AMD Ryzen 9 4900HS Review

Mobile computing has become the adjacent big target at AMD with its new serial of Ryzen 4000 APUs. The new processors will arrive as the U-series for low-power and ultraportables and the H-serial for high functioning laptops. Today we have the first retail Ryzen 4000 laptop on the market to evaluate, so the focus volition be on the benchmarks, so we tin can see for the first time how Zen 2 brought across to mobile stacks upward against Intel's tried and true line-upwardly.

All Ryzen 4000 APUs are based on the Zen ii architecture, built using 7nm technology with a monolithic dice that likewise incorporates a Vega-based GPU. Earlier this month we published a full breakdown of Ryzen 4000 APUs, detailing some of its architectural features and specs. Nosotros'll skip most of those details in this review, just you should definitely bank check that out for an overview of what else is coming in 2020.

Just to be articulate, Ryzen 4000 parts do non use AMD'due south Zen 3 architecture. The naming is a trivial confusing hither – Ryzen 3000 for Zen two desktop fries, and Ryzen 4000 for Zen 2 APUs – only this is but a continuation of what AMD started in 2017 when they launched the beginning Zen APUs equally Ryzen 2000. Ryzen 4000 APUs are thus based on Zen 2 cores, aforementioned as the latest Ryzen desktop CPUs.

Information technology'south no coincidence Ryzen Mobile U and H serial mirror what Intel offers for unlike types of laptops. With ultraportables release all the same pending, today is all near the powerful H-series and how AMD volition fare for content creation, productivity and gaming.

AMD'south Ryzen 4000 H-series consists of three distinct SKUs: the Ryzen v 4600H delivers vi cores and 12 threads for the mainstream, the Ryzen seven 4800H bumps that up to 8 cores and sixteen threads, alongside a college-clocked 8-core variant in the Ryzen nine 4900H. All of these APUs come with a 45W TDP, and are complemented past a low ability 35W variant for laptops that besides adhere to the rest of AMD's HS-series design guidelines.

You'll also detect dissimilar GPU configurations for each SKU, using the refreshed Vega blueprint with upwardly to 8 compute units and higher clock speeds. Interesting to note, simply we'd look most H-series laptops to also include a detached GPU, like our test system. Cache, while listed at 12 MB, is actually a combined L2 and L3 figure: all parts accept 8 MB of L3 cache, Ryzen seven and 9 get 4MB L2, and Ryzen 5 gets 3MB.

The chip we're benchmarking today is the Ryzen 9 4900HS, a 35W SKU that provides slightly college base and heave clock speeds than the Ryzen 7 4800H that sits beneath information technology at 45W, a fleck of binning magic at play at that place. It's not the outright flagship APU in AMD'southward line-up, but it will give united states of america a really solid look at Ryzen 4000 performance. We'll also give y'all a sneak tiptop of Ryzen 7 4800H performance from an technology sample, as we wait to review the rest of processors in the line-up equally new laptops make it to market place.

Our benchmark testbed is the Asus Zephyrus G14, a dandy portable 14-inch gaming laptop that packs in Ryzen 4000 HS APUs and upward to GeForce RTX 2060 Max-Q graphics. Nosotros received the highest-spec model for testing, with the RTX 2060 Max-Q and the 4900HS, 16 GB of DDR4-3200 retentivity and a 1080p 120Hz display.

The focus on this review is purely CPU operation, so nosotros won't get into the design and other features of the Zephyrus G14. We will say this though, after a week of use nosotros think it's a very well built laptop, with a great keyboard and as nosotros're about to meet, very compelling performance in such a small course gene.

You'll besides come across across this review a number of different laptop CPUs in the charts and, at times, GPU configurations as well. The data in the charts is an average from the laptops nosotros've tested with the given hardware. Testing laptop components is naturally a bit more hard than desktops as each configuration can vary in cooling and other hardware, then these averages are meant to illustrate how a 'typical' system will perform. The averages do not include unmarried channel memory systems or whatsoever other situations that heavily throttle the components at hand, we've tried our all-time to create apples-to-apples data where possible.

Benchmarks

Allow'south kick things off with a classic performance benchmark: Cinebench R20. In this test nosotros run across full domination past the red squad. Not only is the 4900HS the fastest laptop processor we've tested in the multi-threaded workload, it'southward likewise the fastest in unmarried-thread performance. The 4900HS is 35% faster than the viii-core Core i9-9880H when using all cores, and 7% faster in single-core. At that place is the Core i9-9980HK that nosotros haven't tested that might put up a bit of a fight, just the 90W numbers from the 9880H suggest this might be a hard task. Also consider, these results are from the lower-TDP 4900HS, the 4900H at a full 45W should exist some other footstep ahead.

There are other brutal results in this Cinebench chart. The 4900HS crushes the Core i7-9750H, which is the most pop CPU used in slim and lite gaming notebooks. Zen 2 offer is over 60% faster in the MT test. We also see the previous-gen AMD part get a bit humiliated, the 4900HS is so much faster than the Ryzen vii 3750H in the aforementioned power envelope information technology's not funny.

We also tested with the legacy Cinebench R15 which has results from a wider range of CPUs going back more years. The 4900HS remains firmly placed at the top of the charts as expected. Anyone upgrading from a Core i7-7700HQ, for case, which was a popular H-series CPU in 2017 volition be treated to more than than double the operation with a Ryzen 9 4900HS.

One area where Zen ii receives a particularly large upgrade is in how it handles AVX-256 instructions. It'due south merely much faster at wide floating point operations than earlier. So the Ryzen 9 4900HS receives an enormous performance upgrade in our Handbrake x265 test, which uses AVX instructions. The 4900HS is a monstrous 179% faster than the 3750H in this workload, which is only unfathomable for a single generation functioning leap.

On an AMD vs Intel forepart, it'south too highly favorable for AMD. Not quite the same margins as we saw in Cinebench, but we still see a 23% performance advantage of the 4900HS over the 9880H, and a 45% advantage over the 9750H. Frankly, these are massive deltas for a laptop form cistron that often receives single digit gen-on-gen improvements.

For Intel to match the 4900HS with its 8-core offer, it needs to accident its power target out the window and instead use a 90W TDP, which is possible on some gaming laptops with a 'Turbo' way or like. The difference in power depict at the wall for these two systems is incredible: the G14 with the 4900HS ran comfortably at around 66W long term, compared to 150W for the ability boosted 9880H in our HP Omen 15 examination system. That but goes to testify how much more efficient AMD's Zen two design is at these long term workloads.

Blender tells u.s. a similar story, with huge operation gains in the ~35% range for the 4900HS over the 9880H, and ~65% range for the 4900HS over the 9750H. Nearly Blender users will probably render on the GPU instead since it tends to be much faster, but it'southward some other criterion that illustrates long term multi-cadre performance on these laptops.

In terms of decompression, we see AMD pull abroad with a pregnant victory in seven-Zip. Ryzen processors are known to work very well in this workload. However it does fall behind the 9880H in terms of compression, to the tune of ~8%, although AMD beats lower core count parts like the 9750H.

Adobe Photoshop operation is interesting. In our Iris Blur examination which is generally CPU express, the 4900HS manages to beat the 9750H but falls backside the 9880H, sitting comfortably between those 2 processors.

This continues to exist the case in the more comprehensive Puget Photoshop criterion, which runs through a range of tests. In both of these workloads, which employ diverse effects to very high resolution images, the 4900HS is around 10 percent slower than the 9880H in a core-for-core battle. Granted, we are seeing 40% college performance than AMD'due south terminal-gen APUs.

Now let'southward check out PCMark x numbers. We're looking at the Essentials and Productivity workloads equally they're CPU limited, whereas the rest of the tests rely more than on the GPU.

The Essentials workload covers things similar app loading, web browsing and video conferencing. AMD manages to match the performance of the 9880H, which may not audio all that impressive, until you realize that the last-gen 3750H gets slaughtered in this test. Now AMD is at performance parity for these everyday workloads.

On the Productivity workload nosotros see something like every bit before, with the Ryzen 9 4900HS outperforming something like the Core i7-9750H. These sorts of tasks were less than decent on previous Ryzen, and then even though Ryzen 4000 isn't burdensome Intel here, performance parity is a good outcome.

However in that location are some situations with productivity workloads where Ryzen 4000 isn't as impressive. Our custom Excel criterion features a lot of number crunching on a large dataset, and here that the 9880H outperforms the 4900HS again. The 4900HS is faster than the 9750H, so information technology'south not a terrible result by any means, only it does seem that big dataset workloads are a weakness for Ryzen.

MATLAB lets us reconfirm this with our ODE and FFT benchmarks. Again, lots of data crunching on large sets of data and Intel's 9880H walks away with a victory.

Another workload where Ryzen performs well, but not enough to crush Intel's 8-cadre competitor is our Acrobat PDF export test, which is fully single-threaded. The 9880H is marginally faster in Acrobat, although we still see a significant performance increase for the 4900HS over the 3750H with a healthy 20% bump to single-threaded operation.

One final workload earlier we expect at GPU dispatch is AES-256 performance every bit provided by SiSoft's Sandra benchmark. In the multi-threaded examination, we see 15% higher AES performance from the 4900HS versus 9880H to brand it the fastest CPU we've looked at for cryptography workloads. This gives Ryzen a groovy advantage in two heavily utilized low-level tasks in decompression and cryptography.

Now allow'due south piece of work through our Premiere tests which are mostly GPU accelerated, starting with our 1 laissez passer encode which takes advantage of Intel'due south QuickSync technology. Premiere does non support hardware accelerated encoding on AMD processors at this stage, then for those that like a quick export with slightly reduced epitome quality at the terminate, Intel is still the way to go. In item, the 4900HS paired with Nvidia's GeForce RTX 2060 Max-Q is ~twenty% slower than a Core i7-9750H with an RTX 2060 simply because hardware acceleration is not available.

On the other hand, our Cadre i9-9880H system doesn't support QuickSync acceleration as the iGPU is fully disabled to back up G-Sync through the Nvidia GPU. And so we are left with a prissy software encoding comparison between the 9880H and 4900HS, where the 4900HS pulls away strongly to the tune of 26%.

Then we go to our 2 laissez passer encode which produces superior paradigm quality and doesn't support hardware acceleration. In this scenario, performance falls back to what we saw from virtually long-term workloads: the 4900HS is 30% faster than the 9880H, and 38% faster than the 9750H, despite our 9880H laptop packing a much faster GPU. This examination isn't GPU limited but even with a moderately capable discrete GPU it appears as though AMD's Zen 2 APU is significantly faster for Premiere encoding.

Merely wait, there's more Premiere tests. Here we have a single example of Warp Stabilizer, which is a hugely demanding effect that runs on a single thread per instance. The 4900HS manages to stabilize the footage xiv% faster than the 9880H, and 22% faster than the 9750H, which shows the ability of the high unmarried-thread performance nosotros first saw with Cinebench.

And finally we have the Puget benchmarks. The Ryzen ix 4900HS is the best laptop CPU for live playback in Premiere, performing 12% better than the 9880H, meaning nosotros're seeing better editing functioning. Then for their export benchmark, we run into similar numbers to what we've only been talking nigh, with QuickSync dispatch assisting with some of this workload.

Gaming Benchmarks

While we don't think many people will actually be using the integrated GPU in these H-series processors given the vast majority of H-serial laptops also include detached graphics, it's worth a brief look at how the iGPU fares in a minor option of low intensity games, just to see what improvements AMD has made to the Vega GPU.

The Ryzen 9 4900HS sports the fastest iGPU configuration available in the serial with 8 compute units clocked up to 1,750 MHz. And information technology does deliver impressive results. In One thousand Theft Auto V, the 4900HS delivered 36% more than operation than the Ryzen 7 3750H, which featured 10 Vega compute units at one,400 MHz. On newspaper, both CPUs have similar raw GPU performance, but with all the advantages AMD talked about like increased memory bandwidth, this new Zen 2 APU is able to pull alee.

In Civilization VI, the 4900HS again provides 37% more performance than the 3750H inside the same 35W power envelope. And moving to CS: Go, that margin remains identical at effectually 37%. The 4900HS running CS Go exclusively on the integrated graphics was able to achieve over 100 FPS on boilerplate using low settings, which is very nice.

And then finally nosotros take our most performance-intensive iGPU test in Gears 5 running at Medium settings. The 4900HS is around 31% faster than the 3750H in this workload, which makes it faster than a low-end discrete GPU offering like Nvidia's MX250.

It's non common to run across an H-series laptop paired with an MX-form GPU. Commonly OEMs opt for more powerful configurations like a GTX 1650 or college, but with Ryzen 4000 there'south really no need to bother with an MX250 or similar discrete GPU in an H-series type design.

Sustained Clocks and More Questions

At this point in the review we'd normally walk you through some comparison summaries between the Ryzen nine 4900HS and various other CPUs. Only we nonetheless think in that location'due south a few performance questions left on the tabular array. One is what clock speeds the CPU actually runs at in do, and how boost behaves. And the other is, why do we see lower performance in some information heavy workloads similar Matlab, Excel and Photoshop. So let'due south tackle this second function kickoff.

Nosotros accept two working theories as to why we see data heavy workloads perform this fashion. The first is a uncomplicated 1 based on the specifications of these processors, in particular cache sizes. The Core i9-9880H has a decent 16 MB of L3 enshroud, which matches what Intel offer on the desktop with parts like the i9-9900K. Nevertheless the Ryzen ix 4900HS has just 8 MB of L3 cache, half of what Intel offers, and well beneath the 32 MB of L3 that AMD packs into their 8-core Zen two desktop processors like the Ryzen seven 3700X.

Having less cache means less data can be stored in super fast retentivity and accessed in an instant. When yous accept high core count, high performance CPU cores but not enough cache, this can become a bottleneck in some instances. And while this cache amount has doubled on Ryzen 4000 from previous mobile series, then has the cadre count. It's probably non the whole story, just definitely office of it.

The other is the memory organization. Yes, AMD offers college memory bandwidth than Intel with the move to support DDR4-3200 speeds, Intel only offers DDR4-2666 with 9th-gen. In a criterion similar Sandra we see AMD providing around 35% more than retentivity bandwidth. However, Ryzen 4000 appears to have inferior memory latency. This, similar cache size can become a performance constraint. The Core i9-9880H has retentiveness latency around 30ns for information sets above 32MB in size, while the Ryzen 9 4900HS has 46ns memory latency. That's a substantial win for Intel.

It'southward hard to say for sure whether these factors are function of the cause, or the entire cause, but looking through low level benchmarks these were the 2 things that stood out to us. When we go to benchmark more Ryzen 4000 APUs nosotros'll get a clearer movie of where these bottlenecks lie.

Every bit for clock speeds and boost behavior, let's take a wait. From a common cold start in our Handbrake AVX workload, the Ryzen nine 4900HS consistently boosted up to around 65W of power for a few seconds achieving 4 GHz heave clocks all core, before dropping down to 54W for a longer sustained flow, with clocks around 3.7 GHz. Eventually the CPU settles down to 35W to provide three.2 GHz all-cadre, just to a higher place this processor'south three.0 GHz base clock. The heave catamenia can vary depending on how warm the organisation is, but from a cold outset we were by and large seeing at to the lowest degree 2 minutes of ~53W boost which is generous. Temperatures were really very well managed on the Zephyrus G14, with its air cooler providing a tick over 70C sustained, but of course, this volition vary between laptops.

Performance Summary

Ryzen 9 4900HS vs. Core i9-9880H

The large one here is the Ryzen 9 4900HS versus the Core i9-9880H. These are like grade processors, 8-core versus 8-core and should give us a pretty solid indication of what to expect from 10th-gen too, if we get pocket-sized clock speed improvements from Intel every bit is rumored.

In most long term, multi-threaded workloads, we're seeing 35% better operation from the Zen 2 chip. Nosotros also get impressive numbers for video encoding. Single-threaded workloads are also typically faster, or in the worst case scenarios like lite productivity, equivalent to Intel's. However, performance does fall behind in data heavy benchmarks like Excel, Photoshop and Matlab.

The amazing thing about nigh of those results is AMD is able to achieve, in many workloads, at least 25% better multi-thread performance while also coming in with lower sustained ability draw, at 35W versus 45W. So what happens when you limit Intel's 9880H to a PL1 of just 35W using Intel's XTU software?

Well, the margins abound even more than. While nosotros exercise let these processors do what they ordinarily exercise in the boost stage, some benchmarks don't modify too much, long term workloads at present are strongly in favor of AMD. Over 50% amend functioning in some situations is possible, and a 40% comeback to Handbrake is impressive. This means that an OEM designing a slim and light system with limited cooling will generally get the best feel past far going with Ryzen.

Amazingly, even when we throw Intel's 45W power limit out the window and boost up to 90W forever, Intel still can't beat the 35W AMD processor in long term multi-thread workloads. In an astounding win for efficiency, the 4900HS is either equal to this 90W processor configuration, or up to xv% faster. With these two systems going at information technology, we observed an 80W power describe difference from the wall, and so if Intel wants to match AMD with 14nm CPUs past just raising power limits, laptops will need much larger coolers to cope.

Ryzen 9 4900HS vs. Core i7-9750H

Comparing the 4900HS to the 9750H, in that location's but one example where the 9750H organization tin be faster, and that'southward with QuickSync accelerated Premiere encoding. In every other benchmark, including those where previously the 9880H was faster, now the 4900HS is faster. This bodes well for any future battles in the Ryzen 7/Core i7 range where AMD has a cadre advantage in offer exclusively 8-cadre parts.

Ryzen nine 4900HS vs. Ryzen seven 3750H

Now allow's wait at how far AMD has come with Zen 2 vs. Zen+ in a 35W mobile design. The difference in certain workloads is staggering. Not only is AMD producing a 30% performance improvement in single-thread workloads, they're able to deliver 2.5x the operation in long term multi-thread tasks like Blender, Handbrake and Cinebench -- with the same power draw.

Ryzen 9 4900HS vs. Ryzen vii 4800H

We did promise a sneak peek at Ryzen 7 4800H functioning on an applied science sample laptop we had brief access to. Going on a small subset of benchmarks, performance is looking equal to, if non slightly improve, than the 4900HS, which bodes very well for more than mid-range systems that will employ the Ryzen 7 office. Yes, the 4900HS is more efficient, but the 4800H should however evangelize pure 8-core functioning.

What Nosotros Learned

Ryzen 4000 is delivering the best performance for heavy productivity workloads yous can go far a mobile course factor. Nosotros can say that without even testing the higher power Ryzen 9 4900H, because the 35W variant in the Ryzen nine 4900HS is already leaving Intel's 8-cadre competitors in the grit.

The Ryzen 9 4900HS is a bang-up selection for core-heavy work: we're talking video encoding or transcoding, 3D rendering, file compression, that sort of thing. It'due south much faster and does so at a lower ability draw, allowing for better performance in a smaller form factor. Fifty-fifty in single-thread workloads, AMD generally comes out on summit, which means that the Premiere editing experience is better on the Ryzen nine 4900HS, for example.

From a pure gen-to-gen upgrade perspective, AMD has done an amazing chore. The Ryzen 7 3750H was hard to recommend and it was handily beaten by Intel's mid-range parts. That has all inverse with the newer APUs.

Technically, Intel parts can yet compete on the performance front end if you remove the 45W long term power limit. We saw that with the Core i9-9880H and we expect information technology'd be similar had we tested the flagship Core i9-9980HK. But to get that sort of performance, you need a larger laptop with a beefier cooler, and information technology'll likely run hotter, too. The Ryzen nine 4900HS can provide all that operation in smaller laptops -- like this Zephyrus G14 -- and run cooler at the same time.

All the same, AMD'due south Ryzen 4000 CPUs aren't the complete package, there are a few limitations. One is with data heavy workloads, similar number crunching massive spreadsheets in Excel, working with huge photos in Photoshop or running Matlab scripts. Intel came out ahead in these tests. Lighter loads volition do just fine on AMD, but if you're a big number cruncher, Intel'south core-equivalent processors might be the way to get.

The other is with workloads that use Intel exclusive technologies like QuickSync, Premiere encoding being one. If that'south something you employ all the time, Intel is the way to get. It's worth mentioning that every other chore in Premiere outside of QuickSync encoding is faster on Ryzen 4000, including editing and applying intensive furnishings like the Warp Stabilizer.

Exterior of those 2 instances, you'll have a better, faster productivity feel with these Ryzen 4000 8-core processors. That'southward uncharted territory for AMD on a mobile PC grade gene.

As well it seems that AMD volition be offering this sort of performance at very competitive prices. The Zephyrus G14 with the Ryzen 9 4900HS and RTX 2060 Max-Q is set to retail for about $ane,500, which is firmly the territory of 6-core Core i7-9750H laptops. The Core i9-9880H laptop nosotros bought for testing in this review cost $two,400 and was one of the least expensive we could detect. Granted, it does have a much faster GPU for gaming, only correct now y'all simply won't find eight-core laptops in the $ane,500 price range. While almost of our data has been focusing on Ryzen nine vs Core i9, they don't really compete head to head on pricing, at least for now equally this could alter with Intel's 10th-gen.

A few additional notes to wrap upwards this review...

With previous Ryzen laptops nosotros didn't have the most stable experience, running into plenty of software bugs and crashes, which we've discussed a few times before. Completely unlike experience with the Ryzen 9 4900HS in the Asus Zephyrus G14. Even with a beta version of the GPU commuter on this laptop, we ran into no stability issues, crashes or applications refusing to work correctly.

You lot likewise might be wondering most gaming performance with a discrete GPU. The Zephyrus G14 does include the RTX 2060 Max-Q after all. That'southward something we'll explore in a hereafter review as we're still working to get the best apples to apples comparison. Hoping to have that soon.

Bombardment life will also exist on people'south minds, but it's non something nosotros set out to examination equally we didn't have enough data for various laptops to arrive a off-white comparison.

Finally, we'll close this 1 out with some comments on Intel'southward 10th-gen. The new laptop CPUs are coming just effectually the corner, likely within a calendar month. Rumors propose Intel is sticking with 8-core parts for the H-serial, and are still using 14nm technology. We just tin can't meet how they can compete on a performance or efficiency level. If all we're getting is a minor clock speed bump with the same 14nm efficiency as the last few generations, Ryzen is going to easily win this one. Nosotros'll see that battle unfold soon, only based on what we've seen so far, nosotros don't hold high hopes for 10th-gen.