Bruno Cardoso Lopes 6ad251358e The following X86 pattern is incorrect: ... def : Pat<(X86Movss VR128:$src1, (bc_v4i32 (v2i64 (load addr:$src2)))), (MOVLPSrm VR128:$src1, addr:$src2)>; This matches a MOVSS dag with a MOVLPS instruction. However, MOVSS will replace only the low 32 bits of the register, while the MOVLPS instruction will replace the low 64 bits. A testcase is added and illustrates the bug and also modified the one that was already present. Patch by Tanya Lattner. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137227 91177308-0d34-0410-b5e6-96231b3b80d8		2011-08-10 17:45:17 +00:00
..
Analysis	Cleanup. Added LoopBlocksDFS::perform for simple clients.	2011-08-10 01:59:05 +00:00
Archive	Rewrite the CMake build to use explicit dependencies between libraries,	2011-07-29 00:14:25 +00:00
AsmParser	Representation of 'atomic load' and 'atomic store' in IR.	2011-08-09 23:02:53 +00:00
Bitcode	Representation of 'atomic load' and 'atomic store' in IR.	2011-08-09 23:02:53 +00:00
CodeGen	Trim an unneeded header.	2011-08-09 23:49:21 +00:00
CompilerDriver	Build CompilerDriver library.	2011-03-12 22:01:42 +00:00
ExecutionEngine	Rewrite the CMake build to use explicit dependencies between libraries,	2011-07-29 00:14:25 +00:00
Linker	Linke NamedMDNodes after linking global values as comment suggests.	2011-08-04 19:44:28 +00:00
MC	Don't truncate MachO addresses.	2011-08-09 22:12:37 +00:00
Object	Rewrite the CMake build to use explicit dependencies between libraries,	2011-07-29 00:14:25 +00:00
Support	Clarify a comment.	2011-08-10 05:02:22 +00:00
Target	The following X86 pattern is incorrect:	2011-08-10 17:45:17 +00:00
Transforms	Invoke SimplifyIndVar when we partially unroll a loop. Fixes PR10534.	2011-08-10 04:29:49 +00:00
VMCore	Whitespace.	2011-08-10 17:39:11 +00:00
CMakeLists.txt	Build CompilerDriver library.	2011-03-12 22:01:42 +00:00
Makefile