News for hackers. Stuff that matters.
Re:Intel Discloses Lakefield CPUs Specifications by Twirrim on Wednesday June 10, 2020 @12:15PM (#23478789)
I'm really curious how they envision this working, given the different instruction sets between the main core and the small cores. That seems like a bit of a nightmare to handle on the OS side of things, unless you turn things in to a two tier environment somehow, and require software (users?) to explicitly opt-in to the small cores somehow.
Re:Intel Discloses Lakefield CPUs Specifications by mackman on Wednesday June 10, 2020 @12:27PM (#23478951)
IBM did this with the PowerPC chips used in the Playstation 3. It was a development headache but part of that was the low power cores were extremely limited... no shared memory so you had to DMA data over and double buffer. They ran mighty fast though. It was a lot like programming a DSP really. If this is anything like that I would expect only some workloads to be pushed to the small cores in a similar way to the way stuff is pushed to GPU today. Frameworks will pop up to make it easier for developers but it will be rough at the get-go.
Re:Intel Discloses Lakefield CPUs Specifications by masklinn on Wednesday June 10, 2020 @01:51PM (#23479978)
> IBM did this with the PowerPC chips used in the Playstation 3

It was a completely different situation, the Cell's SPE were vector coprocessors, they were a completely different architecture than the PPE but they were also interacted with explicitly from the PPE.

Re:Intel Discloses Lakefield CPUs Specifications by sjwright on Wednesday June 10, 2020 @09:28PM (#23484310)
How did Cell compare to doing compute on a GPU? Was the difference in complexity due to support libraries etc, or because it required non-standard thinking about how it can be utilised?
Re:Intel Discloses Lakefield CPUs Specifications by sjwright on Wednesday June 10, 2020 @09:35PM (#23484362)
I remember reading or watching something by Naughty Dog about how they maximised use of Cell which was fascinating. (And something about how they ported to PS4 and made extremely efficient use of the eight cores by running game/physics in parallel with the previous frame’s rendering/graphics. Or something like that. It was ages ago and I can’t seem to find the talk online.)
Re:Intel Discloses Lakefield CPUs Specifications by rbanffy on Wednesday June 10, 2020 @12:32PM (#23479001)
The Cell was very different, and horrendously hard to program. The SPUs had no direct access to memory and had to be fed via DMA transfers coordinated from the PPUs.
Re:Intel Discloses Lakefield CPUs Specifications by wtallis on Wednesday June 10, 2020 @12:58PM (#23479339)
Yeah, there was no way to pretend the Cell was anything close to a traditional SMP design. But Intel's Lakefield and Arm's big.LITTLE are very much meant to be treated as SMP systems, with just a few tweaks on top to deal with/take advantage of the fact that they're not completely symmetrical. That means the CPU designers actually have to be more careful about what functional differences they allow to creep in.
Re:Intel Discloses Lakefield CPUs Specifications by rbanffy on Wednesday June 10, 2020 @01:18PM (#23479585)
I'm assuming the difference in supported instructions will have to be very minimal.

OSs will need to be careful not to move a process from one core to another that supports a subset of the instruction set it was expecting.

Re:Intel Discloses Lakefield CPUs Specifications by dathinab on Wednesday June 10, 2020 @01:03PM (#23479417)
My guess is the little cores are mainly for OS background jobs and a view applications which explicitly opt. for it.

Also while they have different instructions sets they don't have a different arch, i.e. they have a "shared base" of instructions which likely are good enough for many background applications. Like updaters, downloaders, background mail fetching programs etc.

In the end it fits in with their "always connected" approach. Through I'm still somewhat skeptical about the "always connected" approach. Like even in many first world countries always connected is just not a think for many users. Even on phones it not fully given through much more then on laptops.

Re:Intel Discloses Lakefield CPUs Specifications by ww520 on Wednesday June 10, 2020 @12:59PM (#23479352)
I would imagine the difference between the instruction sets of the two CPU types is small since the small CPU is Atom which is not too different from the main CPU.

The program machine code can be scanned when loaded to look for specific assembly opcodes to determine the required capability of the CPU to execute it on. The code with instructions not fitted for Atom will be sent to the main CPU only.

Edit: Just a thought. The OS can install an illegal-opcode exception handler. When a process is first run on the small CPU, the unsupported opcode will raise the exception. The exception handler can simply set the processor affinity of the process to the main CPU and put it to sleep. The OS will handle it like it normally would - putting the process in the run queue of the affined processor.

Re:Intel Discloses Lakefield CPUs Specifications by jlebar on Wednesday June 10, 2020 @01:23PM (#23479655)
> The program machine code can be scanned when loaded to look for specific assembly opcodes to determine the required capability of the CPU to execute it on.

That works as a heuristic, but it's not perfect, since JITs and self-modifying code are a thing.

I expect the chip will raise a fault and the OS will move the process.

Re:Intel Discloses Lakefield CPUs Specifications by aarongolliver on Wednesday June 10, 2020 @01:49PM (#23479948)
This is one of the things we tried when I worked (2011-12) at Intel on QuickIA [0] (dual socket, Atom on one side Xeon on the other). One of my first projects was to write a vectorized matrix multiplication that could only run on the Xeon, so we could demo the fault-to-big-core behavior.

[0] https://www.neotextus.net/hpca12.pdf

(I think the "3.2 QuickIA Software Support" section is interesting, if nearly a decade old by now)

Re:Intel Discloses Lakefield CPUs Specifications by ww520 on Wednesday June 10, 2020 @02:04PM (#23480148)
That's true. The code could be modified on the fly after the scanning so it's good to have a last ditch illegal-opcode exception and let the OS catch the exception to migrate the process.
Re:Intel Discloses Lakefield CPUs Specifications by kllrnohj on Wednesday June 10, 2020 @01:49PM (#23479955)
You would only need to do that scanning if the program had hard requirements like it was compiled to assume AVX512 support was present. Which is going to be extremely rare, since that would already mean an x86 program that's highly non-portable.

Runtime detection would be the only actual concern here, but you can easily just advertise the common baseline. As in, just pretend the sunny cove core doesn't support AVX512. The only problem then becomes the big core is potentially slower than it could be, but given how rare things like AVX512 is in typical desktop applications will anyone actually care?

EDIT: Oh, and this appears to be what they're basically doing. Even though Sunny Cove itself supports AVX-512, it's being disabled in this application: "One thing we can confirm in advance – the Sunny Cove does not appear to be AVX-512 enabled."

Re:Intel Discloses Lakefield CPUs Specifications by jdsully on Wednesday June 10, 2020 @12:18PM (#23478835)
Seems like the OS could solve it easily by trapping on undefined operation exceptions and retrying on the big core. If it still works simply mark the process as big core only.
Re:Intel Discloses Lakefield CPUs Specifications by londons_explore on Wednesday June 10, 2020 @12:39PM (#23479086)
You could take this idea further...

Trap the undefined instructions, and dynamically replace them with a jump to emulation code if running on a little core.

Then let the OS and software folks do a systemwide profile to find out which bits of code most frequently run on which cores. Then configure the compiler not to output any instructions not available on the little cores for code which usually runs on the little cores.

Re:Intel Discloses Lakefield CPUs Specifications by jacques_chester on Wednesday June 10, 2020 @12:58PM (#23479343)
> Trap the undefined instructions, and dynamically replace them with a jump to emulation code if running on a little core.

This was more or less what VMware pioneered to deal with privileged instructions. I expect there are thickets of patents involved, even if the earliest have expired. But it's likely there is or would be some licensing agreement.

Disclosure: I work for VMware, though not in VMs per se. Speaking for myself only.

Re:Intel Discloses Lakefield CPUs Specifications by jdsully on Wednesday June 10, 2020 @01:26PM (#23479688)
This is how FPU emulation worked back in the 8086-386 days. Any patents are long expired or invalidated with prior art.
Re:Intel Discloses Lakefield CPUs Specifications by garmaine on Wednesday June 10, 2020 @02:07PM (#23480186)
No, unfortunately not. Only if you implement it exactly as it was done back in the day for FPUs. Any deviation and you might run into a more recent patent that covers some aspect of a later implementation, maybe even something seemingly obvious or necessary. This is why it is called a patent “minefield.”
Re:Intel Discloses Lakefield CPUs Specifications by ori_b on Wednesday June 10, 2020 @01:02PM (#23479407)
At which point you've lost.
Re:Intel Discloses Lakefield CPUs Specifications by NortySpock on Wednesday June 10, 2020 @12:22PM (#23478885)
I was going to joke about Intel "discovering the big.LITTLE architecture" until you said different instruction sets. It will be interesting to hear how they hope that will work out...
Re:Intel Discloses Lakefield CPUs Specifications by est31 on Wednesday June 10, 2020 @12:27PM (#23478950)
I think in this instance "instruction set" means "set of supported instructions" instead of "architecture".
Re:Intel Discloses Lakefield CPUs Specifications by CountSessine on Wednesday June 10, 2020 @01:24PM (#23479667)
Sure but that’s still a nuisance from the point of view of OS scheduling. You can’t transparently move a process from a big core to a little core or vice versa the way you can with big.little.
Re:Intel Discloses Lakefield CPUs Specifications by mlyle on Wednesday June 10, 2020 @01:49PM (#23479954)
No, but it can be a small nuisance: you can leave a process eligible to run on any core until it faults for an illegal instruction; then you pin it to the big core.
Re:Intel Discloses Lakefield CPUs Specifications by rkangel on Wednesday June 10, 2020 @12:37PM (#23479058)
big.LITTLE kind of is different instruction sets though - full ARM vs thumb.
Re:Intel Discloses Lakefield CPUs Specifications by wtallis on Wednesday June 10, 2020 @01:01PM (#23479386)
The full ARM vs Thumb split never had anything to do with big.LITTLE, and was dropped with AArch64.
Re:Intel Discloses Lakefield CPUs Specifications by CountSessine on Wednesday June 10, 2020 @01:26PM (#23479687)
ARMv7 and ARMv 8 are full-on thumb2. Big.little has nothing to do with ARM vs thumb.
Re:Intel Discloses Lakefield CPUs Specifications by api on Wednesday June 10, 2020 @01:02PM (#23479394)
The fact that it's heterogenous kills it for me. Remember the Cell Broadband Engine? You could get some pretty crazy performance out of that thing, but nobody used the execution units because the instruction set was different.

GPUs get away with it because they are really a completely different kind of processor, but even there GPU processing is under-utilized for this reason. It's really a pain.

Re:Intel Discloses Lakefield CPUs Specifications by imtringued on Thursday June 11, 2020 @03:58AM (#23486273)
GPUs are underutilized because most workloads simply are not suitable for GPUs. It has nothing to do with the instruction set.
Re:Intel Discloses Lakefield CPUs Specifications by rzzzt on Wednesday June 10, 2020 @01:29PM (#23479722)
There was a proof-of-concept "smart network adapter" done by either Intel or MS (don't remember the exact details), which allowed finishing the download of a large file, or receiving emails while the host computer was asleep. I'd imagine tasks like these are well suited for the smaller cores.
Re:Intel Discloses Lakefield CPUs Specifications by monocasa on Wednesday June 10, 2020 @01:49PM (#23479949)
A lot of game consoles have this model too. PS3, PS4, Wii, and WiiU off the top of my head run pretty complex operations on the I/O processor even when the main system is off.
Re:Intel Discloses Lakefield CPUs Specifications by masklinn on Wednesday June 10, 2020 @03:34PM (#23481108)
The big.LITTLE concept was announced in 2011. It's not the concept of using differently sized cores which is odd, it's using cores with different instruction sets.
Re:Intel Discloses Lakefield CPUs Specifications by garmaine on Wednesday June 10, 2020 @02:07PM (#23480196)
macOS does this. Calls it a “power nap.”
Re:Intel Discloses Lakefield CPUs Specifications by dogma1138 on Wednesday June 10, 2020 @03:30PM (#23481058)
Power nap is when your computer periodically wakes up you are switching power states it’s not exactly the same thing.
Re:Intel Discloses Lakefield CPUs Specifications by Gravityloss on Wednesday June 10, 2020 @12:19PM (#23478845)
What's the user and developer experience, do programs need to be recompiled? Are the extra cores meant to typically run something like the JVM so no recompilation is needed?
Re:Intel Discloses Lakefield CPUs Specifications by sesuximo on Wednesday June 10, 2020 @12:28PM (#23478958)
I doubt you will need to recompile, although doing so is often a good idea as new compilers can use new instructions/optimizations.

I’d bet money that the different ISAs are full x86 and a subset of x86 which is a great idea. X86 has a lot of old instructions that almost No one uses. Perhaps the small cores will trap and move to process to the big core if it uses an old instruction.

Re:Intel Discloses Lakefield CPUs Specifications by kllrnohj on Wednesday June 10, 2020 @01:52PM (#23479989)
> I’d bet money that the different ISAs are full x86 and a subset of x86

You don't even need to bet, it's in the article:

"Both SKUs will feature one big ‘Sunny Cove’ CPU core, along with four little ‘Tremont’ Atom CPU cores"

It's a different uArch, but the same ISA. The extension support would be the only concern here, which is super minor.

Re:Intel Discloses Lakefield CPUs Specifications by sesuximo on Wednesday June 10, 2020 @02:10PM (#23480230)
Guess that makes it very good bet ;)
Re:Intel Discloses Lakefield CPUs Specifications by firethief on Wednesday June 10, 2020 @12:59PM (#23479359)
I don't see how the cost of supporting outmoded instructions would be significant. The decoder is a tiny proportion of the die, and not a bottleneck at all. Obsolete instructions that can't be translated to the same uops everything else uses are already microcoded anyway.

I'd bet the instruction set difference is mainly level of SIMD support. Sunny Cove will have AVX2, Tremont won't have enough execution units to go wider than SSE2.

Re:Intel Discloses Lakefield CPUs Specifications by fortran77 on Wednesday June 10, 2020 @12:34PM (#23479027)
It's an interesting architecture. We already do this in a way between CPU and GPU. Let the compilers and language libraries figure it out.
Re:Intel Discloses Lakefield CPUs Specifications by ericlewis on Wednesday June 10, 2020 @12:17PM (#23478826)
I have seen ARM chips with co-processors that work similarly
Re:Intel Discloses Lakefield CPUs Specifications by Twirrim on Wednesday June 10, 2020 @12:21PM (#23478874)
Sure big.LITTLE chips have been around for a while. But my understanding is the instruction set is identical between the cores, they just operate at different speeds. That in itself must be a fun balancing act for the scheduler.

To clarify my concerns (I haven't dug in to the specific instruction set differences):

Assume the main core supports AVX2 and the smaller cores don't. Which core do you execute the code on? Which one will get you the best performance per watt? How do you account for that in the OS scheduler? What do you want to optimise for?

If your code is compiled for AVX2, it'll fail on the small cores unless it does continuous runtime checking (which is expensive, but given processes can migrate between cores, presumably necessary).

Re:Intel Discloses Lakefield CPUs Specifications by gsliepen on Wednesday June 10, 2020 @12:42PM (#23479133)
It's not so much the speeds that differ, but the micro-architecture. The big cores are typically out-of-order cores with a large amount of cache, to get as many instructions as possible per cycle. The SMALL cores are in-order cores with a small amount of cache. These have a lower IPC, but they also use much less energy per instruction compared to the big cores.
Re:Intel Discloses Lakefield CPUs Specifications by jlouis on Wednesday June 10, 2020 @12:36PM (#23479045)
You do the same with fp. First floating point instruction traps and the process is then flagged as needing fp. This is then used in the context switch to also include fp instructions.

The advantage is you avoid storing fp registers unless you are going to use them.

That flag could easily determine what you can run where.

Re:Intel Discloses Lakefield CPUs Specifications by AnotherGoodName on Wednesday June 10, 2020 @12:23PM (#23478900)
No they usually pair different architectures and it will crash if the OS doesn't catch and handle the invalid instruction error the CPU will throw.

https://medium.com/@jaddr2line/a-big-little-problem-a-tale-o...

Re:Intel Discloses Lakefield CPUs Specifications by brigade on Wednesday June 10, 2020 @12:31PM (#23478986)
As mentioned in your link, that's ultimately against ARM's requirements for big.LITTLE and was due to buggy Samsung patches. A fixed kernel only exposes the subset of features available on all CPUs.
Re:Intel Discloses Lakefield CPUs Specifications by johntb86 on Wednesday June 10, 2020 @12:30PM (#23478981)
That's not usual, that's just Samsung's incompetence.
Re:Intel Discloses Lakefield CPUs Specifications by est31 on Wednesday June 10, 2020 @12:35PM (#23479033)
How does the scheduler know which process will use CPU instructions that the small cores don't support? Will it just try it out and then move the process to the higher support core if it detects an error?
Re:Intel Discloses Lakefield CPUs Specifications by AnotherGoodName on Wednesday June 10, 2020 @12:41PM (#23479108)
>How does the scheduler know which process will use CPU instructions that the small cores don't support?

I don't see that as required? If you catch the illegal instruction signal that CPUs throw you can just run it on the other CPU since the instruction counter would not have incremented. There's a delay in the catch and retry on the other CPU but i don't see the big deal here?

Re:Intel Discloses Lakefield CPUs Specifications by mtklein on Wednesday June 10, 2020 @12:48PM (#23479208)
I once ran into the same sort of issue with this very chip, in that the little A55 cores supported half-float compute, while the big Mongoose cores didn't. Seriously a pain.
Re:Intel Discloses Lakefield CPUs Specifications by simias on Wednesday June 10, 2020 @12:24PM (#23478909)
Can you give an example? I've seen ARM chips with co-processors with different features (like no MMU for instance) but not a completely different instruction set. Besides in my experience in these configurations the OS doesn't really do much with the other core, it's generally left to specific applications to have code explicitly meant to run on it, there's no automatic scheduling.

Unless you think about embedded co-processors that are generally here to control a complex subsystem (like video processing or something like that, arguably GPUs fit in that description) but in general those aren't handled like real CPU cores at the OS level, they have dedicated drivers or userland libraries dedicated to a specific purpose.

Something tells me that if Intel wants this architecture to be popular they'll have to work on a tighter and more transparent integration, otherwise this is going to end up like the Cell.

It's a pretty interesting approach though, I'm genuinely curious to see how that's going to end up working.

Re:Intel Discloses Lakefield CPUs Specifications by russdill on Wednesday June 10, 2020 @01:47PM (#23479923)
Go look at a modern automotive SoC. R5s, M3s, A72s, M4s, custom arch for real time, DSP, etc. All in one chip.
Re:Intel Discloses Lakefield CPUs Specifications by simias on Wednesday June 10, 2020 @03:09PM (#23480867)
I'm very familiar with some of these chips but my point still stands, in my experience it generally requires tailor-made software to really benefit from these architectures.

If these Intel CPUs are meant to be general purpose I wonder how that's going to work out.