cancel
Showing results for 
Search instead for 
Did you mean: 

OpenCL

nou
Exemplar

SDK 2.6 issues/questions

enabling extension in kernel with #pragma is only for extension which affects OpenCL C language.

0 Likes
Reply
Meteorhead
Challenger

SDK 2.6 issues/questions

I am also very much interested in getting multi-GPU working. If single-context + multi-GPU would work, that would really simplify things.

I know it's holidays, but is it only in Hungary where people are working between the holidays? Is everyone at AMD out of office? The questions are not that many, and not that complicated.

0 Likes
Reply
NURBS
Journeyman III

SDK 2.6 issues/questions

In the US, don't expect software guys working this week

 

0 Likes
Reply
antzrhere
Adept III

SDK 2.6 issues/questions

@nou

AFAIK The #pragma prefix is required for any and all OpenCL extensions and is certainly required for CL_KHR_gl_sharing - take a look: http://www.khronos.org/registry/cl/sdk/1.0/docs/man/xhtml/gl_sharing.html

0 Likes
Reply
Meteorhead
Challenger

SDK 2.6 issues/questions

Then how come it works without it? Even the AMD SimpleGL example don't use it.

0 Likes
Reply
thejinx0r
Journeyman III

SDK 2.6 issues/questions

Is there a place to submit bugs other than the forum?

I believe that the vload3 is not implemented properly. So from the documentation, is has a prototype of (datatype *) vload3( offset, ptr) and should read from ptr starting from offset * 3.

But, it seems like it's reading from offset*4. Is there something that I am missing?

0 Likes
Reply
antzrhere
Adept III

SDK 2.6 issues/questions

As I know it, 3 component vectors are the same size as four component vectors (the w component is hidden), and as such their offset it calculated the same (sizeof should also report the same size).

I guess they were introduced as they can permit the hidden component to be safely ignored during any arithmetic operations common in 3D calculations.

0 Likes
Reply
antzrhere
Adept III

SDK 2.6 issues/questions

Regarding the CL_KHR_gl_sharing extension, I realise that AMDs samples dont enable this extension, exactly similar to mine. That's because it doesn't work. Just because it doesn't need to be enabled, doesn't mean that it should throw an error when you try and enable it!

What if I want to write something that's portable, how do I know that if I don't enable it some other SDK won't report an error? AMD lists gl sharing as one of the supported extensions, so it should atleast accept it even if it does nothing about it.

Secondly, has anyone tried the new KernelAnalyzer? It reports the same statistics no matter what Function you select.

0 Likes
Reply
thejinx0r
Journeyman III

SDK 2.6 issues/questions

Originally posted by: antzrhere As I know it, 3 component vectors are the same size as four component vectors (the w component is hidden), and as such their offset it calculated the same (sizeof should also report the same size).

 

I guess they were introduced as they can permit the hidden component to be safely ignored during any arithmetic operations common in 3D calculations.

 

Sure. It's implemented as 4 compenent vector for alignment. But how it's implemented under the hood should be consistent in usage. From the reference:

Return sizeof (gentypen) bytes of data read from address (p + (offset * n)).


In vload3 and and similarly in vstore3, it should at least read from  (p+(offset*3)) and not (p+offset*4).

----------

Another question:

Why isn't there a "shuffle" for doubles?

When I try to shuffle doubles around, I get:

  no instance of overloaded function "shuffle"


Will it be implemented in the future?

0 Likes
Reply
MicahVillmow
Staff
Staff

SDK 2.6 issues/questions

antzhere,
It is because the extension is not a compiler extension but a runtime extension.
0 Likes
Reply