mnt reform support?

tuxd3v · 2020-09-13 18:34:32

Head_on_a_Stick wrote:

PowerPC (PPC64?) is old and slow and doesn't really compare with the current 7nm x86_64 AMD processors.

Well, actually PowerPC is one of the newest arch's around, created initially in the 90's, and its a open arch, even NXP gave permission to fully open documentation to the project www.powerpc-notebook.org.
It is part of the Open Power Community..

Yes, this processor in cause, is not as powerful as 7nm x86_64 launched recently, but it is the best performance/Open/Cost option available at the moment by far..
It has all the connectivity modern hardware has, and its a lot more performant than a ARM cortex a53, by far..

zapper · 2020-09-15 07:27:13

Head_on_a_Stick wrote:

tuxd3v wrote:
Other project, that is not ARM based, but Instead PowerPC based is the www.powerpc-notebook.org
PowerPC (PPC64?) is old and slow and doesn't really compare with the current 7nm x86_64 AMD processors.
The RISC-V laptop from Balthazar looks interesting but all RISC-V implementations are focused on power efficiency rather than performance so the same would apply to those.
POWER9 (pp64el) and perhaps POWER10 both compete on performance, if not price, and Raptor offer fully free (as in speech) desktops: https://www.raptorcs.com/content/BK1B01/intro.html
But with a TDP in excess of 90W (!) I don't think we'll see any laptops based on that ISA...

You see, before you why I do not trust openpower for the foreseeable future. Its too damn heavy wattage wise.

If I cannot use it on a laptop, and if its that heavy, no use for me.

Servers it might be good for, but all else... no way...

ARM and Risc-V are the future. Well... actually arm is more now related, but Risc-V is the future period. Until someone else develops something more secure...

zapper · 2020-09-15 07:31:42

tuxd3v wrote:

Head_on_a_Stick wrote:
PowerPC (PPC64?) is old and slow and doesn't really compare with the current 7nm x86_64 AMD processors.
Well, actually PowerPC is one of the newest arch's around, created initially in the 90's, and its a open arch, even NXP gave permission to fully open documentation to the project www.powerpc-notebook.org.
It is part of the Open Power Community..
Yes, this processor in cause, is not as powerful as 7nm x86_64 launched recently, but it is the best performance/Open/Cost option available at the moment by far..
It has all the connectivity modern hardware has, and its a lot more performant than a ARM cortex a53, by far..

I wonder if any processors based on A76 or A77 will be liberated in maybe 5-10 years of their blobs... or perhaps under 5 years...

Why? Well no meltdown spectre vulnerabilities for them.

We can hope right?

Till Risc-V comes out with something as fast as intel's p8600 or faster.

Anyways, I am pondering stuff right now. I will have time to ponder long after this. Thanks for particpating in this thread.

I wonder if I should wait on balthazar.space' idea of a laptop.

tuxd3v · 2020-09-22 03:50:48

zapper wrote:

I wonder if any processors based on A76 or A77 will be liberated in maybe 5-10 years of their blobs... or perhaps under 5 years...
Why? Well no meltdown spectre vulnerabilities for them.
We can hope right?
Till Risc-V comes out with something as fast as intel's p8600 or faster.
Anyways, I am pondering stuff right now. I will have time to ponder long after this. Thanks for particpating in this thread.
I wonder if I should wait on balthazar.space' idea of a laptop.

Well the next devices to expect are like the Rockchip RK3588, 8nm, 4xA76 + 4xA55, its around 30-40% better than the rk3399, which should be ok, for a decent laptop..
But probably we will not see then tile 2021 or 2022 sadly..

This ARM processors are affected by Spectre and/or Meltdown, as they employ the technologies that makes the exploit possible, that already happen in rk3399 for example( 2xA72 )

Everything above Cortex a55, and you have lots of vulnerabilities.. sadly.

zapper · 2020-09-26 07:54:21

tuxd3v wrote:

zapper wrote:
I wonder if any processors based on A76 or A77 will be liberated in maybe 5-10 years of their blobs... or perhaps under 5 years...
Why? Well no meltdown spectre vulnerabilities for them.
We can hope right?
Till Risc-V comes out with something as fast as intel's p8600 or faster.
Anyways, I am pondering stuff right now. I will have time to ponder long after this. Thanks for particpating in this thread.
I wonder if I should wait on balthazar.space' idea of a laptop.
Well the next devices to expect are like the Rockchip RK3588, 8nm, 4xA76 + 4xA55, its around 30-40% better than the rk3399, which should be ok, for a decent laptop..
But probably we will not see then tile 2021 or 2022 sadly..
This ARM processors are affected by Spectre and/or Meltdown, as they employ the technologies that makes the exploit possible, that already happen in rk3399 for example( 2xA72 )
Everything above Cortex a55, and you have lots of vulnerabilities.. sadly.

Good point, also... nvidia just aquired arm, so we'll have to see what happens because of that.

Imx8m might be the way to go for me then... till risc-v is useful for laptops.

zapper · 2020-10-18 02:13:25

tuxd3v wrote:

zapper wrote:
If it can handle an emulator like desmume and palemoon or two emulators and palemoon, than it would probably be good enough for me till they get a better processor.
I wonder what the most recent, fastest processor type that you can get without having any remote backdoors/blobs is with 4gbs of ram or more obviously and if possible LPDDR4,
Anyways thanks for the thoughts.
You welcome,
Indeed maybe mnt reform is the most open of them all( the price seems to go up when you talk of openess.. )
balthazar.space
it seems they will attempt something with RISCV in mind, but they don't rule out a ARM cortex-a7x version..
The project seems ambitious indeed..
Other project, that is not ARM based, but Instead PowerPC based is the www.powerpc-notebook.org
They seem each time closer to get a pcb design, for the Slimbook Eclipse laptop chassis
But its a laptop around 1500€( also a bit expensive.. )
Its also a 4 core cpu( SMT 2 - 8 threads ) at 2Ghz, but with some serious amount of Ram, I believe it goes till 32 or 64 GB Ram..
The problem with PowerPC( to a less extent than RISCV ofcourse,.. because support for RISCV right now almost doesn't exist.... ), is the environment around with supported applications..
At same time Debian has a port for PowerPC 64 bits, and its growing fast..
At the moment, this is my dream of a laptop, I confess!
A powerful AMD eGPU( Open Source Drivers ), mechanical keyboard with RGB, tons of memory Ram( even tough its LPDDR3 ) and its dual chanel, and a cpu with 8 threads at 2Ghz, with nvme disks, everything..
But it costs around some 1500€( its a estimated price range, they have done.. )
It could be that "I loose my head" and advance for this one

Sorry to bug anyone with this thread again, but I wondered, i had a netbook once called the acer aspire one, it had the n450 atom intel processor in it, would the mnt reform be 2x or 4x faster then that laptop and would it be able to handle 2x or 4x more applications then n450? keep in mind, the n450 i had only had one gigabyte of ram vs mnt reform's 4gb.

I also could only load one firefox application. would the mnt reform be able to handle 2-4x more applications.

So, it is this:

https://ark.intel.com/content/www/us/en … 6-ghz.html
with 1gb of ram in acer aspire one

vs mnt reform

with its 1mx8m 4 arm a53 cortex processors.

How much faster do you think it would be?

Or should I have started a new thread?

let me know.

kuleszdl · 2020-12-24 18:57:27

Hi,

I have both a pinebook pro as well as several core2duo Lenovo Thinkpads (such as X200) and also considered getting an MNT Reform. Overall, I think that the MNT Reform is a great project and I hope they will be able to reuse most stuff (such as the case) for a future model with a different PCB. In particular, I am hoping for RISC-V using one of the SiFive cores that are already almost available for Mini-ITX desktops:

https://www.crowdsupply.com/sifive/hifive-unmatched

When considering ARM64, both the rk3399 and NXP's LS1088A might be an option. The LS1088A is used in this box which I find interesting as well:

https://www.crowdsupply.com/traverse-technologies/ten64

However, the rk3399 has the issue that it needs a blob for DDR4 training, but this afaik applies to the current MNT Reform as well. Future Rockchip SoCs might be interesting as well, but if you consider that the pinebook pro still does not run an official version of Debian or Devuan shows that new SoCs really need some time for being supported well enough without tons of unofficial patches.

When comparing performance, I found geekbench.com to be an interesting option as it supports multiple architectures. So, if you want to compare the a typical Core2Duo P8600 with the RK3399 the data looks roughly like this:

P8600: 250 (single), 500 (multi)
RK3399: 250 (single), 700 (multi)
iMX8MQ: (unfortunately not benchmarked)

So YES, the rk3399 is almost as fast as an P8600. BTW: The fastest libre x86 option from the core2duo generation is a quadcore CPU in a T400 or T500 (requires some modding):

Q9000: 300 (single), 1000 (mutli)

However, if you consider running a "me cleaned" X230 with an i7 CPU as a viable option as well you will notice that the X230 is still waaay faster (not talking about quadcore i7 in a W530):

i7-3620M: 650 (single), 1500 (multi)

Overall, I am pretty optimistic that we will see some very interesting new options in 2021 and 2022 both based on ARM64 and RISC-V. Regarding PPC64LE (POWER9, POWER10), I am not that optimistic, at least for mobile.

zapper · 2020-12-25 12:17:19

kuleszdl wrote:

Hi,
I have both a pinebook pro as well as several core2duo Lenovo Thinkpads (such as X200) and also considered getting an MNT Reform. Overall, I think that the MNT Reform is a great project and I hope they will be able to reuse most stuff (such as the case) for a future model with a different PCB. In particular, I am hoping for RISC-V using one of the SiFive cores that are already almost available for Mini-ITX desktops:
https://www.crowdsupply.com/sifive/hifive-unmatched
When considering ARM64, both the rk3399 and NXP's LS1088A might be an option. The LS1088A is used in this box which I find interesting as well:
https://www.crowdsupply.com/traverse-technologies/ten64
However, the rk3399 has the issue that it needs a blob for DDR4 training, but this afaik applies to the current MNT Reform as well. Future Rockchip SoCs might be interesting as well, but if you consider that the pinebook pro still does not run an official version of Debian or Devuan shows that new SoCs really need some time for being supported well enough without tons of unofficial patches.
When comparing performance, I found geekbench.com to be an interesting option as it supports multiple architectures. So, if you want to compare the a typical Core2Duo P8600 with the RK3399 the data looks roughly like this:
P8600: 250 (single), 500 (multi)
RK3399: 250 (single), 700 (multi)
iMX8MQ: (unfortunately not benchmarked)
So YES, the rk3399 is almost as fast as an P8600. BTW: The fastest libre x86 option from the core2duo generation is a quadcore CPU in a T400 or T500 (requires some modding):
Q9000: 300 (single), 1000 (mutli)
However, if you consider running a "me cleaned" X230 with an i7 CPU as a viable option as well you will notice that the X230 is still waaay faster (not talking about quadcore i7 in a W530):
i7-3620M: 650 (single), 1500 (multi)
Overall, I am pretty optimistic that we will see some very interesting new options in 2021 and 2022 both based on ARM64 and RISC-V. Regarding PPC64LE (POWER9, POWER10), I am not that optimistic, at least for mobile.

Hmm, well from what you said, I gather it isn't too far off from the same speed... But yeah, I will consider it now, mostly because x86 is so bugged out due to, so many vulnerabilities... I already had kind of made up my mind, I appreciate though you replying to me.

Just a heads up though, it's the iMX8M I think that is used by mnt reform. At first anyways, but yeah, LS1028A is supposedly there next PCB, I wonder if they could get the LS1088 as well...

That one has 8x A53's. Which would be more secure than A72's or whatever else due to the newer ones having more security issues.

kuleszdl · 2020-12-25 14:43:57

Yes you are right - the RK3399 is about the speed of the P8600, maybe even faster in some situations. Since I have both machines here I could run some benchmarks if you have something particular in mind?

And well, the LS1088 would be interesting as well. However, a single A53 core is not very fast, and therefore singlecore performance would be awful. Also, the Ten64 seems to be rather power hungry and I am not sure how this chip would perform with passive cooling in the MNT Reform.

Since your requirements seem to be freedom, security and performance I guess the current MNT Reform could be still a viable option as the X200 looses a lot in terms of security (especially in terms of virtualization). And the next option would be probably an upgraded MNT Reform if it gets released next. Yet I hope they will skip ARM and go directly for RISC-V. The mentioned SiFive chips also have no out-of-order execution, so they are not a bad option. Another interesting option on the horizon is Alibaba's 16-core RISC-V chip, but I doubt it is targeted at mobile devices at this stage:

https://www.techspot.com/news/81177-chi … -risc.html

zapper · 2020-12-25 20:54:34

kuleszdl wrote:

Yes you are right - the RK3399 is about the speed of the P8600, maybe even faster in some situations. Since I have both machines here I could run some benchmarks if you have something particular in mind?
And well, the LS1088 would be interesting as well. However, a single A53 core is not very fast, and therefore singlecore performance would be awful. Also, the Ten64 seems to be rather power hungry and I am not sure how this chip would perform with passive cooling in the MNT Reform.
Since your requirements seem to be freedom, security and performance I guess the current MNT Reform could be still a viable option as the X200 looses a lot in terms of security (especially in terms of virtualization). And the next option would be probably an upgraded MNT Reform if it gets released next. Yet I hope they will skip ARM and go directly for RISC-V. The mentioned SiFive chips also have no out-of-order execution, so they are not a bad option. Another interesting option on the horizon is Alibaba's 16-core RISC-V chip, but I doubt it is targeted at mobile devices at this stage:
https://www.techspot.com/news/81177-chi … -risc.html

Feel free to run benchmarks, but yeah, I think LS1088 having 8 A53 cores would make it much faster than 2 A72's. That's just what I think though... unless I am missing something important. As for skipping to get a RISC-V chip, I would only want that if Devuan or something better has support for Risc-V.

Otherwise, go for LS1088 if possible.

or something else that is equivalent or better.

Last edited by zapper (2020-12-25 20:55:03)

Head_on_a_Stick · 2020-12-25 21:09:39

zapper wrote:

As for skipping to get a RISC-V chip, I would only want that if Devuan or something better has support for Risc-V

Unofficial at the moment but they're working on it:

https://wiki.debian.org/RISC-V

Drew DeVault was working on porting Alpine Linux to RISC-V but I'm not sure how that's going:

https://drewdevault.com/2018/12/20/Port … ISC-V.html

https://lists.alpinelinux.org/~alpine/d … 0hifive%3E

Nothing concrete from OpenBSD yet though, unfortunately:

https://marc.info/?l=openbsd-misc&m=160807140003965&w=2

But it looks like both FreeBSD and NetBSD have made some progress:

https://wiki.freebsd.org/riscv

http://wiki.netbsd.org/ports/riscv/

kuleszdl · 2020-12-28 01:49:31

Well, not all software is optimized for multiprocessing loads. I used an x86 cpu with cores but very slow per-core performance (AMD Opteron) and processing larger TEX documents on it was no fun at all. So in the end it really depends on what you use your box for. In general, I think the MNT Reform should be up to most everyday tasks and its batteries should last much longer than on a X200.

Apart from blobs, my main concern with the Pinebook Pro is the keyboard and (especially) touchpad when compared to the Lenovo machines that shine here. This tought me that the general ergonomics should be taken into account very seriously. I really hope the MNT Reform can get much closer here than the Pinebook Pro did. But please don't get me wrong - the Pinebook Pro isn't worse than many "consumer" laptops here, I am just used the Thinkpad experience and that's what I miss there.

Regarding RISC-V: Yes, the port is not officially supported but most packages seem to build fine. I tried to find information on whether or not risc-v support is planned for Debian bullseye but was unable to find any info on that. So I guess the actual problem with risc-v in production on Debian is simply getting packages and timely security updates...

zapper · 2020-12-28 23:00:04

Head_on_a_Stick wrote:

zapper wrote:
As for skipping to get a RISC-V chip, I would only want that if Devuan or something better has support for Risc-V
Unofficial at the moment but they're working on it:
https://wiki.debian.org/RISC-V
Drew DeVault was working on porting Alpine Linux to RISC-V but I'm not sure how that's going:
https://drewdevault.com/2018/12/20/Port … ISC-V.html
https://lists.alpinelinux.org/~alpine/d … 0hifive%3E
Nothing concrete from OpenBSD yet though, unfortunately:
https://marc.info/?l=openbsd-misc&m=160807140003965&w=2
But it looks like both FreeBSD and NetBSD have made some progress:
https://wiki.freebsd.org/riscv
http://wiki.netbsd.org/ports/riscv/

I bet OpenBSD will start to work on it more once they see hardware close to being out. As for NetBSD and Devuan... Those would be good to have till HyperbolaBSD is out. which sadly might out in close to a few years or more. oh well. I need to learn patience, I guess...

Look forwarding to it though!

The officially official Devuan Forum!

#26 2020-09-13 18:34:32

Re: mnt reform support?

#27 2020-09-15 07:27:13

Re: mnt reform support?

#28 2020-09-15 07:31:42

Re: mnt reform support?

#29 2020-09-22 03:50:48

Re: mnt reform support?

#30 2020-09-26 07:54:21

Re: mnt reform support?

#31 2020-10-18 02:13:25

Re: mnt reform support?

#32 2020-12-24 18:57:27

Re: mnt reform support?

#33 2020-12-25 12:17:19

Re: mnt reform support?

#34 2020-12-25 14:43:57

Re: mnt reform support?

#35 2020-12-25 20:54:34

Re: mnt reform support?

#36 2020-12-25 21:09:39

Re: mnt reform support?

#37 2020-12-28 01:49:31

Re: mnt reform support?

#38 2020-12-28 23:00:04

Re: mnt reform support?

Board footer