Ask HN: Can competitors catch up to Apple Silicon? • Hacker News Board

Re: Ask HN: Can competitors catch up to Apple Silicon?

#301

Post by hajile » Tue, Jul 05, 2022, 4:25 AM UTC

saagarjha wrote: post #289

hajile wrote: post #232

Earlier quoted context omitted.

The X2 cores in 8cx gen3 get similar performance to Zen 2 U-series chips while using 7-10w instead of 15-50w. How many more ARM chips have to get equivalent performance at a tiny fraction of the power before people will finally start considering that either AMD and Intel hire the most incompetent people out there or that ISA actually matters?

The competent people say that ISA doesn’t matter, so there’s that.

Do their actions match their words?

ARM could have extended their ARMv7 ISA to also be 64-bit without much trouble at all (plenty of space in the ISA). Instead, we got a ground up redesign that has more in common with MIPS64 than with ARMv7 (to the point that it's fascinating that ARM and some others bought MIPS just to get patent rights before immediately selling them off again).

I'm sure the go-to individual here is Jim Keller.

First, were his words free from constraint? If he said "x86 is crap and we should be using ARM or RISC-V" while working for those companies, how long would it take for him to be fired? Even if he were working at another company, saying that would burn a bridge that has kept him fed for decades. Would that be worth it?

He later said that if he were designing a new chip from the ground up, he'd probably go with RISC-V. He then proceeded to do that when he went to work for TensTorrent even though licensing ARM cores and adding their custom units on the side would be cheaper and faster to market. Given his connections, working with the AMD custom division would also be possible and would not only save some time and money for the startup, but would also have a massive set of available and heavily-optimized software working from the very start which would save even more money.

I'd say that his actions when free from corporate constraints show a definite opinion on the matter.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#302

Post by fomine3 » Tue, Jul 05, 2022, 4:28 AM UTC

modeless wrote: post #211

throw34 wrote: post #208

Earlier quoted context omitted.

That’s an interesting take given this thread because Apple has explicitly stated they don’t prioritize performance, they prioritize performance per watt, which is not the same thing. And that also shows there’s a whole design space here and just focusing on one dimension, process node, is overly simplistic.

Top end performance is power limited, so optimizing for performance per watt is almost the same thing as optimizing for performance.

Yes. Now every computers tend to be power limited (or say heat limited).

Re: Ask HN: Can competitors catch up to Apple Silicon?

#303

Post by pjmlp » Tue, Jul 05, 2022, 4:55 AM UTC

philistine wrote: post #283

pjmlp wrote: post #184

Given that whatever Apple has is not going into 80% of the desktop market, 60% of the mobile market, 100% of game consoles, or 100% of the server market, it matters much less than some Apple afficionados make out of it.

When Apple can make a game console for half the price with the same GPU power as the competition, which is something that could happen in ten years, Microsoft and PlayStation are going to sweat and pay very close attention to what Apple is doing.

Good luck with that. Remember Pippin.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#304

Post by tdsanchez » Tue, Jul 05, 2022, 5:16 AM UTC

wmf wrote: post #226

tdsanchez wrote: post #194

Most of the performance advantage of Apple silicon is that it puts CPU, GPU and all memory (that is typically VRAM and DRAM in traditional architectures) millimeters from primary DRAM. When competing purveyors start do this with their own clever packaging, they will start to approach Apple’s mips/watt. Emulation on M1 is outstanding. The spatial locality of main memory nullifies emulation penalty. Apple has come clos…

Nope. There's little or no advantage to 2 mm vs. 20 mm.

When multiplied over billions of clock cycles it makes a tremendous amount of difference.

There's a reason why PCB board specs say that all DRAM traces need to be the same length - the length of the trace, and it's capacitance are the main speed limiter for any signal. This is true whether the trace is 20 mm long or 2.

"the critical point to DDR circuitry is in the timing. This means that the clock lines will determine the timing of the input and output of the memory chip data lines. Electrical signals can not be sped up, so the only way to control the timing is to add length to the traces in order to delay the arrival of the clock signal. This is accomplished by adding serpentine routing to the trace routing."

https://resources.pcb.cadence.com/blog/2019-ddr-routing-tech...

"So the physical RAM modules are still separate entities, but they are sitting on the same green substrate as the processor. “Big whoop,” I hear you saying. “What’s the big deal?” Well, first of all, this means faster access to memory, which inevitably improves performance. In addition, Apple is tweaking how memory is used within the system."

https://www.howtogeek.com/701804/how-unified-memory-speeds-u...

Re: Ask HN: Can competitors catch up to Apple Silicon?

#305

Post by r00bot » Tue, Jul 05, 2022, 5:18 AM UTC

bluescrn wrote: post #13

Performance isn't everything. Even if the comparisons to the RTX3090 were legit, all that power is still 'trapped' inside a Mac. As the main reasons to have that level of power are gaming and VR, you'd be probably be better off having a bit less performance but on a Windows machine.

The main reasons to have that power certainly are not gaming and VR. A computer is a tool for work as well as leisure. For artists, editors, programmers, scientists, etc. more power means less time sitting around waiting on a render, build, simulation, or export. Apple aren't making these chips for gamers lol.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#306

Post by fxtentacle » Tue, Jul 05, 2022, 6:41 AM UTC

Const-me wrote: post #297

fxtentacle wrote: post #206

Earlier quoted context omitted.

I believe ROCm isn't usable yet. I don't know anyone who successfully trained a state of the art neural network on anything that was not NVIDIA. AMD keeps offering their own forks of PyTorch and TensorFlow, but last time I checked they were years outdated, and nobody uses them. So either PyTorch/TensorFlow are secretly sponsored by NVIDIA, or AMD's and Apple's CUDA replacements aren't mature enough yet. Given how man…

> building a GPU-capable BLAS library is just a lot more work than one would think I made a few pieces when needed: dense and sparse matrices, conjugate gradient, householder QR decomposition, other things. Wasn’t terribly hard. I only needed to support relatively new GPUs, that’s one reason why. Another one, I based on DirectCompute not ROCm. The thing’s well tested (modern videogames are using compute shaders a lot…

DirectCompute is only the execution of fully trained neural networks, so they can skip all the gradient calculations, which are the compute-heavy and memory-heavy part.

To give you and idea, I need 24GB of GPU RAM to build a background separation model, but once it's finished, it's only 500kb of parameters and it can run on CPU in JavaScript in realtime.

As for the friction, CUDA is easy enough for motivated gaming kids to handle. AMD is not. But I'd predict that today's GPU enthusiast kids will become tomorrow's AI experts. As an example, look at the LAION chat which is a weird mixture of childish humor, gaming memes, and discussions about analytical approximations for probabilistic differential equations. (the Elucidated paper applied to Imagen's DDPM)

Re: Ask HN: Can competitors catch up to Apple Silicon?

#307

Post by fxtentacle » Tue, Jul 05, 2022, 6:44 AM UTC

pclmulqdq wrote: post #216

tambourine_man wrote: post #143

Earlier quoted context omitted.

Is that more an indictment of ROCm immaturity or of PyTorch/TensorFlow unwillingness to support it?

ROCm is pretty mature, but harder to support than CUDA. Its BLAS library works well. PyTorch and TensorFlow are likely getting a lot more help from Nvidia than from AMD on compatibility. The ROCm ecosystem is a lot smaller, too, so there are many fewer examples to copy. Still, if you want to do floating point math with high performance for a lot cheaper than Nvidia, investing the time in ROCm is probably worth it.

In our case, we train on NVIDIA and then port to C++ with AVX. It's a bit more work, but deployment on AMD CPUs is even cheaper than on AMD GPUs.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#308

Post by GeekyBear » Tue, Jul 05, 2022, 11:16 AM UTC

pella wrote: post #44

camillomiller wrote: post #25

Earlier quoted context omitted.

Qualcomm has been "on track" with desktop level chips based on their mobile platforms for at least four years. I've tested the first Windows on Arm laptop with a series 8 "desktop" Snapdragon in 2018. Yet, they still have to ship anything meaningful. They lake the vertical integration Apple has, and they will never have it. Hard for me to see how competitors (Qualcomm + Microsoft + OEMs) are supposed to go after Appl…

> are supposed to go after Apple in this area, Talent can be poached [1] and Technology can be acquired [2] [1] "Intel Poaches Head Apple Silicon Architect Who Led Transition To Arm And M1 Chips" https://hothardware.com/news/intel-poaches-head-apple-silico... [2] https://www.qualcomm.com/news/releases/2021/03/qualcomm-comp... ------ The real problem - Apple is slowing down [3][4] [3] "Apple CPU Gains Grind To A Halt…

> Apple CPU Gains Grind To A Halt

Apple is playing a different game than it's competitors. They aren't looking to make performance gains no matter what happens to power draw and waste heat by endlessly cranking up the clocks.

The Anandtech deep dive into the cores used in the A15 and M2 show that Apple didn't just increase performance by about 18%, they cut power while increasing performance.

>Apple A15 performance cores are extremely impressive here – usually increases in performance always come with some sort of deficit in efficiency, or at least flat efficiency. Apple here instead has managed to reduce power whilst increasing performance, meaning energy efficiency is improved by 17% on the peak performance states versus the A14.

In our initial coverage of Apple’s announcement, we theorised that the company might possibly invested into energy efficiency rather than performance increases this year, and I’m glad to see that seemingly this is exactly what has happened, explaining some of the more conservative (at least for Apple) performance improvements.

https://www.anandtech.com/show/16983/the-apple-a15-soc-perfo...

Apple isn't winning at the game of performance increases no matter what happens to heat and power draw, because that isn't the metric they care about.

They care about performance per watt.

That's how dropping the M2 into the same entry level Macbook Pro they sold last year doesn't just bump up performance, it also gains you a couple more hours of battery life.

>MacBook Pro 2022 battery life tested — this is the longest-lasting laptop ever

https://www.tomsguide.com/opinion/macbook-pro-2022-battery-l...

Re: Ask HN: Can competitors catch up to Apple Silicon?

#309

Post by maccard » Tue, Jul 05, 2022, 11:18 AM UTC

postalrat wrote: post #199

maccard wrote: post #87

Earlier quoted context omitted.

I dont fall in the "apple has changed the world" camp, but bear in mind what you're saying here - the flagship $1500 MSRP GPU is less than an order of magnitude quicker than a $2000 (total) device, with less than half the power usage. That's a pretty impressive feat for a first attempt.

It wasn't their first attempt. Apple has been making chips for their phones for years.

There's a huge difference between mobile and desktop chips. They have very different constraints. As I said, I'm not in the "apple have changed the world camp" but they have managed to bring high end desktop performance at laptop level power usage, that also sustains output.

Re: Ask HN: Can competitors catch up to Apple Silicon?

#310

Post by philistine » Tue, Jul 05, 2022, 11:51 AM UTC

pjmlp wrote: post #303

philistine wrote: post #283

Earlier quoted context omitted.

When Apple can make a game console for half the price with the same GPU power as the competition, which is something that could happen in ten years, Microsoft and PlayStation are going to sweat and pay very close attention to what Apple is doing.

Good luck with that. Remember Pippin.

How can the Pippin relate to any future console endeavour of Apple? I can't think of any piece of tech, or employee, who was there when the Pippin was released.