Nadav Rotem c42f90b1f4 LoopVectorizer: Implement a new heuristics for selecting the unroll factor. ...

We ignore the cpu frontend and focus on pipeline utilization. We do this because we
don't have a good way to estimate the loop body size at the IR level.

llvm-svn: 172964

2013-01-20 05:24:29 +00:00

..

avx1.ll

ARM Cost model: Use the size of vector registers and widest vectorizable instruction to determine the max vectorization factor.

2013-01-09 22:29:00 +00:00

conversion-cost.ll

ARM Cost model: Use the size of vector registers and widest vectorizable instruction to determine the max vectorization factor.

2013-01-09 22:29:00 +00:00

cost-model.ll

Loop Vectorizer: Update the cost model of scatter/gather operations and make

2012-12-23 07:23:55 +00:00

gcc-examples.ll

Remove the -licm pass from the loop vectorizer test because the loop vectorizer does it now.

2013-01-09 01:20:59 +00:00

lit.local.cfg

…

no-vector.ll

Make TargetLowering::getTypeConversion more resilient against odd illegal MVTs.

2012-12-19 14:34:28 +00:00

small-size.ll

Move test that depends on the x86 target into a target-specific directory.

2013-01-16 13:25:56 +00:00

struct-store.ll

Fix typo "Makre" -> "Make".

2012-12-24 19:55:47 +00:00

unroll_selection.ll

LoopVectorizer: Implement a new heuristics for selecting the unroll factor.

2013-01-20 05:24:29 +00:00

unroll-small-loops.ll

Change the cpu type in the test.

2013-01-20 05:20:56 +00:00