Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.

Messages - pocock

Pages: 1 [2] 3 4 ... 19

I decided to make another test of OpenBSD using the nightly build from 29 August that I found here.

The system is Talos II, dual CPU, 128GB and AMD Radeon RX 580 8GB.  Is this GPU currently supported on OpenBSD ppc?

I looked at the instructions here in the FAQ for X setup

Code: [Select]
# rcctl enable xenodm
# rcctl start xenodm

# pkg_info

amdgpu-firmware-20220708 firmware binary images for amdgpu(4) driver

Looking at the log, the X server is failing to run

Code: [Select]
cat /var/log/Xorg.0.log

[    19.833] (--) no aperture driver access: only wsfb driver useable
[    20.049] (EE)
Fatal server error:
[    20.049] (EE) xf86OpenConsole: No console driver found
Supported drivers: wscons
Check your kernel's console driver configuration and /dev entries(EE)
[    20.049] (EE)
Please consult the The X.Org Foundation support
 for help.
[    20.049] (EE) Please also check the log file at
"/var/log/Xorg.0.log" for additional information.
[    20.049] (EE)
[    20.050] (EE) Server terminated with error (1). Closing log file.

Talos II / mixing memory sizes on the same CPU?
« on: August 30, 2022, 03:00:09 am »

I understand that each CPU has four memory channels, therefore, optimum performance is achieved when all four memory banks have an identical size and they are accessed in parallel.

Nonetheless, is it safe or practical to mix memory sizes in the memory banks on the same CPU?

For example, could the user have 2 x 16GB and 2 x 32GB connected to a single CPU?

Would the CPU ignore the extra capacity in the larger modules and use them all as 16GB?  Or would it somehow access the RAM using two channel speeds?

Talos II / different memory sizes on each CPU in multi-CPU systems?
« on: August 30, 2022, 02:56:21 am »

For dual CPU systems, is it necessary to have an identical memory configuration on each CPU?

For example, if a user has 4 x 16GB on CPU1 does that mean the user must have 4 x 16GB on CPU2?

Or can the user have 4 x 16GB on CPU1 and 4 x 32GB on CPU2?


If you decide to loan it to hackerspaces that are nearby for me then I'm personally happy to visit them, take it there in person and run a workshop on it.  I would then be willing to go back a few weeks later, collect it and take it to the next hackerspace or post it back


Why not simply give it to a hackerspace as a gift?

If people see it at the hackerspace they will be more likely to buy one themselves

There is a hackerspace in Locarno, Switzerland, near the Swiss birds of prey park.  Don't leave small children unattended when the Condor is on the loose.

They don't currently have any black birds on their list

1. Debian Germany to use it to set up an additional build server and porterbox for Debian using PowerKVM for PowerPC big-endian Debian ports.


Any helpful opinions welcome!

The Debian Project Leader recently commented:

During my 2 terms we went from having around ~$750k in available funds to having about ~$1.25m now. Every time I mention what we've been spending on (like DSA upgrades, hardware for DDs, etc), we get more donations. As long as this is the case, I have no problem with DDs spending any money they want to if it helps them make Debian better. After all, this is literally the only reason why someone donates money to Debian in the first place. So, I don't believe that the Debian funds should be preserved like some kind of treasure. We should make it as easy as possible for people to give us money, and as easy as possible for DDs to spend money, all within our legal and social frameworks, of course.

Therefore, Debian can probably buy a few Blackbirds with funds from that bank account.  Debian paying for some Blackbirds (or bigger Talos II) is probably good business for retailers like Raptor and Vikings.

The Blackbird in question would still be available for somebody else who doesn't have $1 million (or €1 million)

I created a flavor of the Debian kernel package for a 4k page size (Gitlab commit) and nobody has integrated it in the Debian kernel repository.  This isn't a problem for me because I already know how to build a kernel but it would be helpful for other Debian users if they put the politics aside and merge that patch.  Due to the way Debian builds kernels it doesn't have any side effects for the 64k page size kernel packages.  Both types of kernel can coexist in the Debian archive and they can build different permutations of the installer for each of them.

I created a standalone topic for the idea of creating a dashboard or heat map to identify pinch points that can be addressed with donations of hardware or funds.

This was a comment in the discussion about donating a Blackbird to a worthy cause

It is probably not hard to create a dashboard to scrape or aggregate issues from bug trackers in various free software projects and assemble them into some kind of dashboard or heat map to identify the pinch-points for widespread OpenPOWER use.

Scraping the data is rather easy, most bug trackers have at least one well known API like RSS or iCalendar.

Identifying which issues relate to OpenPOWER depends on how diligent people are in tagging their bugs.

Deciding how to prioritize the issues on a dashboard or heat map may be more contentious as different people have different perspectives about which issues are important.


Consider the following setup:

main workstation:
- capture hardware

secondary workstation or laptop
- x86
- untrusted OS (e.g. Windows)
- applications that you are required to run for a client or employer (e.g. a messaging or remote desktop app) or a video meeting system that requires WebAssembly

You can generate an RTP video stream from the workstation, receive it on the secondary workstation and make it available as a virtual webcam for the software on that machine

I opened a couple of discussions about the topic:


Getting lists of issues from other projects is quite easy, I already did some work on that, creating scripts to scrape and merge issue lists from Github, Bugzilla, Redmine, etc

The more important and controversial thing is prioritization: for example, do the users simply vote for which issue is most important?  Do we focus on issues that help developers or issues that help end-users?  I won't use this post to give an answer to that.

Anyhow, if something like that comes together then I'm happy to provide feedback and maybe some code without any personal concern for who ends up getting this kit

The first link has screenshots


Does anybody maintain some kind of dashboard of what is either urgent or important or both for this platform?

It could be a useful way to guide the allocation of the hardware.


You could send it to me.  Some of the things I do with GPU testing are not possible on my primary workstation because I don't want to crash my desktop.

Talos II / Re: Indium pads required for 18-core CPU on Talos II Lite?
« on: July 29, 2022, 03:19:53 pm »

For a question like this, I would strongly recommend sending a formal support request to Raptor

If they supplied the CPU then they are responsible for any issues that arise if you fry your CPU during the warranty period

Please ask them to document stuff like this publicly, it will help the next person to avoid asking the same question

Applications and Porting / Re: FFMPEG
« on: July 23, 2022, 04:37:13 pm »

Maybe some of the other users can get together and crowdfund this bounty so the developer can feed his family.

We can impersonate IBM and pay $50 each in IBM's place

If we pay IBM's bills for them, will they accuse us of violating their trademark?


Thanks for this feedback

Looking at the IBM doc, the STOP4 and subsequent states (STOP5, STOP11) have some similarities to S3 sleep.  They are not related to full hibernation/suspend.

For those states:

- are they supported in the Talos II / Blackbird firmware?

- are they supported in the Linux (or *BSD) kernels?

- do they require any special utilities in the userspace or desktop?

For a full hibernate / suspend to disk: that particular IBM doc doesn't really indicate whether hibernate is supported.

In the S3 sleep mode from the x86 world, similar to the POWER modes where some cores remain active, RAM continues to have power.

In the full hibernate, you can completely unplug the power supply.  All state from the CPU, RAM, hardware and GPU has been persisted on disk and all of those devices can recover their state when power comes back.

Applications and Porting / Re: FFMPEG
« on: July 10, 2022, 04:45:47 pm »

I had some communication with one of the developers who contributed a patch for one of these bounties

He said he did not receive payment

I feel very uncomfortable using ffmpeg if people have not been paid for their work

Personally, I found the unit tests did not pass, this implies that some more work may be necessary before the patch is merged.

On the other hand, if nobody looks at the patch from the developer or the feedback from other users then it is very unfair to the person who did the work.

Pages: 1 [2] 3 4 ... 19