Hacker News Reader

Will running without relying on blobs mean that processing can be further optimised or is it more of a moral victory than a technical progression.

I'm assuming doing away with the shim means that there is some gain but in practical terms is it likely to be quite minimal? Will there be routines accessible that weren't accessible via the shim?

View on HN

More a moral victory from my PoV. Remember, code that runs in the blob is running on another processor, so not costing you ARM cycles. That's why we've set the Quake fps target much lower than what you can hit with the blob.

Thanks for all the effort to get to this stage Eben. As someone who was repeatedly told (on the RP forums) that I had no business to desire the user-land graphics to be open-sourced, and that only hardware engineers would get any benefit from this code, I thought this day would never come!

I'm happy to be proved wrong, and happy that many little 'RasPis' will have an extended lifespan from this decision by your employer. :-)

Fingers crossed. I'm most excited about the GPGPU stuff people will be able to do now we've documented the instruction set for the QPU. More on this next week.

Reply on news.ycombinator.com