Nate Begeman 95743d8748 Add the minimal amount of smarts necessary to instcombine of shufflevectors to recognize ... patterns generated by clang for transpose of a matrix in generic vectors. This is made of two parts: 1) Propagating vector extracts of hi/lo half into their users 2) Recognizing an insertion of even elements followed by the odd elements as an unpack. Testcase to come, but this shrinks the # of shuffle instructions generated on x86 from ~40 to the minimal 8. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110734 91177308-0d34-0410-b5e6-96231b3b80d8		2010-08-10 21:38:12 +00:00
..
Hello	Reapply r110396, with fixes to appease the Linux buildbot gods.	2010-08-06 18:33:48 +00:00
InstCombine	Add the minimal amount of smarts necessary to instcombine of shufflevectors to recognize	2010-08-10 21:38:12 +00:00
Instrumentation	Reapply r110396, with fixes to appease the Linux buildbot gods.	2010-08-06 18:33:48 +00:00
IPO	Fix a use after free error caught by the valgrind builders.	2010-08-09 21:03:28 +00:00
Scalar	Don't attempt the PRE inline asm calls, since we don't value number them yet. Fixes PR7835.	2010-08-07 00:20:35 +00:00
Utils	Eliminate PromoteMemoryToRegisterID; just use addPreserved("mem2reg")	2010-08-06 21:48:06 +00:00
Makefile	Revert r100896 and around - this breaks the only mingw32 buildbot we have.	2010-04-15 19:51:42 +00:00