News for hackers. Stuff that matters.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by getcrunk on Saturday October 08, 2022 @01:24AM (#33129989)
After apple silicon was released, I was wondering if intel and amd would respond with some arm socs down the line due to the seeming "end of road" for x86. But now what if they are intending to hold out on x86 long enough (~5-7 years) to be able to go all in on riscV?
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by vosper on Saturday October 08, 2022 @01:28AM (#33130012)
Is x86 at the end of the road? I don’t follow closely, but I impression is it’s been getting faster and faster ever since AMD stepped up and provided some competition with Ryzen.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by ahartmetz on Saturday October 08, 2022 @01:47AM (#33130092)
Almost like AMD is saving Intel from itself...

In any case, if Intel needs to diversify, open source (RISC-V) does seem better than proprietary mortal enemy (ARM).

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by baruch on Saturday October 08, 2022 @02:29AM (#33130273)
Any Intel server comes with an ARM chip (at least one that I know of), the BMC.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by tim-- on Saturday October 08, 2022 @05:05AM (#33130887)
And most modern AMD chips ship with ARM cores in them... https://en.m.wikipedia.org/wiki/AMD_Platform_Security_Proces...
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by acomjean on Saturday October 08, 2022 @07:16AM (#33131382)
Competition works wonders.. having both of them (what happened to cyrix?) keeps them honest to some extent.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by atty on Saturday October 08, 2022 @02:00AM (#33130155)
Both AMD and Intel have released some truly impressive CPUs lately, and this month both of them are releasing their next-gen products (ryzen 7000 and raptor lake respectively, I believe). The new ryzen chips are looking very impressive, and if Intel’s announced numbers are to be believed, raptor lake is going to be pretty great.

Where they fall down is on perf/watt, not raw performance. However there’s a lot of things that go into that difference, not just ISA, so I’m not sure if anyone has really decided if x86 is fundamentally less efficient, or just currently less efficient due to current design choices and constraints.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by harpratap on Saturday October 08, 2022 @02:53AM (#33130367)
> Where they fall down is on perf/watt, not raw performance

Raptor Lake is a pretty big jump in perf/watt. In just one generation they are claiming similar perf to Alder Lake at 250W but just 65W on Raptor Lake. AMD did a similar huge jump in efficiency last year with Ryzen 6000 for mobile

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by KingOfCoders on Saturday October 08, 2022 @03:27AM (#33130503)
Intel x86 will make even greater leaps in the future. The eCores (where they added more this generation, but no (?) pCores) are as small as ARM cores and the saved die space can be used for chaches (Intel already increased caches again on Raptor) for performance and power efficiency (as Apple shows). Then there will be 5nm which is a big reason for Apples Perf/Watt performance.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by jabl on Saturday October 08, 2022 @05:27AM (#33130959)
> Is x86 at the end of the road?

No. AMD and Intel are the oligopolistic providers for an unbelievably vast software ecosystem that practically rules all computing outside embedded (and some legacy mainframes here and there), are they going to throw away that market position just because the cleaner encoding of ARM or RISC-V would save an estimated low single-digit % of decoding power [1]?

[1]: https://www.usenix.org/system/files/conference/cooldc16/cool...

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by dmitrygr on Saturday October 08, 2022 @10:27AM (#33132542)
Top of the line x86 decoders are 6 wide (with limits of 64 aligned bytes on input, making average throughout around 4 per cycle as admitted by intel in their docs). Aarch64 can be decoded as wide as you wish thanks to fixed size. No solution to this other than a fixed length encoding.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by jabl on Saturday October 08, 2022 @10:50AM (#33132761)
> No solution to this other than a fixed length encoding.

Micro-op caching enters the room.

I mean, seriously, micro-op caching has been extensively used for over 20 years, including on ARM64 designs although Apple M1 doesn't have it.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by snvzz on Saturday October 08, 2022 @01:18PM (#33134116)
>No solution to this other than a fixed length encoding.

This problem does not apply to RISC-V, where with the C extension you get either 32bit or 2x 16bit. The added complexity is negligible, to the point where if a chip has any cache or rom in it, using C becomes a net benefit in area and power.

ARMv8 AArch64 made a critical mistake in adopting a fixed 32bit opcode size. A mistake we can see in practice when looking at the L1 cache size that Apple M1 needed to compensate for poor code density.

L1 is never free. It is always very costly: Its size dictates area the cache takes, the latency of this cache, the clocks the cache itself can achieve (which in turns caps the speed of the CPU), and how much power the cache draws.

As you mentioned decoder width: There's Ascalon[0], a RISC-V microarchitecture that's 8-decode (like M1), and 10-issue, by Jim Keller's team at Tenstorrent. It isn't in the market yet, but is bound to be among the first RISC-V chips targeting very high performance.

Note that, at that size (8-decode implies lots of execution units, a relatively large design), the negligible overhead of C extension is invisible. There's only gains to be had.

C extension decode overhead would only apply in the comically impractical scenario of a core that has neither L1 Cache nor any ROM in the chip. Such a specialized chip would simply not implement C. Otherwise, it is a net win.

0. https://youtu.be/yHrdEcsr9V0?t=346

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by mhh__ on Saturday October 08, 2022 @07:44PM (#33137092)
No. It's not a nice ISA but in the 20 Billion transistor limit it's not the pressing issue
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by jillesvangurp on Saturday October 08, 2022 @02:37AM (#33130299)
An ARM based design would make sense, except unlike Apple they'd have to buy a license. Apple has a perpetual license so they don't have to pay a thing and can do what they want with it. Like the M1 processor. But Intel does not have that. So, developing risc v in the background without committing to it, yet, makes a lot of sense. It might actually give them a path to come up with an answer to the M1 that isn't just a slightly more efficient x86 processor.

Apple just demonstrated that changing CPU architecture is not that big of a deal; so the value of x86 compatibility isn't what it used to be. You can just emulate it and it's fine. Even for games apparently. So Intel, backing an architecture that is already starting to compete with arm that is free makes a lot of sense.

AMD has the same challenge. And despite Nvidia failing to buy ARM, it's pretty clear that their long term strategy is not going to be letting other companies supply CPUs but to provide a complete solution.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by scrlk on Saturday October 08, 2022 @02:56AM (#33130378)
At one point, Intel stated that they retained their ARM architectural licence even after they sold their XScale line to Marvell.

https://www.zdnet.com/article/intel-we-have-arm-license-no-p...

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by ZiiS on Saturday October 08, 2022 @03:03AM (#33130406)
Intel used to make a whole line of StrongArm chips. Even today they ship Arm softcores with thier FPGAs. They have no issue with Arm's licensing.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by andromeduck on Saturday October 08, 2022 @06:18AM (#33131164)
Intel SSDs used ARM cores too.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by retrocryptid on Saturday October 08, 2022 @12:49PM (#33133855)
I think I remember hearing that Intel's current or recent past networking products are Arm based. I had always assumed Intel was interested in RISC-V as a possible replacement for the wide array of non-x86 cores in network, baseband and storage controller products they fab.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by rjsw on Saturday October 08, 2022 @09:19AM (#33132050)
Intel has "hard" ARM cores in their FPGAs, as does AMD (Xilinx).
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by KerrAvon on Saturday October 08, 2022 @12:31PM (#33133661)
IIRC, that turned into “XScale” and was sold off to Marvell.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by cma on Saturday October 08, 2022 @03:35AM (#33130530)
> You can just emulate it and it's fine.

Not quite.. Apple also had to modify ARM on the hardware side to support x64's stronger memory ordering. But RISC-V has options for both I think.

For an attempt at doing it without modifying the hardware see Microsoft's slow emulation attempt on their ARM version that was rejected by consumers and increased battery consumption much more.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by brucehoult on Sunday October 09, 2022 @05:55AM (#33139507)
TSO memory model is indeed a standard option on RISC-V, that no one had implemented yet as far as I know.

Software designed for the normal RISC-V memory model will work perfectly on a TSO machine, if perhaps a bit more slowly. Programs that depend on TSO semantics may be buggy on the standard RISC-V memory model (or on ARM too).

RISC-V also has a FENCE.TSO instruction that can be inserted as needed into software running on normal RISC-V. If you're going to use it a lot then you'd be better off implementing an actual TSO mode (not least because of code size). FENCE.TSO even works on (standards compliant) hardware that doesn't know about it, because unknown fences are supposed to be executed as FENCE RW,RW (the strongest fence), at some loss in efficiency.

Alibaba T-Head unfortunately didn't read this part of the spec when they designed the C906 and C910 cores, which give illegal instruction trap if they encounter an unknown fence such as FENCE.TSO. OpenSBI now does trap-and-emulate if necessary, but of course at another loss of efficiency. This bug affects the Allwinner D1 and Alibaba ICE SoC.

I don't know whether this errata in the C910 has been fixed in the TH1520 SoC in the Roma laptop (and other unannounced, cheaper, SBCs).

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by Havoc on Saturday October 08, 2022 @04:18AM (#33130688)
>Apple just demonstrated that changing CPU architecture is not that big of a deal;

That's if you have monopoly like control over your entire eco-system...

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by KerrAvon on Saturday October 08, 2022 @12:30PM (#33133658)
Not sure what this refers to. The Mac isn’t a monopoly and isn’t locked down like the iPhone. And Apple’s done this before and made it look easy.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by toast0 on Saturday October 08, 2022 @02:27PM (#33134695)
The Mac isn't locked down like iOS, but there's still no expectation that software built for one OS major release will continue to work for the next.

If the Apple fandom wiki is correct, the 68k emulator for PPC was included in all PPC releases, but Rosetta was included in 10.4 and 10.5, optional in 10.6 and unsupported in 10.7; it's scope was more limited than the 68k emulator as well. I expect Rosetta 2 will have a similar limited lifetime.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by dmitriid on Saturday October 08, 2022 @04:23AM (#33130716)
> An ARM based design would make sense, except unlike Apple they'd have to buy a license.

License is the least of it.

Apple released their first custom chip in 2013. And spent several years before that designing it.

So, it took Apple up to 15 years to get to where they are now with M1.

Even if AMD and Intel start now, and are twice as fast at developing new CPUs, they will need 6-7 years to reach parity with 2022 Apple in... 2028

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by mkl on Saturday October 08, 2022 @04:56AM (#33130852)
That doesn't make sense to me. Apple was starting from scratch (well, from PA Semi), but Intel and AMD have been designing high-performance CPUs for decades, and already changed architecture (to AMD64) successfully. On top of that, both have experience with ARM processors.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by dmitriid on Saturday October 08, 2022 @07:11AM (#33131356)
It takes around 4 to 6 years to design a new processor even if you have experience with it.

A new competitive processor in an area where all you have is "some experience"... Well, I wouldn't hold my breath.

If (and that's a big if) AMD and Intel started looking into ARM seriously after Apple unveiled M1, I wouldn't expect any ARM processor out of them earlier than 2025-2026.

Funnily enough I'd expect Amazon to perform better in this space (Graviton has been in deployment since 2019, three years ago, and is now in its third iteration).

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by formerly_proven on Saturday October 08, 2022 @07:19AM (#33131394)
AMD had K12 (Zen for AArch64)
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by dmitriid on Saturday October 08, 2022 @08:43AM (#33131835)
Never released. They did have an Opteron A1100 which was 3 years later than its orginal announcement date (released in 2017, announced for 2014)... and somehow I couldn't even find proper overview of its performance.

So AMD hasn't had much in the ARM department in the past 5-7 years.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by snvzz on Saturday October 08, 2022 @10:30AM (#33132576)
But we don't know what they have unless they announce it.

My guess is that they kept an ARM Zen frontend working, internally. And they probably have a RISC-V frontend now, alongside many other projects. They are large enough to do so.

When they perceive they can launch a successful product, they do so. Otherwise, we never know of these efforts.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by fmajid on Sunday October 09, 2022 @08:13PM (#33146551)
I would only take it seriously if Intel tasked this to its scrappy Israeli R&D, which saved the company from Itanic and Netburst irrelevance.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by jabl on Saturday October 08, 2022 @05:18AM (#33130923)
> Apple has a perpetual license so they don't have to pay a thing and can do what they want with it.

"Everybody" knows that Apple has an ARM architectural license, but AFAIU the terms haven't been disclosed. Presumably they got a sweeter deal than other ARM architectural licensees when they got rid of their ownership in ARM ages ago, but, "don't have to pay a thing" and "can do whatever they want" sounds a bit too sweet to be true?

> So, developing risc v in the background without committing to it, yet, makes a lot of sense.

TBH, I think Intel's interest in RISC-V is more about hurting ARM in the embedded market than about planning to sunset x86.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by MobiusHorizons on Saturday October 08, 2022 @02:15PM (#33134590)
Intel is demonstrating the capabilities of their fab services including the ip blocks they have available. This scifive core is no different in that respect from the pci controller or ddr5 memory controller in that respect. Many companies want to build custom silicon for various reasons (although the current value proposition seems to be ML related). Those companies will need many pieces to get data in and out of their custom solution, and a Linux capable cpu core to handle networking or a small amount of traditional compute is often necessary. Intel building a risc V core should not be seen in light of their traditional cpu business, it’s not even in the same league in terms of performance. It’s just a technology demonstrator to prove to companies that intel can actually deliver designs that integrate intel designed ip and regular fabless semiconductor designs. The fact that risc V is guaranteed press is just icing on the cake.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by jabl on Saturday October 08, 2022 @03:13PM (#33135091)
> Intel is demonstrating the capabilities of their fab services including the ip blocks they have available.

Oh yes, absolutely. (I was going to mention that earlier, but the edit timer had expired.)

But yes, splitting fab service into a separate business unit that is seriously open for 3rd parties seem to be a major strategic shift since Gelsinger took over the helm. And it probably makes sense, as TSMC et al have demonstrated the merchant fab model can work for the top end designs as well and the entire rest of the industry is moving towards that.

So in a way, unless Intel wants to be the odd man out with their own idiosyncratic workflows this is a route they must go down on.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by hnaccount_rng on Saturday October 08, 2022 @06:06AM (#33131123)
I think the recognition of “Apple showed that it’s not a big deal” would end similar to the one “The US showed that military invasions from superpowers into middle powers are not a big deal”.

The amount of raw effort that Apple put into making that transition _appear_ “no big deal” will be hard to adequately appreciate! It _noticeably_ affected software quality at least two MacOS versions prior (drop of 32-bit support and forcing all API accesses to go via their frameworks) and will have cost them hundreds of millions if not billions in engineering effort and unknowable amounts of lost sales in the mean time.

Yes it paid off. Obviously. But emulating their move, I’m not sure if there is even a single company able to do that.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by allie1 on Saturday October 08, 2022 @05:10AM (#33130903)
I am a M1 Max user and I would love to have Apple go back to Intel.

Sure, the battery life and not overheating is great, but you are limited to Arm based solutions, when installing linux VMs for example. Or gaming. Everyone seems to have forgotten how awesome it was to be able to do everything on one machine.

It is a compromise I live with, not something I prefer.

And at least half of Apple’s benefit comes from process technology, where the gap will be closing very soon, if for no other reason than the fact that after 2nm there is not much more room to grow with silicon, so even laggards will have time to catch up on process and yields.

The would has been running on x86 for so long it’s a waste to just decide to rework so many chunks of it.

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by biehl on Saturday October 08, 2022 @07:25AM (#33131422)
I am getting one of these https://dk.starlabs.systems/pages/desktops to go with my M1 to run x86 based VMs, docker and similar stuff. An extra expense, but hopefully a good combination.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by allie1 on Saturday October 08, 2022 @08:59AM (#33131952)
Those look good, a bulkier beasty option on the topic of intel: https://www.intel.com/content/www/us/en/products/docs/boards...

Just need to find a way to justify it to myself after spending on the MBP xD

Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by biehl on Saturday October 08, 2022 @11:23AM (#33133061)
Yes, I looked at that one too. But since I only need it for work I went with the small and quiet.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by KerrAvon on Saturday October 08, 2022 @12:36PM (#33133726)
Macs are not and never will be ideal for gaming. Apple execs don’t care about gaming, don’t understand it, are not interested in it, are not willing to do what is necessary to excel in gaming. Lots of people at Apple are working on game-adjacent technologies and their efforts are doomed because the execs sabotage every gaming opportunity eventually.
Re:Intel, SiFive Demo High-Performance RISC-V on Intel 4 by CharlesW on Saturday October 08, 2022 @12:58PM (#33133932)
> And at least half of Apple’s benefit comes from process technology…

Apple's performance-per-watt advantage is boosted by process improvements, but nothing I've read attributes anything close to half of that advantage to process. (References would be welcome.)

"Chips manufactured with this [3nm] process deliver 30% improvements in power consumption and 15% better performance in comparison with 5nm chips." https://www.computerworld.com/article/3609778/apple-on-track...