Hacker News Reader

These days you can't say anything positive about Intel even if it is factually true. I am personally excited about the 10900K and the competition with AMD is bringing Intel prices down.

People seem to have a deep hatred for Intel, exactly the way they had deep hatred for AMD (pre-Conroe days, when Intel released Conroe in 2005/06, people were rooting so hard for Intel, it was hard to find any positive comments about AMD). I don't get it. Both are multi-billion dollar companies and innovating like crazy. We can't just sit back, and feel the utter awe of what it takes to make computer chips whether it is Intel or AMD. You know, its engineers like anyone else - they have good intentions and work hard to make all of this possible, the fans have this egregious entitlement that is so infuriating and dismissive.

The engineering is great. People's bias likely stems from the numerous security scandals surrounding intel's CPUs in the last few years.

Hardly unique to intel's cpus... they're just the biggest target.

That's simply not true the biggest target is ARM. Most of the worlds devices run ARM.

Which also have side channel attacks... these and much more:

[1] https://www.blackhat.com/docs/eu-16/materials/eu-16-Lipp-ARM...

[2] https://duo.com/decipher/new-side-channel-attack-extracts-pr...

[3] https://eprint.iacr.org/2016/980.pdf

Still not even close to the clusterfuck that is Intel CPU's

Well they’re typically not as superscalar in processing, which helps. But I wouldn’t make an assumption that ARM chips generally are more secure — plenty of weaknesses have been found, and doubtlessly many more exist. Security research has shown there are always new untapped directions to exploit, and really nothing can be assumed to be actually secure at this point. Like I said before, Intel is the big target, especially as they run the servers you access over the internet. ARM devices tend to be local and thus aren’t as valuable for side channel attacks. Instead, most attacks for ARM chips tend to be at the sandbox/OS level.

to be a little more explicit: there are ARM chips that are affected by meltdown.

People shit on Intel like it's their particular mistake, but POWER, ARM, and basically everyone's out-of-order cores except Ryzen were affected by Meltdown. It's some oddity of Ryzen's cache predictor that make it immune, basically everybody else was affected by it.

You seem to miss the huge list of speculation bugs with mitigations that take a variable chunk of performance away with no buyback or return program in place. VW diesel gate was less of a blunder than the Intel speculative execution saga and one cost a company $33 billion.

Wait, really? My understanding was that, whereas VW intentionally cheated to fool regulators, Intel (and others) got blind-sided by a creative attack against a fundamental, well-established technique for gaining performance. These seem like very different problems.

Note: I haven't followed the "saga" closely so maybe there is more to it that I'm not aware of.

Speculative execution is fine, speculative execution across protection domains is not. So VW cheated for better milage, Intel cheated for better performance.

"Cheating" implies something sinister. Far more likely, they just missed it.

Modern CPUs are at the very edge of what humans can design and build. Hundreds of verification engineers try to make sure they work. Not one of them will have a whole picture of the entire machine in their head, or really understand all of its requirements. The very best, hardest working, most diligent and dedicated teams will still ship a CPU with bugs. Perfection is simply not possible in this domain.

AMD is still a bit of an underdog valued at a fraction of Intel. People like rooting for the underdog.

Second to this, is competition is important and having competitive products tends to bring pricing down to what is probably closer to optimale.

Aside: I've thought for a long time, that if medications had a dual-sourcing requirement it would help a lot.

If "rooting for the underdog" means becoming deeply viled, callous and irrational when facing facts, I don't think that's a good thing.

That cuts both ways... there are definitely Intel fans that will excuse everything Intel is/has ever done that isn't above board.

I was only stating part of why someone might favor for AMD strongly, without going into the irrational, which you seem to be focusing on here.

Right now, AMD is largely better at every price bracket and in general has done better in terms of security and long-term support (don't have to by a new motherboard every year if you want to upgrade).

>That's competitive with the 3700X: little higher cost, and more heat, but more gaming performance too.

I wouldn't call the cost « little higher » if you factor in the motherboard (and possibly the cooler). Any AM4 board will run a 3700X whereas Intel's using yet another socket for their new chips.

The value of the pack-in cooler is sub-$20, it's quite noisy and not particularly good at cooling. Something like a Hyper T4 or Deepcool Gammax 400 is in the ballpark, something like the Hyper 212 Evo is cooler and quieter, so that sets very low bounds on the value of that pack-in.

You don't really want to be using the sub-$100 tier of motherboards for AMD either. People will talk up how cheap motherboards are but tell people you're going to put a 3900X (only 105W TDP) on a B450 and their eyes will roll at you.

> Base clocks are irrelevant on desktop

It's relevant for the TDP number.

> I'd personally point at the 10700F as being the winner from the specs, 4.6 GHz all-core 8C16T with slightly higher IPC in gaming than AMD, for under $300

I think the 10700F would only be the winner if you have a motherboard that either isn't following Intel's recommendations for turbo or lets you ignore them.

Otherwise the 10700F's 4.6ghz all-core isn't going to happen with a 65W limit after unknown seconds. That TDP limit is going to really cripple that chip. Whether or not you can ignore that limit will I guess decide whether or not the i7-10700KF is worth the extra $50.

But the 9700 appears to be almost nonexistent. I think the 10700 will end up in the same camp. The 10700K will likely be the only chip with any meaningful coverage/reviews in the i7 lineup.

Official TDP limits are almost irrelevant now. AFAIK, most consumer motherboards do not target the official TDP.

e.g. it's possible for a Intel chip to sustained turbo at levels unsupported by the nominal TDP.

> CS:GO loves Zen2's cache

what do you mean by this? I researched intel vs. amd gaming performance pretty extensively last summer, and I paid particular attention to csgo benchmarks. AFAIK, 9700k/9900k are a little faster than the 3900X in csgo at stock speeds, and a good bit faster on a typical overclock.

HWUB: https://static.techspot.com/articles-info/1877/bench/CSGO.pn...

LTT (not OC'd): https://i.redd.it/fnw15b6dxv831.png

The doubled cache really made an enormous difference in performance. Zen2 averaged about a 15% IPC improvement on average, in games the average was more like 30%, and in CS:GO it was about 42% improvement. It went from being pounded in this title to tying or beating the 9900K.

And that's against a 2700X, the 1800X was significantly worse than that. Compared to the 1800X, CS:GO is more like 50-60% improved.

The slightly higher clocks don't hurt, but Zen2 really made huge progress in handling the "unhappy cases" for their architecture. I tend to point the finger at cache for this specific case, cause I don't think of source engine titles when I think clean, well-optimized, highly threaded code.

> Base clocks are irrelevant on desktop, it's not Sandy Bridge days anymore

Reading this makes me feel like I need to build a new PC now lol. Any idea what percentage of desktop PCs are still on Sandy Bridge?

Good statistics about the current install base rather than market share are hard to come by. The Steam Hardware Survey is a decent source when you're looking at desktop PCs, because there's pretty strong overlap between desktop PC users and gamers. Slightly more than 25% of machines measured by the Steam survey don't support AVX2, which means they're pre-Haswell on the Intel side or pre-Excavator on the AMD side, or a newer but low-end Intel model. (Those recent low-end Intel chips that have AVX2 disabled also tend to have Turbo Boost disabled.) It's plausible that Sandy Bridge and earlier may still account for 10+% of gaming desktops.