The R300 GLSL Compiler Improvements Are Coming

[curaga]

I would still be using my r500 had it not broken down :P

[elanthis]

The R300 driver is more complete in many ways. Adding new features there first makes some sense. They can be ported to R600/R800 drivers later.

A few Mesa/X developers have an entirely new GLSL stack up on git.freedesktop.org. I don't know where it's going, but it's a particularly high quality compiler using a lot of modern compiler design elements that the old Mesa compiler lacks. I'm expecting it'll be the basis for a new GLSL compiler in upcoming months. The design is really great, lacking perhaps only in that it uses standard memory allocator calls (new/delete as it's in C++) which is really not a good thing for a core driver component that may be called many times over the lifetime of an application (possibly one or more times per frame for some apps); the memory fragmentation and allocator churn kills performance. Sadly, few people outside of game developers and some embedded developers seem to have much head for that sort of thing these days. The last big popular C/C++ project I saw that made serious effort towards reducing fragmentation from frequent small object allocation was the Samba folks. :/

[Ragas]

I don't know how often 'normal' People buy hardware but I do only within about 5-6 years.
And the computers I see around .. from my parents ... or even the stoneage Machines of my girlfriends family ... anybody cares to better support the R100 family?! (and that's the new Machine)
(and I have issues with compiz on it, it works but sometimes the background doesn't get refreshed. Just imagine Windows trying composite on such a machine. )

One of the reasons that make linux so cool is that you can throw any antique hardware at it and it will (somehow) work with it.

So way to go.

[xeros]

R300? Isn't that, you know, laughable?

And I'm still using my two R3xx cards! and I'll still use them for few years more.

[pingufunkybeat]

1) Many people are quite upset that r500-class hardware is not supported by Catalyst anymore, and they are complaining about the support. So yeah, they are worried about performance, and are very vocal about it.

2) r600+ already have decent GLSL

3) People hack on the things they want to hack. This is mostly free software developers nowadays, and a Google student in this case. It's quite possible that this particular guy can make a decent job of the GLSL stuff for r300, but couldn't do Evergreen EXA support or hack OpenGL 3+ features into Mesa, or something else.

But yeah, I'm also happy about all the improvements for newer hardware.

[Melcar]

I am. I can use all the performance I can get.

[droidhacker]

R300? Isn't that, you know, laughable?

I think it would be better to focus on the newer parts... how many people still actually have those parts and are worried about getting peak performance out of them?

[yoshi314]

R300? Isn't that, you know, laughable?

i don't know. i'm still using my r500 card, and it shares the 3d code with r300. so i appreciate any related mesa developments.

[RealNC]

R300? Isn't that, you know, laughable?

[aaaantoine]

Good news. But...

Tom Stellard is the student developer working on the R300 GLSL improvements, which should benefit many include with the ATI Gallium3D stack for this older hardware architecture. Tom wrote to the Mesa development list a few days back to the Mesa development list that he's published a branch of Mesa that now supports loop unrolling for R300 ASICs that don't natively support the unrolling of loops.

Were you in a hurry, Michael?