Hi Robert,
My understanding of the way bindness graphics actually achieves its speedup is
by not requiring CPU dereferencing of graphic object pointers and the likely L2
cache misses this causes.
nVidia states:
OpenGL has evolved in a way that allows applications to replace many of the
original state machine variables with blocks of user-defined data. For example,
the current vertex state has been augmented by vertex buffer objects,
fixed-function shading state and parameters have been replaced by
shaders/programs and constant buffers, etc.. Applications switch between coarse
sets of state by binding objects to the context or to other container objects
(e.g. vertex array objects) instead of manipulating state variables of the
context. In terms of the number of GL commands required to draw an object, this
enables applications to be an order of magnitude more efficient. However, this
explosion of objects bound to other objects has led to a new bottleneck -
pointer chasing and CPU L2 cache misses in the driver, and general L2 cache
pollution.
Recent OpenGL graphics applications tend to change state at roughly these
frequencies:
for (...) { // cold
data downloads, render target changes, etc.
for (...) { // warm
bind textures
for (...) { // hot
bind constants
bind vertex buffers
Draw();
}
}
}
The most frequent state changes are binding vertex buffer objects (every draw),
followed closely by binding constant buffers. Vertex buffer and constant buffer
binds are significantly more expensive than one might expect. These binds
require several reads from the driver internal object data structure to
accomplish what the driver actually needs to do. In an OpenGL driver, it looks
like this:
name->obj (lookup object by name)
obj->{refcount, GPU address, state, etc.} (dereference object to reference
count it, to get its GPU virtual address, and validate its state).
Each of these dereferences has a high probability of causing a CPU L2 cache
miss due to the inherently LRU-eviction-unfriendly nature of graphics
applications (each frame starts over at the beginning). These L2 cache misses
are a huge bottleneck in modern drivers, and a penalty paid for every frame
rendered.
End nVidia states.
I think these extensions address new bottlenecks created by the switch to gl3
style vertex and constant buffers, shaders for everything, etc. It seems to be
a graphic driver bottleneck, not a scenegraph problem. But what nVidia is doing
is admitting the problem and is trying to provide OpenGL users a way to take
advantage of an optimization technique.
The OpenGL extensions are GL_NV_shader_buffer_load and
GL_NV_vertex_buffer_unified_memory.
I am not competent enough with gl3 yet to begin to implement these in code, but
it seems it may be worth doing that at some point. I like to add quality in
things I pursue. As I progress, I will keep in touch. For now I am a toddler.
Thank you!
Cheers,
John
------------------
Read this topic online here:
http://forum.openscenegraph.org/viewtopic.php?p=20462#20462
_______________________________________________
osg-users mailing list
osg-users@lists.openscenegraph.org
http://lists.openscenegraph.org/listinfo.cgi/osg-users-openscenegraph.org
