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

Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

anandtech.com

Post reply on HN
Print view View original

201–210 of 277 posts

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#201

Post by fwip »

hmottestad wrote: post #27
lkschubert8 wrote: post #23

Should they be describing it as 8 cores 16 threads when there have been multiple security vulnerabilities that have to turn off hyperthreading to be mitigated?

This is a very good point. I hope AMD brings it up with the EU. Might be a very slow process though, but at this point it is anticompetitive behaviour. AMD could probably squeeze a fair bit more performance out of their processors if they were allowed to cut some security corners.

Who do you think is disallowing AMD from cutting security corners? (Not rhetorical)

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#202

Post by serf »

gameswithgo wrote: post #112
gameswithgo wrote: post #91

Earlier quoted context omitted.

maybe it is just hard. amd isnt shipping clearly better stuff either.

show me what amd chip performs better instead of just downvoting.

performance benchmarks go out the window once you realize that a platform is woefully and unfixably insecure.

performance benchmarks mean even less when those security issues are band-aided by performance metric-hurting-workarounds.

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#203

Post by earenndil »

ricardobeat wrote: post #194
earenndil wrote: post #109

Earlier quoted context omitted.

That's an overexaggeration, IMO. Moore's law didn't really start losing steam until 2014-2015.

If you look at transistor count, yes. But single-core performance has stagnated since ~2003, that’s when we hit the 3Ghz mark. Progress since then has been a lot slower.

GHz are basically meaningless. The 2GHz CPU in my laptop is an order of magnitude faster than anything 3GHz from 2003.

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#204

Post by fwip »

ricardobeat wrote: post #194
earenndil wrote: post #109

Earlier quoted context omitted.

That's an overexaggeration, IMO. Moore's law didn't really start losing steam until 2014-2015.

If you look at transistor count, yes. But single-core performance has stagnated since ~2003, that’s when we hit the 3Ghz mark. Progress since then has been a lot slower.

IPC's gone up quite a bit though, right?

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#205

Post by dfrage »

pkaye wrote: post #195
lawrenceyan wrote: post #148

Earlier quoted context omitted.

What would you say are the primary differences between the two companies? Is it more just a matter of luck that has allowed for TSMC to have been able to succeed where Intel hasn't? Or is there actually a meaningfully different process design and/or problem solving approach that is enabling this?

I think Intel having their own manufacturing fab is hurting them in the longterm. By outsourcing it you can go with whomever has the best solution. By matter of pride, Intel has not done this but AMD, Nvidia, Apple all do this.

I've heard entirely the opposite, that having a close relationship between chip designers and fabricators allows for higher performance designs. I don't know of anyone who interpreted AMD selling off its foundries as anything other than severe financial distress, and it worked supremely well for Intel while they stayed at least one step ahead of the competition. Enough so this is said to have wiped out a generation of CPU architects while Dennard scaling still worked, no matter how clever they were, Intel moving to its next process node wiped out their speed advantage.

But it's a brittle model, if a company screws up a node and is too messed up to handle the failure gracefully, as Intel is doing with their "10nm", no doubt with pride as a factor. And it's not uncommon for institutions to permanently lose abilities, I'm not counting on Intel succeeding with their "7nm" node.

On the third hand, we're now down to 2-3 high end CPU fab companies, Samsung, TSMC, and maybe Intel. That also can be a brittle thing.

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#206

Post by chimpburger »

ricardobeat wrote: post #194
earenndil wrote: post #109

Earlier quoted context omitted.

That's an overexaggeration, IMO. Moore's law didn't really start losing steam until 2014-2015.

If you look at transistor count, yes. But single-core performance has stagnated since ~2003, that’s when we hit the 3Ghz mark. Progress since then has been a lot slower.

Moore's law is specifically about transistor count/density only.

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#207

Post by wtallis »

pkaye wrote: post #196
throwaway2048 wrote: post #108

Earlier quoted context omitted.

Not directly no, but the actual feature size and density of TSMC 7nm and Intel 10nm are comparable.

What about die size?

Then you have to ensure you're comparing chips designed for the same market segment. Die size comparisons work well if you're talking about a Cortex-A53 on 16nm vs 12nm. It doesn't work as well when you're talking about a full SoC, or even a desktop CPU+GPU combo where core counts for both sides of the chip can vary greatly.

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#208

Post by wtallis »

leggomylibro wrote: post #178
kzrdude wrote: post #30

Earlier quoted context omitted.

What does stability mean, a bit more exactly? Just curious

Disclaimer: this is an oversimplification and I only have a lay person's understanding. CPUs are basically huge networks of transistors (on/off switches). They're sort of like tiny printed circuit boards; lots of individual 'parts' are connected by 'wires' on top of a silicon wafer. The distances are miniscule, but the lengths of wires running between transistors still varies. So when a transistor switches between 'o…

I think the inconsistencies between samples of the same model of chip are much less about the interconnect wires than about the transistors themselves, having variation in their individual switching speed vs voltage curves. There's nor really much variation in interconnect length between a given two gates when both chips are made from the same masks. But especially at the lower (finer pitch) layers of metal interconnect, variations in resistance and capacitance can affect how things operate.

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#209

Post by davrosthedalek »

serf wrote: post #202
gameswithgo wrote: post #112

Earlier quoted context omitted.

show me what amd chip performs better instead of just downvoting.

performance benchmarks go out the window once you realize that a platform is woefully and unfixably insecure. performance benchmarks mean even less when those security issues are band-aided by performance metric-hurting-workarounds.

If I buy 100k chips for my HPC to do single-tenant processing, performance, and performance/watt are priority one. The vulnerabilities intel has to fight right now are irrelevant for this use case.

Re: Intel Announces 8 Core I9-9900KS: Every Core at 5Ghz, All the Time

#210

Post by kristianp »

AmVess wrote: post #75
qwerty456127 wrote: post #55

Why 5 Hz all the time? I'd love to have such an extremely powerful CPU but I'd actually appreciate if it could downclock itself automatically and stay as cold as possible whenever I don't need it's full power. Some times I run heavy computations and having 8 5Hz cores sounds great but most of the time I just read or write something so even 1000 Hz sounds an overkill.

It doesn't run at 5Ghz all the time. 5GHz is it's all-core turbo. It simply means that all cores will run at 5Ghz under full load.

Yes, the article title is misleading, it actually says "All the time".
Post reply on HN