Recent content by warmi

  1. W

    Gles Driver Bug

    They still do ... fixed point is most likely implemented using shaders and from what it looks like they have uvs on mediump.
  2. W

    Reverse Engineering Powervr Is Now A High Priority

    From what I hear, ImgTech folks have reference drivers but generally it is up to licensee to integrate/rewrite them to suit their platform of choice ( TI in this case) For instance, Apple folks are already on their , I think 5th or 6th, major driver version - it took them almost 2 years to get...
  3. W

    Reverse Engineering Powervr Is Now A High Priority

    Just the opposite. When it comes out (2-3 SGX generations from now) out it will slower and more buggy ...
  4. W

    Depressing

    You must be living in some other reality cause the way I see it , the whole thing shapes up to be an absolute disaster and frankly, being an outsider ( who actually ordered Pandora 2 years ago and kind of forgot about it ), spaceballs appears to be the voice of reason here, not the other way around.
  5. W

    Psuedogl

    If you target your code for OpenGL and GLES then that's a good idea .. on the other hand if you are using your desktop machine purely as a "GLES emulator" then using a wrapper library ( like the one from Imagination Technologies) is much more convenient ( they directly support a lot of...
  6. W

    Psuedogl

    No, it is not. You just download an emulator library running on top of Open GL and you are basically done.
  7. W

    Gles2.0 Shaders Are Slow?

    From what I have heard on the iPhone (SGX based iPhones to be precise) GLES 1.x is emulated with shaders but not your vanilla GLSL shaders but something more native ( perhaps optimized native asm code ). In fact, someone from Imagination Technologies even suggested that trying to write your own...
  8. W

    Gles2.0 Shaders Are Slow?

    Fixed pipelines on SGX devices are implemented using ... shaders so I doubt you will get much better results.
  9. W

    Fairly Decent Results With Bullet Physics

    SGX natively is using tri-strips... in fact,as far as I know, everything you submit is converted by the driver into tri-strips. Of course, you are right, some models using tri-strips will result in a lot of batches or tons of degenerated tris... personally, I use tri-lists sorted into a...
  10. W

    Gles2.0 Shaders Are Slow?

    Don't expect miracles ... in terms of shader processing SGX 530 can be about 1000 times slower than a decent PC based graphic card. Not in this case, but I see it all the time, people pick up shaders from some PC based book , dump it on SGX and expect miracles.
  11. W

    Panmmo

    Pretty much ... the "a bit more slowly" part is a bit misleading though ... if you were to take a decent Nvidia card and run it at 800x480 it would probably run about 100x faster in terms of basic fillrate/vertex throughput so you gonna have to cheat ...
  12. W

    Pandora What Are The 3D Limitations Of The Pandora?

    Nah, these wer just fake numbers ... essentially vertex counts calculated out of triangle counts ( admittedly useless data and I got rid of that since then)
  13. W

    Pandora What Are The 3D Limitations Of The Pandora?

    Assuming no fancy shaders (and a reasonable backend implementation , meaning decent batch counts etc ), you could count on being able to display around 50-60K polys at around 30 fps - of course that's a very rough estimate ... there are many other things in play. PS. With a very basic shader...
  14. W

    Performance Of The Sgx 530?

    No alpha-test just alpha-blend and there is a quad underneath . Everything is sorted based on a custom mask which in this case sorts based on blend states/texture changes and some other stuff. The models themselves are using indexed triangle lists exported with my own exporter (POD) from...
  15. W

    Performance Of The Sgx 530?

    This test was ran in GLES 1.x mode using their internal shaders which presumably are reasonably optimized but that's beside the point .... I suspect the issue here is not how many triangles you can render but how many vertices you can submit for rendering - this was the bottleneck with the...
Back
Top