No, AMD Will Not Be Opening Up Its Firmware/Microcode

[pal666]

So it is turning into a fully-fledged operating system

operating system's job is not managing storage, but managing processes. nevertheless even if it will turn into operating system, it will turn into remote operating system. so you are arguing for opening of operating system of any website you are using

[chithanh]

That's microcode meant to initialize them and set how they should work at low-level.

The microcode is not only active at initialization time but also at runtime from what I read:

Well, the various rings (graphics, compute, transfer, uvd, etc.) are already being run by Command Processors fed by a microcode since GCN1, and possibly earlier

https://www.semiaccurate.com/forums/...585#post269585

The ability to write stuff in a disk does not turn low-level firmwares in an operating system.

Well, what are the tasks of an operating system?

IPC
Memory management
Scheduling
Networking
Storage

Anyway, as bridgman has noted, storage isn't managed by the GPU but by the driver, though I have a hard time imagining how this is going to happen without any supporting code or logic for that on the GPU itself. The considerable speed gains that were demonstrated by AMD supposedly come from not having to move the data via the host, but directly between GPU and SSD.

fixed.
legit firmwares like these are too low-level to be seen as distinct from the hardware they run. This stuff is usually burned on ROMs or on NOR chips on the boards since decades.

But of course if it is in a chip on the board it's 100% fine, while if it is loaded on runtime it is 100% wrong.

Do note that I did not make that argument. A more nuanced version of this is what the FSF says.
And besides, I think your comment shows that you failed to fully grasp the FSF position on the matter.

[RussianNeuroMancer]

My 6550M still gets "ATOMBIOS stuck in loop" messages if I enable dynamic power management on it...
And without power management enabled, it runs slower than the APU graphics core, which sucks.

Is there bugreport about this? For example mine 6650M is fine.

[pal666]

Well, what are the tasks of an operating system?
...
Networking
Storage

lol, didn't you hear about networked microcontrollers? those are not os' tasks, os' task is arbitrating access to those

[pal666]

My 6550M still gets "ATOMBIOS stuck in loop" messages if I enable dynamic power management on it...

well, you can be sure that without atombios half of cards will not be supported at all, like with nouveau just because card vendors like to change things

[libv]

pal666: that would not have been true if we had stuck with it, and there was no nasty fork for personal glorification and linux distribution competition reasons.

[nomadewolf]

Unfortunately, there will always be a part of the code that is closed source.
Maybe someday, someone will successfuly crowdfund a completely open source GPU?...
Maybe even a company...
Even Sony is turning to crowdfuncding, so who knows...

[chithanh]

operating system's job is not managing storage

lol, didn't you hear about networked microcontrollers? those are not os' tasks, os' task is arbitrating access to those

You may want to fix Wikipedia then:

Access to data stored on disks is a central feature of all operating systems.

https://en.wikipedia.org/wiki/Operat...d_file_systems

Currently most operating systems support a variety of networking protocols, hardware, and applications for using them.

https://en.wikipedia.org/wiki/Operat...tem#Networking

[pal666]

You may want to fix Wikipedia then:

why? it says that os provides filesystem service to applications, not what writing to drive implies os. every hard drive or ssd has internal controller with microcode, which does real io to/from drive

[pal666]

same for network. os provides shared access to nic, but any microcontroller can use its nic and it does not need os for that