Libre RISC-V Open-Source Effort Now Looking At POWER Instead Of RISC-V

[milkylainen]

I've been following the "Open HW/CPU communities" for the better part of two decades.
Right when the OpenRISC community was born and SPARC was forked off to different projects.
Also all of the MIPS clones etc.

It always comes down to the same old issues.
Building a CPU that can compete costs shitloads of engineering hours.
And it requires resources and tools way beyond sitting at your desktop with just code.

Nobody is willing to put down the resources required to feed a continuously thriving and "free" community.
And if for whatever reason something starts gaining momentum, companies start to fork things off,
building their own hardware to earn money.

As it is with hardware. After all this time with software. It's still easier to "sell" hardware than software.

So here it is with RISC-V. As was with OpenRISC, as is with SPARC etc.
The people/companies earning money have forked their own implementation from the ISA.
Getting real opensource hardware implementations that is worth a damn is still at position zero.

But here is to hoping. Cheers.

[wizard69]

Honestly I’m not surprised. I always thought that the RISC-V project was a bit screw balled. .

As for using a general purpose processor to handle GPU duties, didn’t Intel more or less tried that already. There is enough variance in what GPU’s and CPU’s do that it really doesn’t work out well. By the way that doesn’t mean GPUs can’t be improved for today’s workloads just that you can’t ignore their core reason for being.

[microcode]

"We cannot even get access to documentation explaining how to propose newextensions."

Can't you literally just write an extension document like the other ones (which have open TeX source), then propose it? Far as I can tell this isn't like the Bluetooth SIG, you don't need to use their super secret MS Word template to get started.

[Djhg2000]

So now the "Libre RISC-V" name is taken and it might not even end up using RISC-V.

The lesson here is when you name your project after a critical component you better be sure you can actually use that component. Since producing an open source GPU seems to still be the main focus the name isn't (and probably wasn't) appropriate for the task.

The only good solution I see is to turn over the name to some new leadership with the explicit goal of opening up RISC-V to the public again, then pick a new (ISA neutral) name for the GPU project.

[OneTimeShot]

Erm... ok but let's face it, building a GPU based off either the Power or RISC-V ISA isn't a real product. It's a fun idea, but GPUs are mostly thousands of ALUs being controlled by groups of fairly restricted instruction decoders. Otherwise GPUs and CPUs wouldn't exist as separate things by now.

The only Open part of RISC-V is the ISA, and that's the set of documents you can download from the website (heck - you can download ARM and Intel's they just have a different copyright). You can also download the "Rocket" Verilog code (or one of the other ones), but I'm not sure what magic secret sauce they believe exists outside that.

Maybe they should just join the consortium and be working on something that isn't fundamentally screwball, and people will listen to them...

[tuxd3v]

As much as there is hype around RISC-V, I hope POWER gets some traction with their efforts, too. And if it suits their needs, why not?!

there are already a powerpc laptop in the works..

[andyprough]

He doesn't appear to have any criticism of the architecture itself but rather how the organization stewarding it is treating the effort / community collaborations not ranking high compared to their commercial/business members.

Take as old as time. It's all about the money.

[blubbaer]

That's why lately it got quieter on the RISC-V mailing lists, especially on the ISA-Dev mailing list. Lets see how the discussion will be there in the future.

[ms178]

As much as there is hype around RISC-V, I hope POWER gets some traction with their efforts, too. And if it suits their needs, why not?!

[cb88]

Seems pretty obvious to me... Fork RISC-V ala OpenOffice... since nobody can get on the foundations mailing list nobody will be using it anyway especially if the fork's ML is more active and useful.