On Fri, Dec 2, 2011 at 8:26 PM, Jakub Jelinek ja...@redhat.com wrote:
Hi!
As I found during investigation of PR51387, e.g. on the attached testcase
we generate pretty bad code (for f1 even with bigger N like 256 for avx2),
because after vectorization cunroll unrolls the loops completely and
Hi!
As I found during investigation of PR51387, e.g. on the attached testcase
we generate pretty bad code (for f1 even with bigger N like 256 for avx2),
because after vectorization cunroll unrolls the loops completely and we
end up with lots of VEC_PACK_TRUNC_EXPR etc. expressions with VECTOR_CST