I am using Thrust library for solving a problem. The problem that I am facing on using that library is that when I allocate memory using device_vector then thrust automatically manages the memory. Now I have an array allocated by cudaMalloc and I want to populate it using the device_vector created before parallely. So I will write a kernel for doing so but what will be the data type for the vector created by thrust.
Asked
Active
Viewed 84 times
0
-
1Confirmed exact duplicate, please vote to close. – harrism Oct 24 '12 at 04:47
-
If the other question and answers worked for you, please consider voting them up. It will make them more prominent on SO and others will be able to find them more easily in the future – talonmies Oct 24 '12 at 07:18