This patch changes the implementation of vector reductions. Currently we emit a
sequence of shuffle/op pairs. The size of the sequence depends on the vector size.
This changes the implementation to emit a loop, the number of iterations of
which depends on the vector size. the goal here is a
I've committed this reimplementation of the vector shuffling code. In preparing
a fix for the worker reductions (to use a lockless scheme), I wanted to check
VIEW_CONVERT_EXPR DTRT. Use of gimplify_assign also reduces the code size.
nathan
2015-09-23 Nathan Sidwell
* config/nvptx/nvptx.c
