The M4 frequency is 4.41GHzOn a different topic, Arm's hesitancy to put absolute numbers on its charts is not inspiring, but if we want to do some pixel peeping:
With the helpful note from @SarahKerrigan that "2023 Best-in-Class @ 3.8GHz" is likely referring to the late 2023 Apple A17 Pro (P-cores @ 3.78 GHz), as it lines up quite closely:
Each tick mark appears to be 10%. And, it seems to align up: the A17 Pro is ~28% faster in 1T than the 8G3 for Galaxy, which is close to the chart's ~26% faster via the rough bar width.
From @uzzi38's earlier image, I've added it, too, as 1.15x multipliers if "ISO" seemingly means frequency only.
Predicted 1T GB6.2 scores & "IPC" are in bold and were calculated from the bar widths. Thus, for the "Cortex-X925 @ 3.8 GHz" score, it's the X4 2287 base score * 1.33 bar width = 3041.71, rounded to 3042.
Arm Marketing Name Rough Bar Width Possible SoC Clock GB6.2 1T GB6.2 1T Pts / GHz "IPC" "IPC" Relative 2023 Premium Android 1.0 QC SD8G3 for Galaxy 3.39 GHz 2287 674.6 100.0% 2023 Best-in-Class @ 3.8 GHz 1.26x Apple A17 Pro 3.78 GHz 2930 775.1 114.9% Cortex-X925 @ 3.8 GHz 1.33x ?? 3.80 GHz 3042 800.5 118.7% Cortex-X925 @ 38 GHz (+ sw & sys "optimizations") 1.36x ?? 3.80 GHz 3110 818.5 121.3% X925 vs X4 "ISO" 1.15x ?? 3.60 GHz 2793 775.8 115.0% X925 vs X4 "ISO" 1.15x ?? 3.80 GHz 2948 775.8 115.0% n/a n/a Apple M4 4.38 GHz 3715 848.2 125.7%
Sources:
//
- 2023 Premium Android: Snapdragon 8G3 for Galaxy (X4 @ 3.39 GHz) = 1.0x
- 2023 Best-in-Class @ 3.8 GHz: Apple iPhone 15 Pro Max (P-core at 3.78 GHz)
- Apple M4 GB6.2 run
So is X925 a GB6.2 1T Perf / GHz gain of +15% or +19% over X4? I can't argue that my pixel counting nor rounding are very precise.
Thus a range of GB6.2 1T runs, assuming +15% Pts / Ghz (2nd chart estimate from "ISO" comparisons) to +18.7% Pts / Ghz (1st chart estimates from "1.33x").
Hypothetical 3.6 GHz X925 core: ~2793 → ~2883
Hypothetical 3.8 GHz X925 core: ~2948 → ~3042
I'd rather not consider the "optimized" estimate (+21.3% IPC gain) as it's unclear what those optimizations actually are and how they would affect the Cortex-X4.
All this, when Arm could just label their silly charts. I might have some typos to fix tomorrow, too.
Your posts may be few in quantity, but great in quality!On a different topic, Arm's hesitancy to put absolute numbers on its charts is not inspiring, but if we want to do some pixel peeping:
With the helpful note from @SarahKerrigan that "2023 Best-in-Class @ 3.8GHz" is likely referring to the late 2023 Apple A17 Pro (P-cores @ 3.78 GHz), as it lines up quite closely:
Each tick mark appears to be 10%. And, it seems to align up: the A17 Pro is ~28% faster in 1T than the 8G3 for Galaxy, which is close to the chart's ~26% faster via the rough bar width.
From @uzzi38's earlier image, I've added it, too, as 1.15x multipliers if "ISO" seemingly means frequency only.
Predicted 1T GB6.2 scores & "IPC" are in bold and were calculated from the bar widths. Thus, for the "Cortex-X925 @ 3.8 GHz" score, it's the X4 2287 base score * 1.33 bar width = 3041.71, rounded to 3042.
Arm Marketing Name Rough Bar Width Possible SoC Clock GB6.2 1T GB6.2 1T Pts / GHz "IPC" "IPC" Relative 2023 Premium Android 1.0 QC SD8G3 for Galaxy 3.39 GHz 2287 674.6 100.0% 2023 Best-in-Class @ 3.8 GHz 1.26x Apple A17 Pro 3.78 GHz 2930 775.1 114.9% Cortex-X925 @ 3.8 GHz 1.33x ?? 3.80 GHz 3042 800.5 118.7% Cortex-X925 @ 38 GHz (+ sw & sys "optimizations") 1.36x ?? 3.80 GHz 3110 818.5 121.3% X925 vs X4 "ISO" 1.15x ?? 3.60 GHz 2793 775.8 115.0% X925 vs X4 "ISO" 1.15x ?? 3.80 GHz 2948 775.8 115.0% n/a n/a Apple M4 4.38 GHz 3715 848.2 125.7%
Sources:
//
- 2023 Premium Android: Snapdragon 8G3 for Galaxy (X4 @ 3.39 GHz) = 1.0x
- 2023 Best-in-Class @ 3.8 GHz: Apple iPhone 15 Pro Max (P-core at 3.78 GHz)
- Apple M4 GB6.2 run
So is X925 a GB6.2 1T Perf / GHz gain of +15% or +19% over X4? I can't argue that my pixel counting nor rounding are very precise.
Thus a range of GB6.2 1T runs, assuming +15% Pts / Ghz (2nd chart estimate from "ISO" comparisons) to +18.7% Pts / Ghz (1st chart estimates from "1.33x").
Hypothetical 3.6 GHz X925 core: ~2793 → ~2883
Hypothetical 3.8 GHz X925 core: ~2948 → ~3042
I'd rather not consider the "optimized" estimate (+21.3% IPC gain) as it's unclear what those optimizations actually are and how they would affect the Cortex-X4.
All this, when Arm could just label their silly charts. I might have some typos to fix tomorrow, too.
And Oryon has neither!So Cortex X925 has SVE but no SME.
Apple M4 has SME but no SVE.
Anybody?Are there any Geekbench 6 subtests that benefit from SVE2, like object detection does with SME?
Here. Yes, it does. SVE is supported.Anybody?
old design.And Oryon has neither!
They can, but 15W 1t boost in phones is no bueno.because I don't expect Mediatek will clock it at 3.8 GHz.
the x925 is also a laptop core, on a WoA laptop it is more likely. we will see at computex?Your posts may be few in quantity, but great in quality!
This tracks with rumours that next gen Dimensity 9400 with Cortex X925 will have a GB6 score of 2700-2800. It's not reaching 3000, because I don't expect Mediatek will clock it at 3.8 GHz.
See Post in thread 'NV Re-Enter ARM PC market in 2025!'the x925 is also a laptop core, on a WoA laptop it is more likely. we will see at computex?
GB is probably getting pumped by additional SIMD units so yea.It looks likes the IPC increase for SPECINT may only be around ~8% if we assume 3.4 GHz for X4 vs 3.8 GHz for X925 was used.
This is why Samsung should never have shut down the Mongoose team. They're now totally beholden to ARM as their only CPU provider, and they're getting squeezed.Mediatek isn't the only culprit. Samsung is still using A78 cores for their midrange SoCs.
Exynos 1280 : 2×A78 + 6×A55
Exynos 1380 : 4×A78 + 4×A55
Exynos 1480 : 4×A78 + 4×A55
3 generations of SoCs using the same cores. I am beyond outraged.
I would be somewhat sated if they had put an X1 in the 1480. But they didn't. The poor ST performance of the A78 really hurts the experience in the midrange Galaxy phones, becuase Samsung's OneUI android skin is really heavy and needs strong ST performance to have a smooth experience.
Idk man. Mongoose cores were using more die area than Apple's P cores, while having similar performance to ARM's A7x cores and worse efficiency. In fact, Mongoose M6, the 2021 core (which was cancelled), was rumoured to add SMT.This is why Samsung should never have shut down the Mongoose team. They're now totally beholden to ARM as their only CPU provider, and they're getting squeezed.
M6.Mongoose M5, the 2021 core (which was cancelled), was rumoured to add SMT.
2010 called, wants Moorestown back.SMT in phones!
Wake up, the x86 everywhere mantra has long died. Intel piled up poor chips for years while cheating on benchmarks. That was so funny to watch. Complacency kills.2010 called, wants Moorestown back.
It's nothing to sneeze at.Samsung is still using A78 cores for their midrange SoCs
Got to hand it to Samsung, they really hung in there even when it was clear Mongoose just wasn't paying out - meanwhile QC folded in just one generation for Kryo.Idk man. Mongoose cores were using more die area than Apple's P cores, while having similar performance to ARM's A7x cores and worse efficiency. In fact, Mongoose M6, the 2021 core (which was cancelled), was rumoured to add SMT.
SMT in phones!
Edit: corrected to M6
Back when Huawei/HiSilicon wasn't getting gimped by the US govmt that would have been possible, or at least the equivalent hardware as they produced SBCs using HiSilicon SoCs from the Mate and Px line of phones.Imagine an SBC with Snapdragon 8 Gen 3.
At that time yes they look bad but since A78 Arm mid cores don't have any meaningful upgrade, A710 and A715 they are same as A78 and A720 isn't that fast compare to A78, so if Samsung persist probably they would have better core by now.Idk man. Mongoose cores were using more die area than Apple's P cores, while having similar performance to ARM's A7x cores and worse efficiency. In fact, Mongoose M6, the 2021 core (which was cancelled), was rumoured to add SMT.
SMT in phones!
Edit: corrected to M6
Yes, imagine: https://www.lantronix.com/products/snapdragon-8-gen-3-mobile-hardware-development-kit/Imagine an SBC with Snapdragon 8 Gen 3.
Did you forget that Cortex X series exists.At that time yes they look bad but since A78 Arm mid cores don't have any meaningful upgrade, A710 and A715 they are same as A78 and A720 isn't that fast compare to A78, so if Samsung persist probably they would have better core by now.
It has been a while since i used WOA, but the x86-64 emulator did not emulate AVX when I used it, hopefully Microsoft has a solution for that.From the way the FEX-emu devs talk about AVX on their discord I'm pretty sure that they don't emulate it either.
this. Unfortunately Qualcomm won’t sell a chip even remotely cheap enough for that. The SoC in the pie is under $10.It's nothing to sneeze at.
RPi5 and RK3588 are still stuck on A76 after all, and my poor ODROID N2+ with its AML S922 is stuck on A73 😭
Geez they could literally sell midrange phone SoCs for SBCs and smoke everything on the market.
Dimensity 9400 will reportedly clock it's Cortex X925 core at 3.4 GHz.
View attachment 99986
So according to ikjadoon's calculations based on ARM'S numbers, Dimensity 9400 should have a Geekbench 6 score of ~2700. That actually tracks with the leaked Geekbench scores.
Meanwhile Qualcomm is cooking up 4.2 GHz...
View attachment 99987
Well the problem on SBC is that they need to be cheap, sub $100 or very low 100s, anything higher and you have better x86 options.It's nothing to sneeze at.
RPi5 and RK3588 are still stuck on A76 after all, and my poor ODROID N2+ with its AML S922 is stuck on A73 😭
Geez they could literally sell midrange phone SoCs for SBCs and smoke everything on the market.
Meaning what?This is NOT the first time something like this has happened.