I work in CPU security and it's the same with microarchitecture. You wanna know if a machine is vulnerable to a certain issue?
- The technical experts (including Intel engineers) will say something like "it affects Blizzard Creek and Windy Bluff models'
- Intel's technical docs will say "if CPUID leaf 0x3aa asserts bit 63 then the CPU is affected". (There is no database for this you can only find it out by actually booting one up).
- The spec sheet for the hardware calls it a "Xeon Osmiridium X36667-IA"
Absolutely none of these forms of naming have any way to correlate between them. They also have different names for the same shit depending on whether it's a consumer or server chip.
Meanwhile, AMD's part numbers contain a digit that increments with each year but is off-by-one with regard to the "Zen" brand version.
Usually I just ask the LLM and accept that it's wrong 20% of the time.
> - Intel's technical docs will say "if CPUID leaf 0x3aa asserts bit 63 then the CPU is affected". (There is no database for this you can only find it out by actually booting one up).
I’m doing some OS work at the moment and running into this. I’m really surprised there’s no caniuse.com for cpu features. I’m planning on requiring support for all the features that have been in every cpu that shipped in the last 10+ years. But it’s basically impossible to figure that out. Especially across Intel and amd. Can I assume apic? Iommu stuff? Is acpi 2 actually available on all CPUs or do I need to have to have support for the old version as well? It’s very annoying.
I feel like it's a cultural thing with the designers. Ceragon were the exact same when I used to do microwave links. Happy to provide demo kit, happy to provide sales support, happy to actually come up and go through their product range.
But if you want any deep and complex technical info out of them, like oh maybe how to configure it to fit UK/EU regulatory domain RF rules? Haha no chance.
We ended up hiring a guy fluent in Hebrew just to talk to their support guys.
Super nice kit, but I guess no-one was prepared to pay for an interface layer between the developers and the outside world.
I have three Ubuntu servers and the naming pisses me off so much. Why can't they just stick with their YY.MM. naming scheme everywhere. Instead, they mostly use code names and I never know what codename I am currently using and what is the latest code name. When I have to upgrade or find a specific Python ppa for whatever OS I am running, I need to research 30 minutes to correlate all these dumb codenames to the actual version numbers.
> AMD's part numbers contain a digit that increments with each year
Aha, but which digit? Sure, that's easy for server, HEDT and desktop (it's the first one) but if you look at their line of laptop chips then it all breaks down.
Oh, the Xeons are with the vX vs vY nonsense, where the same number but a different version is an entirely different CPU (like the 2620 v1 and v2 are different microarchitecture generations and core counts). But, not to leave AMD out, they do things like the Ryzen 7000 series which are Zen 4 except for the models that are Zen 2 (!). (yes if you read the middle digits there's some indication but that's not that helpful for normal customers).
That's been the case with hardware at several companies I was at.
I was convinced that the process was encouraged by folks who used it as a sort of weird gatekeeping by folks who only used the magic code names.
Even better I worked at a place where they swapped code names between two products at one time... it wasn't without any reason, but it mean that a lot of product documentation suddenly conflicted.
I eventually only refereed to exact part numbers and model numbers and refused to play the code name game. This turned into an amusing situation where some managers who only used code names were suddenly silent as they clearly didn't know the product / part to code name convention.
You can correlate microarchitecture to product SKUs using the Intel site that the article links. AMD has a similar site with similar functionality (except that AFAIK it won't let you easily get a list of products with a given uarch). These both have their faults, but I'd certainly pick them over an LLM.
But you're correct that for anything buried in the guts of CPUID, your life is pain. And Intel's product branding has been a disaster for years.
Also technically the code names are only for unreleased products so on ark it’ll say “products formerly Ice Lake” but the intel will continue to calm them Ice Lake.
> Absolutely none of these forms of naming have any way to correlate between them.
I've found that -- as of a ~decade ago, at least, ark.intel.com had a really good way to cross-reference among codenames / SKUs / part numbers / feature set/specs. I've never seen errata there but they might be. Also, I haven't used it in a long time so it could've gotten worse.
I've also found the same thing a decade ago,
apparently lots of features(e.g. specific instruction, igpu)
are broadly advertised as belonging to specific arch,
but pentium/celeron(or for premium stuff non-xeon) models often lack them entirely and
the only way to detect is lscpu/feature bits/digging in UEFI settings.
- sSpec S0ABC = "Blizzard Creek" Xeon type 8 version 5 grade 6 getConfig(HT=off, NX=off, ECC=on, VT-x=off, VT-d=on)=4X Stepping B0
- "Blizzard Creek" Xeon type 8 -> V3 of Socket FCBGA12345 -> chipset "Pleiades Mounds"
- CPUID leaf 0x3aa = Model specific feature set checks for "Blizzard Creek" and "Windy Bluff(aka Blizzard Creek V2)"
- asserts bit 63 = that buggy VT-d circuit is not off
- "Xeon Osmiridium X36667-IA" = marketing name to confuse specifically you(but also IA-36-667 = (S0ABC|S9DFG|S9QWE|QA45P))
disclaimer: above is all made up and I don't work at any of relevant companies
Since everyone is complaining about the naming schemes of CPUs, I'll pitch in.
An Intel Core Ultra 7 155U and a Core Ultra 7 155H, are very different classes of CPUs!
If you're comparing laptops, you'll see both listed, and laptops with the U variant will be significantly cheaper, because you get half the max TDP, 4 fewer cores, 8 fewer threads, and a worse GPU.
This isn't to say the 155U is a bad chip, it's just a low-power optimized chip, while the 155H is a high-performance chip, and the difference between their performance characteristics is a lot larger than you'd expect when looking at the model numbers. Heck, if you didn't know better, you might text your tech-savvy friend "hey is a 155 good?", and looking that up would bring up the powerful H version.
Their laptop naming scheme at least is fairly straightforward once you figure it out.
U = Low-TDP, for thin & light devices
H = For higher-performance laptops, e.g. Dell XPS or midrange gaming laptops
HX = Basically the desktop parts stuffed into a laptop form factor, best perf but atrocious power usage even at idle. Only for gaming laptops that aren't meant to be used away from a desk.
And within each series, bigger number is better (or at least not worse - 275HX and 285HX are practically identical).
That reminds me when I got a server-grade Xeon E5472 (LGA771) and after some very minor tinkering (knife, sticker mod) fit it into a cheap consumer-grade LGA775 socket. Same microarchitecture, power delivery class, all that.
LGA2011-0 and LGA2011-1 are very unalike, from the memory controller to vast pin rearrangement.
So not only they call two different sockets almost the same per the post, but they also call essentially the same sockets differently to artificially segment the market.
I recall standing in CEX one day perusing the cabinet of random electronics ( as you do ) and wondering why the Intel CPUs were so cheap compared to the AMD ones. I eventually concluded that the cross generation compatibility of zen cpus meant they had a better resale value. Whereas if you experienced the more common mobo failure with an Intel chip you were likely looking at replacing both.
It has pretty much always been the case that you need to make sure the motherboard supports the specific chip you want to use, and that you can't rely on just the physical socket as an indicator of compatibility (true for AMD as well). For motherboards sold at retail the manufacturer's site will normally have a list, and they may provide some BIOS updates over time that extend compatibility to newer chips. OEM stuff like this can be more of a crapshoot.
All things considered I actually kind of respect the relatively straightforward naming of this and several of Intel's other sockets. LGA to indicate it's land grid array (CPU has flat "lands" on it, pins are on the motherboard), 2011 because it has 2011 pins. FC because it's flip chip packaging.
> For motherboards sold at retail the manufacturer's site will normally have a list, and they may provide some BIOS updates over time that extend compatibility to newer chips.
Ah, but if you want to buy a newly released CPU and the board does support/work with it, but nobody has updated the documentation on the website: How do you know?
Ultimately it's always a crapshoot. Some manufacturers don't even provide release notes with their BIOS updates...
Back in the day, this is what forums were for. Unfortunately forums are dead, Facebook is useless, and Google search sucks now. So you should just buy it, if it doesn't work ask for a refund and if they refuse just do a chargeback.
This is too forgiving of intel in this case. It has a name. They just don't use it. "Sockets Supported: FCLGA2011". It's not like this is poorly named. It's not even true.
It's because naming products is done by the marketing dept. Sometimes they decide to increase a "major" version number for a product that is a rehash of a previous line just to confuse people and sell more units.
People believe "bigger number" = better, and marketing teams exploit that.
At least with CPUs, I believe the the retail product names are deliberately confusing by design so that you as a consumer get confused (and mislead) into buying older models, whose sales tend to stagnate when newer models are released. (Newer models are of course, obscenely priced to differentiate them). A somewhat aware tech consumer what like to buy the latest affordable model they can. But if you can't easily identify the latest model or the next best one after it, they will often end up purchasing some older model with similar name.
In fairness, the author should've known something was up when they thought they could put a multiple year newer chip in an Intel board. That sort of cross-generational compatibility may exist in AMD land but never in Intel.
I mean sure, that would seem suspicious. But not suspicious enough that I'd likely have caught the problem. It's not that far fetched that Intel may occasionally make new CPUs for older sockets, and when Intel's documentation for the motherboard says "uses socket FCLGA2011" and Intel's documentation for the CPU says "uses socket FCLGA2011", I too would have assumed that they use the same socket.
The author would likely be able to put a v3 generation processor in the motherboard, they just didn't do the necessary research to find that out before pulling the trigger.
I agree their name scheme sucks. But the way to buy a new CPU is to check with the motherboard vendor about what CPUs the motherboard supports. You can't expect it to work (although it may) if the motherboard maker doesn't list it as supported.
Having some portion of the socket name stay the same can still be helpful to show that the same heatsinks are supported. I agree there are many far better ways Intel could handle this.
LGA2011 was an especially cursed era of processors and motherboards.
In addition to all of the slightly different sockets there was ddr3, ddr3 low voltage, the server/ecc counterparts, and then ddr4 came out but it was so expensive (almost more expensive than 4/5 is now compared to what it should be) that there were goofy boards that had DDR3 & DDR4 slots.
By the way it is _never_ worth attempting to use or upgrade anything from this era. Throw it in the fucking dumpster (at the e waste recycling center). The onboard sata controllers are rife with data corruption bugs and the caps from around then have a terrible reputation. Anything that has made it this long without popping is most likely to have done so from sitting around powered off. They will also silently drop PCI-E lanes even at standard BCLK under certain utilization patterns that cause too much of a vdrop.
This is part of why Intel went damn-near scorched earth on the motherboard partners that released boards which broke the contractual agreement and allowed you to increase the multipliers on non-K processors. The lack of validation under these conditions contributed to the aformentioned issues.
Intel and AMD naming schemes are extremely confusing these days. I can understand that naming these things must be really complicated these days since we have different core counts, thread counts, different types of cores, different clock speeds etc, but still
Because I don't follow CPUs constantly and only check in from time to time, all the code names (for cores, CPUs and platforms), generations, marketing names, model numbers, etc make it hopelessly confusing. And it's not just Intel but AMD and other companies have been doing this chronically for >10 years. It seems almost like intentional obfuscation yet I can't really think of a long-term reason that creating confusion systemically is in the company's interest. Sure, every company occasionally has a certain generation they might like to forget but that's too unpredictable to be the motivation behind such a consistent long-term pattern.
So I suspect maybe it's just a perverse effect of successive generations of marketing and product managers each coming up with a new system "to fix the confusion?" What's strange is that there's enough history here that smart people should be able to recognize there's a chronic problem and address it. For example, relatively simple patterns like Era Name (like "Core"), Generation Number, Model Number - Speed and then a two digit sub-signifier for all the technical variants. Just two digits of upper case letters and digits 1-9 is enough to encode >1200 sub-variants within each Era/Gen/Model/Speed.
The maddening part is that they not only change the classifiers, they also sometimes change the number and/or hierarchy of classifiers, which eliminates any hope of simply mapping the old taxonomy to the new.
This reminds me of my ASRock motherboard, though this was over a decade ago now. The actual board was one piece of hardware, but the manual it shipped with was for a different piece of hardware. Very similar, but not identical (and worse, not identical where I needed them to be, which, naturally, is both the only reason I noticed and how these things get noticed…), but yet both manual and motherboard had the same model number. ASRock themselves appeared utterly unaware that they had two separate models wandering around bearing the same name, even after it was pointed out to them.
The next motherboard (should RAM ever cease being the tulip du jour) will not be an ASRock, for that and other reasons.
For the love of everything though, just increment the model number.
It's fascinating how 'Naming Schemes' are supposed to clarify hierarchy but end up creating more chaos. When the signifier (FCLGA2011) detaches from the signified (physical compatibility), the system is officially broken. Feels like a hardware version of a bureaucratic loop.
Yea, old server hardware can be super cheap! In my opinion though, the core counts are misleading. Those 24 cores are not compareable to the cores of today. Plus IPC+power usage are wildly different. YMMV on if those tradeoffs are worth it.
Yeah, Intel has some crazies in the naming department since they abandoned Netburst with clear generation number and frequency in the name. I remember having two CPUs with exact same name E6300 for the exact same socket LGA775, but the difference was 1 GHz and cache size. Like, ok, I can understand that they were close enough, but at least add something to the model number to distinguish them.
AWS just renamed their Security Hub service to Security Hub CSPM and then created a new service named Security Hub that is related but completely different than the original service.
[+] [-] bjackman|3 months ago|reply
- The technical experts (including Intel engineers) will say something like "it affects Blizzard Creek and Windy Bluff models'
- Intel's technical docs will say "if CPUID leaf 0x3aa asserts bit 63 then the CPU is affected". (There is no database for this you can only find it out by actually booting one up).
- The spec sheet for the hardware calls it a "Xeon Osmiridium X36667-IA"
Absolutely none of these forms of naming have any way to correlate between them. They also have different names for the same shit depending on whether it's a consumer or server chip.
Meanwhile, AMD's part numbers contain a digit that increments with each year but is off-by-one with regard to the "Zen" brand version.
Usually I just ask the LLM and accept that it's wrong 20% of the time.
[+] [-] josephg|3 months ago|reply
I’m doing some OS work at the moment and running into this. I’m really surprised there’s no caniuse.com for cpu features. I’m planning on requiring support for all the features that have been in every cpu that shipped in the last 10+ years. But it’s basically impossible to figure that out. Especially across Intel and amd. Can I assume apic? Iommu stuff? Is acpi 2 actually available on all CPUs or do I need to have to have support for the old version as well? It’s very annoying.
[+] [-] ErroneousBosh|3 months ago|reply
But if you want any deep and complex technical info out of them, like oh maybe how to configure it to fit UK/EU regulatory domain RF rules? Haha no chance.
We ended up hiring a guy fluent in Hebrew just to talk to their support guys.
Super nice kit, but I guess no-one was prepared to pay for an interface layer between the developers and the outside world.
[+] [-] 7bit|3 months ago|reply
Same with Intel.
STOP USING CODENAMES. USE NUMBERS!
[+] [-] automatic6131|3 months ago|reply
Aha, but which digit? Sure, that's easy for server, HEDT and desktop (it's the first one) but if you look at their line of laptop chips then it all breaks down.
[+] [-] hedgehog|3 months ago|reply
[+] [-] duxup|3 months ago|reply
I was convinced that the process was encouraged by folks who used it as a sort of weird gatekeeping by folks who only used the magic code names.
Even better I worked at a place where they swapped code names between two products at one time... it wasn't without any reason, but it mean that a lot of product documentation suddenly conflicted.
I eventually only refereed to exact part numbers and model numbers and refused to play the code name game. This turned into an amusing situation where some managers who only used code names were suddenly silent as they clearly didn't know the product / part to code name convention.
[+] [-] 7bees|3 months ago|reply
But you're correct that for anything buried in the guts of CPUID, your life is pain. And Intel's product branding has been a disaster for years.
[+] [-] mastax|3 months ago|reply
[+] [-] zrm|3 months ago|reply
https://en.wikipedia.org/wiki/List_of_Intel_Core_processors
https://en.wikipedia.org/wiki/List_of_Intel_Xeon_processors
It doesn't have the CPUID but it's a pretty good mapping of model numbers to code names and on top of that has the rest of the specs.
[+] [-] balou23|3 months ago|reply
Coincidentally, if anyone knows how to figure out which Intel CPUs actually support 5-level paging / the CPUID flag known as la57, please tell me.
[+] [-] wyldfire|3 months ago|reply
I've found that -- as of a ~decade ago, at least, ark.intel.com had a really good way to cross-reference among codenames / SKUs / part numbers / feature set/specs. I've never seen errata there but they might be. Also, I haven't used it in a long time so it could've gotten worse.
[+] [-] TiredOfLife|3 months ago|reply
Under https://en.wikipedia.org/wiki/Ryzen#Mobile_6 Ryzen 7000 series you could get zen2, zen3, zen3+, zen4
[+] [-] countWSS|3 months ago|reply
[+] [-] andrewf|3 months ago|reply
"Products formerly Blizzard Creek"
WTF does that even mean?
[+] [-] RealStickman_|3 months ago|reply
[+] [-] greggsy|3 months ago|reply
[+] [-] numpad0|3 months ago|reply
[+] [-] nnevatie|3 months ago|reply
NVidia has these, very different GPUs:
Quadro 6000, Quadro RTX 6000, RTX A6000, RTX 6000 Ada, RTX 6000 Workstation Edition, RTX 6000 Max-Q Workstation Edition, RTX 6000 Server Edition
[+] [-] PunchyHamster|3 months ago|reply
It would be like having Quadro 6000 and 6050 be completely different generation
[+] [-] yonatan8070|3 months ago|reply
An Intel Core Ultra 7 155U and a Core Ultra 7 155H, are very different classes of CPUs!
If you're comparing laptops, you'll see both listed, and laptops with the U variant will be significantly cheaper, because you get half the max TDP, 4 fewer cores, 8 fewer threads, and a worse GPU.
This isn't to say the 155U is a bad chip, it's just a low-power optimized chip, while the 155H is a high-performance chip, and the difference between their performance characteristics is a lot larger than you'd expect when looking at the model numbers. Heck, if you didn't know better, you might text your tech-savvy friend "hey is a 155 good?", and looking that up would bring up the powerful H version.
[+] [-] the_pwner224|3 months ago|reply
Their laptop naming scheme at least is fairly straightforward once you figure it out.
U = Low-TDP, for thin & light devices
H = For higher-performance laptops, e.g. Dell XPS or midrange gaming laptops
HX = Basically the desktop parts stuffed into a laptop form factor, best perf but atrocious power usage even at idle. Only for gaming laptops that aren't meant to be used away from a desk.
And within each series, bigger number is better (or at least not worse - 275HX and 285HX are practically identical).
[+] [-] MadameMinty|3 months ago|reply
LGA2011-0 and LGA2011-1 are very unalike, from the memory controller to vast pin rearrangement.
So not only they call two different sockets almost the same per the post, but they also call essentially the same sockets differently to artificially segment the market.
[+] [-] shortercode|3 months ago|reply
[+] [-] 7bees|3 months ago|reply
All things considered I actually kind of respect the relatively straightforward naming of this and several of Intel's other sockets. LGA to indicate it's land grid array (CPU has flat "lands" on it, pins are on the motherboard), 2011 because it has 2011 pins. FC because it's flip chip packaging.
[+] [-] duskwuff|3 months ago|reply
That's an industry-wide standard across all IC manufacturing - Intel doesn't really get to take credit for it.
[+] [-] tristor|3 months ago|reply
Ah, but if you want to buy a newly released CPU and the board does support/work with it, but nobody has updated the documentation on the website: How do you know?
Ultimately it's always a crapshoot. Some manufacturers don't even provide release notes with their BIOS updates...
Back in the day, this is what forums were for. Unfortunately forums are dead, Facebook is useless, and Google search sucks now. So you should just buy it, if it doesn't work ask for a refund and if they refuse just do a chargeback.
[+] [-] kwanbix|3 months ago|reply
[+] [-] knorker|3 months ago|reply
[+] [-] sph|3 months ago|reply
People believe "bigger number" = better, and marketing teams exploit that.
[+] [-] thisislife2|3 months ago|reply
[+] [-] agos|3 months ago|reply
[+] [-] ocdtrekkie|3 months ago|reply
[+] [-] mort96|3 months ago|reply
[+] [-] justinclift|3 months ago|reply
[+] [-] userbinator|3 months ago|reply
[+] [-] D13Fd|3 months ago|reply
Having some portion of the socket name stay the same can still be helpful to show that the same heatsinks are supported. I agree there are many far better ways Intel could handle this.
[+] [-] monster_truck|3 months ago|reply
In addition to all of the slightly different sockets there was ddr3, ddr3 low voltage, the server/ecc counterparts, and then ddr4 came out but it was so expensive (almost more expensive than 4/5 is now compared to what it should be) that there were goofy boards that had DDR3 & DDR4 slots.
By the way it is _never_ worth attempting to use or upgrade anything from this era. Throw it in the fucking dumpster (at the e waste recycling center). The onboard sata controllers are rife with data corruption bugs and the caps from around then have a terrible reputation. Anything that has made it this long without popping is most likely to have done so from sitting around powered off. They will also silently drop PCI-E lanes even at standard BCLK under certain utilization patterns that cause too much of a vdrop.
This is part of why Intel went damn-near scorched earth on the motherboard partners that released boards which broke the contractual agreement and allowed you to increase the multipliers on non-K processors. The lack of validation under these conditions contributed to the aformentioned issues.
[+] [-] pkphilip|3 months ago|reply
[+] [-] mrandish|3 months ago|reply
So I suspect maybe it's just a perverse effect of successive generations of marketing and product managers each coming up with a new system "to fix the confusion?" What's strange is that there's enough history here that smart people should be able to recognize there's a chronic problem and address it. For example, relatively simple patterns like Era Name (like "Core"), Generation Number, Model Number - Speed and then a two digit sub-signifier for all the technical variants. Just two digits of upper case letters and digits 1-9 is enough to encode >1200 sub-variants within each Era/Gen/Model/Speed.
The maddening part is that they not only change the classifiers, they also sometimes change the number and/or hierarchy of classifiers, which eliminates any hope of simply mapping the old taxonomy to the new.
[+] [-] deathanatos|3 months ago|reply
The next motherboard (should RAM ever cease being the tulip du jour) will not be an ASRock, for that and other reasons.
For the love of everything though, just increment the model number.
[+] [-] Suggger|3 months ago|reply
[+] [-] kosolam|3 months ago|reply
[+] [-] titaniumtown|3 months ago|reply
[+] [-] Yizahi|3 months ago|reply
[+] [-] johng|3 months ago|reply
[+] [-] vladde|3 months ago|reply
looking at you USB 3.0 (or USB 3.1 Gen 1 (or USB 3.2 Gen 1))
[+] [-] Corrado|3 months ago|reply
[+] [-] tomcam|3 months ago|reply
[+] [-] baden1927|3 months ago|reply