JinwoongKim / Massively-Parallel-Query-Processing-on-Heterogeneous-Architecture

Homepage
http://jinwoongkim.github.io/Massively-Parallel-Query-Processing-on-Heterogeneous-Architecture/
1 stars 2 forks source link

Use smart pointers with cudaMemcpy #35

Open JinwoongKim opened 8 years ago

JinwoongKim commented 8 years ago

When we call cudaMemcpy with smart pointers, it incurs compile errors

tree.cpp(101):   ERROR : no suitable conversion function from "std::shared_ptr<ursus::node::Node>" to "const void *" exists

Need to find solutions ...

JinwoongKim commented 8 years ago

Moohyeon said get function in shared_ptr returns raw pointer so that I can pass it to cudaMemcpy

Try it out someday.