AMD Ryzen 9 5980HS Cezanne Review: Ryzen 5000 Mobile Testedby Dr. Ian Cutress on January 26, 2021 9:00 AM EST
- Posted in
- Zen 3
- Ryzen 9 5980HS
- Ryzen 5000 Mobile
Since AMD’s introduction of its newest Zen 3 core for desktop users, the implementation for notebooks and mobile users has been eagerly awaited. In a single generation, on the same manufacturing process, AMD extracted +19% more performance per clock (we verified), so for any system that is power limited, extra performance is often very well received. AMD announced its new Ryzen 5000 Mobile processor family at the start of the year, with processors from 15W to 45W+ in the pipeline, and the first mobile systems coming to market in February. AMD sent us a peak example of Ryzen 5000 Mobile for today’s review, the 35W Ryzen 9 5980HS, as contained in the ASUS ROG Flow X13.
Ryzen 5000 Mobile: Eight Zen 3 cores and Vega 8 Graphics
For those that didn’t catch the original announcement a couple of weeks ago, here is a recap of the Ryzen 5000 Mobile family as well as the key points from the announcement.
The Ryzen 5000 Mobile processor series is an upgrade over last year’s Ryzen 4000 Mobile processor series. AMD co-designed both of these processor families to re-use key parts of the chip design, enabling a fast time-to-market and quicker upgrade cycle for AMD’s notebook manufacturing partners (OEMs), like Dell, HP, Lenovo, and others. The major difference between the two processors that most users will encounter is that the new hardware uses eight of AMD’s latest Zen 3 CPU cores, which is an upgrade over the eight Zen 2 cores from last year. The highlight is the +19% raw performance uplift when comparing the two at the same frequency.
Under the hood, there are a few more key changes that enthusiasts will be interested in. The new 8-core Zen 3 design shares a combined 16 MB L3 cache, which enables any of the eight cores to access the full cache, reducing latency to main memory (from 4 MB to 16 MB) compared to the previous design which had two clusters of four Zen 2 cores, each with 4 MB of cache.
The new processor is 180 mm2 in size, compared to 156 mm2 of last generation, but still fits into the same socket. It contains 10.7 billion transistors, which is up from 9.8 billion. This means an effective decrease in transistor density, although we know that Zen 3 cores are slightly larger than Zen 2 cores, and some additional security measures have been added (more on this on the next page).
AMD CEO Dr. Lisa Su Showcasing Ryzen 5000 Mobile at CES
Users may be upset that the new processor range only features Vega 8 graphics, the same as last year’s design, however part of the silicon re-use comes in here enabling AMD to come to market in a timely manner. The Vega 8 design in the previous generation already had a big boost in efficiency and frequency, and this time around we get another +350 MHz on the high-end. Users who want to see RDNA in a mobile processor may have to wait longer. AMD’s re-use strategy may lend itself to changing CPU one generation, GPU the next – we will have to wait and see.
There are other SoC changes, which we will get to later in this review.
The Ryzen 5000 Mobile family is split into two broad product ranges, but both ranges use the same underlying silicon. At the top is the traditional 45 W H-series processors, aimed at productivity notebook designs. For this generation, AMD is pairing the traditional 45 W parts with a range of 35 W ‘HS’ models, optimized for more efficient designs – this will be AMD’s second generation of 35 W ‘HS’ class processors. AMD is also introducing a new range of ‘HX’ processors at 45 W and above which will allow AMD’s partners to co-design high-performance and/or overclockable AMD notebook solutions.
|AMD Ryzen 5000 Mobile: H-Series|
|Ryzen 9 5980HX||8C / 16T||3300||4800||8||2100||45W+||Zen3|
|Ryzen 9 5980HS||8C / 16T||3000||4800||8||2100||35W||Zen3|
|Ryzen 9 5900HX||8C / 16T||3300||4600||8||2100||45W+||Zen3|
|Ryzen 9 5900HS||8C / 16T||3000||4600||8||2100||35W||Zen3|
|Ryzen 7 5800H||8C / 16T||3200||4400||8||2000||45W||Zen3|
|Ryzen 7 5800HS||8C / 16T||2800||4400||8||2000||35W||Zen3|
|Ryzen 5 5600H||6C / 12T||3300||4200||7||1800||45W||Zen3|
|Ryzen 5 5600HS||6C / 12T||3000||4200||7||1800||35W||Zen3|
When HS was introduced last year with Ryzen 4000 Mobile, it was an AMD-OEM partnership-only co-designed product requiring AMD approval in order to have access to them. This year however, they seem to be part of the full stack, indicating perhaps that demand for these HS designs was higher than expected.
The new HX models are here to enable high-end gaming, workstation, and desktop-replacement systems, as well as enabling vendors to supply overclockable laptops into the market with sufficient cooling provided. Overclockable laptops isn’t a new concept (Intel has been doing it a while), but it seems that AMD’s partners have requested higher power parts in order to enable this market on AMD. The official TDP for these processors is 45+ W, showcasing that partners can adjust the sustained TDP values north of 45 W if required, likely up to 65 W as needed. In the past, if OEMs wanted to go down this route, they would need to build a portable chassis capable of supporting a desktop processor.
There is some slight deviation from the regular H-series, in that there is no Ryzen 9 standard ‘H’ processor. The Ryzen 7 5800H will sit at the top of that particular market, but the way these numbering systems work means that the Ryzen 7 still has the full eight cores and fast integrated graphics. In that instance, Ryzen 9, with only HS and HX models, are arguably for more ‘specialist’ focused designs.
AMD is advertising the Ryzen 9 5980HS as the best processor for portable gaming performance, while the Ryzen 9 5980HX is ‘the best mobile processor for gaming’. As part of the launch day materials, AMD showcases the Ryzen 9 5980HS as scoring 600 pts in Cinebench R20, which would put it at the same level of performance as AMD’s desktop-class Zen 3 processors. We didn’t quite score 600 in this review with the R9 5980HS (we scored 578).
The traditional 15 W processors, used for ultra-thin and light portable notebooks, form part of the Ryzen 5000 Mobile U-series. AMD is enabling a number of parts with updated Zen 3 cores, but also introducing several processors based on the older Zen 2 design, albeit with updates.
|AMD Ryzen 5000 Mobile: U-Series|
|Ryzen 7 5800U||8C / 16T||1900||4400||8||2000||15W||Zen3|
|Ryzen 5 5600U||6C / 12T||2300||4200||7||1800||15W||Zen3|
|Ryzen 3 5400U||4C / 8T||2600||4000||6||1600||15W||Zen3|
|Ryzen 7 5700U||8C / 16T||1800||4300||8||1900||15W||Zen2|
|Ryzen 5 5500U||6C / 12T||2100||4000||7||1800||15W||Zen2|
|Ryzen 3 5300U||4C / 8T||2600||3800||6||1500||15W||Zen2|
The simple way to identify this is with the digit after the number 5. Even digits (5800, 5600, 5400) are based on Zen 3, whereas odd digits (5700, 5500, 5300) are the updated versions of Zen 2. A lot of users will consider these latter processors identical to the previous generation, however we have learned that there are a number of key differences which we will cover in a separate article.
Nonetheless, AMD is promoting the top Ryzen 7 5800U as the company’s most efficient mobile processor to date. Based on a number of enhancements to the silicon design, AMD is claiming a +2hr battery life from a simple processor swap from Ryzen 4000 to Ryzen 5000, even if everything else in the chassis is the same. Nonetheless, AMD is stating that it has worked with controller companies, power delivery suppliers, and notebook designers in order to ensure that those OEMs that want to build systems with more than 20+ hours battery life have the tools to do so. Other OEMs however, particularly for low cost designs or perhaps education models, can freely change the processor from old to new with only a firmware update, as both Ryzen 4000 and Ryzen 5000 are pin compatible.
Overall AMD is claiming 150+ designs with Ryzen 5000 Mobile so far, a significant step up from the 100 designs on Ryzen 4000 Mobile. These are set to include high-end gaming designs with the latest premium graphics cards, a market that AMD has had difficulty breaking into so far.
|AMD Generation Code Names|
|Cezanne||Ryzen 5000 Mobile||8 x Zen 3||Vega 8||TSMC N7|
|Lucienne||Ryzen 5000 Mobile||8 x Zen 2||Vega 8||TSMC N7|
|Renoir||Ryzen 4000 Mobile||8 x Zen 2||Vega 8||TSMC N7|
|Picasso||Ryzen 3000 Mobile||4 x Zen+||Vega 11||GF 12nm|
|Raven Ridge||Ryzen 2000 Mobile||4 x Zen||Vega 11||GF 14nm|
|Dali||Athlon 3000||2 x Zen||Vega 3||GF 14nm|
|Pollock||?||2 x Zen||Vega 3||GF 14nm|
|Vermeer||Ryzen 5000||16 x Zen 3||-||TSMC N7|
|Matisse||Ryzen 3000||16 x Zen 2||-||TSMC N7|
|Pinnacle Ridge||Ryzen 2000||8 x Zen+||-||GF 12nm|
|Summit Ridge||Ryzen 1000||8 x Zen||-||GF 14nm|
|Genesis Peak||'4th Gen'||Zen 3||-||?|
|Castle Peak||Threadripper 3000||64 x Zen 2||-||TSMC N7|
|Colfax||Threadripper 2000||32 x Zen+||-||GF 12nm|
|Whitehaven||Threadripper 1000||16 x Zen||-||GF 14nm|
|Genoa||'4th Gen'||Zen 4||-||?|
|Milan||EPYC 7003||64 x Zen 3||-||TSMC N7|
|Rome||EPYC 7002||64 x Zen 2||-||TSMC N7|
|Naples||EPYC 7001||32 x Zen||-||GF 14nm|
Here is a handy table of processor codenames we might use at various parts of these review. These refer to AMD’s internal codenames for the silicon designs, and act as an easier way to talk about the hardware without constantly referring to the branding (especially if certain silicon is used in multiple product ranges).
Testing AMD’s Claims: The Notebook
For this review, AMD supplied the Ryzen 9 5980HS inside the ASUS ROG Flow X13 laptop. It is one of AMD’s key design wins, with a 35 W-grade processor in a sleek design aimed for mobility. As a reviewer who in a normal year spends a lot of time travelling, the specifications on the box make a lot of sense to my regular workflow.
The system features a 13.4-inch 360º hinged display, which as an IPS touchscreen with a 3840x2400 resolution (16:10, finally) running at 120 Hz with adaptive sync, Pantone color certified, and coated in Corning Gorilla Glass. The display is rated for 116% sRGB, 86% Adobe, and 85% DCI-P3.
Under the hood is that AMD Ryzen 9 5980HS processor, with eight Zen 3 cores and sixteen threads, with a 3.0 GHz base frequency and a 4.8 GHz single core turbo frequency, rated at 35 W. ASUS says that they buy the best versions of the 5980HS for the Flow X13 to ensure the best performance and battery life. This processor has Vega 8 graphics, however ASUS has paired it with a GTX 1650 4 GB discrete graphics processor, enabling CUDA acceleration as well as higher performance gaming when needed.
Our unit comes with 32 GB of LPDDR4X-4267 memory, as well as a Western Digital SN350 1TB PCIe 3.0 x4 NVMe storage drive. Both of these would appear to be the standard install for the Flow X13.
ASUS claims the 62 Wh battery is good for 18 hours of use, and the Flow X13 is one of a handful of devices that supports 100 W USB Type-C power delivery. ASUS claims the bundled charger can charge the unit from 0% to 60% in around 39 minutes.
Other features include a back-lit keyboard with consistently sized arrow keys, a full-sized HDMI output as well as a USB 3.2 Gen 2 (10 Gbps) Type-A port, a USB 3.2 Gen 2 (10 Gbps) Type-C ports, a 3.5 mm jack, and a custom PCIe 3.0 x8 output connector for use with ASUS’ XG Mobile external graphics dock. This custom graphics dock can come with a custom designed RTX 3070/3080, and along with graphics power also provides the system with four more USB Type-A ports, HDMI/DP outputs, and Ethernet. With this dock installed, technically the system would have three graphics cards.
All of this comes in at 2.87 lbs / 1.30 Kg, all for under 16mm thick. This is often a key category for both AMD and Intel when it comes to mobility combined with productivity. ASUS has not announced pricing of the ROG Flow X13 yet – the other model in the range is based on the Ryzen 9 5900 HS, but is otherwise identical.
This review is going to be mostly about the processor rather than the Flow X13, due to time constraints (our sample arrived only a few days ago). However, it is worth noting that as with most notebooks, the ROG Flow X13 comes with multiple power and performance modes.
In fact, there are two: Silent and Performance. In each mode there are different values for idle temperature, in order to keep the any audible noise lower, and then different values for power/thermals for turbo and sustained power draw.
These two differ primarily in the sustained power draw and thermal limits:
|ASUS ROG Flow X13 Power Options|
|Silent||70ºC||65 W||42 W||85ºC||6 sec||15 W @ 68ºC|
|Performance||65ºC||65 W||42 W||85ºC||120 sec||35 W @ 75ºC|
*The idle temperature here is so high, as you'll see later in the review, because AMD's high-frequency levers are very aggressive such that our sensor monitoring tools are activating high frequency modes, despite the small load.
Testing AMD’s Claims: The Ryzen 9 5980HS
Similar to the launch of Ryzen 4000 Mobile, the unit AMD has supplied us is their top of the line but most efficient H-series processor. For the last generation it was the Ryzen 9 4900HS found in the ASUS ROG Zephyrus G14. The Zephyrus G14 is slightly bigger than the ROG Flow X14 we have today, but the GPU is also better on the G14 (2060 vs 1650). Both processors are rated at 35 W, and both showcase some of the best design AMD wants to lead with at the start of a generation.
The main competition for these processors is Intel’s Tiger Lake. A couple of weeks ago Intel announced its new line of H35 processors, whereby they boost the 15 W U-series processors up to 35 W for additional performance. We have no word on when those units will be in the market (we are told soon), however we have managed to secure an MSI Prestige 14 Evo which contains Intel’s best U-series processor (Core i7-1185G7) and allows for sustained performance at 35 W.
|Device||ASUS ROG Flow X13||ASUS ROG Zephyrus G14||Intel Reference Design||MSI Presige 14 Evo|
|CPU||R9 5980HS||R9 4900HS||i7-1185G7||i7-1185G7|
|IGP||Vega 8||Vega 8||Iris Xe 64||Iris Xe 64|
|dGPU||GTX 1650||RTX 2060||-||-|
PCIe 3.0 x4
PCIe 3.0 x4
PCIe 3.0 x4
PCIe 3.0 x4
Alongside these numbers we also have historical data from Intel’s Tiger Lake reference platform which ran in 15 W and 28 W modes.
But first, let us discuss the new features in Ryzen 5000 Mobile.
Post Your CommentPlease log in or sign up to comment.
View All Comments
Meteor2 - Thursday, February 4, 2021 - linkGreat point.
ikjadoon - Tuesday, January 26, 2021 - linkIt's great to see AMD kicking Intel's butt in a much larger market (i.e., laptops vastly outsell desktops): AMD really should be alongside, or simply replacing, Intel in most premium notebooks. Gaming notebooks are not my cup of tea, but glad to see for upcoming 15W Zen3 parts.
Will we see actual, high-end Zen3 notebooks? Lenovo, HP, ASUS, Dell: for shame if you keep ramming toasty Tiger Lake down customers' throats. Lenovo's done some great offerings with both AMD & Intel; that means some compromises with notebook design (just go all AMD, man; if/when Intel is on top, switch back!), but beefier cooling for Intel will also help AMD.
Still, overall, I don't see anything convincing me that x86 is really right for notebooks, either. So much waste heat...for what? The M1 has rightly rejiggered expectations: 20 hours on 150 nits should be ordinary, not miraculous. Limited to no fan spin-up and max CPU load should yield a chassis maximum of 40C (slightly warmer than body temperature). And, all the while with class-leading 1T performance.
As this is a gaming laptop, it's not too relevant to compare web benchmarks (what most laptops do), but this is peak Zen3 mobile and it still falls quite short:
35W Ryzen 5980HS: 102 points (-57%)
125W i9-10900K: 119 points (-49%)
35W i7-1185G7: 128 points (-46%)
105W Ryzen 5950X: 140 points (-40%)
30W Apple M1: 234 points
You can double / triple x86 wattage and still be miles behind M1. I almost feel silly buying an x86 laptop again: just kilowatts of waste heat over time. Why? Electrons that never get used, just exhausted and thrown out as soon as possible because it'll throttle even worse otherwise.
but not being enough you are comparing those in single thread so here you are comparing 1/16 of the 5950hs vs 1/4 of the m1
a 128core epyc or a 64core threadripper probably will be even worse in this single threaded benchmark ( because those are levaring threads and are less efficient in single threaded app )
if you like wrong calculations then 1 core of the 15w version use less tha 1w for what result ? ~ 100 points ? so who is wasting electrons here ?
( btw 1 core doesn't use 1/16 because there are boosts , but it's even less wrong than your comparison )
ZoZo - Tuesday, January 26, 2021 - link128-core EPYC? Where?
His comparison is indeed misleading in terms of energy efficiency, but it's sad that no x86 is able to come even close to that single-threaded performance.
WaltC - Tuesday, January 26, 2021 - linkDoubly sad for the M1 that we are living in the multicore/multithread era...;)
ikjadoon - Tuesday, January 26, 2021 - linkThe energy efficient comparisons are pretty clear: the best x86 (Zen3) has stunningly lower IPC than M1, which barely cracks 3 GHz. The only way to make up for such a gulf in IPC is faster clocks. Faster clocks require the 100+W TDPs so common in high-performance desktop CPUs. It's why Zen3 mobile clocks so much lower than Zen3 desktop (3-4 GHz instead of 4-5 GHz)
A CPU that needs 3x power to do the same work (and do it slower in most cases) must exhaust an enormous amount of heat, when considering nT or 1T benchmarks (Zen3 requires ~20W for 5 GHz boost on a *single* core). Look at those boost power consumption measurements.
Specifically in desktops (noted in my comparison about tripling TDP...), the CPU *alone* eats up an extra 60 to 90 watts during peak usage. Call it +20W average continuously, so we can do the math.
20W x 8 hours x 7 days a week = +1.1 kWh excess exhaust heat per week. x86 had two corporate giants to do better. It's been severely litigated, but that's Intel's comeuppance. If Intel can't put out high-perf, high-efficiency x86 architectures, then people will start to feel less attached to x86 as an ISA. x86 had billions and billions and billions of R&D.
I see no reason for consumers to religiously follow x86 Wintel or Wintel-clones in laptops especially, but desktops, too: where is the efficiency going to be coming from? Even if Apple *had flat 1T* for the next three years, I'd still feel more optimistic about M1-based CPUs in the long-term than x86.
Dug - Tuesday, January 26, 2021 - link"I see no reason for consumers to religiously follow x86 Wintel or Wintel-clones in laptops especially, but desktops, too: where is the efficiency going to be coming from?"
Software, and getting work done. M1 is great and all, but just need to convince the boss that Apple or 3rd party has software available for our company....... Nope, oh well.
For personal use, people aren't going to spend thousands of dollars to get new software on new platform.
They can't play games (or should I say they can't play a majority), which is probably the largest market.
They can't change anything about their software
They can't customize anything.
They can't upgrade any piece of their hardware.
They don't have options for same accessories.
So I'll go ahead and spend the extra $15 a year on energy to keep Windows.
Spunjji - Thursday, January 28, 2021 - link"A CPU that needs 3x power to do the same work"
It doesn't. It's been demonstrated a few times now that if you scale back Zen 3 cores to similar performance levels to M1, M1's perf/watt advantage drops to about 30%. It's still better than the node advantage alone, but it's not crippling, and M1 is simply not capable of scaling up to the clock speeds required to match x86 on desktop / HPC workloads.
They're different core designs matched to different purposes (ultra-mobile first vs. server first) and show different strengths as a result.
M1 is a significant achievement - no doubt about it - but you're *massively* overstating the case in its favour.
GeoffreyA - Friday, January 29, 2021 - linkThank you for this.
Meteor2 - Thursday, February 4, 2021 - link"M1 is simply not capable of scaling up to the clock speeds required to match x86 on desktop / HPC workloads" ...Yet. In a couple of years x86 will be behind ARM across the board.
Fastest HPC in the world is ARM *right now*. Only the fifth fastest is x86.