881–890 of 1001 posts
Earlier quoted context omitted.
True, but you are talking about devices that are 4-6 years old. Storage is now soldered. Ram has been soldered for a while now, and with Apple Silicon its part of the SoC.
Perhaps leading to fewer failures and longer device lifespans. As far as I understand, the less components and heat, the longer the electronics keep working.
Earlier quoted context omitted.
Hyper threading has nothing to do with instruction decode. It's for hiding memory latency. The sparc T line is 8 way threaded.
It's slightly more general than that, hiding inefficient use of functional units. A lot of times that's totally memory latency causing the inability to keep FUs fed like you say, but i've seen other reasons, like a wide but diverse set of FUs that have trouble applying to every workload.
Earlier quoted context omitted.
In this context the absence of the 27 inch iMac was interesting. If these SoC were not deemed to be 'right' for the bigger iMac then possibly a more CPU focused / developer focused SoC may be in the works for the iMac?
I doubt they are going to make different chips for prosumer devices. They are going to spread out the M1 pro/max upgrade to the rest of the lineup at some point during the next year, so they can claim "full transition" through their quoted 2 years. The wildcard is the actual mac pro. I suspect we aren't going to hear about mac pro until next Sept/Oct events, and super unclear what direction they are going to go. Mayb…
Earlier quoted context omitted.
You are mistaken. On both PS3 and Xbox 360 CPU and GPU is on different chips and made by different vendors(CPU made by IBM and GPU by Nvidia in case of PS3 and CPU by IBM and GPU by ATI for Xbox 360). Nonetheless in PS4/XOne generation they both use single die with unified memory for everything and their GPU could be called integrated.
For the 360, from 2010 production (when they introduced the 45nm shrink), the CPU and GPU was merged into a single chip.
Earlier quoted context omitted.
Sounds more like using a sword where a knife is needed.
So what’s your proposal? How big would a “phone” be with all those features that an iphone pro has? I am by no means an apple fanboy, but the same way a modern car engine can’t just be tweaked the way it was 50 years ago due to all the miniaturizations that are in large part due to efficiency gains, the same is just as true of phones. But at the same time, a single chip with everything included will also make these p…
Earlier quoted context omitted.
Does an Intel 286 without coprocessor count? C64? I remember those, but I wouldn't say I'm extremely old (just regular old).
The C64 was discontinued in 1994 but is technically still available in 2021 as the C64 Mini. ;-)
Earlier quoted context omitted.
In this context the absence of the 27 inch iMac was interesting. If these SoC were not deemed to be 'right' for the bigger iMac then possibly a more CPU focused / developer focused SoC may be in the works for the iMac?
I doubt they are going to make different chips for prosumer devices. They are going to spread out the M1 pro/max upgrade to the rest of the lineup at some point during the next year, so they can claim "full transition" through their quoted 2 years. The wildcard is the actual mac pro. I suspect we aren't going to hear about mac pro until next Sept/Oct events, and super unclear what direction they are going to go. Mayb…
Earlier quoted context omitted.
On reflection I think they've decided that their pro users want 'more GPU not more CPU' - they could easily have added a couple more CPU cores but it obviously wasn't a priority. Agreed that it's hard to see how designing a CPU just for the Mac Pro would make any kind of economic sense but equally struggling to see what else they can do!
There is only so much you can do improving the CPU. On the other hand, we still haven't really reached the limit for GPUs.
Earlier quoted context omitted.
My mistake. But it doesn't have a 32 core GPU! Agreed these counts look high - but the fact that they can slot this into a $3,499 laptop is remarkable and must say something about the cost effectiveness of TSMC 5nm process.
The CPU may not have a 32 core GPU inside it but that doesn't stop you from adding the 2 numbers together and seeing it's still significantly less than 57 billion. Would be very curious to see what took all of the die space. Neural engine? Those additional video encoding engines? I doubt we'll get to know unfortunately.