Sanjay Patel 81b61c0e50 [X86, SSE] instcombine common cases of insertps intrinsics into shuffles ... This is very similar to D8486 / r232852 (vperm2). If we treat insertps intrinsics as shufflevectors, we can optimize them better. I've left all but the full zero case of the zero mask variants out of this patch. I don't think those can be converted into a single shuffle in all cases, but I'd be happy to be proven wrong as I was for vperm2f128. Either way, we'd need to support whatever sequence we come up with for those cases in the backend before converting them here. Differential Revision: http://reviews.llvm.org/D8833 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@235124 91177308-0d34-0410-b5e6-96231b3b80d8		2015-04-16 17:52:13 +00:00
..
Hello
InstCombine	[X86, SSE] instcombine common cases of insertps intrinsics into shuffles	2015-04-16 17:52:13 +00:00
Instrumentation	DebugInfo: Gut DICompileUnit and DIFile	2015-04-15 23:19:27 +00:00
IPO	DebugInfo: Gut DICompileUnit and DIFile	2015-04-15 23:19:27 +00:00
ObjCARC
Scalar	DebugInfo: Require a DebugLoc in DIBuilder::insertDeclare()	2015-04-15 21:18:07 +00:00
Utils	Silencing a -Wunused-but-set-variable warning; NFC.	2015-04-16 13:29:36 +00:00
Vectorize
CMakeLists.txt
LLVMBuild.txt
Makefile