Because it ruffles x86 feathers, despite geekbench corresponding very closely to SPEC as well and there being no indication that the results aren’t comparable.
What people willfully conflate this with often is that you shouldn’t compare FLOP numbers between GPU arches and instead rely on benchmarks.
Geekbench when run on Asahi Linux is practically the same as when run on macOS, just like Linux and Windows in the same x86 chip don’t give significant differences.
Processors, not just Apple’s, change constantly between generations. The core instruction set doesn’t change, but they get new capabilities, not just with new instruction sets.
Remember the SoC isn’t just the CPU. It’s display engines, GPUs, storage controllers, video decoders and more.
Even outside of Apple, you’ll see hardware vendors provide Linux patches for their latest CPUs to keep working well. There’s some baseline functionality that works out of the box but it’s never a free ride.
The simulator is a different SDK target than iOS itself.
You have to compile completely independently for it, and depending on your dependencies they may not compile for the simulator.
Additionally the simulator runs a really ancient and feature restricted version of Metal. That means you can’t test a lot of graphical things that the hardware actually supports. I’m not sure if this supports GPU passthrough but the macOS VMs do, so that alone would be a huge improvement if possible.
Sure, you can also have iOS binaries forward relevant iOS SDK symbols to macOS. That doesn’t mean they’re not different SDKs with different limitations, and not everything that is on the store can be patched to run in the simulator because there are legitimately symbols missing or with stubbed functionality.
HBM itself is very expensive but it’s not really fair to compare to LPDDR or GDDR
They’re very different things.
The more logical argument to me is that Apple uses its upgrade price points as more than just direct BOM and rather as a proxy for things that are amortized across all their sales like support/warranty/etc so higher SKUs subsidize the costs of the lower ones.
I’m not sure I follow why the performance is “Insane”
This is a M5 level chip that runs slightly within a ballpark of M5 wattage (afaik M5 is between 15W max on an iPad and 30W max CPU+GPU on a cooled Mac)
This is running in a thermally unconstrained bench setup and has potentially worse power consumption with what will be lower than previous gen performance when this and the alleged M6 are truly out.
So tired of people on HN calling you out for being excited about tech.
It gets M5-level numbers at 12-14W.
It gets about 30% better perf than the A19 Pro at equal wattage on the whole 4W - 8W range.
So no it's not worse power consumption than prev gen. This is ARM's stock GPU having finally caught up and being competitive with Apple and Qualcomm's mobile GPUs.
This is insane to me. Stay cynical if you want, I have the right to be excited about it.
I’m not trying to say you shouldn’t be excited by it. But there’s a significant number of caveats to every single number you posted but you glossed over the points I made.
And in being defensive, you jumped straight from the topic you were discussing (GPU perf) to CPU perf numbers to try and make a point.
There’s a difference between being cynical and pragmatic, just as there’s a difference between being hyped and realistic.
You haven’t seen this in a product. You’re seeing development board numbers. Be excited all you want but it’s a public forum, if you want to just post without any responses make a blog.
No? The numbers I quoted were GPU numbers, sourced from this video [1].
Also I explicitly acknowledged in my first comment that real devices won't be able to draw that kind of power. But 4 watts is 4 watts whether it's in a test bench or a phone.
Oh yes, Claude seems to be loving the word vacuous recently. My test bed side project is full of vacuous this and that now.
I even try and get it to define what it classifies as vacuous and it can’t do so without getting stuck in some kind of trap. It’s like a word with some kind of huge gravity for it.
Though the lawsuits are more complex with multiple parties suing RED, of which Nikon also fought RED and ended up buying them out to win that side of the battle. On the panasonic side it was more of their cinema line of cameras rather than Lumix that was the driver (though they have trickle down)
And prores isn’t necessarily RAW, it’s just one of the variants.
I disagree with your assessment. My twitter feed pre and post Elon’s takeover changes dramatically.
Pre his takeover , it would more reliably show me my niches of design, technology, gamedev etc
After his take over I’d start seeing more and more boosted content from frankly abhorrent individuals. The whole blue check mark thing being paid instead of truly verified also messed with the algorithm.
I’m sure it’s doable to curate it into what you want again, but it was a night and day shift for me and why I eventually left.
Even filtering out content wasn’t enough because it would get boosted through other means.
That's a fair perspective of before/after. And yea, possibly this was just me curating my feed to a point where it's kind/pleasant. It truly is though - mine is free from politics and dinguses, it's just design and ai people I follow.
My feed suddenly started showcasing far-right lunatics and grifters. It didn't settle down until I blocked them all - which was drastic, but did the job.
What people willfully conflate this with often is that you shouldn’t compare FLOP numbers between GPU arches and instead rely on benchmarks.
reply