Robert Crovella questions

Robert Crovella answers

• How to generalize fast matrix multiplication on GPU using numba
• Can anyone provide sample code demonstrating the use of 16 bit floating point in cuda?
• CUDA: __restrict__ tag usage
• CUDA/Thrust: How to sum the columns of an interleaved array?
• Thrust Gathering/Filtering
• How is stack frame managed within a thread in Cuda?
• CUDA C/C++: Calculate the average of inverse of distance per point (interaction energy, perhaps?)
• CUDA, is there an atomicRead?
• Can Thrust transform_reduce work with 2 arrays?
• Undefined reference to `cublasCreate_v2’ in ‘/tmp/tmpxft_0000120b_0000000-10_my_program”