multithread add operation in kernel 'renderCUDA_count'

VITA-Group / LightGaussian

"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang

https://lightgaussian.github.io/

Other

506 stars 41 forks source link

multithread add operation in kernel 'renderCUDA_count' #24

Open humphryey131 opened 3 months ago

humphryey131 commented 3 months ago

Hi guys, I am wondering if the following accumulation in renderCUDA_count kernel shall use atomic operation : As far as I know, the collected_id[j] in different parallel threads may run into idential value. Thanks.

linwk20 commented 2 months ago

I also found this problem, did you try atomicAdd(&gaussian_count[collected_id[j]], 1);? Will it be very slow?