search

lion03 / thrust

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

eliminate device:: implementations of extrema.h functions #197

Closed GoogleCodeExporter closed 8 years ago

GoogleCodeExporter commented 8 years ago 
Blocked by a CUDA 3.1 WAR:
http://code.google.com/p/thrust/source/browse/thrust/detail/device/generic/extre
ma.inl#41

Original issue reported on code.google.com by wnbell on 1 Sep 2010 at 5:30

GoogleCodeExporter commented 8 years ago

Original comment by wnbell on 21 Aug 2011 at 10:36

GoogleCodeExporter commented 8 years ago 
It occurred to me that implementing these algorithms immediately in terms of 
transform_reduce (as is done in the generic backend) would prevent the entry 
points from being intercepted in dispatch.  Also, the sequential implementation 
in system/detail/scalar is faster than the generic version for the case of 
non-random-access iterators, so there are valid reasons to keep things as-is.

Original comment by wnbell on 23 Jan 2012 at 11:01