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

Apple Silicon M1: Black Magic Fuckery

singhkays.com

Post reply on HN
Print view View original

111–120 of 1001 posts

Re: Apple Silicon M1: Black Magic Fuckery

#111

Post by sliken »

brundolf wrote: post #74
klelatti wrote: post #70

Earlier quoted context omitted.

I know it's a fast Arm CPU - I've read the Anandtech analysis etc - and that there is lots of extra hardware on the SoC. But the specific point was why is it a Swift machine. What makes it particularly suited to running Swift?

The exact reason is out of my depth, but the original quote makes it clear that there is something. Memory bandwidth would be one possibility.

Extremely low memory latency is another. It's also has 8 memory channels, most desktops have 2. It's an aggressive design, Anandtech has a deep dive. Some of the highlights, lower latency cache, larger reorder buffer, more in flight memory operations, etc.

Re: Apple Silicon M1: Black Magic Fuckery

#112

Post by duskwuff »

CountSessine wrote: post #78
trevyn wrote: post #27

Earlier quoted context omitted.

They stuff the reference count in the unused bits of the 64-bit pointers.

Yikes. That's the same shenanigans that got them into trouble with the 68000. Everyone stuffed data into the top 8 bits of pointers because even though the 68000 had 32-bit addressing registers, it only had a 24-bit address bus and the top 8 bits were dontcare's. Then, the 6802x came out with more address lines and... ...and that's basically why x86_64 was specified to require a particular bit pattern in high-order b…

Tagged pointers are an officially accepted thing in ARM -- the relevant feature is called top-byte ignore (TBI). It only applies to the upper 8 bits of a pointer, leaving 56 bits for addressing.

Re: Apple Silicon M1: Black Magic Fuckery

#113

Post by chipotle_coyote »

dheera wrote: post #40
neilpanchal wrote: post #4

I just got one. I’m blown away by the speed as well. Chrome runs insanely fast! Alas, it’s not developer ready yet. Brew is a mess. Docker doesn’t work. PyCharm is WIP although can use x86 version. I was skeptical of the hype but this little laptop has made me realize how slow everything else is. Unfortunately, while the hardware has accelerated far beyond expectations, the software - specifically MacOS BigSur is a m…

On the other hand, Apple is fashion. They have always advertised and placed themselves as such. If you want functionality, you need a non-Mac running Linux. I'm just hoping we have better silicon options soon, for those of us who don't want customization-unfriendly, upgrade-unfriendly Apple hardware.

While you're getting rightfully downvoted (although I won't join in), it's worth underlining how much "they have always advertised and placed themselves as such" is utter nonsense. Apple has always advertised functionality and performance of their products, even when the case was (charitably) pretty shaky. They advertised their PowerPC Macs that way, up until the point they couldn't, then advertised their Intel Macs that way. Now they're advertising their ARM Macs that way. They proudly advertised their moves to 64-bit CPUs. They proudly advertised to consumers how cool it was that OS X was "Unix certified." Repeat: to consumers.

Yes, Apple is super conscious of design, occasionally to an obvious fault, from "butterfly" keyboards back through the G4 Cube. But they've absolutely always been interested in aiming for seriously high-end machines, from all of the Mac Pro incarnations all the way back to oldies like the Mac IIfx.

I hope other people make competitive silicon, too. I want Linux around and high-performing, and it's still a bit of an open question what the future holds for development environments on ARM-based Macs. But it is just so wearying for people who are otherwise technically literate to still be trotting out "Apple has never cared about anything but looks" after literally decades of obvious counter-examples.

Re: Apple Silicon M1: Black Magic Fuckery

#114

Post by murukesh_s »

neilpanchal wrote: post #4

I just got one. I’m blown away by the speed as well. Chrome runs insanely fast! Alas, it’s not developer ready yet. Brew is a mess. Docker doesn’t work. PyCharm is WIP although can use x86 version. I was skeptical of the hype but this little laptop has made me realize how slow everything else is. Unfortunately, while the hardware has accelerated far beyond expectations, the software - specifically MacOS BigSur is a m…

>Chrome runs insanely fast! Alas, What hardware you were using before? I am using MBP retina 2013 and chrome loads and run fast. Browsing was never a bottleneck except few heavily bloated (ads and stuff) pages. I have noticed chrome can slow down on few windows machine with poorer hardware(which is the case of 90% of windows laptops).

Re: Apple Silicon M1: Black Magic Fuckery

#115

Post by nottorp »

nojito wrote: post #101
darren_ wrote: post #87

Earlier quoted context omitted.

This quote doesn’t really cover why M1 macs are more efficient with less ram than intel macs? You’ve got a memory budget, it’s likely broadly the same on both platforms, the speed at which your retains/releases happen isn’t going to be the issue. it’s not like intel macs use GC where m1 uses RC. (It explains why iOS does better with less ram than android, but the quote is specifically claiming this as a reason for 8G…

The quote right after explains your concerns. >The memory bandwidth on the new Macs is impressive. Benchmarks peg it at around 60GB/sec–about 3x faster than a 16” MBP. Since the M1 CPU only has 16GB of RAM, it can replace the entire contents of RAM 4 times every second. Think about that…

Sounds like some form of GDDR instead of plain DDR. Not only faster, but I bet simultaneously accessible from both the CPU and GPU.

Re: Apple Silicon M1: Black Magic Fuckery

#116

Post by pritovido »

berkut wrote: post #15

I don't quite understand how 'retain' and 'release' can be more memory efficient on Apple Silicon than x86.... I can understand how they can be more efficient from a performance standpoint in terms of more efficient reference counting, but I don't understand how that translates to less memory usage which is apparently what's being argued... ? Unless on x86 some of the 'free's when the ref counts hit 0 were being batc…

It is a simple process, everything that you do in a language needs to be mapped into lower level instructions.

If the lower level hardware instruction does not exist, you use multiple of other instructions to emulate that.

If you add a low level instruction that maps a very common high level operation in hardware, you don't need to call 5 to 10 software functions(extremely expensive),each calling lots of opcodes but just can execute a single opcode and works by hardware beings extremely faster.

It is not hard to be better than Microsoft here. From my personal experience and having disassembled lots of their code they always were lazy bastards. They cared 0 about efficiency. Why should they? They had monopolies like Office or Windows giving them over 95% margins. They could just use the money they printed to buy everything instead of competing.

Lisp machines did that (adding opcodes that map the high level language) with the most common Lisp operators. Those machines were extremely expensive, in the hundreds of thousands of dollars because few could afford that. Apple sells in massive scale, in the hundreds of millions of CPUs per year, making this cheap for them.

Re: Apple Silicon M1: Black Magic Fuckery

#117

Post by sliken »

liamcardenas wrote: post #91

I know very little, so perhaps someone could enlighten me. But I am curious how Apple Silicon will be for machine learning. When Apple releases a MacBook Pro with 64GB of unified memory (assuming they will) — won’t that be amazing for machine learning? I am under the impression that GPU memory is a huge factor in performance. Also, is there any way that the neural engine can accelerate training — or is it just for ex…

https://blog.tensorflow.org/2020/11/accelerating-tensorflow-...

So way better than a regular Intel CPU, I've heard comparisons with the GTX 1050. Definitely not going to replace a top of the line GPU for ML.

Re: Apple Silicon M1: Black Magic Fuckery

#118

Post by Scarbutt »

megablast wrote: post #97
ianhowson wrote: post #26

Earlier quoted context omitted.

I don't think retain/release perf has anything to do with memory consumption, but I have seen a bunch of reviews claiming that 8GB is perfectly fine. This is fascinating to me, because: (a) every 8GB Mac I've used in the past has been unusably slow (b) since upgrading my 32GB Hackintosh to Big Sur, my usual 40GB working set is only about 20GB. (c) My 2015 16GB MBPr with Big Sur is also using about half as much physic…

Every 8gb mac I’ve used before was fine, and that was with running Xcode, Firefox, photoshop, mail, terminal, and other programs.

4GB MBA user here, don't have any problems either running Chrome or Firefox with 10-20 tabs and iTerm (Safari does feel much faster than other two and my dev enviroment is on a remote server though).

Re: Apple Silicon M1: Black Magic Fuckery

#119

Post by nottorp »

meragrin_ wrote: post #75
klelatti wrote: post #66

Earlier quoted context omitted.

But how? It has an Arm CPU - how does it differ from any other machine with a 64 bit Arm CPU?

I doubt Apple allows anyone with the knowledge to speak about it.

This is where it's worth pointing out that Apple is an ARM architecture licensee. They're not using a design from ARM directly, they're basically modifying it however it suits them.
Post reply on HN