Hal Finkel 245b657ab6 BBVectorize: Better use of TTI->getShuffleCost ... When flipping the pair of subvectors that form a vector, if the vector length is 2, we can use the SK_Reverse shuffle kind to get more-accurate cost information. Also we can use the SK_ExtractSubvector shuffle kind to get accurate subvector extraction costs. The current cost model implementations don't yet seem complex enough for this to make a difference (thus, there are no test cases with this commit), but it should help in future. Depending on how the various targets optimize and combine shuffles in practice, we might be able to get more-accurate costs by combining the costs of multiple shuffle kinds. For example, the cost of flipping the subvector pairs could be modeled as two extractions and two subvector insertions. These changes, however, should probably be motivated by specific test cases. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@173621 91177308-0d34-0410-b5e6-96231b3b80d8		2013-01-27 20:07:01 +00:00
..
Hello
InstCombine	Use the AttributeSet instead of AttributeWithIndex.	2013-01-27 02:08:22 +00:00
Instrumentation	[msan] A comment on ICmp handling logic.	2013-01-25 15:35:29 +00:00
IPO	Use the AttributeSet instead of AttributeWithIndex.	2013-01-27 01:57:28 +00:00
Scalar	Renamed function IsPotentialUse to IsPotentialRetainableObjPtr.	2013-01-27 06:19:48 +00:00
Utils	Re-revert r173342, without losing the compile time improvements, flat	2013-01-27 06:42:03 +00:00
Vectorize	BBVectorize: Better use of TTI->getShuffleCost	2013-01-27 20:07:01 +00:00
CMakeLists.txt
LLVMBuild.txt
Makefile