Sanjay Patel be9ee96926 [X86, AVX] instcombine common cases of vperm2* intrinsics into shuffles ... vperm2* intrinsics are just shuffles. In a few special cases, they're not even shuffles. Optimizing intrinsics in InstCombine is better than handling this in the front-end for at least two reasons: 1. Optimizing custom-written SSE intrinsic code at -O0 makes vector coders really angry (and so I have regrets about some patches from last week). 2. Doing mask conversion logic in header files is hard to write and subsequently read. There are a couple of TODOs in this patch to complete this optimization. Differential Revision: http://reviews.llvm.org/D8486 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@232852 91177308-0d34-0410-b5e6-96231b3b80d8		2015-03-20 21:47:56 +00:00
..
Hello	[CMake] Add LLVM_LINK_COMPONENTS to loadable modules, LLVMHello and BugpointPasses, on Win32.	2014-07-13 13:36:48 +00:00
InstCombine	[X86, AVX] instcombine common cases of vperm2* intrinsics into shuffles	2015-03-20 21:47:56 +00:00
Instrumentation	SanitizerCoverage: Check for null DebugLocs	2015-03-20 18:48:45 +00:00
IPO	Verifier: Remove the separate -verify-di pass	2015-03-19 22:24:17 +00:00
ObjCARC	One more try with unused.	2015-03-16 08:00:27 +00:00
Scalar	SampleProfile: Check for missing debug locations	2015-03-20 00:56:55 +00:00
Utils	Fixing a bug with WinEH PHI handling	2015-03-20 21:42:54 +00:00
Vectorize	Try to fix a test broken by one of my previous commits.	2015-03-17 20:31:56 +00:00
CMakeLists.txt
LLVMBuild.txt
Makefile