221–230 of 1001 posts
Server Chips: if you removed the GPU, and added ECC - these would be dang nice server chips.
how does this new GPU and "neural engine" perform comparing to Nvidia GPUs, and do they support Tensorflow and something similar to CUDA SDK
Earlier quoted context omitted.
I'm not going to wait for the comparisons this time. Maxing this baby out right now.
Honest question, what do you do where a $6,099 laptop is justifiable?
Not to mention if it makes a 200k salary worker 5% more productive, its a win. (Give or take for taxes.)
It’s interesting that the M1 Max is similar in GPU performance to RTX 3080. A sub $1000 Mac Mini would end up being the best gaming PC you could buy, at less than half the price of an equivalent windows machine.
The comparison to higher end graphics uses the M1 Max 32-core GPU which starts at $3500.
I'm not seeing a way for a Mac Mini to have the M1 Max, and still be priced below $1000.
The benchmark to power consumption comparisons were very interesting. It seemed very un-Apple to be making such direct comparisons to competitors, especially when the Razer Blade Advanced had slightly better performance with far higher power consumption. I feel like typically Apple just says "Fastest we've ever made, it's so thin, so many nits, you'll love it" and leaves it at that. I'll be very curious to see those…
> This also means that every chip Apple creates, from design to manufacturing, will be 100 percent carbon neutral. How is that even possible?
Earlier quoted context omitted.
I thought the memory was one of the more interesting bits here. My 2-year-old Intel MBP has 64 GB, and 8 GB of additional memory on the GPU. True, on the M1 Max you don't have to copy back and forth between CPU and GPU thanks to integrated memory, but the new MBP still has less total memory than my 2-year-old Intel MBP. And it seems they just barely managed to get to 64 GiB. The whole processor chip is surrounded by…
Why 1TB? 640GB ought to be enough for anything...
Earlier quoted context omitted.
Honest question, what do you do where a $6,099 laptop is justifiable?
If you don't max out the HDD space, but max out all the portions which effect performance, it only about half that.
Earlier quoted context omitted.
The big ticket items: Hardware-accelerated VSCode cursor animation. Dedicated button for exiting vim. Additional twelve function keys, bringing the total to 24; further, vectorised function key operations, so you can execute up to 12 "nmap :set background=dark" statements in parallel. Dedicated encode and decode engines that support YAML, TOML and JWT JSON. A neural engine that can approximate polynomial time registe…
You could just say "I want Linux" and get the same point across.
Earlier quoted context omitted.
Really curious if the memory bandwidth is entirely available to the CPU if the GPU is idle. An nvidia RTX3090 has nearly 1TB/s bandwidth, so the GPU is clearly going to use as much of the 400GB/s as possible. Other unified architectures have multiple channels or synchronization to memory, such that no one part of the system can access the full bandwidth. But if the CPU can access all 400GB/s, that is an absolute game…
I suspect the GPU is never really idle. Even simple screen refresh blending say 5 layers and outputting it to a 4k screen is 190Gbits at 144 Hz.