Intel Updates Alder Lake Tuning For GCC, Reaffirms No Official AVX-512

[skeevy420]

Pretty cool, that was quick.

Has anyone (Michael included) been using Alder Lake day to day? How's it going? Any noticeable "wow" moments or anything? Curious if it's a game-changer by any means like Apple's M1.

Unless a person is coming from older platforms, I doubt they'll have a good "wow" moment until next year or the year after....let AMD and Intel have a year with DDR5 combined with things like 3D Infinity Cache and whatever Intel has up its sleeve; release their next generation of cool shit.

My POV is if you're already running some form of AMD Zen or a Win11 compatible Intel CPU then there aren't many CPU upgrades that will actually knock your socks off unless you're a hardcore developer or CPU bound gamer with the earliest of those aforementioned CPUs.

As someone using a Zen 2 APU there is nothing that compels me to upgrade to a Zen 3 APU. There aren't enough gains GPU or CPU to warrant the upgrade. Coming from my previous Westmere Xeons, Zen 2 knocked my socks off with an actual "wow" moment so it'll take a substantial change for me to have another moment like that.

[drakonas777]

This can be trivially fixed by setting PL1/PL2 limits. It's power hungry only for massively parallel computational tasks. In every day common tasks it's the most power efficient high performance x86-64 CPU out there.

Oh yeah, sure, just set PL1 on 12900K and loose 20-30% MT. I really do not get this braindead argument. A lot of people buy i9s specifically for MT loads in the first place, not for "every day common tasks". Also, AL MT efficiency is about the same as ZEN3, so it's not like you are getting most efficient CPU by a large margin.

[CtrlAltShift]

Linus can finally prize Intel for stepping away from AVX-512. I remember him bashing Intel for prioritizing AVX-512 over core performance and core count. So, I believe he got what he wanted.

[avem]

Oh yeah, sure, just set PL1 on 12900K and loose 20-30% MT. I really do not get this braindead argument. A lot of people buy i9s specifically for MT loads in the first place, not for "every day common tasks". Also, AL MT efficiency is about the same as ZEN3, so it's not like you are getting most efficient CPU by a large margin.

At 160W it loses 17.6% of its performance, not 30%. Somewhere between 160W and 200W there's a sweet spot where the Intel CPU is faster and more efficient than 5900X. Yes, Intel overclocked the 12900K to hell to rival 5950X in lots of MT tasks but at 125W it beats 5950X hands down in absolute most low threaded tasks.

Again, you're 100% offtopic. You're welcome in this topic.

[avem]

Linus can finally prize Intel for stepping away from AVX-512. I remember him bashing Intel for prioritizing AVX-512 over core performance and core count. So, I believe he got what he wanted.

You can perfectly use AVX-512 after disabling E-cores and AVX-512 tasks run circles around AMD CPUs.

[uid313]

Not to make any excuses for Intel, but you don't have to cool it as much as it wants. If you use a less capable cooler, the tradeoff is just that the CPU fan spins up quicker and it throttles more readily.

I'm contemplating an upgrade to Alder Lake. If I do, I'll probably tweak around with the scheduler and frequency settings to tradeoff a bit of boost for less fan noise and lower room temps in the summer. I'm sure it'll still be plenty fast and decent value for money.

I can hear you thinking: "why don't you just get AMD, then?" But I've long had a primary and secondary Linux box that were Intel and AMD, respectively. I kind of like to keep one of each, especially if I get the chance to switch on/off AVX-512, should the occasion arise.

Yes, the i5 is said to be good value for the money. Note however that motherboards are very expensive, and DDR5 costs much and available is extremely low.

The AVX-512 is pretty useless for most people, it is only useful for very specific things. Personally, I don't care for AVX-512.

This can be trivially fixed by setting PL1/PL2 limits. It's power hungry only for massively parallel computational tasks. In every day common tasks it's the most power efficient high performance x86-64 CPU out there.



Completely different classes of devices. The Ryzen G lineup is not meant to run with a discrete GPU, while ADL implies a discrete GPU.

The ADL comes with a iGPU unless it is the F model. The model requires a discreet GPU, but the non-F model has a integrated GPU but it is not as good as the Ryzen G series. I wish ADL had one with a good integrated Xe GPU.

[drakonas777]

At 160W it loses 17.6% of its performance, not 30%. Somewhere between 160W and 200W there's a sweet spot where the Intel CPU is faster and more efficient than 5900X. Yes, Intel overclocked the 12900K to hell to rival 5950X in lots of MT tasks but at 125W it beats 5950X hands down in absolute most low threaded tasks.

Again, you're 100% offtopic. You're welcome in this topic.

OK, so it's 17-30. Depends on the workload - that's why I gave a rough range and not an exact number. The point is it's non-trivial. Also, I was writing about MT efficiency, not low threaded tasks. AL efficiency across mixed workloads at certain power limits is indeed better, but PL2 of 12900K is just not practical in MT. What's the point to pay premium for i9 K and then limit the power. Choosing non-K potential future i9 or at least current 12700K makes much more sense.

My main criticism is that 12900K PL2 is insane and kind of misleading. It's basically "benchmarking mode". Also, PC tech community seems not to care much and does not call it out generally speaking, which means raising power limits to insane levels for the mainstream parts will become a norm in the future. It all kind of started with Ampere. Now AL i9. I'm not a fan of this tendency for a lot of reasons - but it's offtopic, yes.

[sdack]

My daughters' bedroom is the coldest room in the house over winter ...

Give them your room when you love them. Best advice you will get here on Phoronix.

[avem]

Yes, the i5 is said to be good value for the money. Note however that motherboards are very expensive, and DDR5 costs much and available is extremely low.

The AVX-512 is pretty useless for most people, it is only useful for very specific things. Personally, I don't care for AVX-512.


The ADL comes with a iGPU unless it is the F model. The model requires a discreet GPU, but the non-F model has a integrated GPU but it is not as good as the Ryzen G series. I wish ADL had one with a good integrated Xe GPU.

Let me repeat myself, please read slowly and attentively: "Completely different classes of devices. The Ryzen G lineup is not meant to run with a discrete GPU, while ADL implies a discrete GPU". I should have thrown "different markets" and "different customers" into the mix as well.

Nowhere in its marketing materials Intel makes a fuss of the ADL iGPU. It's there to be able to boot and run your system while you're looking for a discrete GPU. It's not a gaming iGPU by no means thus pitting it against Ryzen 5600G or 5700G is boderline stupid. Lastly Ryzen high performance parts (5800X, 5900X and 5950X) don't even have a built-in iGPU, OK? Let's talk about that, no? Then why did you start talking about ADL graphics performance for no reasons? Looks like you just wanna desperately find something bad about the new Intel CPUs lineup.

[Michael_S]

This news post is about GCC patches for ADL for Christ's sake.

The news post is also about Intel reaffirming that their new flagship won't have supported AVX-512, it's right in the headline - which you conveniently overlooked.

Yes, I was joking around in my post. But my point is that a technology Intel heralded as hugely significant at introduction has been deemed by Intel as not significant. That change is, if you'll pardon the repetition, significant.

Edit: and mocking fanboyism is not itself fanboyism. The room I'm in has more and faster Intel parts than AMD.