> 3-nanometer technology
Wow. I remember being assured that we would never reach even low double-digit nanometer processes.
Apple introduces M4 chip
961–970 of 1001 posts
Re: Apple introduces M4 chip
#962Re: Apple introduces M4 chip
#963I get frustrated seeing this go into the iPad and knowing that we can't get a shell, and run our own binaries there. Not even as a VM like [UserLAnd]( https://userland.tech ). I could effectively travel with one device less in my backpack but instead I have to carry two M chips, two displays, batteries, and so on... It's great to see this tech moving forward but it's frustrating to not see it translate into a more si…
yup - im honestly tired of the Apple ~~~jail~~~ ecosystem. I love the lower power usage/high efficiency of ARM chips but the locked down ecosystem is a drag. Just the other day, I was trying to get gpu acceleration to work within a vm on my m1 mac. I think it’s working? But compared to native it’s slow. I think it’s just a misconfig, somewhere (ie, hypervisor or qemu or UTM or maybe the emulation service in vm). On o…
gpu passthrough for VMs is not supported on apple silicon period afaik. there may be some "native" renderer built on top of metal but apple doesn't support SR-IOV or "headless passthrough".
https://chariotsolutions.com/blog/post/apple-silicon-gpus-do...
otoh no, it is not "more or less [automatic]" in other hardware either, SR-IOV has been on the enthusiast wishlist for a ridiculously long time now because basically nobody implements it (or, they restrict it to the most datacenter-y of products).
intel iGPUs from the HD/UHD Intel Graphics Technology era have a concept called GVT-g which isn't quite SR-IOV but generally does the thing. Newer Xe-based iGPUs do not support this, nor do the discrete graphics cards.
AMD's iGPUs do not have anything at all afaik. Their dGPUs don't even implement reset properly, which is becoming a big problem with people trying to set up GPU clouds for AI stuff - a lot of times the AMD machines will need a hard power reset to come back.
NVIDIA GPUs do work properly, and do implement SR-IOV properly... but they only started letting you do passthrough recently, and only 1 VM instance per card (so, 1 real + 1 virtual).
Curious what you're using (I'm guessing intel iGPU or nvidia dGPU) but generally this is still something that gets Wendell Level1techs hot and bothered about the mere possibility of this feature being in something without a five-figure subscription attached.
https://www.youtube.com/watch?v=tLK_i-TQ3kQ
It does suck that Apple refuses to implement vulkan support (or sign graphics drivers), I think that's de-facto how people interact with most "hardware accelerated graphics" solutions in vmware or virtualbox, but SR-IOV is actually quite a rare feature, and "passthrough" is not sufficient here since the outer machine still needs to use the GPU as well. The feature point is SR-IOV not just passthrough.
Re: Apple introduces M4 chip
#964I've got a Mac Pro paperweight because the motherboard went. It's going to the landfill. I can't even sell it for parts because I can't erase the SSD. If they didn't solder everything to the board you could actually repair it. When I replace my current Dell laptop, it will be with a repairable framework laptop.
Even repairable only buys you a few years repairability that actually makes sense. For example something similar happened to me, lost the mac mobo on a pre solder addiction model. Only thing is guess how much a used mobo is for an old mac: nearly as much as the entire old mac in working shape. It makes no sense to repair it once the computer hits a certain age between the prices of oem parts and the depreciation of c…
ok but now get this: what if we started a program where people prepay part of the repair with an initial fee, and then for a couple years they can have their laptop repaired at a reduced, fixed price? That helps secure the supply chain. You could then partner with a retail computer store (or start your own!) and have a network of brick-and-mortar stores with subject-matter experts to perform the repairs as well as more minor troubleshooting etc. It’d basically be like healthcare, but for your computer!
I think if you partnered with a major computer brand, that kind of thing could really be huge. Maybe someone like framework perhaps. Could be a big brand discriminator - bring that on-site service feel to average consumers.
Re: Apple introduces M4 chip
#965Earlier quoted context omitted.
If these things will ever get MacOS support it will be useless with 8 GB of Ram. Such a waste of nice components.
I have a minimum of 64GB on my all my main developer machines (home, work, laptop), but I have a spare laptop with only 8GB of RAM for lightweight travel. Despite the entire internet telling me it would be "unusable" and a disaster and a complete disaster, it's actually 100% perfectly fine. I can run IDEs, Slack, Discord, Chrome, and do dev work without a problem. I can't run a lot of VMs or compile giant projects wi…
> 8gb is actually 100% perfectly fine
Thus making your three other machines 400% perfectly fine?
Re: Apple introduces M4 chip
#966Re: Apple introduces M4 chip
#967Earlier quoted context omitted.
On one hand, it's crazy. On the other hand, it's pretty typical for the industry. Average performance per watt doubling time is 2.6 years: https://newsroom.arm.com/blog/performance-per-watt#:~:text=T... .
It's a shame performance per watt doesn't double every 2.6 years for modems and screens.
Watts per pixel probably did something close for a long time for screens.
Same for Watts per bit.
There's just a lot more pixels and bits.
Re: Apple introduces M4 chip
#968Together with next-generation ML accelerators in the CPU, the high-performance GPU, and higher-bandwidth unified memory, the Neural Engine makes M4 an outrageously powerful chip for AI. In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending dat…
> In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending data up to the cloud for processing). Their primary business goal is to sell hardware. Yes, they’ve diversified into services and being a shopping mall for all, but it is about selling lu…
What do you mean luxury? Samsung produces phones that are 2x more expensive and are more luxurious.
E.g. Apple still doesn't offer a flipphone that turns into a tablet when you open it.
Re: Apple introduces M4 chip
#969Together with next-generation ML accelerators in the CPU, the high-performance GPU, and higher-bandwidth unified memory, the Neural Engine makes M4 an outrageously powerful chip for AI. In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending dat…
In case it is not abundantly clear by now: Apple's strategy is to turn developers into slaves.
Run away from these temptations. You will never truly own the hardware anyway.
Re: Apple introduces M4 chip
#970Together with next-generation ML accelerators in the CPU, the high-performance GPU, and higher-bandwidth unified memory, the Neural Engine makes M4 an outrageously powerful chip for AI. In case it is not abundantly clear by now: Apple's AI strategy is to put inference (and longer term even learning) on edge devices. This is completely coherent with their privacy-first strategy (which would be at odds with sending dat…
Every embedded company is pushing ML at the edge with inference engines. Check out MLPerfTiny. They’ve been benchmarking all sorts of edge AI since 2019.