Questions tagged [prefix-sum]
63 questions
-1
votes
2 answers
CUDA Paralell prefix sum error
I'm trying to implement a three phase parallel scan as described in chapter 8 of Programming Massively Parallel Processors 3rd edition (there are any line of code but only instructions).
This algorithm allow to use only 1 block with the maximum…
sgiraz
- 141
- 2
- 11
-1
votes
1 answer
maximum supported size for cub library
Does anyone know what is the maximum supported size for cub::scan ? I got core dump for input sizes over 500 million. I wanted to make sure I'm not doing anything wrong...
Here is my code:
#define CUB_STDERR
#include
#include…
JacobS
- 11
- 3
-2
votes
1 answer
Multiple pointer accesses cause failure of printf in CUDA
I'm currently trying to implement the Blelloch Algorithm in CUDA. I want to use printf for debugging but it has this weird behaviour that it won't work when I'm accessing different positions of the same array in a Kernel. cudaDeviceSynchronize() is…
StrangeMortim
- 1
- 3