes I think), reducing any generational gains.
    Reply
  • Kangal - Thursday, June 23, 2022 - link

    These are not exciting at all. I was pretty stoked with their first-gen product, the v1605b that was found on a SBC. The Udoo Bolt V8 is arguably still the most powerful SBC out there, despite using 2016-era technology.

    I've been hoping AMD would give the crimson treatment for all product segments. As in use the latest node, with the latest CPU architecture and latest GPU architecture. Think: 2017 + 16nm + Zen1 + Vega... 2019 + 8nm + Zen2 + RDNA2... 2021 + 6nm + Zen3 + RDNA2.... 2023 + 4nm + Zen4 + RDNA3. Whilst the Thermal range from the 5W, 10W, 15W, 25W, 40W, and all the way up to the likes of the r9-3950x. They just need to make a compelling case even if produced in a small batch. You never know how popular they could get.
    Reply
  • mode_13h - Thursday, June 23, 2022 - link

    I agree that by now, we should normally expect at least Zen2. However, I expect TSMC N7 production is still under too much strain to hit the volume/price targets AMD has in mind. Meanwhile, they probably still have that wafer supply agreement in place with GF, giving them easy access to 12 nm. Reply
  • Wereweeb - Thursday, June 23, 2022 - link

    Exciting? This is for a market that isn't willing to pay more for more performance. Underclocked 12nm Zen+ is OK for them, because cost per transistor is lower so they'll pay less for each IP block/feature that they include (E.g. for driving three 4K displays).

    It's why the Raspberry Pi is stuck with a 28nm chip despite being fanless - 28nm is simpler to fab than FinFET nodes, so it's still got the lowest transistor cost.

    If you want a powerful low-power machine, you go laptop or mini PC. There's not a market for powerful low-power SBC's. Consumers have no use for it, and anyone else would rather pay less for the hardware and let it pull more power (Resulting in more perf/$)
    Reply
  • mode_13h - Friday, June 24, 2022 - link

    > If you want a powerful low-power machine, you go laptop or mini PC.

    Due to supply chain issues, Pi is still stupidly expensive. For how much it costs, you'd do a lot better with one of the new RK3588 boards, finally starting to hit the market:

    https://www.cnx-software.com/2022/05/12/mekotronic...

    For less money and still better specs than a Pi (except limited to 4GB), there's ever the ODROID-N2+

    https://www.hardkernel.com/shop/odroid-n2-with-4gb...
    Reply
  • mode_13h - Friday, June 24, 2022 - link

    BTW, RK3588 is 4x A76 @ 2.4 GHz + 4x A55 @ 1.8 GHz. I think it could probably hold its own against a Tremont-powered laptop or mini PC.

    Here's one on a mini-ITX board, but it's marketed at industrial applications & therefore has a starting price of $459:

    https://en.t-firefly.com/product/industry/itx3588j
    Reply
  • Kangal - Friday, June 24, 2022 - link

    I disagree.
    If there is No Product, you cannot conclude there is No Demand. What AMD should have done is to setup a division which creates these high-end products. They can release these in a small batch (1,000 - 9,000 units), even give them away free, to staff, developers, influencers, and certain fans. Things like that do a lot of good-will and positive advertising.

    Once they do something like this, they can see if there is demand from consumers and vendors. Then they can look into making mass produced runs of specific chipsets. Again, AMD has a huge advantage to scale things up anywhere from 5W to 200W, and they should take advantage of it. It won't really hurt their bottom-line to invest a fraction of their silicon-allocation into these adventures.
    Reply
  • mode_13h - Friday, June 24, 2022 - link

    > What AMD should have done is to setup a division which creates these high-end products.

    I think you're trying to solve a different problem than AMD. I think these embedded products tend to be lower-margin, higher-volume. When their N7 production is constrained, they have a disincentive to use their existing wafer supply to service this market.

    > even give them away free, to staff, developers, influencers, and certain fans.
    > Things like that do a lot of good-will and positive advertising.

    I disagree.
    If there is No Product, you only hurt yourself by creating more Demand.

    As a consumer, if there's a product that I want to buy & I cannot get it, that only creates frustration. Case in point: Ryzen 3300X. Before the latest round of Zen 3 CPUs and Alder Lake i3's launched, this little CPU was the ultimate performance bargain. Unfortunately, it was only available for a short while, and then disappeared for years at a time! To those of us who wanted one, it was so frustrating to know that it existed but simply wasn't available.

    > Then they can look into making mass produced runs of specific chipsets.

    They already look into making mass produced runs of chiplets. That's their business, after all!

    > It won't really hurt their bottom-line to invest a fraction of their silicon-allocation
    > into these adventures.

    How do you know? Tell us: how big is this market, in terms of units sold annually. And if the market is so tiny that it wouldn't hurt to divert that many chips from their more profitable products, then you've got to ask whether it would be worth the overhead/NRE costs, as well as the distraction of attention and focus from more critical areas of their business.
    Reply

Log in

Don't have an account? Sign up now