• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Discussion Qualcomm Snapdragon Thread

Page 82 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Snapdragon X Elite and X Plus (3 8 TFLOP) GPU versions have appeared in Geekbench 6 GPU OpenCL list.

~20.000 points.


For context:

Apple M3 : 30000 points
Apple M2 : 26000 points
Radeon 780M : 26500 points
Radeon 680M : 25000 points
George 1060 : 30000 points.

Hmmm not great if you ask me. Barely quicker than the M1.

I guess to be expected and it's certainly not awful. I was just hoping for a bit more.
 
Hmmm not great if you ask me. Barely quicker than the M1.

I guess to be expected and it's certainly not awful. I was just hoping for a bit more.
This is OpenCL, a GPU Compute Test, not a GPU Graphics test.

Qualcomm's Adreno architecture is known for being weaker in compute. Not a problem in smartphones, where they were mostly used until now.
 
Interestingly it looks like the Samsung with x1e84 is not plagued by performance issues on Geekbench since June 13th.


I wonder if there was a software update.

Regardless, it is a really bad look for a new platform to have such serious performance issues days before launch. How in the world did the software update that caused that regression make it past QA and get released to OEMs mere weeks before launch? Someone deserves to be fired.
 
Regardless, it is a really bad look for a new platform to have such serious performance issues days before launch. How in the world did the software update that caused that regression make it past QA and get released to OEMs mere weeks before launch? Someone deserves to be fired.
Lol. I mean, it is, but it’s a firmware clock cap and limited to some units, the release isn’t even on yet, and it’s only Samsung and Asus you see this from (and even then only some).
 
Cinebench 2024 ST
Screenshot_20240617_091241_Chrome.jpg
I wonder where CPUMonkey sourced these X Elite numbers from...

How does a 2.5% increase in clock speed (4.2 -> 4.3 GHz) for the same CPU give a 5% ST gain?
 
Cinebench 2024 ST
View attachment 101294
I wonder where CPUMonkey sourced these X Elite numbers from...

How does a 2.5% increase in clock speed (4.2 -> 4.3 GHz) for the same CPU give a 5% ST gain?
I mean, lol, think logically about this. It's just sampled data. You could pick a better run from the 4.3GHz set and pick a lower or even midrange number (depending on the std deviations) from the 4.2GHz set, wholla.

Don't read into small stuff like this.
 
I mean, lol, think logically about this. It's just sampled data. You could pick a better run from the 4.3GHz set and pick a lower or even midrange number (depending on the std deviations) from the 4.2GHz set, wholla.

Don't read into small stuff like this.
QC themselves seems to be expecting a max of 128 for X1E84100 in CB2024 ST:
SNAPDRAGON-X-ELITE-PERFORMANCE-1200x783.jpg
 
QC themselves seems to be expecting a max of 128 for X1E84100 in CB2024 ST:
View attachment 101295
Well they expect a 2900 GB6 too which is obviously just a rounded number and not to be taken too seriously, but you can find plenty of 2930 and 2950 GB6 STs for the X1E-84.

At any rate who knows, who cares, it's probably just cooling. Cinebench is a long benchmark even for ST.
 
So which reviewers' reviews of the X Elite / X Elite devices are you looking forward to the most?

Personally, Notebookcheck and Geekerwan are at the top of my list.
 
Yes, in this day and age we definitely need to have reviewers reviewed!
Quis custodiet ipsos custodes?

10631.gif
 
Back
Top