Can I use thrust::host_vector or I must use cudaHostAlloc for zero-copy with Thrust?

Created Jul 27, 2012 Edited Jul 27, 2012

Viewed 1388

I want to use zero-copy on mapped memory by cudaHostGetDevicePointer. Can I use thrust::host_vector or I must use cudaHostAlloc(...,cudaHostAllocMapped)? Or is it somehow easier to do with Thrust?

thrust zero-copy cuda gpu

Can I use thrust::host_vector or I must use cudaHostAlloc for zero-copy with Thrust?

1 Answers