Intel Confirms Soldered IHS for 9th Gen Core Series

[btarunr]

Soldered integrated heatspreader has been a longstanding demand of PC enthusiasts for Intel's premium "K" mainstream-desktop processors. With AMD implementing it across all its "Summit Ridge" and "Pinnacle Ridge" Ryzen AM4 processors, just enough pressure for built on Intel. The company, in a leaked slide, confirmed the feature-set of its upcoming 9th generation "K" Core processors, which highlights "STIM" (soldered thermal interface material) for this chip. It shows that STIM could be exclusive to the "K" series SKUs, namely the i9-9900K, i7-9700K, and i5-9600K.

The slides also list out the clock speeds and cache sizes of the three first 9th generation desktop SKUs, confirming that the Core i7-9700K will indeed be the first Core i7 desktop SKU ever to lack HyperThreading. The TDP of the 8-core chips don't seem to breach the 95W TDP barrier Intel seems to have set for its MSDT processors. The slides also seem to confirm that the upcoming Z390 Express chipset doesn't bring any new features, besides having stronger CPU VRM specifications than the Z370. Intel seems to recommend the Z390 to make the most out of its 8-core chips.



View at TechPowerUp Main Site

 

[cucker tarlson]

8c/8t and solder, 4.6GHz all core turbo out of the box, 9700K looks incredibly good.

 

[randomUser]

There is some confusion tho.

The slides also seem to confirm that the upcoming Z390 Express chipset doesn't bring any new features

The author is wrong. The slides confirm, that there WILL be new features.

These slides were either made when original Z390 was planned, or they ARE actually adding new stuff into it.

It says Z390 will have integrated USB 3.1 G2 and Wifi (CNVi). So at this point its hard to say what will happen.

 

[DarkHill]

Im sorry but... Intel confirms... would suggest that these are official slides from intel - they are not. There is no need to sensationalize the topics TPU. If i wanted that i could just go directly to videocardz.

"Leaked slides from Intel confirms soldered TIM on 9th gen unlocked processors.." would be just as fine and accurate - unlike this one.

 

[RejZoR]

8c/8t and solder, 4.6GHz all core turbo out of the box, 9700K looks incredibly good.

6 and 8 core CPU's without HT in 2018. Clock or not, this is incredibly poor. I have a 6 core CPU with 12 threads. Sure, it doesn't clock to 4.x out of the box, but come on, with manual overclocking, I have it at 4.5GHz and 12 freaking threads. TWELVE! The IPC gain is nowhere near as significant as some say it is on newer CPU's, it's basically just gains from higher clocks. 5820K is 4 years old. One would expect things from HEDT to finally trickle down to normies ranges by now. I guess Intel just can't get out of their skin...

9600K should be 6c/12t
9700K should be 8c/16t
9900K should be 10c/20t

With HEDT far beyond that starting at 16c/32t. Sigh.

 

[The Quim Reaper]

Intel seems to recommend the Z390 to make the most money for its board partners & licensing fees.

Fixed.

 

[hat]

Wow! NEW Solder Thermal Interface Material!

 

[cucker tarlson]

6 and 8 core CPU's without HT in 2018. Clock or not, this is incredibly poor. I have a 6 core CPU with 12 threads. Sure, it doesn't clock to 4.x out of the box, but come on, with manual overclocking, I have it at 4.5GHz and 12 freaking threads. TWELVE! The IPC gain is nowhere near as significant as some say it is on newer CPU's, it's basically just gains from higher clocks. 5820K is 4 years old. One would expect things from HEDT to finally trickle down to normies ranges by now. I guess Intel just can't get out of their skin...

9600K should be 6c/12t
9700K should be 8c/16t
9900K should be 10c/20t

With HEDT far beyond that starting at 16c/32t. Sigh.

Lol who wants HT for gaming if they can get a core count increase.

I get you CPU has TWELVE "friggin threads" , but 8600K whips it in gaming so who cares about that.

 

[noel_fs]

8c/8t and solder, 4.6GHz all core turbo out of the box, 9700K looks incredibly good.

to me it looks ridiculous, disabling ht is just autistic for me.

 

[Xzibit]

read the fine print asterisk

*NOT all features available on all SKUs

Wait and see until one of the OCers delids one

 

[noel_fs]

Lol who wants HT for gaming if they can get a core count increase.

I get you CPU has TWELVE "friggin threads" , but 8600K whips it in gaming so who cares about that.

I dont think you are too smart, he is just saying that at this point in 2018 almost every cpu show have ht independently of the core count, furthermore the 700k nomenclature should be already 8 cores and if they wanted to sell something else then 10c would make sense with the 900k nomenclature.

You are the cause why in 2k18 Intel is still selling 4c for 300$.

 

[RejZoR]

Lol who wants HT for gaming if they can get a core count increase.

I get you CPU has TWELVE "friggin threads" , but 8600K whips it in gaming so who cares about that.

I guess you're one of those kind of people who like to get ripped off and they are even proud of it in the end. XD 4 years newer CPU barely "whips" it. Wow, what an achievement lol

 

[R0H1T]

6 and 8 core CPU's without HT in 2018. Clock or not, this is incredibly poor. I have a 6 core CPU with 12 threads. Sure, it doesn't clock to 4.x out of the box, but come on, with manual overclocking, I have it at 4.5GHz and 12 freaking threads. TWELVE! The IPC gain is nowhere near as significant as some say it is on newer CPU's, it's basically just gains from higher clocks. 5820K is 4 years old. One would expect things from HEDT to finally trickle down to normies ranges by now. I guess Intel just can't get out of their skin...

9600K should be 6c/12t
9700K should be 8c/16t
9900K should be 10c/20t

With HEDT far beyond that starting at 16c/32t. Sigh.

You might wanna rethink about that

Red Hat strongly recommends that customers take corrective actions, including manually enabling specific kernel parameters or potentially disabling features like Intel Hyper-Threading, after the available updates have been applied. More details can be found in the Mitigations section of this article.

https://access.redhat.com/security/vulnerabilities/L1TF

Another aspect of the risk in this area goes away if SMT is disabled, so keep it disabled!

https://marc.info/?l=openbsd-tech&m=153431475429367

 

[noel_fs]

Ah, and of course, after 5 years asking for soldered IHS they bring it, they already have stretched it enough to make nice benefits from filling their cpu's with clay

You might wanna rethink about that
https://access.redhat.com/security/vulnerabilities/L1TF

https://marc.info/?l=openbsd-tech&m=153431475429367

Another retard, its supposed that these cpu's already come hardware patched for this vulnerability type of thing

 

[RejZoR]

It's also cute how they make solder sound like it's some new exciting feature. You already had it, but you baboons also took it away and now trying to sell it it as best thing after sliced bread again. Great, they brought it back after years of bitching over it, but their PR department man...

 

[R0H1T]

Ah, and of course, after 5 years asking for soldered IHS they bring it, they already have stretched it enough to make nice benefits from filling their cpu's with clay


Another retard, its supposed that these cpu's already come hardware patched for this vulnerability type of thing

WTH are you talking about, these NG spectre vulnerabilities were reported this year. The hardware fixes aren't coming before ICL, at the earliest. And you might wanna tune up that language of yours!

 

[Nokiron]

You might wanna rethink about that
https://access.redhat.com/security/vulnerabilities/L1TF

https://marc.info/?l=openbsd-tech&m=153431475429367

Disabling HT for end-users is absolutely not needed. It's for cloud-based servers.

I suggest you read on what the reason for it is.

The precise impact of L1TF to Hyper-Threading depends upon the specific use case and the virtualization environment being used. In some cases, it may be possible for public cloud vendors (who have often built special purpose hardware to assist in isolation) to take steps to render Hyper-Threading safe. In other cases, such as in a traditional enterprise environment featuring untrusted guest virtual machines, it may be necessary to disable Intel Hyper-Threading.

https://www.redhat.com/en/blog/deeper-look-l1-terminal-fault-aka-foreshadow

 

[R0H1T]

Disabling HT for end-users is absolutely not needed. It's for cloud-based servers.

I suggest you read on what the reason for it is.


https://www.redhat.com/en/blog/deeper-look-l1-terminal-fault-aka-foreshadow

Disabling HT will reduce the avenues where such spectre vulnerabilities affect current Intel processors, and no it's not just about VM. IIRC the first reveal earlier this year also suggested disabling HT in extreme cases where security was paramount.

 

[ViperXTR]

 

[randomUser]

https://access.redhat.com/security/vulnerabilities/L1TF

https://marc.info/?l=openbsd-tech&m=153431475429367

All vulnerabilities are about virtualization. This means that this only applies to enterprise, who are using these cpu's for their servers.
The gamers and the majority of the consumers of these cpus, will most likely never have such situation, thus vulnerability is meaningless and turning off HT is pointless.

The next vulnerability about the 'code' from one browser tab reaching memory of the other tab may happen at the computers of the majority of these users, but again, i think it was not related to HT at all.
Besides, what stops you from closing the browser, reopening it freshly and then navigating to your bank account. Its not like people have tabs of pron open at the same time as internet bank tabs.

 

[R0H1T]

All vulnerabilities are about virtualization. This means that this only applies to enterprise, who are using these cpu's for their servers.
The gamers and the majority of the consumers of these cpus, will most likely never have such situation, thus vulnerability is meaningless and turning off HT is pointless.

The next vulnerability about the 'code' from one browser tab reaching memory of the other tab may happen at the computers of the majority of these users, but again, i think it was not related to HT at all.
Besides, what stops you from closing the browser, reopening it freshly and then navigating to your bank account. Its not like people have tabs of pron open at the same time as internet bank tabs.

Say that again? SGX isn't about virtualization, you might wanna reread CVE-2018-3615, CVE-2018-3620, CVE-2018-3646.

 

[Nokiron]

Disabling HT will reduce the avenues where such spectre vulnerabilities affect current Intel processors, and no it's not just about VM. IIRC the first reveal earlier this year also suggested disabling HT in extreme cases where security was paramount.

It's all about virtualization. If you run on physical hardware only the software patches are the only ones needed.

It was only OpenBSD that decided they preventatively disabled HT.

In particular, it is ill-advised to run different security domains (address spaces) on a pair of hyperthread CPUs," he said. "Maybe there are other ways to resolve this problem, but Intel isn't sharing solutions with us. We have selected the expedient approach of disabling hyperthreading until we know more.

https://www.itwire.com/security/833...-for-intel-cpus-due-to-likely-data-leaks.html

Intel themselves said that disabling HT is not a mitigation.

However, the general mitigations described in this paper should still be applied as disabling hyperthreading does not in itself provide mitigation for L1TF. Mitigation is also not required in situations where step 2 in the L1TF Limiting Factors section has been entirely mitigated, such as on systems with mitigations in the bare-metal OS that do not run virtual machines.

https://software.intel.com/security...ts/deep-dive-intel-analysis-l1-terminal-fault

It's fearmongering to suggest that you turn off HT as a normal consumer. If you know that you are affected by this CVE you already know what to do.

 

[Upgrayedd]

I want that 9700K designed with no iGPU in mind, not a disabled P version. HEDT is too damn expensive..

 

[londiste]

I have a feeling that security plays a larger role than Intel is willing to admit in these non-HT SKUs. No specific hidden meaning, simply reducing potential attack surface.

 

[R0H1T]

It's all about virtualization. If you run on physical hardware only the software patches are the only ones needed.

It was only OpenBSD that decided they preventatively disabled HT.


https://www.itwire.com/security/833...-for-intel-cpus-due-to-likely-data-leaks.html

Intel themselves said that disabling HT is not a mitigation.


https://software.intel.com/security...ts/deep-dive-intel-analysis-l1-terminal-fault

Again it's not, CVE-2018-3615 is about SGX. Though the other two vulnerabilities affect VM's more than anything else. I may have linked just that one article from Redhat, but the broader point still remains.

Yes, then again software patches are the only mitigation for current gen hardware.

This is twice, IIRC they said the same about some of the original smeltdown vulnerabilities or was it someone from Linux

It's not the only mitigation, but perhaps the easiest one. Software mitigation btw is OS dependent.