Jump to content

  • Log In with Google      Sign In   
  • Create Account


sth

Member Since 23 Aug 2004
Offline Last Active Oct 13 2012 05:54 AM
-----

Posts I've Made

In Topic: High performance texture splatting?

19 June 2012 - 03:00 AM

The thing is that these days it's not just phone screens, it's also tablet screens and (wireless) TV output.

Well the thing really is, you don't have enough power currently on GLES. If you want 20 different types of splats, you could do that as well, just divide your terrain into sections and only allow 1 section 3 splats (rgb). Each section can have any 3 of the 20 splats.

I'll have to see. My current implementation already allows every chunk of the terrain to have its own set of textures, although it would be nicer not to be bound to the fixed chunk structure.

In Topic: High performance texture splatting?

18 June 2012 - 05:22 PM

If you throw out the vsync sample, your frame times are 40Hz/25ms for 2 samples, and 15Hz/66.6..ms for 5 samples. Divide the frame times by the number of samples and you get 12.5ms and 13.3..ms, which are pretty similar.
From that, it looks like you're just using more texture bandwidth than your GPU can cope with...

I think you're right, it looks pretty much bandwidth-limited right now.
Today I realized that I still had trilinear filtering enabled. Disabling it cut the frame times in half. I can't recall trilinear filtering ever having such a profound effect in any of my projects, but I guess that's just what happens when you're running at the limit.

Anyway, at least I'm now back to playable framerates.

Perhaps try avoiding the mix and optimize the code manually:

Thanks for the suggestion. I tried it but it didn't have any effect on the performance.

Also, Why not try just 3 splat channels instead of 4. 3 should be sufficient especially if it is for a small screen embedded device.

I'm considering it, but I'm still not sure if I really want it.
The thing is that these days it's not just phone screens, it's also tablet screens and (wireless) TV output.

In Topic: GL_RGB_SCALE and multipass rendering

23 March 2009 - 02:58 AM

Thanks but that would make the scene even darker. I need the opposite effect.

In Topic: GL_RGB_SCALE and multipass rendering

23 March 2009 - 12:41 AM

My target hardware doesn't support shaders - OpenGL ES 1.1 only ;-)

Believe me, I would be _very_ happy if I could just use shaders instead...

In Topic: Recommended High-Performance Workstation CPU (AMD - Intel) Present-2006

02 August 2006 - 11:38 AM

A state of the art workstation...

2 DualCore CPUs (Xeon or Operon)
4 Gigabytes of RAM
1 SCSI-RAID-Controller
4 Fast SCSI-Disks in a RAID10

The fastest CPUs for the job will probably be the new Intel Xeon lineup based on the Woodcrest core in combination with DDR2-1066 RAM. They were released just a few days ago.

Will it be expensive? Yes it will =) Will it be fast? Hell yeah!


But I would suggest:
Get a DualCore CPU that fits your budget, 2gb RAM and a reasonably fast Serial ATA disk. Best value for money and still waaaaay faster than you old Athlon.


Quote:
Original post by Toolmaker
And get yourself a sexy RAID 0 setup too. Raid 0 improves drive performance by 2(By making 2 disks become 1 disk, thus dual writing speeds).

Not true! Only for linear reads/writes. Random access can even get a bit slower when using RAID0!
But more important than that: Never use RAID0 for anything important! If one disk breaks, everything is lost.
I would suggest RAID1 (mirror) for a normal development machine. If you really need the performance, use RAID10. For mass-storage use RAID5 ;^)

PARTNERS