Intel to Refresh its LGA2066 HEDT Platform This Summer?

[efikkan]

So this is what qualifies as newsworthy these days; one random guy in a forum mentioning something…

Cascade Lake (-SP) was promised for last year, but is pretty much MIA. It promised cache improvements and higher clock speeds (for Cascade Lake-SP), but this is the first I'm hearing in a while about a Cascade Lake-X.

 

[cucker tarlson]

Pooper Lake

 

[wrathchild_67]

Zen 2 is interesting, but we need to see where it lands clocks wise and such.

I'd say it's more than interesting if this Intel refresh story is true. We're talking about potential 10 core Intel CPUs on the standard consumer platform when they had been content to string that segment along for years at just 4 cores. Intel in the past (prior to Ryzen 2xxx) has been fairly reserved at product releases to counteract rumored AMD chips. This refresh seems to paint a different picture. These Ryzen leaks we're seeing about high boost clocks and high core counts in an efficient TDP envelope are looking more and more realistic and this Intel story, if true, is further confirmation. For the sake of consumers, I hope all of the hype is true.

 

[lexluthermiester]

So this is what qualifies as newsworthy these days; one random guy in a forum mentioning something…

Kinda like your comment.

This only makes sense. Intel knows AMD is working on the next iteration of Ryzen and they know it's going to make a marked improvement over the current gen.

 

[cucker tarlson]

Going over 8 cores on s.11xx will hurt intel more than do any good,as they'd need to ditch ring design for that.They don't need to go into the core race,that's for fanboys.Tell me one thing an 8c/16t cpu can't do for a mainstream user/enthusiast gamer that 12c/24t can. Just do a 6c/12t i5 and 8c/16t i7. What they need is a die shink and new architecture.

 

[lexluthermiester]

Tell me one thing an 8c/16t cpu can't do for a mainstream user/enthusiast gamer that 12c/24t can.

Gaming, no. Most gamers do other things as well that can and do benefit from extra cores. However, I personally would be very happy with a 4ghz 8c/16t CPU with quad channel ram.

 

[efikkan]

Going over 8 cores on s.11xx will hurt intel more than do any good,as they'd need to ditch ring design for that.They don't need to go into the core race,that's for fanboys.Tell me one thing an 8c/16t cpu can't do for a mainstream user/enthusiast gamer that 12c/24t can. Just do a 6c/12t i5 and 8c/16t i7. What they need is a die shink and new architecture.

Yes, >8 cores on their mainstream platform is not required, especially if they have to sacrifice clock speed. Intel will probably still have an edge in core speed, and 12 core Zen 2 on AM4 will probably be a low-volume product. And I agree, which workloads needs >8 cores without other HEDT features?

Intel have a new architecture ready, it's been ready for nearly two years, just waiting for the node to be ready. What they should have done instead of Coffee Lake rev 1 & 2 and Comet Lake(?) is a "backport" of Ice Lake to 14nm.

 

[EarthDog]

I'd say it's more than interesting if this Intel refresh story is true. We're talking about potential 10 core Intel CPUs on the standard consumer platform when they had been content to string that segment along for years at just 4 cores. Intel in the past (prior to Ryzen 2xxx) has been fairly reserved at product releases to counteract rumored AMD chips. This refresh seems to paint a different picture. These Ryzen leaks we're seeing about high boost clocks and high core counts in an efficient TDP envelope are looking more and more realistic and this Intel story, if true, is further confirmation. For the sake of consumers, I hope all of the hype is true.

Intel has had Octo's since 8700K. Frankly, nobody needed more than that when it was released and only now in some cases are more cores/threads helpful. They have to be used in order to be effective.

The refresh is different because consumers are still, for the most part, clueless. Think in the clockspeed days of P4 and AMD Newcastle chips... AMD had to name their chips so that their naming convention reflected Intel performance (Athlon 64x2 3800 for example). Now, instead of clocks and IPC, which matter to most, we see meager IPC bumps and more cores/threads when software can't use it... I hope we see software gain momentum on this, but, since hex's and octo's have been out for nearly a decade now, I don't see much point in going over a 6c/12t CPU for 95% of people.... even the 'enthusiasts' here.

 

[juiseman]

"no one will ever need more than 640k"

Microsoft Corp. chairman Bill Gates once said 640K of memory was more than anyone needed.

 

[EarthDog]

"no one will ever need more than 640k"

Microsoft Corp. chairman Bill Gates once said 640K of memory was more than anyone needed.

blanket statements FTL.

It's going to be another few years before more than 6c/12t are going to be useful for the average Joe.

 

[efikkan]

"no one will ever need more than 640k"

Microsoft Corp. chairman Bill Gates once said 640K of memory was more than anyone needed.

Another famous misquote. Mr. Gates said "ought to be enough for anybody" about 640kB for the original IBM PC, not that no one will ever need more.

Back on topic.
Most non-server tasks, including multithreaded tasks, scale better on fewer faster cores than many slower cores. More cores are of course welcome, as long as we don't have to sacrifice too much core speed.

 

[Kapone33]

I have been watching youtube videos on the X58 system and even though it lacks in some new instructions it would be what I would do if I wanted an Intel build. A CPU for $70 with 6 cores and 12 threads boosted to 4.5 GHZ is no joke regardless of age. Especially now in the days of multi core programs and games.

 

[juiseman]

I agree;
guess that's because its basically the same CPU on a smaller node with little 2-3% IPC improvements per gen.
And a few added instructions....
If your lucky and find a EVGA Classified SR2 for cheap; that platform is still good for a lot of stuff....

I'll shut my pie hole now...
I've stated my findings and personal experience .....

 

[EarthDog]

I have been watching youtube videos on the X58 system and even though it lacks in some new instructions it would be what I would do if I wanted an Intel build. A CPU for $70 with 6 cores and 12 threads boosted to 4.5 GHZ is no joke regardless of age. Especially now in the days of multi core programs and games.

Lol, yes it is.... try gaming at 1080p and not placing a bottleneck on midrange card...will it work, surely! But it limits potential. It's a solid desktop for an average user, but any modern gamer at 1080p will want something a lot faster to remove that glass ceiling. Not to mention missing out any new features over the last decade.

 

[phanbuey]

Kind of hoping for this... if AMD releases their chips, then intel should drop cascade lake prices on the 8 & 10 core varieties, which would be perfect.

Right now the 7820x is excellent (especially since when i bought it, my options were 7700k, 1800x or 7820x) and with overclocking it beat the pants off everything else out there at the time. But it definitely could use a better cache hierarchy and a bit of an ipc boost to keep up with the 9900k/z390 setup.

If they release something semi reasonable and cascade lake X has faster cache latency and memory this will be a perfect upgrade for the skylake X crowd.

As it stands, the Skylake-X platform doesnt seem like it can hold onto the HEDT crown from Zen 2, so hoping for something a special from intel.

 

[timta2]

I have been watching youtube videos on the X58 system and even though it lacks in some new instructions it would be what I would do if I wanted an Intel build. A CPU for $70 with 6 cores and 12 threads boosted to 4.5 GHZ is no joke regardless of age. Especially now in the days of multi core programs and games.

The CPUs may be cheap, but the motherboards are expensive. Once you start adding it all together, it's a lot of money towards something more recent, more powerful, and more efficient.

 

[Caring1]

"no one will ever need more than 640k"

Microsoft Corp. chairman Bill Gates once said 640K of memory was more than anyone needed.

Another famous misquote. Mr. Gates said "ought to be enough for anybody" about 640kB for the original IBM PC, not that no one will ever need more.

You beat me too it.
At that time, 640KB was enough for the average home user.

 

[hat]

Well, at least we finally get solder and those Meltdown/Specture hardware mitigations in the HEDT space.

Those security vulnerabilities are really smegging me off, though. Over a year later since the original announcement and we're still finding new crap... just as I thought it would be. It's a never ending battle.

 

[Slizzo]

Well, at least we finally get solder and those Meltdown/Specture hardware mitigations in the HEDT space.

Those security vulnerabilities are really smegging me off, though. Over a year later since the original announcement and we're still finding new crap... just as I thought it would be. It's a never ending battle.

When they first announced the vulnerability, they said that the two would be the first in a long line of vulnerabilities that will be found.

Only way to truly mitigate would be to change the way their speculative execution takes place.

 

[efikkan]

Those security vulnerabilities are really smegging me off, though. Over a year later since the original announcement and we're still finding new crap... just as I thought it would be. It's a never ending battle.

In principle, I believe that bugs should be addressed and fixed. Still, it's important to keep things in perspective. These vulnerabilities require the attacker to run malicious code on the victim's hardware, and the concern is that someone in like a public cloud could use this to dump the memory of other people's virtual machines, but not like your home computer though.

In reality though, it seems like more a theory at this point. The proof-of-concept attacks are not super reliable, and leaks data at B/s or kB/s, and I'm not sure if you can even leak arbitrary targeted parts of memory this way. So it will take a good while to dump a larger chunk of memory like this, and in reality memory will be moved around much quicker than you are able to dump it.

The actual thing you should worry about is the performance penalties of the workarounds, which luckily has become less with more refined approaches. These bugs have led to scheduling changes in both Windows, Linux and BSD, so perhaps some good have come of it after all…