Friday, February 18th 2022

AMD Zen3+ Architecture and Ryzen 6000 "Rembrandt" Mobile Processors Detailed

AMD on Thursday unveiled its Ryzen 6000 series "Rembrandt" mobile processors. The company claims these chips offer generational increases in CPU performance, along with big leaps in energy-efficiency and integrated graphics performance. At the heart of these processors is the new 6 nm "Rembrandt" silicon that the company is building on the TSMC N6 silicon fabrication node that leverages EUV lithography.

The "Rembrandt" silicon broadly combines an 8-core/16-thread CPU based on the new Zen 3+ microarchitecture, a large new iGPU based on the RDNA2 graphics architecture, complete with real-time ray tracing support; a DDR5 + LPDDR5 memory controller, and a full PCI-Express Gen4 root-complex. The iGPU, memory interface, and PCIe interface are generational updates over the previous-gen "Cezanne," and it may seem like the CPU is largely unchanged, but AMD claims there are several optimizations that have gone into the CPU to earn the "+" tag.
The biggest engineering investment with "Rembrandt" is its ground-up power-management redesign that heavily leverages power-gating (as opposed to clock-gating). Every major component on the processor, including the individual CPU cores, the individual iGPU compute units, the memory controllers, and the display controller, can be put to sleep through power-gating (cutting their power), and woken up, in millisecond timescale. This allows the processor to use fraction-of-a-second opportunities within your normal use (such as a still screen when reading a document or a web-page), to put select components to sleep. These "power-naps" have a compounding effect on power efficiency, and AMD claims significant battery-life improvements.
The power-optimization of "Rembrandt" is achieved by adopting a five-pronged approach. The first of course is the energy-efficiency gains obtained from the switch to the 6 nm process, which yields a roughly 18% transistor density gain, and improvements with iso-power. The second is optimizations to the CPU microarchitecture, with fine-grained power-gating of individual cores within the CPU. The third includes the SoC-level power optimization that introduces several new power-planes, deep-partitioning of components that allows pretty much all redundant/scalable components to be turned off when not needed. The fourth is firmware-level optimization. The system firmware now has greater interactivity with the OS to understand the nature of the performance demand. And lastly, at the platform-level, AMD works with notebook OEMs to choose the most efficient discrete components that make up the system, along with AMD Advantage device co-engineering.
The new Zen 3+ CPU core comes with over 50 new or updated features over Zen 3. Eight of these key enhancements are a re-engineering of all design-elements to allow for better power leakage; a hardware-assisted wake from sleep, called PC6 Restore; de-coupled L3 cache initialization to allow for faster wake times; per-thread UEFI CPPC capability (as opposed to per-core in the previous-generation); several cache-level power optimization, including the ability to disallow power-down of caches if there are too many cache misses (which saves power in the long run from having to wake up the cache); a granular peak-current control that ramps power as needed instead of an "all-or-nothing" power-up of components; intelligent CPU Core wake sequence that takes into account usage patterns before sleep; and the new Enhanced CC1 state that puts cores to sleep based on low utilization. The "Rembrandt" silicon has one Zen 3+ CCX (CPU core complex) with 8 CPU cores. Each of these has 32 KB of L1I and 32 KB of L1D caches; a dedicated 512 KB L2 cache, and share a 16 MB L3 cache.
The SoC-wide power optimizations include C-states for Infinity Fabric, the interconnect that binds all the components on the SoC. Infinty Fabric clock and bandwidth now scales with workload. The processor now has the ability to reduce SoC-wide power draw by 99%, keeping just the display on in self-refresh mode. The memory controllers, too, can be turned off, leaving the DDR5 memory running in self-refresh. The fast sleep and restore accelerators provide the largest chunk of AMD's power optimization, so individual components can be put to sleep and woken up in millisecond intervals. These include the CPU cores, the iGPU CUs, the Infinity Fabric, the memory controller, and display engine. Platform-level power optimization incorporate power savings from the use of LPDDR5 memory, displays with less than 1 W power draw, panel self-refresh capability, where in power is saved in display data transmission if there's nothing new on the screen, and panel delta updates (the ability to refresh only select regions of the panel (eg: the one that's displaying a real-time clock or system notifications).

AMD introduced several firmware-level power optimizations. The system firmware now works along with drivers to achieve greater interoperability with the OS to help with management of power, performance, thermals, and acoustics relative to every workload scenario. Windows 11 does away with slider-based power-performance scaling, and so AMD's power management works in the background to automatically scale performance to your needs.

The company works with notebook manufacturers to introduce several display panel-level power-optimizations, including support for new Z-power states, which give the platform the ability to completely power down the display controller; getting OEMs to use new SVI3 voltage regulator for display panels; various device design optimizations from AMD Advantage co-engineering; support for new-generations of display panels with typical power-draw under 1 W; and the new AMD FreeSync PSR-SU (panel self-refresh and selective-update) technology.

FreeSync PSR-SU dynamically brings down refresh-rate to sync with what's being displayed on screen. If there's a 24 FPS video playback, panel refresh-rate is brought down to match the frame-rate. Selective update allows different regions of the display to update at a different rate. Display Stream Compression and Forward Error Correction (DSC and FEC) are leveraged to reduce the number of embedded DisplayPort TMDS lanes, resulting in additional power savings.
The PCI-Express interface sees an update to PCI-Express Gen4 spec. The processor now puts out 8 PCI-Express Gen 4 lanes toward a discrete GPU, 4 Gen4 lanes toward a CPU-attached M.2 NVMe SSD, and the remaining 4 lanes toward chipset-bus.

The Radeon 600M series integrated graphics solution leverages the company's latest RDNA2 graphics architecture. It features 12 compute units amounting to 768 stream processors, 48 TMUs, 16 ROPs, and 12 Ray Accelerators. The only things setting this iGPU apart from the discrete Radeon RX 6400 is its ROP count (16 vs. 32), lack of Infinity Cache, and lack of dedicated memory. There are two iGPU models based on the number of CUs enabled. The Radeon 680M comes with all 12 CUs enabled, while the Radeon 660M has 6 of them enabled (amounting to 384 stream processors).

AMD claims that when combined with the right settings, and FidelityFX Super Resolution (FSR), the Radeon 680M provides sufficient performance for 1080p gaming, while the 660M should provide enough for today's visually-intensive non-gaming accelerated workloads. The Video CoreNext (VCN) component is the same as the one found in RX 6800-series discrete GPUs, and provides hardware-accelerated decoding of 10-bit AV1, VP9, and HEVC.

When it comes to gaming performance, AMD claims a nearly 2X performance lead over the Xe LP-based Iris Xe iGPU powering the Core i7-1185G7, which has 96 EUs. AMD is also claiming performance in the league of the GeForce GTX 1650 Max-Q "Turing" discrete GPU, which means it is already beating most GeForce MX series discrete GPUs found in entry-level gaming notebooks. For enthusiast-segment gaming notebooks, AMD is pushing the Radeon RX 6800S as the discrete GPU of choice, squaring off against the combination of the previous-generation Ryzen 9 5900HS and RTX 3080 Laptop GPU.

AMD is debuting the Ryzen 6000 series with 10 processor models, which include two models for the Thin-and-Light segment (15 to 28 W), four models for the Thin Enthusiast segment (35 W class), and four for the Ultra Enthusiast (45 W and >45 W) category. All segments have 8-core/16-thread SKUs across the Ryzen 7 series. The 35 W and 45 W segments include Ryzen 9 SKUs with higher clock-speeds; The Ryzen 5 series are 6-core/12-thread parts across all segments.
AMD is claiming a 2.62X lead over the Core i9-12900HK "Alder Lake" processor in CPU performance-per-Watt, measured using Cinebench R20 nT. The Ryzen 9 6900HS scored 5733 points in this test, compared to 6894 points for the i9-12900HK (the Intel chip is 20% faster). AMD boasts about the fact that in comparable categories of 28 W, AMD offers 8 performance cores, compared to Intel's P-core count of 6, whereas Intel 15 W category chips only have 2 P-cores and rely heavily on the E-core clusters.

The 15 W AMD Ryzen 7 6800U with its 8-core/16-thread CPU posts big performance gains over the previous-generation 5800U, as well as Intel's previous-generation i7-1185G7 "Tiger Lake-U" processor, which is a 28 W-category chip. The 6800U can be configured for 28 W, where it posts even higher performance across a number of use-cases.

The Ryzen 9 6900HX isn't even the top part from this series, but is shown to post anywhere between 8% to 47% performance leads over the 8-core/16-thread Core i9-11980HK, the previous-generation flagship based on the 8-core "Tiger Lake" silicon.

And lastly, AMD is claiming up to 24 hours of battery life for its 15 W-class and 28 W-class notebooks, which culminates its power-optimizations, Adaptive Power Control framework, and the 6 nm silicon fabrication process.

Performance and Efficiency Claims by AMD
AMD summarizes the various I/O capabilities of "Rembrandt" in this slide. The chip supports 40 Gbps-capable USB4 without the need for discrete controllers, PCI-Express 4.0 for discrete graphics as well as CPU-attached NVMe; DDR5 and LPDDR5 memory support; the latest generation AMD+MediaTek WiFi 6E + Bluetooth LE 5.2 wireless interfaces; Microsoft Pluton-based feature-rich TPM, the latest generation display outputs including HDMI 2.1 and DisplayPort 2.1, and acceleration for the latest video formats.

The complete AMD slide-deck follows.
Add your own comment

56 Comments on AMD Zen3+ Architecture and Ryzen 6000 "Rembrandt" Mobile Processors Detailed

#1
tabascosauz
12CU RDNA2, 16 ROPs...I like where this is going. What Cezanne should have been; finally the GPU doesn't look like a tiny afterthought on the floorplan. Looking forward to seeing this silicon come to desktop.
Posted on Reply
#2
Selaya
i was under the impression that the vega 8's about as high as it'll get for ddr4 like, any more powerful would've just been memory bandwidth starved?
so yeah, 12cu rdna2 sounds like the natural progression for ddr5
Posted on Reply
#3
R0H1T
tabascosauzLooking forward to seeing this silicon come to desktop.
Not coming to desktop because it only has (lp)ddr5 support so at best maybe an NUC like thing with BGA.
Posted on Reply
#4
Crackong
It is a blood bath to those unreleased low power Alder Lake SKUs

Posted on Reply
#5
tabascosauz
Selayai was under the impression that the vega 8's about as high as it'll get for ddr4 like, any more powerful would've just been memory bandwidth starved?
so yeah, 12cu rdna2 sounds like the natural progression for ddr5
We had Vega 11 in Raven Ridge and Picasso, but crippled with 8 ROPs. AMD die shrunk and took away 3 CUs and compensated with 2GHz clock. Even when OC'd the GPU domain barely gets lukewarm, they had the space/thermal/power envelope for it. For OEM and laptops sure, but on desktop 7nm Vega doesn't have a bandwidth problem if you know what budget sticks to go for. It was just a matter of saving a buck by recycling most of Renoir as they felt no need to do any more.
R0H1TNot coming to desktop because it only has (lp)ddr5 support so at best maybe an NUC like thing with BGA.
I was referring more to the new GPU that's going to be new standard, CPU is what GPU was for Cezanne, power optimization only. And lack of DDR4 support doesn't mean it's never coming, we're not going to be chained to hybrid IMCs forever.
Posted on Reply
#6
Selaya
i see, makes sense
Posted on Reply
#7
Wirko
CrackongIt is a blood bath to those unreleased low power Alder Lake SKUs
Hah, noble men's blue blood versus commoners' red blood. But it's closer to the truth that both will be very competitive (and both will sometimes bleed through the nose).
Posted on Reply
#8
R0H1T
tabascosauzAnd lack of DDR4 support doesn't mean it's never coming, we're not going to be chained to hybrid IMCs forever.
It kind of does unless you think they're releasing another set of boards for AM4 past x570 or B550.

Come again?
Posted on Reply
#9
Valantar
R0H1TIt kind of does unless you think they're releasing another set of boards for AM4 past x570 or B550.

Come again?
Given that AMD is releasing a DDR5-capable desktop platform this year I don't see an issue with these coming to desktop at some point - they just won't come to AM4-based desktop. So no hybrid IMC needed, just an updated platform that we already know is coming in H2 (and most recently rumored for Q3 with a Computex launch/announcement, though that is obviously unconfirmed).
tabascosauz12CU RDNA2, 16 ROPs...I like where this is going. What Cezanne should have been; finally the GPU doesn't look like a tiny afterthought on the floorplan. Looking forward to seeing this silicon come to desktop.
Yep, this looks very promising. Promising enough that it's making me have some second thoughts about my Steam Deck preorder. That definitely has its advantages, but also its drawbacks. a 28-35W laptop with one of these 12CU chips in it would be a very, very interesting proposition. It'll also be fantastic for next-gen HTPCs and SFF APU builds.

I'm also curious how these will look when paired with the new 6400M and 6500M GPUs - the 25W 6400M seems like it wouldn't really outperform a 680M, so I guess that's meant for Ryzen 5 chips, but the 35-50W 6500M would certainly be an interesting comparison to the 680M. Likely a decent bit faster, but worth the extra power draw and board space needed?


Overall though, I'm almost as interested in the power savings here as in the iGPU improvements - if they can live up to those promises, that bodes very well for highly performant, compact laptops that still deliver on performance. The early reviews on the Zephyrus G14 (6900HS + RX 6800S) are certainly quite impressive, though most note a battery life regression from the previous generation even under light loads, which is a bit worrying. Hopefully that's just down to early firmware and software.

I'm also very much looking forward to a future where most (all? yes please!) laptops have FreeSync displays that scale down to 24Hz (and, of course, 30Hz as well). This will be excellent for both low-end iGPU gaming and power savings in regular usage.
Posted on Reply
#10
R0H1T
ValantarGiven that AMD is releasing a DDR5-capable desktop platform this year I don't see an issue with these coming to desktop at some point - they just won't come to AM4-based desktop.
You mean release it to an LGA based AM5 socket? I mean how trivial is it to add desktop support & move to an LGA (desktop) socket given ~

a) They'll generally have higher margins in the notebook space.

b) Demand will be much much more there!

So no I don't expect AMD to launch these on AM5 this year or possibly add support in 2023, when zen4 would already be a quarter or two on the market.
Posted on Reply
#11
Shatun_Bear
CrackongIt is a blood bath to those unreleased low power Alder Lake SKUs

The difference in efficiency and gaming performance is hugely in favour of the AMD laptop yet the difference in absolute all-cores stressed performance seems imperceptibly ahead for the Intel.

Huge win for the 6000-series, battery life seems amazing compared to 5000.
Posted on Reply
#12
Valantar
R0H1TYou mean release it to an LGA based AM5 socket? I mean how trivial is it to add desktop support & move to an LGA (desktop) socket given ~

a) They'll generally have higher margins in the notebook space.

b) Demand will be much much more there!

So no I don't expect AMD to launch these on AM5 this year or possibly add support in 2023, when zen4 would already be a quarter or two on the market.
Well, first off none of what you just said is equal to "these will never come to desktop". "They will be late" or "other markets are more attractive" are in no way identical to that statement, nor are they causally deterministic in any way that would lead to that necessarily being true. Also, what you're saying here has been true for literally every generation of AMD Ryzen APU. There's no change there. Sure, they're getting more laptop design wins, but they're also producing a lot more and have a lot more DIY mindshare (=desktop sales), so those all roughly equalize. There's no reason to expect that we won't see these hit AM5 desktops in a somewhat reasonable timeframe. Remember, previous desktop APUs have also launched 6-9 months after their mobile counterparts - exactly due to what you say here, with mobile being a much larger market with much higher demand. They've still come to desktop. Even the 4000-series, which never saw a consumer release, saw relatively wide adoption in OEM desktops on AM4. So again, there's no reason to not expect these to hit AM5 desktops towards the end of this year. Heck, they might even launch simultaneously, given how AMD has been pushing the 5000G series as their lower-tier 5000-series alternative for AM4.
Posted on Reply
#13
Turmania
With the pricing of these ddr5 modules. It just does not make sense to go ddr5 route for now at least.
Posted on Reply
#14
DeathtoGnomes
WirkoHah, noble men's blue blood versus commoners' red blood. But it's closer to the truth that both will be very competitive (and both will sometimes bleed through the nose).
IDK about competitive, its more like gamers vs the average joe. Gamers will buy accordingly, Intel according to the video.
Posted on Reply
#15
persondb
It's actually 32 ROPs, each of the RB+ can do 8 pixels/clk so it's 32 pixels/clk in total.
Posted on Reply
#16
Valantar
TurmaniaWith the pricing of these ddr5 modules. It just does not make sense to go ddr5 route for now at least.
DDR5 is going to drop rapidly in price as more platforms adopt it and production starts to scale. RAM is always expensive for the first platform to use it, and DDR5 is no different than DDR4 or DDR3. There weren't as many scalpers back then, but scalpers won't even remotely be able to keep up with the mass-scale DDR5 distribution that will come in the next 6-12 months.
Posted on Reply
#17
trsttte
I really wished they kept ddr4 support and could bring this to AM4, it could have been the true swan song for the platform instead of the 5800X3D that is looking to be mostly disappointing. I know i know, AM4 had a good run, but a person can always dream.

It will be interesting to see what AM5 launches with, there's little information on how the line up will look like but there's a lot of talk about Zen 4 having some compute units either in the IO die or some chiplet and APUs are destined to move to a modular design instead of the current monolithic dies, with how long it will take for something like this to come to the desktop AM5 is anyones guess, there may be no reason to, after all it's zen3+ and not zen4, why adapt it to fit into the AM5 platform when they can move forward with whatever plans they have for future APUs? (only reason I can see is prebuilts that certainly want new material to market asap)
Posted on Reply
#18
Chrispy_
I'm eagerly anticipating real-world IGP testing of a 15-28W R7 6800U or a 35W R7 6800HS.

This is, without a doubt, the sweet spot and may be the first time in a very long time that gaming on battery power isn't cut short halfway through a short-haul flight.
Posted on Reply
#19
Daven
So the current state of laptops is as follows:

Apple M1 Max/Pro - best performance and efficiency but you have to be willing to work in the MacOS ecosystem
Intel Alder Lake Mobile + Nvidia 3000 mobile - best desktop replacement at the expense of efficiency
AMD 6000 mobile - best all round laptop SoC

Special mention goes to an AMD 6000 mobile + AMD 6000S mobile GPU
Posted on Reply
#20
Assimilator
LMAO @ AMD randomly changing the CPUs they compare to... first they start off against the current-gen 12900HK, then they use previous-gen CPUs. Dishonest much? Oh well, at least they finally got USB4.

I guess this also means that AMD is keeping up its tick-tock approach to laptop vs mobile GPUs. Tick = desktop CPU with new microarchitecture, tock = mobile CPU with revised microarchitecture.
Posted on Reply
#21
Pumper
AssimilatorLMAO @ AMD randomly changing the CPUs they compare to... first they start off against the current-gen 12900HK, then they use previous-gen CPUs. Dishonest much?
Not to mention that when they compare it to 12900, they are using the max 110W OC TDP on the Intel vs base 35W TDP on AMD to show how much more efficient AMD is.
Posted on Reply
#22
TechLurker
I wish the CPU-side improvements were also brought to AM4 Desktop in a 6000 refresh of the 5000 series, or even just select, high-selling versions, then just slap on the 3D Cache on the "6800X3D" and "6950X3D" versions. Basically, depart the AM4 platform with the best optimized CPUs one could buy for the platform as they shift everything over to AM5.
Posted on Reply
#23
Chrispy_
TechLurkerI wish the CPU-side improvements were also brought to AM4 Desktop in a 6000 refresh of the 5000 series, or even just select, high-selling versions, then just slap on the 3D Cache on the "6800X3D" and "6950X3D" versions. Basically, depart the AM4 platform with the best optimized CPUs one could buy for the platform as they shift everything over to AM5.
the CPU-side improvements mostly target efficiency and on desktop that's really not as much of a concern since AMD are already winning that race comfortably and with 350W GPUs saving 50W on a CPU seems like wasted effort.
Posted on Reply
#24
phanbuey
I like it when marketing starts mysteriously moving generations of CPUs around... usually a sign that competition is coming back.
Posted on Reply
#25
TechLurker
Chrispy_the CPU-side improvements mostly target efficiency and on desktop that's really not as much of a concern since AMD are already winning that race comfortably and with 350W GPUs saving 50W on a CPU seems like wasted effort.
I know that deep down; but still, I'd love it more for the theoretical that one could build a small home server that can more intelligently idle down when no one's home, or even leave a personal PC on but idling for longer stretches. Basically, that extra efficiency providing a little more savings on almost-always on systems, where the savings are counted over longer stretches of time rather than for mobility/portability reasons.
Posted on Reply
Add your own comment
Dec 18th, 2024 00:44 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts