Tuesday, June 18th 2024

First Reviews are Live and Snapdragon X Elite Doesn't Quite Deliver on Promised Performance

The first reviews of a notebook with Qualcomm's Snapdragon X Elite SoC have appeared today, and it looks like the promised performance isn't quite there. And yes, all the reviews that went live today are all based on Asus' Vivobook S 15 OLED, so it might be a bit too early to state that Qualcomm isn't delivering on its claimed performance, as other manufacturers might deliver better performance. Let's start with the battery life. The Vivobook S 15 OLED comes with a 70 Wh battery pack which enables it to deliver better battery life than many AMD or Intel notebooks, but Apple's MacBook Air 15 M3 delivers on average a 40 percent better battery life, with a smaller 66.5 Wh battery pack. Browsing the web or watching movies aren't really too taxing for the Snapdragon X Elite, but under heavier loads the battery life drops off a cliff.

When it comes to application performance, the Snapdragon X Elite offers good multicore performance in benchmarks like Cinebench 2024 and PCMark 10, but it falls way behind in most other tests, ranging from video encoding to file extraction and document conversion, with Intel Core Ultra 7 155H based notebooks often pulling ahead by 50 percent or more. Despite being equipped with LPDDR5X-8448 memory, the Snapdragon X Elite falls behind in both the memory copy and write tests in AIDA64 compared to the Intel powered laptops. However, it's not all doom and gloom, as the Qualcomm chip delivers an impressive memory latency of a mere 8.1 ns, compared to 100+ for the Intel based laptops. It also outclasses the Intel laptops when it comes to memory read performance.
Asus went with a fairly basic Micron 2400 SSD which is a DRAM-less Phison based drive and this might be part of the reason for some of the less flattering results in some tests. However, this shouldn't affect the gaming tests and this is another area where the Snapdragon X Elite doesn't deliver, and most games are unplayable at 1080p resolution. Many games don't run on the Qualcomm chip for obvious reasons, but many that do, suffer from texture and graphics glitches at times. Most games don't even manage 30 FPS at reduced graphics settings, let alone 60 FPS, but then again, this is hardly expected from an integrated GPU. Considering that the Vivobook S 15 OLED comes in at US$1300 with 16 GB of RAM and 1 TB SSD, you would expect it to deliver in terms of performance, but it seems like Qualcomm and Microsoft have a lot of work to do to optimize the platform as a whole.
Sources: Windows Central, Notebook Check (in German)
Add your own comment

124 Comments on First Reviews are Live and Snapdragon X Elite Doesn't Quite Deliver on Promised Performance

#52
Jermelescu
DenverWow... The performance at 20w collapses... Loses in all real-world scenarios vs x86 zen4/MeteorLake competitors, including battery life.

That is not true. I’ve read a lot of (mostly early) reviews and they are way too different in lots of scenarios. Give it a week and then we’ll have a better picture of the situation.
Posted on Reply
#53
Neo_Morpheus
R0H1TIntel had the most efficient desktop & laptop processors at the time, surely that helped right? Talking about Conroe so 2005/06 or slightly later.
Motorola was in charge of developing low power PowerPC cpus but bailed.

IBM took over but couldn’t justify the expense of developing such chips just for Apple, since they weren’t selling that many systems, so at that point, apple had no choice but to jump to intel, which had more efficient cpus.

The irony is that Intel own inefficient chips forced Apple to jump to Arm.

Whic is something also interesting since Apple was a founding member of Arm.
AnotherReaderThe failure of RISC to supplant x86 was clear when the Pentium Pro became the SpecInt champion.
The irony of your post is that Intel went full RISC (internally) with the Pentium.
Posted on Reply
#54
Easy Rhino
Linux Advocate
It will only get better. x86 days are numbered.
Posted on Reply
#55
AnotherReader
Easy RhinoIt will only get better. x86 days are numbered.
I wouldn't count x86 out just yet, but ARM is here to stay.
Neo_MorpheusMotorola was in charge of developing low power PowerPC cpus but bailed.

IBM took over but couldn’t justify the expense of developing such chips just for Apple, since they weren’t selling that many systems, so at that point, apple had no choice but to jump to intel, which had more efficient cpus.

The irony is that Intel own inefficient chips forced Apple to jump to Arm.

Whic is something also interesting since Apple was a founding member of Arm.


The irony of your post is that Intel went full RISC (internally) with the Pentium.
RISC and CISC are about ISAs, i.e. programmer visible instructions. The microarchitecture doesn't define a CPU as RISC or CISC.
Posted on Reply
#56
sephiroth117
I’m a big supporter of ARM (I mean it’s more choices and emphasis on efficiency) but I am quite unfamiliar with Qualcomm, it’s important for Mediatek and many others to join the PC arm race (no pun intended) this is where we’ll truly have a price competition and more specialized options: SoC x for gaming, y excels in productivity/CAD etc

right now if we just have this X1 SoC it’s hard to really assess. If I have just one choice, I pick a more mature macbook m3/m4, beauty of personal computers is having choice, SoC included.
Posted on Reply
#57
Denver
Easy RhinoIt will only get better. x86 days are numbered.
It surprises me that someone has the courage to say that. It seems likely that Qualcomm will face significant financial challenges(Billion-dollar losses) and may eventually give up, because no one in their right mind is going to buy an expensive product, with less performance, compatibility, efficiency, less EVERYTHING than the competition.

It surprises me even more that such a wide core design, larger than Zen4, has such disgraceful performance. Strix-Point will arrive like a steamroller crushing everything. :p
Posted on Reply
#58
Easy Rhino
Linux Advocate
DenverIt surprises me that someone has the courage to say that. It seems likely that Qualcomm will face significant financial challenges(Billion-dollar losses) and may eventually give up, because no one in their right mind is going to buy an expensive product, with less performance, compatibility, efficiency, less EVERYTHING than the competition.

It surprises me even more that such a wide core design, larger than Zen4, has such disgraceful performance. Strix-Point will arrive like a steamroller crushing everything. :p
Then short the stock.
Posted on Reply
#59
phanbuey
The saddest thing... Im watching the Just Josh livestream of all these... NOT ONE WORKING LINUX ARM VERSION. 7 Laptops...

Like... what a gigantic miss.

YouTube
Posted on Reply
#60
Carillon
DenverStrix-Point will arrive like a steamroller crushing everything. :p
No please, no more steamrollers!
Posted on Reply
#61
v12dock
Block Caption of Rainey Street
v12dockI just picked one up today. I will say the my first experiences are very impressive. The emulation layer works exceptionally well. I played a bit of CS2 and it worked pretty flawless. I will post more as I explore.
Posted on Reply
#62
simlariver
ARM based Windows was always going to be a low-end solution. I'm glad we have more credible competition in the low-end / Chromebook space for hardware but Qualcomm fucked-up by marketing this as a high-end solution.
Posted on Reply
#63
dragontamer5788
Neo_MorpheusThe irony of your post is that Intel went full RISC (internally) with the Pentium.
The irony of your post is that "Reduced Instruction Set Computer" these days includes the FJCVTZS instruction, aka Floating-point Javascript Convert to Signed fixed-point, rounding toward Zero, instruction.

developer.arm.com/documentation/dui0801/h/A64-Floating-point-Instructions/FJCVTZS

CISC has won. Its better to add complexity to modern processors to do 16-bit Matrix Multiplication (aka Tensor Cores), to do AES-encryption (riscv.org/news/2020/12/the-design-of-scalar-aes-instruction-set-extensions-for-risc-v/), SHA1, 512-bit SIMD and more.

Complex cores are the winner. No one is "RISC" anymore (which was, at least in the 1990s, defined as having no division instruction. Instead, you used code to perform division rather than making a "complex" instruction to do so).

----------

RISC vs CISC has been dead for decades. Ever since ARM and RISC-V adopted AES Instructions, Javascript instructions, and SIMD, the world has gone 100% CISC.

-------

ARM is a fine instruction set in any case, but ISAs don't really matter anymore. The implementation details of the cores are far more important. Apple's implementation is pretty good (though exceptionally bulky), the Intel/AMD implementations are pretty good. Qualcomm will just have to tweak its design and figure things out.
Posted on Reply
#64
Darmok N Jalad
I think the long term reviews are going to be the real answer for these. We can bench, we can give initial impressions, but what is it like to actually live with the device? I know that can be true of most things, but I think it's especially true of WOA devices.
Neo_MorpheusAlpha was killed by Compaq, because they believed the lies stated by Intel with the upcoming Itanium.

PowerPC failed mostly because of Apple.

The original plan was to have an open platform (CHRP) that would accept all OS (Win NT, OS/2, Unix and MacOS)

NT and Unix were ported, OS/2 was delayed (and then canceled) and Apple pretended to be stupid and never released MacOS as originally planned (they went with the clones though.)

Everyone bailed, Apple volumes weren’t enough to sustain the development cost and ended moving to Intel.

Its more complicated than that (and I’m going by memory) but its the gist as to why PowerPC died.
I dunno, I think Apple gave up on PowerPC when it became obvious that the G5 was under-delivering. They never made a G5 MacBook Pro, I believe because it wouldn’t hit performance and thermal results, even on desktop it required way too much cooling. The writing was on the wall for PPC.
Posted on Reply
#65
Tropick
CarillonNo please, no more steamrollers!
Shared FPU is back, baby!!! :laugh:
Posted on Reply
#66
A&P211
P4-630Good for browsing, email, online banking and online shopping, netflix and prime video...
That's about it then.
I can get a AMD apu basic laptop for that, with almost the same amount of battery life, and cheaper in price.
Posted on Reply
#67
dragontamer5788
TheLostSwedeHowever, it's not all doom and gloom, as the Qualcomm chip delivers an impressive memory latency of a mere 8.1 ns, compared to 100+ for the Intel based laptops
This is an unrealistic result.

AMD's on-package L3 SRAM for the x3d chips is above 10ns of latency. Something glitched out in this discussion.
TheLostSwedeWell, could be AIDA64 that's borked then.
Crap, I missed the discussion. Sorry for being late!
Posted on Reply
#69
Wirko
dragontamer5788This is an unrealistic result.

AMD's on-package L3 SRAM for the x3d chips is above 10ns of latency. Something glitched out in this discussion.
Yeah, 8.1 ns looks like CAS latency alone.
Easy Rhinox86 days are numbered.
By an 8086-class (16-bit) counter?
Posted on Reply
#70
trsttte
R0H1TWell Apple could in theory wipe out the entire sub $1k Windows laptops if they weren't so greedy SoB's ~ so no you're wrong about "ARM" as a whole! Having said that, like I said in other threads, it really depends a lot on the software you use :ohwell:
They wouldn't need to stop being all that greedy, a slightly cheaper magic keyboard and an ipad air with a proper desktop interface would annihilate most cheap laptops.
TheinsanegamerNApple's not interested in budget machines nor the audiences they attract and the problems they bring.
They don't even need to, an ipad or ipad air if you're feeling fancy with a reasonably price keyboard and a proper desktop interface would kill most laptop. Hell, that's what smartphones started doing with apps for every service and why manufacturers saw fit to start raising the prices (they saw smartphones were reaplacing personal computers and wanted their share of the cake, samsung is on the record saying something to that effect around 2015 irc).

Apple wants to protect macbook sales but their lack of vision is really limiting what their possibilities.
phanbueyThe saddest thing... Im watching the Just Josh livestream of all these... NOT ONE WORKING LINUX ARM VERSION. 7 Laptops...
Tuxedo announced they were developing an ARM laptop with one of these snapdragon elite chips, they'll come eventually. If Tuxedo is doing one, some big white label oem is doing one and so there will be at least a couple on offer from the usual suspects (shenker, tuxedo, system76, etc)
Darmok N JaladThey never made a G5 MacBook Pro
I don't think back then "Pro" was such a marketing gimmick like it is now
Posted on Reply
#71
Psyclown
I’m really not surprised to see windows performing poorly when paired with a newcomer chip like this. I wouldn’t be surprised with any OS being this way really. It just needs more time.
Posted on Reply
#72
Minus Infinity
We want Strix, we want Strix, we want Strix. What do we want? STRIX!

Hopefully fw and software updates will improve the results, I want ARM to succeed, but I always say never buy into a brand new architecture, you'll be a beta tester for a long time.
Posted on Reply
#73
user556
Neo_MorpheusIBM took over but couldn’t justify the expense of developing such chips just for Apple, since they weren’t selling that many systems, so at that point, apple had no choice but to jump to intel, which had more efficient cpus.
Intel didn't make efficient chips at all. They were fast CPUs just through brute force of having the vastly biggest budget.
Posted on Reply
#74
watzupken
I feel the Snapdragon Elite is a significant step up from previous ARM attempts on Windows. From a software perspective, I think it will take time to refine.
Posted on Reply
#75
Visible Noise
phanbueyPlus they did it before with PowerPC to x86
Rosetta 1 wasn’t an Apple product, it was licensed from IBM.
Posted on Reply
Add your own comment
Sep 29th, 2024 03:56 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts