Qualcomm's Next-Gen Snapdragon 8cx Rivals Intel 11th Gen Tiger Lake in Early Benchmarks
Geekbench scores for Qualcomm's Snapdragon 8cx Gen 3 published
The first benchmark results for Qualcomm's 3rd Generation Snapdragon 8cx system-on-chip (SoC) for always-connected PCs has been posted to the Geekbench 5 database. The numbers show the Snapdragon 8cx Gen 3 beating its predecessors and even competing with Intel's latest 11th Gen Core i7 "Tiger Lake" mobile chip in multi-threaded workloads.
Qualcomm has been fairly consistent in updating its Snapdragon 8cx family of SoCs for notebooks annually. This year, the company is expected to launch its third-generation Snapdragon 8cx chip, which is rumored to significantly change its architecture. Instead of integrating four high-performance CPU cores and four low-power ones, the Snapdragon 8cx Gen 3 is expected to pack eight high-performance cores working at different clock speeds, omitting low-power cores. This should improve performance, but it's unclear whether the chip will match its predecessor's 7W thermal envelope.
Qualcomm yet has to formally announce its Snapdragon 8cx Gen 3, but someone has already submitted test results of a Qualcomm Reference Design (QRD) platform running the new SoC to the Geekbench database, as spotted by NotebookCheck.
Just like other notebook development platforms, QRD platforms are meant for developers of hardware and software, so performance usually differs from that of retail products. Nonetheless, such platforms still tend to give a good hint of what to expect from new chips.
Qualcomm Snapdragon 8cx Gen 3 Benchmarks
CPU | Single-Core | Multi-Core | Cores/Threads, uArch | Cache | Clocks | TDP |
---|---|---|---|---|---|---|
Qualcomm Snapdragon 8cx Gen 3* | 982 | 4,918 | 4C Kryo Gold+ + 4C Kryo Gold | ? MB | 2.69 GHz | ? |
Qualcomm Snapdragon 8cx Gen 2 | 795 | 3,050 | 4C Kryo 495 Gold + 4C Kryo 495 Silver | ? MB | 3.15 GHz + 2.42 GHz | 7W |
Qualcomm Snapdragon 8cx Gen 1 | 725 | 2,884 | 4C Kryo 495 Gold + 4C Kryo 495 Silver | ? MB | 2.84 GHz + 1.80 GHz | 7W |
AMD Ryzen 9 5980HS | 1,540 | 8,225 | 8C/16T, Zen 3 | 16MB | 3.30 ~ 4.53 GHz | 35W |
AMD Ryzen 9 4900H | 1,230 | 7,125 | 8C/16T, Zen 2 | 8MB | 3.30 ~ 4.44 GHz | 35~54W |
Intel Core i7-1160G7 | 1,400 | 5,000 | 4C/8T, Willow Cove | 12MB | 2.10 ~ 4.40 GHz | 15W |
Intel Core i7-1185G7 | 1,550 | 5,600 | 4C/8T, Willow Cove | 12MB | 3.0 ~ 4.80 GHz | 28W |
Apple M1 | 1,710 | 7,660 | 4C Firestorm + 4C Icestorm | 12MB + 4MB | 3.20 GHz | 20~24W |
*Chip not confirmed by Qualcomm
The Snapdragon 8cx Gen 3 showed notably higher results in single-thread workloads when compared to previous generations. It was 35% faster than the 8cx Gen 1 and 24% faster than the 8cx Gen 2. We don't yet know the frequency of the 8cx Gen 3's cores for sure, but it appears that the 8cx Gen 3 packs something better than Qualcomm's Kryo 495 Gold (a custom version of Arm's Cortex-A76).
On the other hand, the Snapdragon 8cx Gen 3's performance paled in comparison to chips from AMD and Intel competing with the best CPUs for desktops. The latest Zen 3 and Willow Core microarchitectures can run at higher clocks and consume more power. Meanwhile, Apple's M1 beat Qualcomm's Snapdragon 8cx Gen 3 (at least in its current form) in single-threaded workloads by 74%.
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
When it came to performance in multi-threaded workloads, the Snapdragon 8cx Gen 3 clearly benefits from eight high-performance cores (albeit running at different clocks) inside. The new SoC outperformed the 8cx Gen 2 by over 60% and is on par with Intel's four-core, eight-thread Core i7-1160G7, a 15W SoC.
The Snapdragon 8cx Gen 3 tested couldn't compete with the higher-wattage Apple M1 and AMD's Ryzen SoCs, but systems based on Qualcomm's 8cx platforms are not really meant to compete against higher-end machines in terms of performance.
Overall, the benchmark results show the Snapdragon 8cx Gen 3 demonstrating single-thread and multi-thread performance improvements in a synthetic benchmark. Of course, it remains to be seen how commercial devices based on the new SoC will stack up against rivals in real-world applications.
Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends.
-
abufrejoval Where is 982/4918 close to the 1721/5955 I see on my i7-1165G7 on Linux? (Yes, Linux and Android-x86 results are typically quite a bit higher than Windows results on the very same hardware and single core Tiger Lake pretty much on par with my Ryzen 5800X 1794/11120 with 4.95 GHz PBO vs 4.7GHz and 4 vs 8 cores)Reply
The multi-threaded scores point to an 8-core chip, which I'll admit is always nicer all other things being equal, but not when 4 cores on one hand deliver the work of 8 on the other. Normally that's just how CMOS scales to frequency.
If it were 5Watts top power vs 30Watts (that's all cores sustained Wattage on my Tiger Lake NUC9), at the cost of doubling the cores and losing single core Oomph, we could be talking.
And yes, even the latest Atoms seem 10 years behind against these figures.
As good as the Qualcomm cores are, they are not near the M1, nor do they threaten Ryzen or Tiger Lake just yet on the same battleground and you know that Anton, so please don't fall to the temptation of a headline like this. -
jakjawagon Similar multicore performance to a 15W CPU with half as many cores. If previous generations are any indication, I expect devices with this processor to cost at least 1.5 times as much as an equivalent Intel/AMD device.Reply -
zodiacfml commendable now that this is far different from its mobile counterpart, ditching the slower cores. pricing is where the fight is. they can't simply sell products with this part more than it costs Apple M1 products, considering M1 is more powerful and will be soon updated, and Apple price premiumReply -
Flemishdragon What who where when??? So the M1 at 3.2Ghz surpasses an overclocked 4.5GhzAmd 4.8GhzIntel, in singel thread??? There is no way this is not possible. The benchmarks are comparing to standard non overclocked probably all on +3.2 Ghz-ish or baloney sausage payed for benchmark?Reply -
hotaru.hino
And 16 years ago, 2.4 GHz AMD processors were beating the snot out of 3.8GHz Intel processors.Flemishdragon said:What who where when??? So the M1 at 3.2Ghz surpasses an overclocked 4.5GhzAmd 4.8GhzIntel, in singel thread??? There is no way this is not possible. The benchmarks are comparing to standard non overclocked probably all on +3.2 Ghz-ish or baloney sausage payed for benchmark?
If you know how to make a processor, then you can do things like this. -
Flemishdragon
Which AMD cpu are you referring to you mean the first dual core from AMD or something that's in multi thread. Yea had one but as I recall it was only 2.5 times faster in multithread ( it was running overclocked on both core at at 3.4 I think forgot) my Intel was3.2Ghz only one single core? So that is still very close considering the Intel was older and had also a slower Front Side Bus and only one core. Pretty amazing but seems like a M1 can do 1683 single thread geekbench 5, the Intel has to be on 5.3ghz to have a 1900-ish score so that's only desktop still faster but seems like Intel has a lot work to do.hotaru.hino said:And 16 years ago, 2.4 GHz AMD processors were beating the snot out of 3.8GHz Intel processors.
If you know how to make a processor, then you can do things like this. -
watzupken I feel ARM chips may struggle with adoption on Windows OS. Unlike Apple that's got a tight integration on hardware and software, there is no such tight integration on Windows. The OS in my opinion is looking nicer, but consequently also becoming a resource hog. In addition, I don't feel there is strong support by Microsoft to push software developers to develop their software natively for ARM based chips as well. So while the Qualcomm chip may look great running on selected benchmarks, I wonder how it will fare in real world applications with an extra layer of emulation.Reply -
hotaru.hino
I was thinking of the AMD FX-53 vs. the Pentium 4 670. However a cursory glance at the 670's review shows that the FX-55, a 2.6GHz 1C/1T processor, was able to keep a small lead in most tests over the 670 despite being clocked at 3.8GHz and being a 1C/2T processor (https://www.anandtech.com/show/1695)Flemishdragon said:Which AMD cpu are you referring to you mean the first dual core from AMD or something that's in multi thread. Yea had one but as I recall it was only 2.5 times faster in multithread ( it was running overclocked on both core at at 3.4 I think forgot) my Intel was3.2Ghz only one single core? So that is still very close considering the Intel was older and had also a slower Front Side Bus and only one core. Pretty amazing but seems like a M1 can do 1683 single thread geekbench 5, the Intel has to be on 5.3ghz to have a 1900-ish score so that's only desktop still faster but seems like Intel has a lot work to do.
Actually heck, I didn't have to go that back. I'm pretty sure Ivy Bridges were easily dancing around the FX-9590.
Either way, beating or matching the performance of much faster clocked processors isn't an unheard of thing.