*using sbo on non compute shaders (like fragment shaders seems no be not correct) Seems to compile so please fix to be able to use not only 32767 bytes of shared mem but full 32768 bytes. I verify this issue is on shared mem size usage as using something like Size (GL_MAX_COMPUTE_SHARED_MEMORY_SIZE: 32768). Isn't a issue so 32 should work as for this conf each of this two shared arrays is size 8192 (sizeof(double)*32*32) so total shared mem usage is 2*8192 and is equal to reported max Layout (local_size_x = 32, local_size_y = 32) in Layout (local_size_x = BLOCK_SIZE, local_size_y = BLOCK_SIZE) in ĭiminishing BLOCK_SIZE to less than 32 seems to work. *using a compute shader with following launch size and shared arrays usage: *using atomicMax and atomicMin on shared variables hang the GLSL compiler others like atomicOr are OK! (please note all the samples I use for testing this work correctly on Nvidia OGL 4.3 cards) I have been testing new OGL compute shader and storage buffer objects extension and found following bugs (13.4 on 7950):
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |