So why build powerful laptops? Simple: people want powerful laptops. Remoting to a desktop isn't really a slam dunk experience, so having sufficient local firepower to do real work is a selling point. I do work on both a desktop and a laptop and it's nice being able to bring a portable workstation wherever I might need it, or just around the house.
I'd work from my workstation at all times if I could. Tramp is alright, but not too fast and fundamentally can't make things transparent.
This solves those problems but apparently uncovers a new one.
Surely the vast majority of laptops sold in the last five years don't have unified memory yet.
- The CPU/GPU memory are shared (does not have to be dedicated to be used by either).
- You don't need to copy data in memory to move it between the CPU/GPU.
- It still uses separate caches for the CPU & GPU but the two are able to talk to each other directly on the same die instead of an external bus.
But these have long been true of traditional APUs/iGPUs, not new changes. I did even see some claims Apple put the memory on die too and that's what makes it unified but checking that it seems to still actually be "on package", which isn't unique either, and it wouldn't explain any differences in access patterns anyways. I've been particularly confused as to why Strix Halo would now qualify as having Unified Memory when it doesn't seem anything is different than before, save the performance.
If anyone has a deeper understanding of what's new in the Unified Memory approach it'd be appreciated!
Reading about HSA again (it's been many years) it seems like ARM was one of the ones originally part of defining it back then and I wonder if Apple actually did anything different on top this at all or just branded/marketed the use of what was already there.
It seems there are 3 key things which distinguish the modern "unified memory architecture" from its predecessors:
1. Pointer passing instead of buffer copying
2. Separate bus for memory access alongside the PCIe bus
3. No partitioning of RAM into exclusive CPU vs. GPU areas
These features seem to have come at different times, and it's the combination of all three that defines the modern approach. Broadly speaking, whereas classic iGPUs were still functionally "peripheral devices", modern UMA/HSA iGPUs are coequal partners with their CPUs.AMD seems to have delivered the first hardware meeting these criteria about 8-9 years ago, beating Apple to the punch by a couple years. However, AMD's memory bandwidth can be quite a bit behind Apple's. The M1 Pro handily beats anything AMD had out at the time (200 GB/s vs. 120 GB/s), and the M1 Max has double that bandwidth.
Framework (I believe) made one of these into a purchasable desktop.
The mini-PC market (which basically all uses laptop chips) seems pretty robust (especially in Asia/China). They've basically torn out the bottom of the traditional small form factor market.
They tend to come out much slower than the laptop chips, or the "CPU-only" desktop chips.
This is one of the more recent examples: https://www.amd.com/en/products/processors/desktops/ryzen/80...