[Date Prev][Date Next][Thread Prev][Thread Next]
- Subject: Re: OpenCL
- From: askok@...
- Date: Wed, 10 Dec 2008 10:01:00 +0200
About the capabilities of OpenCL, we simply need to know
The best I've seen is the slides here:
About the iteration, yes, basically as you wrote. Except
it will be better to just give the iteration loop contents
so that the framework can utilize parallelism.
run_on_cuda( matrix, function(x,y)
-- some big fat (or slim) equation in pure Lua for
dealing with (x,y)
Please don't shoot the idea down; I will need to test this
once I get a Cuda capable machine. Even if you shoot it
down, I'll still do it! ;D
On Tue, 9 Dec 2008 23:54:21 -0800
"Wesley Smith" <email@example.com> wrote:
One scenario is meteorological data analysis, where
are run for huge data matrices. In this case, we would
be able to define the
operations as Lua codelets, and run them parallel on the
data. I guess only
Lua of the current scripting languages (and Forth) would
be small enough to
effectively fit in on the CUDA/OpenCL. Even there, some
limitations s.a. no
recursive calls may be too much. But we'll see.
Are you suggesting running Lua instructions in OpenCL?
-- begin codelet
for i=1, 10000 do
for j=1, 10000 do
-- some big fat equation in pure lua that runs in
-- end codelet
What about making some form of OpenCL flavored shader as
in GLSL or Cg
shaders? Basically some C codelet that is dynamically
run in OpenCL. I haven't read the docs in a while, but
from what I
remember from a presentation this summer, code can be
compiled and executed.