Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Dissecting the Apple M1 GPU, Part II

rosenzweig.io

Post reply on HN
Print view View original

91–100 of 195 posts

Re: Dissecting the Apple M1 GPU, Part II

#91

Post by pimeys »

cwhiz wrote: post #78
vbezhenar wrote: post #33

Earlier quoted context omitted.

What exactly do you expect? x86 is quite competitive. M1 might be slightly better, but it's not like it's miles ahead.

Fiddling around on an M1 MBA it felt faster than my 2020 16" MBP. It's half the weight, seems to get double the battery life, and costs less than 1/3. I just can't even imagine what the gap is going to look like when Apple really refines this down.

You should compare it to other than the old Apple laptops. The Ryzen models, such as ThinkPad T14 are very fast, and if you want to go tenfold from there, there is no comparison with the modern Ryzen desktop CPUs. Why Apple always failed with Intel and its thermals is why they feel so slow compared to the M1.

Re: Dissecting the Apple M1 GPU, Part II

#92

Post by jayd16 »

cwhiz wrote: post #78
vbezhenar wrote: post #33

Earlier quoted context omitted.

What exactly do you expect? x86 is quite competitive. M1 might be slightly better, but it's not like it's miles ahead.

Fiddling around on an M1 MBA it felt faster than my 2020 16" MBP. It's half the weight, seems to get double the battery life, and costs less than 1/3. I just can't even imagine what the gap is going to look like when Apple really refines this down.

>It's half the weight

Its 70% the weight at 70% the volume of the 16". What is the point of comparing the weight of a 13" and a 16" laptop?

Re: Dissecting the Apple M1 GPU, Part II

#93

Post by phkahler »

gonehome wrote: post #82
The_Colonel wrote: post #72

Earlier quoted context omitted.

> My prediction is x86 is dead. I don't see that. At least in corporate environment with bazillion legacy apps, x86 will be the king for the foreseeable future. And frankly I don't really see the pull of ARM/M1 anyway. I mean, I can get a laptop with extremely competitive Ryzen for way cheaper than MacBook with M1. The only big advantage I see is the battery, but that's not very relevant for many use cases - most peo…

This is the first release targeting macOS, I'm not pretending their chips for phones don't exist - but the M1 is still version 0 for macs. > "And frankly I don't really see the pull of ARM/M1 anyway. I mean, I can get a laptop with extremely competitive Ryzen for way cheaper than MacBook with M1..." Respectfully, I strongly disagree with this - to me it's equivalent to someone defending the keyboards on a palm treo.…

Remember, M1 is on the leading edge 5nm fab process. Ryzen APUs are coming and may be competitive in terms of power consumption when they arrive on 5nm.

Apple software is also important here. They do some things very much right. It will be interesting to run real benchmarks with x64 on the same node.

Having said all that, I love fanless quiet computers. In that segment Apple has been winning all along.

Re: Dissecting the Apple M1 GPU, Part II

#94

Post by littlestymaar »

cambalache wrote: post #6

OK I love this, but I am pretty sure my chances of getting a mac in the future are zero. From which side should I expect the PC response? Intel? AMD? Microsoft? ARM? Samsung? I think Apple willingly or not has just obliterated the whole consumer pc market.

> Apple willingly or not has just obliterated the whole consumer pc market.

Apple probably has the best laptop out there as of today, but I don't think Apple sales performances are impacted that much by their hardware perf actually: around 2012-2015 or something they had several years with a subpar mobile phone, both on the hardware a and the software side, and it still sold very well. A few years later, they have the best phone on the market and… it didn't change their dynamic much: it still sells very well, as before. On the laptop market, they have been selling subpar laptops for a few years without much issue, and I guess it won't change much that they now have the best one.

Apple customers will get a much better deal for their bucks, which is good for their long term business, but I don't think it will drive that many people out of the Windows world[1] just for that reason (especially with the migration/compatibility issues which are even worse now than they where running on Intel).

Also, many people outside of HN just don't listen to Apple “revolutionary” announcement, they have used that card too much, for no good reason most of the time, so people just stopped listening (even my friends who are actually Apple customers).

[1]: which is where most people are tbh, and I don't think that many Linux people would switch either.

Re: Dissecting the Apple M1 GPU, Part II

#95

Post by The_Colonel »

gonehome wrote: post #82
The_Colonel wrote: post #72

Earlier quoted context omitted.

> My prediction is x86 is dead. I don't see that. At least in corporate environment with bazillion legacy apps, x86 will be the king for the foreseeable future. And frankly I don't really see the pull of ARM/M1 anyway. I mean, I can get a laptop with extremely competitive Ryzen for way cheaper than MacBook with M1. The only big advantage I see is the battery, but that's not very relevant for many use cases - most peo…

This is the first release targeting macOS, I'm not pretending their chips for phones don't exist - but the M1 is still version 0 for macs. > "And frankly I don't really see the pull of ARM/M1 anyway. I mean, I can get a laptop with extremely competitive Ryzen for way cheaper than MacBook with M1..." Respectfully, I strongly disagree with this - to me it's equivalent to someone defending the keyboards on a palm treo.…

> but the M1 is still version 0 for macs.

Fair enough, it's just important to keep in mind that M1 is a result of decade(s) long progressive enhancement. M2 is going to be another incremental step in the series.

> to me it's equivalent to someone defending the keyboards on a palm treo. This is a major shift in capability ...

That's a completely unjustified comparison. iPhone brought a new way to interact with your phone. M1 brings ... better performance per watt? (something which is happening every year anyway)

What new capabilities does M1 bring? I'm trying to see them, but don't ...

Re: Dissecting the Apple M1 GPU, Part II

#96

Post by localhost »

gjsman-1000 wrote: post #55

Everyone, remember that in 2019 Alyssa was in _High School_. Where do people get this knowledge? It's astounding. She was literally reverse-engineering Mali for Panfrost starting in her Sophomore year.

As one of the older folks here on HN, I fondly remember the time when almost everything had to be done by reverse-engineering. Some friends of mine and I were the first people to reverse engineer the Commodore 4040/8050 disk drive "computers". We had to write all of the software to do this, including custom disassemblers that eventually spat out printouts that we annotated first by hand and later transcribed into source code files. There were no memory maps, and our knowledge of electronics was too rudimentary to figure out much by looking at the traces on the circuit boards. There were no places for folks to discuss these ideas - bulletin boards of the day were one-user-at-a-time things which meant that topics like this were way too niche to garner any discussion at all. I was fortunate enough to grow up in Toronto which was a hot-bed of Commodore hackers and we had a vibrant community that could gather to meet face-to-face to discuss ideas. But in between meetups we had to sit and think harder until we figured it out.

It was a wonderful time to learn about computing from first principles without the distractions that exist today.

Re: Dissecting the Apple M1 GPU, Part II

#97

Post by tenebrisalietum »

varispeed wrote: post #83
tenebrisalietum wrote: post #51

Earlier quoted context omitted.

Maybe because ... those developers want to use Linux on hardware they bought and own instead of the built-in operating system? The developers are helping themselves, not Apple. Apple could save some money by selling bare metal M1's without an OS installed, but then it might get into the hands of people who want a "cheaper Mac but your hacker friend can get it working" and it would damage their brand, so I see why the…

Well, is this M1 really _that_ good to commit considerable amount of time into it instead of working on something more meaningful or benefitting ones personal life more? Are they able to make a commercial product out of it? Unless it gives the person the same kick as fishing or building Lego - but these hobbies don't have a side effect of filling the pockets of a big co. The idea about "cheaper Mac" is weak, because…

> Well, is this M1 really _that_ good to commit considerable amount of time into it instead of working on something more meaningful or benefitting ones personal life more?

M1 is an ARM chip that's up there with Intel desktop PCs. That's awesome. It's possibly the real beginning of the end of the effective Wintel monopoly on personal computing and if we are going to continue to have Linux on hardware that's not locked-down phones it needs to happen. I'd certainly put my effort there if I had the skill.

> Isn't actually more damaging to their brand that they don't support their products that will benefit professional users and that they rely on people doing work for free and thus Apple is avoiding paying fair share?

Apple has $100 billion in cash. Whatever they are doing now, is working.

Re: Dissecting the Apple M1 GPU, Part II

#98

Post by neogodless »

unix_fan wrote: post #42
flatiron wrote: post #8

Earlier quoted context omitted.

The new Ryzen mobile processors should be interesting. Their GPU drivers (while not of the best code quality) are in the mainline Linux kernel. So it all should just “work”

The new mobile chips are basically a mix of new and old stuff, with them rebranding ryzen 2 parts. Kind of disappointing.

But the slightly tweaked "old stuff" is relatively low-end - up to and including the 5700U. You'll find it in thin 'n light, budget and business laptops that will have more than enough power from a Zen 2 core. If you really absolutely need more power, you'll know it and you'll be shopping for a 5800H (or above).

If you don't know enough about CPUs to even read reviews that compare the CPU to other CPUs, then you either don't need the extra IPC of Zen 3 (and you won't notice when you use your laptop day to day) or you just... don't care.

If you care, get a 5600U/5800U or H line and it will never affect you. The laptops these come in should be priced accordingly.

Re: Dissecting the Apple M1 GPU, Part II

#99

Post by junipertea »

jayd16 wrote: post #92
cwhiz wrote: post #78

Earlier quoted context omitted.

Fiddling around on an M1 MBA it felt faster than my 2020 16" MBP. It's half the weight, seems to get double the battery life, and costs less than 1/3. I just can't even imagine what the gap is going to look like when Apple really refines this down.

>It's half the weight Its 70% the weight at 70% the volume of the 16". What is the point of comparing the weight of a 13" and a 16" laptop?

It is faster despite the lower battery capacity and thermals. In fact, the Macbook air has no fan.

Re: Dissecting the Apple M1 GPU, Part II

#100

Post by remexre »

wg0 wrote: post #35

This 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?

Intel's GPUs are fairly well-documented at https://01.org/linuxgraphics/documentation/hardware-specific...

IMO, writing some Vulkan (it being a thin layer over what a modern GPU's "actually" doing) would be good to get fundamentals down first, not the least of which because you'll have the validation layers to yell at you for incorrect usage instead of getting mysterious GPU behavior.

Post reply on HN