[HN Gopher] Exciting Days for ARM Processors
___________________________________________________________________
Exciting Days for ARM Processors
Author : diehunde
Score : 27 points
Date : 2020-07-06 21:14 UTC (1 hours ago)
(HTM) web link (smist08.wordpress.com)
(TXT) w3m dump (smist08.wordpress.com)
| velox_io wrote:
| I'm quite interested in what Nvidia is planning. Nvidia purchased
| Mellanox last year (they make high-end network gear often used in
| compute clusters). Nvidia is very involved in machine learning
| with their GPUs. The only missing part of puzzle is CPUs which
| was either Intel or AMD (a direct competitor). ARM changes things
| and means they're not dependant on those companies (and the x86
| licensing clusterfcuk preventing newcomers), and they have some
| room to tailor it to fit their needs (like Amazon & Google
| recently).
|
| These definitely are exciting times. Most Brits born in the 80's
| and 90's will have used Acorn computers in school, no one
| predicted that what would grow out of it (they weren't
| particularly fast).
| Rolcol wrote:
| What size is a memory page on other ARM CPUs? I think Apple's
| processors use 16KiB pages. Doesn't x86 software assume a 4KiB
| page size, unless it deals with huge pages?
| saagarjha wrote:
| > One possible downside of the new Macs, is that Apple keeps
| talking about the new secure boot feature only allowing Apple
| signed operating systems to boot as a security feature. Does this
| mean we won't be able to run Linux on these new Macs, except
| using virtualization?
|
| No, you can turn off secure boot.
| kick wrote:
| Was it just a gaffe when Federighi mentioned you couldn't
| install alternative operating systems in his recent Daring
| Fireball interview, then? I admit I could have misunderstood
| him, but it seemed like that was what he was saying.
| neilalexander wrote:
| Did he say you couldn't install them or that they wouldn't be
| "supported"? Those are two different things.
| saagarjha wrote:
| Haven't gotten to that part yet! Maybe I will on my next
| walk. But I would guess that he was talking about Linux
| virtualization being good enough that you wouldn't need to do
| this and/or no Bootcamp support?
| iknowstuff wrote:
| Not on ARM macs. The option is missing. The only remaining
| option is for allowing older versions of the OS, which must
| still be signed by Apple.
| selsta wrote:
| The GUI does not display all options. You most likely can use
| csrutil to disable it, see the "Platforms State of the Union"
| WWDC talk.
| saagarjha wrote:
| I think I remember a WWDC talk mentioning that it would be
| possible via a revamped csrutil from recovery.
|
| Edit: this one, about 19 minutes in:
| https://developer.apple.com/videos/play/wwdc2020/10686/
| Yetanfou wrote:
| You can on Intel-based machines, as far as I know it is not
| clear yet whether you can on ARM-based systems.
| somerandomqaguy wrote:
| Pressure for that came from Microsoft for Windows 8 certified
| devices:
|
| "Enable/Disable Secure Boot. On non-ARM systems, it is
| required to implement the ability to disable Secure Boot via
| firmware setup. A physically present user must be allowed to
| disable Secure Boot via firmware setup without possession of
| PKpriv. A Windows Server may also disable Secure Boot
| remotely using a strongly authenticated (preferably public-
| key based) out-of-band management connection, such as to a
| baseboard management controller or service processor.
| Programmatic disabling of Secure Boot either during Boot
| Services or after exiting EFI Boot Services MUST NOT be
| possible. Disabling Secure Boot must not be possible on ARM
| systems."[1]
|
| This requirement is no longer needed for Windows 10 logo
| certified x86_64 computer,[2] but I've yet to see a vendor
| actually take it out.
|
| For SOC systems, at least if you wish to have Windows 10
| Logo, it makes it optional if I'm reading their spec sheet
| correctly:
|
| "Requirement 10: OPTIONAL. An OEM may implement the ability
| for a physically present user to turn off Secure Boot either
| with access to the PKpriv or with Physical Presence through
| the firmware setup. Access to the firmware setup may be
| protected by platform specific means (administrator password,
| smart card, static configuration, etc.)"[3]
|
| That said, that's only for Windows logo certified devices.
| I'd assume if you don't intend to make you system Windows
| compatible then you can do whatever you want.
|
| ------
|
| [1]https://docs.microsoft.com/en-us/previous-
| versions/windows/h...
|
| [2]https://www.pcworld.com/article/2901262/microsoft-
| tightens-w...
|
| [3]https://docs.microsoft.com/en-us/windows-
| hardware/drivers/br...
| treebornfrog wrote:
| Read the first paragraph then wished that the font on mobile was
| a lot bigger.
| dang wrote:
| " _Please don 't complain about website formatting, back-button
| breakage, and similar annoyances. They're too common to be
| interesting. Exception: when the author is present. Then
| friendly feedback might be helpful._"
|
| https://news.ycombinator.com/newsguidelines.html
| saagarjha wrote:
| Is this a new addition to the guidelines? I could have sworn
| it wasn't there before...
| rwmj wrote:
| Surprised he doesn't mention Nuvia, which could be a very
| exciting development in Arm servers (if it lives up to the hype
| of course).
| camillomiller wrote:
| > I think Apple should be thanking the Raspberry Pi world for
| showing what you can do with SoCs, and for driving so much
| software to already be ported to the ARM processor.
|
| With all due respect, I love my raspberry pi, but Apple just
| needs to thank whoever was in charge of acquiring PA Semi's know
| how in 2008, along with the chip mastermind that is Johni Srouji.
| Or themselves from 1990, when they actually founded ARM as a
| joint venture with Acorn computers to make chips for the Newton.
| gorgoiler wrote:
| I take delivery of a Raspberry Pi 4 tomorrow. I'm really hoping
| it will replace my MBP for almost everything I do -- namely
| clerical office work, teaching high school CS, and web browsing.
| Exciting times.
| grugagag wrote:
| Honest question. How is that any better than a small laptop? Is
| the price point that makes the difference?
| gorgoiler wrote:
| The price, and I'm also interested in portability and
| robustness. My plan is to hot desk with this thing between
| three locations: my office in school, my classroom, and my
| home office.
|
| I also want something _weird_. Kids kind of look down on PCs
| and especially Linux. It's seen as kind of crappy compared to
| the shiny of iPhones and Windows gaming rigs. I hope to show
| them that there's a third kind of computer with which one can
| do a lot, that also happens to be pocketable and under $100.
|
| (And also: ANSI keyboard Pinebook Pro has been sold out for
| weeks.)
| wayneftw wrote:
| You could do the same thing with a $100/150 NUC and get
| better performance and software compatibility -
| https://www.amazon.com/Wintel-Pro-Mini-
| ordenador-T8/dp/B083V...
| Klinky wrote:
| I would be prepared to be underwhelmed at using a rpi as a
| desktop. Graphics drivers still need work.
|
| This is where I think Apple can do it right. They can tune
| drivers and fully optimize system performance, since they
| basically own the whole stack, and won't be stuck with
| proprietary broken blobs or reverse engineering a 3rd party
| design.
| gorgoiler wrote:
| I've watched a lot of YouTube videos of, ironically, people
| using Raspberry Pis to watch YouTube videos. The UI seems
| snappy, and I can live without full screen 1080p -- the only
| thing that seems poor is full screen full resolution video.
|
| Is there anything else I should be looking out for?
|
| Raspberry Pi 4 is now OpenGL ES 3.0 certified, so I'm
| expecting it to only get faster with time. My main concern is
| a Pi5 being released and my "old" hardware becoming obsolete.
| simcop2387 wrote:
| I wouldn't expect a pi5 any time soon. Maybe another
| revision of the pi4 or a new compute module system that
| allows a proper pi4 compute module (apparently not enough
| pins on the sodimm form factor they use currently to give
| the pcie lanes and other things the processor supports).
| DesiLurker wrote:
| NanoPi M4V2 may be better. plus you can install nvme drives in
| it for additional io perf.
| gorgoiler wrote:
| I love the diversity in this space but unfortunately I've
| been burned by off-brand pi stuff before.
|
| Pine's RockPro64 and Libre Renegade Elite are two lovely
| RK3399 devices that I've tried. However, each has sufficient
| quirks that something more mainstream like the Raspberry Pi 4
| (with a wide user base, more Google hits for common problems,
| etc) will hopefully let me focus on using the device as
| opposed to getting it to function.
|
| Non-RPi SBCs also seem to require a lot of off-brand
| community patches to get them working. I'm pretty wary of
| bringing an OS build which I downloaded from a third party
| github page onto a campus full of children. I don't have any
| reason to believe the community builds are nefarious, but
| it's less of a risk to stick with Raspberry Pi, IMHO.
| SillaDeRuedas wrote:
| Amazing! Isn't this the greatest idea ever?
| ttul wrote:
| Where can a developer buy one of these $500 ARM minis?
| thenewwazoo wrote:
| https://developer.apple.com/programs/universal/
| butz wrote:
| Are Apple ARM chips the same as other ARM chips or are there any
| "magic" that requires more work for developer to port software?
| baddox wrote:
| Apple licenses the ARM CPU architecture from Arm Holdings. My
| understanding is that Arm Holdings doesn't sell any hardware
| themselves.
___________________________________________________________________
(page generated 2020-07-06 23:00 UTC)