Honestly, AppleSilicon feels even better than the benchmarks would suggest I think mainly due to the degree of integration/optimization Apple has been able to do with their own silicon. I jumped from a top of the line i9 MBP to a M1 Max and yeah, the Max benched faster, but the machine felt 5x faster. I attribute a LOT of that to Apple being able to dump virtually all of the system tasks on the E cores freeing up the P cores completely. So even though the i9 wasn't that much slower than the M1 in benchmarks it had this tendency to throttle back to a single core on which everything was trying to run. There is no scenario where an AS Mac isn't running the E cores full speed, so worst case the system is still responsive even if my front app is lagging.
The 1/2 of the problem is Microsoft, which is why Valve is putting all their might into moving away from them.
The battery life differences from SteamOS versus Windows is astounding, because OS differences shouldn't be that large. This is why I say Microsoft is the perfect partner to Intel, because they are the software side sucking to Intel's hardware side sucking. Actually compared to ARM vendors, AMD is not much better than Intel either. Actually with telemetry and spyware bundled with things like Management Engine, AMD PSP, they are going from sucking to the realm of evil.
Blowing x86 apart is incredibly risky for whichever party does it, which is why no party does it - that's the lesson of Itanium - someone is going to make a big bet and lose. Apple doesn't have to worry about someone undercutting their decision - they only have to worry about their own ability to execute.
Why do we have to worry about what Intel/AMD thinks? That is WHY we have this problem in the first place. It's the fault of the lawyers and the bribery they call lobbying in America. They always sided with Intel. They should have ignored Intel and just opened up x86. And since you are having a hard time of comprehension, I will make it clear - "they" meaning the courts.
If Transmeta did what they did running a translation layer, I wonder how much better they would have done without one? At RWT there was a comparison of 90nm Transmeta with 45nm Atom, and the perf/W were similar. Yes, the in-order Atom was a particular sucky chip, but 2 full generations of process technology resulting in similar results is a huge thing, especially since the Transmeta chip was years earlier.. We saw from just having a 3rd vendor through Cyrix how nimble a team could be. 1/3rd the development time with 50 core engineers. x86 isn't as bloated as much as the companies running them are. ARM has true competition, because anyone come in and make a chip. x86 is almost as bad as a monopoly. They are a duopoly.
Wasn't the ST power of Strix point 22W?
In summer I had a highend Arrow Lake laptop in hands that was equipped with a GeForce RTX 5090 mobile. Even though there should supposedly be GPU switching going one, that GPU kept eating like 15W permanently when the laptop was idling, doing light use or just showing desktop (you can imagine the temps and battery life), instead of the 0 W you would expect based on marketing. I hope that was due to a broken configuration and is not the usual case. But getting 45W ST load power for Strix Point feels like a similar case, I would double-check there's not GPU or another component sucking power there. Or, extra cores beyond the one being active...
That system is indeed using 45W. It's not the chip using 45W, it's the system, so the entire laptop. That particular system is inefficient. Other Strix systems are using little over 30W, which is still phenomenally higher than the Macbook at 15W, meaning SoC power is 3x+ the difference.
Facebook
Twitter