Nadav Rotem 06ab05f47a CostModel: increase the default cost of supported floating point operations from 1 to two. Fixed a few tests that changes because now the cost of one insert + a vector operation on two doubles is lower than two scalar operations on doubles. ...

llvm-svn: 179413

2013-04-12 21:15:03 +00:00

..

cmp-types.ll

BBVectorize: Check the types of compare instructions

2012-11-12 19:41:38 +00:00

loop1.ll

CostModel: increase the default cost of supported floating point operations from 1 to two. Fixed a few tests that changes because now the cost of one insert + a vector operation on two doubles is lower than two scalar operations on doubles.

2013-04-12 21:15:03 +00:00

pr15289.ll

BBVectorize: Fix an invalid reference bug

2013-02-17 15:59:26 +00:00

sh-rec2.ll

BBVectorize: Only some insert element operand pairs are free.

2012-11-12 23:55:36 +00:00

sh-rec3.ll

BBVectorize: Don't vectorize vector-manipulation chains

2012-11-13 03:12:40 +00:00

sh-rec.ll

BBVectorize: Use a more sophisticated check for input cost

2012-11-12 21:21:02 +00:00

sh-types.ll

BBVectorize: Check the input types of shuffles for legality

2012-11-12 14:50:59 +00:00

simple-int.ll

BBVectorize: Use VTTI to compute costs for intrinsics vectorization

2012-12-26 01:36:57 +00:00

simple-ldstr.ll

BBVectorize: Use target costs for incoming and outgoing values instead of the depth heuristic.

2012-11-01 21:50:12 +00:00

simple.ll

CostModel: increase the default cost of supported floating point operations from 1 to two. Fixed a few tests that changes because now the cost of one insert + a vector operation on two doubles is lower than two scalar operations on doubles.

2013-04-12 21:15:03 +00:00

vs-cast.ll

…