The AMD Ryzen AI 9 HX 370 Review: Unleashing Zen 5 and RDNA 3.5 Into Notebooks
by Gavin Bonshor on July 28, 2024 9:00 AM ESTGraphics Performance
Moving on to gaming performance, AMD has upgraded their integrated graphics within Strix Point to the RDNA 3.5 architecture. RDNA 3.5 improves things over RDNA 3 within Phoenix and Hawk Point in multiple areas. One thing RDNA 3.5 does is greatly increase the GPU's capacity to execute complicated graphics operations more effectively by optimizing key things such as texture sampling and interpolation. Upgrading the memory management in RDNA 3.5 also allows for better overall power optimization and data handling to address major GPU performance issues.
Screenshot of the AMD Ryzen AI 9 HX 370 with Radeon 890M in GPU-Z
All of the improvements and upgrades over RDNA 3 should theoretically translate into better real-world gaming performance. Generally, any form of mobile SoC doesn't quite bring the power or graphics compute to the same level as discrete graphics, which have more die area to play with, a higher transistor budget at the manufacturing level, and more power.
As the new AMD Radeon 890M graphics is the direct successor to the Radeon 780M, it does have an obvious competitor in the previous Phoenix and Hawk Point mobile SoCs. Until Intel launches its upcoming Lunar Lake mobile SoC, the other competitor is Intel's current Meteor Lake-based Arc Xe LPG integrated graphics. Another contender is AMD's own RDNA 3.5 sibling to the Radeon 890M in the Ryzen AI 9 HX pairing, which is the Radeon 880M and is found in the Ryzen AI 9 365. The main difference between the Radeon 890M and the 880M is in the number of graphic cores or compute units (CUs). The Radeon 890M features 16 x CUs, while the Radeon 880M comes with 12 x CUs.
As integrated graphics get their memory from the primary pool of DRAM installed, slower system memory can be hindered by bandwidth. AMD's Ryzen AI 300 series allows for both DDR5-5600 and LPDDR5x-7500, which is what the ASUS Zenbook S 16 we're testing uses.
For this review, we will focus on gaming performance at 1080p, which is the most commonly used gaming resolution according to the latest Steam survey. Given that these are mobile chips, we've opted for middle-of-the-road settings using the Medium preset. Despite the advancements in integrated graphics, they still lack the horsepower of discrete graphics.
Gaming Performance @ 1080p Medium Settings
Looking at the performance of the Radeon 890M within the Ryzen AI 9 HX 370, we can see that the combination of Zen 5/Zen 5c cores and the latest RDNA 3.5 graphics performs consistently well at 1080p. Given the Ryzen AI 9 HX 370 has a higher core count with 12C/24T (4 x Z5 + 8 x Z5c) compared to the Ryzen 9 7940HS (8C/16T), the latest Soc also has a higher number of graphics compute units (16 CUs vs. 12 CUs). On top of that, you also have to factor in the jump in CPU architecture to Zen 5 over Zen 4; the latest SoC certainly does have an advantage.
In Company of Heroes 3 at medium settings, this game can simultaneously be very taxing on the CPU cores and graphics. The Ryzen AI 9 HX 370 with the Radeon 890M graphics is around 23% faster than the Ryzen 9 7940HS/Radeon 780M, although to make things a level playing field, we are testing the 7940HS at 35 W.
We also see good gains over the Ryzen 9 7940HS and Intel's Core Ultra 7 155H, which is a 6P+8E/22T chip with their Arc Xe integrated graphics that has 8 x CUs in Cyberpunk 2022 and F1 2023, but we are also seeing an uptick of 38% compared to the Core Ultra 7 155H in Returnal; for contrast, it beats the Ryzen 7940HS by around 57%.
Overall, AMD's latest RDNA 3.5 graphics architecture and the Zen 5 pairing certainly improve integrated graphics performance. This is a good thing, although integrated graphics are still not quite there when it comes to achieving a consistent 1080p/60fps in demanding titles. Games such as MOBAs, including League of Legends and DOTA 2, and other less demanding games will certainly play well on this iGPU.
Facebook
Twitter
RSS
72 Comments
View All Comments
Khanan - Tuesday, July 30, 2024 - link
It’s practically maxed out, these are high end mobile parts. However there will be a APU later with an extra big GPU called Strix Halo, the only difference will be that it will have a mid range desktop level GPU with over 32 CUs - comparable to console APUs.mczak - Tuesday, July 30, 2024 - link
You can find annotated die shots for Strix like here:https://www.techpowerup.com/325035/amd-strix-point...
The die area spent for the NPU is quite significant, someone estimated around ~14mm².
As for Phoenix, I've never seen a die shot of it (only Phoenix2 which doesn't feature the NPU). According to AMD, the NPU in Phoenix though was made up of 5x4 tiles, whereas the one in Strix is 8x4 tiles (with twice the MAC throughput per tile, and other improvments), as can be seen in the slides from AMD: https://www.anandtech.com/show/21469/amd-details-r... - so maybe it was like half the size? But that's just a crude guess.
zamroni - Tuesday, July 30, 2024 - link
the npu is overkill.i'd rather have bigger igpu or more cpu caches.
gpu can do anything that npu can anyway
Khanan - Tuesday, July 30, 2024 - link
It’s not, as per MS it needs to be at least 40 TOPS fast and AMD made sure to be faster than the competitors, it’s a marketing win. And copilot doesn’t run on CPU or GPU as that costs too much energy on the go, and in general it won’t use those, even if you’re on desktop and have no battery constraints.jmke - Tuesday, July 30, 2024 - link
> . The first to market in the consumer space with a dedicated AI engine in the notebook space was AMD with their Zen 4-based Phoenix Point or the Ryzen 7040 seriesRyzen 7040 released March 2023
Macbook M1 with dedicated ML chip released in 2020, that one already has dedicated ML chip with support for a slew of models, including text and image (stable diff); ....
jeromec - Tuesday, July 30, 2024 - link
Did I miss the battery test?And why no comparison with the Nvidia-powered ARM Windows PCs? Was it an AMD request?
Also, which model of MacBook Pro is included in the benchmarks? Apple's naming convention is currently very confusing and there are 14" MacBook Pros with M3, 2 flavors of M3 Pro and 2 flavors of M3 Max.
Also, I do not see the point of comparing, weight-wise, this Asus with a 16" MacBook Pro with M3 Max, which is in a different league, performance and price-wise.
lmcd - Tuesday, July 30, 2024 - link
Nvidia-powered ARM Windows PCs?I'm so sorry to inform you that the last Nvidia ARM Windows PC was the Surface RT 2, which launched with a Tegra 4. We have not seen anything since.
Hopefully that will change, but seriously: what are you talking about?
nandnandnand - Tuesday, July 30, 2024 - link
There's rumors of a MediaTek/Nvidia chip coming within a couple years, but jeromec meant the Qualcomm Snapdragon X Elite.patel21 - Tuesday, July 30, 2024 - link
Minor Correction:>> Core Ultra 7 155H, which is a 6P+8E/22T chip
It should be:
Core Ultra 7 155H, which is a 6P+8E/20T chip
emn13 - Wednesday, July 31, 2024 - link
The argument to use LLVM for SPEC based on cross-platform ease is not a good one. Compilers don't perform equally competitively across different platforms. A compiler that works well on, say, apple silicon need not be optimal nor typical elsewhere. Fortunately, LLVM is fairly broadly liked, so hopefully this isn't a huge impact, but we don't know. Could be this alone pretty invalidates the spec2017 resultsAdditionally, particularly for *new* platforms the exact version of the compiler and whatever tuning it has had can make a difference; it's easy to test with a compiler that's older than the platform and thus tunes poorly. As it happens the LLVM version listed - 10.0.0 is simply ancient; over 4 years old - the current version is 18. A bit of web searching suggests that at least until fairly recently no znver5 tuning was merged into even dev LLVM; GCC happened to have tuning merged in march (not sure if this is typical between those two compilers).
Finally, the text implies you disabled avx512. I'm not sure why; even on zen4 with its half-rate execution path this can have considerable performance advantages; it pretty plausible it will on zen5 too (even on models with half-rate execution rates such as mobile chips).
All in all, I'm not sure what the point of the spec result is in this form. On the one hand, the vast majority of software run is compiled targetting old processors, so that's realistic. On the other hand, you already have benchmarks for that, and kind of the whole allure of a compiled-from-scratch benchmark like SPEC is that you can see what the platform is capable of natively, not when running legacy software. It's not too different from how it's interesting to see ARM chips running both emulated x86 code, but also see native results even if that's not 100% representative.
Still I guess an interesting result, but those caveats are large and worth mentioning IMHO. It's very likely a more reasonably tuned run could be significantly different for all of these chips, particularly newer ones that deviate most from the platform described by -march=x86-64 -mtune=core-avx2 -mfma -mavx -mavx2 - is that haswell? It's ancient anyhow.