Good point
Something interesting, Apple and ARM seem to be going high IPC and lower clocks vs Qcomm going higher clocks and relatively lower IPC... but then Apple and Qualcomm use the same general caching setup (and interestingly enough, Tenstorrent too) while ARM uses the more traditional one.
This is the laptop part, yeah? We don't know that the clock rate is accurate. But it being roughly correct is a very simple explanation to the low results in e.g. ... all the non-SME subtests.
The part in question is meant for smartphones. I mean Snapdragon 8 Elite 2 that the leak is about.
The expensive team failing to deliver is the easy answer, but not a complete certainty. The new team still had to integrate in a complex organization, and that cost (in time, stress, politics etc) may reflect on the Geekbench sheet more than we'd like.
4.74 is the figure reported by CPU itself.
Very true, GB6 clock readings are wildly inconsistent. Given that the predecesessor already pulls considerable amount of power @ 4.37, I wouldn't be surprised if 4.7 is only achievable in actively cooled devices (or in a fridge lmao)
Here’s a good benchmark for memory latency etc, been playing with it. Will share my results soon.
github.com
I'll try compiling it in Windows with aggressive optimizations if possible (python libs and include folder may pose a challenge
). 
My mildly tweaked 245KF's 10 cores (6 Lion Cove and alternate Skymonts disabled) vs. yours: https://browser.geekbench.com/v6/cpu/compare/13456504?baseline=13457441
Zen 5 or GB6...
we kind of knew that already that's why i liked GB5 it's MT Scaling was decent and ST as well
You sure theyre using the same power limits? Does the clockspeed url show they were running the same clocks or was the asus at an advantage in the test?
Haven't checked that. The Acer one is acing the bandwidth sensitive MT tests though. Wouldn't be able to do that with lower power limits I think.
Huh? DDR5 4800 JEDEC does have more bandwidth than DDR4 3200 JEDEC, so I am unsure what your initial complaint is if the DDR5 one is doing better on the bandwidth sensitive tests?
I was lamenting that DDR5 is more bandwidth focused at the expense of latency which hurts many workloads and allows DDR4 to pull ahead. They could at least have strived to release just the initial DDR5-4800 spec with CL36 instead of something like CL46+. Then even these bargain bin laptops could've extracted optimal performance out of their scrawny CPUs.
CL46+? The vast majority of 4800 JEDEC is CL40. CL42 is the worst bin per JEDEC.
My bad. I misremembered probably coz I recall some reviews using bad Corsair CL46 RAM. But that CL34 bin was pretty sweet. Wish they had launched with that.
It feels like DDR5 barely scraped out the door and hardly worked when it first came out. I don't think launching with 4800CL34 was ever going to happen.
Facebook
Twitter