Earlier quoted context omitted.
Process node improvements don’ty bring that much performance.
Given the massive drop in power consumption and therefore heat, they seem to bring inordinate amounts of performance in a mobile chip.
Dissecting the Apple M1 GPU, Part II
181–190 of 195 posts
Re: Dissecting the Apple M1 GPU, Part II
#182Earlier quoted context omitted.
>There is a world of difference in free time between "having a 9-5 job" and "being in high school", though. Funny how this works. In high school I had a ton of free time. In college, not a lot of free time and very stressed. Entering the workforce, again a lot of free time and very stress free. I expect free time will disappear if children ever come into play
> I expect free time will disappear if children ever come into play That would very much depend on how you choose to live. As for me, living in Thailand and being a father of one daughter, I need to earn about 1.500 USD per month for our monthly needs. Which is easily achievable for me with less than a week of work. All extra money I earn above basic needs, I invest. My current client sometimes has work for me 40 hou…
Re: Dissecting the Apple M1 GPU, Part II
#183This might be a stupid question but if someone wants to start with some basic GPU to get an an understanding of how these things work, what that GPU would be that's wide spread, not that archaic?
Re: Dissecting the Apple M1 GPU, Part II
#184So Apple strategy seems to be to commit as little resources as possible to their products knowing that "open source" developers will do their work for free thus Apple will not have to pay extra salaries and taxes? I don't understand why people bother working for free to e.g. run Linux or even write a GPU driver? I get this is a nice developer challenge, and being involved with Apple stuff is still being seen as "cool…
It's not about helping Apple. The M1 beats every x86 CPU in absolute single threaded performance, as well as multicore performance per watt. Hopefully AMD will close the gap (I don't have much hope for Intel), but for now it's an extremely attractive target for Linux.
The M1 is slower in single threaded performance than any AMD Zen 3 CPU at 4.8 GHz or higher clock frequency and also slower than any Intel Tiger Lake or Rocket Lake CPU at 5.0 GHz or higher clock frequency.
For example the maximum recorded single-thread Geekbench 5 score for M1 is 1753, while Ryzen 9 59xx score above 1800 and up to 1876. The first Rocket Lake record at 5.3 GHz is 1896, but it is expected that it will score better than that, above 1900.
In benchmarks that unlike GB5 focus more on computational performance in optimized programs, Intel/AMD have an even greater advantage in ST performance than above. (For example, in gmpbench even the old Ryzen 7 3700X beats Apple M1, even when using on Apple a libgmp that was tuned specifically for M1.)
What is true is that Apple M1 is much faster (on average) in ST than any non-overclocked CPU launched before mid 2020.
Re: Dissecting the Apple M1 GPU, Part II
#185Earlier quoted context omitted.
A 2020 16" Macbook Pro isn't old by any measure. This argument seems disingenuous.
But they are extremely bad with their thermals and Intel is way slower than whatever AMD is pushing right now. The thing is Apple just made quite mediocre hardware. And now they're back where the competition is.
Re: Dissecting the Apple M1 GPU, Part II
#186Re: Dissecting the Apple M1 GPU, Part II
#187Earlier quoted context omitted.
The response from Intel seems to be betting on the Evo platform [1], with third parties announcing laptops like the XPG Xenia XE 1 https://www.intel.com/content/www/us/en/products/docs/evo.ht...
You have to read between the lines here. They make no claims about CPU performance - just integrated GPU performance from Xe (which is a big improvement from previous Iris GPUs.) Then they claim battery life (9 hours, FHD, 250-nits, etc.) What that means is laptop OEMs will have to limit TDP on CPUs - probably 15W or less. Given current Intel chips being very power hungry, these are likely NOT going to be great CPU p…
Am I right to assume we can see benchmarks within the next few weeks?
Re: Dissecting the Apple M1 GPU, Part II
#188Earlier quoted context omitted.
I think to understand the M1, you have to be a Mac laptop user. For years, Mac laptop performance lagged years behind high-end desktop performance -- they have been stuck on 14nm+ process chips with a mobile power budget, while desktop users have had 7nm chips that can draw 500W with no trouble. As a result, what M1 users tell you is fast is what PC desktop users have had for ages. A Threadripper and 3090 will blow t…
I've been high-end desktop Linux user all my life and Thinkpads were my primary choice for laptops. Last two years I've been using x1 carbon gen3 released in 2017 so it's not so far from current-gen Intel laptops. Yeah Air on M1 cannot beat triple 1440p 164HZ monitor setup with high end desktop hardware, but it's still damn impressive. It's has slightly better 16:10 screen, more performance than any of current x1 thi…
Right now, I am torn between a *FHD*, AMD X13, 16GB RAM/500GB SSD for about *1000€* and the Air 16/500 at 1400€. I hate my life for that decision right now...
Re: Dissecting the Apple M1 GPU, Part II
#189Earlier quoted context omitted.
It's not about helping Apple. The M1 beats every x86 CPU in absolute single threaded performance, as well as multicore performance per watt. Hopefully AMD will close the gap (I don't have much hope for Intel), but for now it's an extremely attractive target for Linux.
The M1 beats every old x86 CPU in single threaded performance. The M1 is slower in single threaded performance than any AMD Zen 3 CPU at 4.8 GHz or higher clock frequency and also slower than any Intel Tiger Lake or Rocket Lake CPU at 5.0 GHz or higher clock frequency. For example the maximum recorded single-thread Geekbench 5 score for M1 is 1753, while Ryzen 9 59xx score above 1800 and up to 1876. The first Rocket…
I hope the M1 will bring a change to computation in general..
Re: Dissecting the Apple M1 GPU, Part II
#190Earlier quoted context omitted.
>There is a world of difference in free time between "having a 9-5 job" and "being in high school", though. Funny how this works. In high school I had a ton of free time. In college, not a lot of free time and very stressed. Entering the workforce, again a lot of free time and very stress free. I expect free time will disappear if children ever come into play
> I expect free time will disappear if children ever come into play That would very much depend on how you choose to live. As for me, living in Thailand and being a father of one daughter, I need to earn about 1.500 USD per month for our monthly needs. Which is easily achievable for me with less than a week of work. All extra money I earn above basic needs, I invest. My current client sometimes has work for me 40 hou…
Wrote about it here https://link.medium.com/BAGPsTlChdb