search

allendaicool / thrust

Automatically exported from code.google.com/p/thrust
Apache License 2.0
0 stars 0 forks source link

built-in CUDA vector types should work with device_vector pure c++ subset #68

Closed GoogleCodeExporter closed 9 years ago

GoogleCodeExporter commented 9 years ago 
If we can correctly recognize the built-in CUDA vector types are POD, then a 
subset of device_vector's functionality should work in pure c++ mode.

To do this, we should implement is_pod with compiler intrinsics to avoid 
polluting the global namespace with the names of the CUDA vector types 
(rather than specializing is_pod).

Original issue reported on code.google.com by jaredhoberock on 7 Jan 2010 at 2:10

GoogleCodeExporter commented 9 years ago 
Thrust r709 implements is_pod using a compiler intrinsic if the compiler is 
recognized.

Original comment by jaredhoberock on 11 Jan 2010 at 7:46

GoogleCodeExporter commented 9 years ago 
Fixed by r709.

Original comment by jaredhoberock on 11 Jan 2010 at 7:04