Chandler Carruth 7024c7e949 [x86] Teach the new shuffle lowering's blend functionality to use AVX2's ... VPBLENDD where appropriate even on 128-bit vectors. According to Agner's tables, this instruction is significantly higher throughput (can execute on any port) on Haswell chips so we should aggressively try to form it when available. Sadly, this loses our delightful shuffle comments. I'll add those back for VPBLENDD next. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218322 91177308-0d34-0410-b5e6-96231b3b80d8		2014-09-23 18:16:12 +00:00
..
Analysis	AVX-512: added cost for some AVX-512 instructions	2014-09-16 07:57:37 +00:00
Assembler
Bindings
Bitcode	Ensure bitcode encoding stays stable.	2014-09-23 08:48:01 +00:00
BugPoint
CodeGen	[x86] Teach the new shuffle lowering's blend functionality to use AVX2's	2014-09-23 18:16:12 +00:00
DebugInfo	Fix segfault in AArch64 backend with -g and -mbig-endian	2014-09-23 15:38:11 +00:00
ExecutionEngine
Feature
FileCheck
Instrumentation
Integer
JitListener
Linker
LTO	Try to fix i686-cygming bots.	2014-09-18 22:56:00 +00:00
MC	MC: ReadOnlyWithRel section kinds should map to rdata in COFF	2014-09-22 20:39:23 +00:00
Object
Other
TableGen	[TableGen] Fully resolve class-instance values before defs in multiclasses	2014-09-16 17:14:13 +00:00
tools	Rebuild the inputs for the codeview-linetables.test with VS2013	2014-09-23 13:49:51 +00:00
Transforms	[IndVarSimplify] Partially revert r217953 to see if this fixes the bots.	2014-09-17 16:35:09 +00:00
Unit
Verifier
YAMLParser
.clang-format
CMakeLists.txt
lit.cfg	Exclude known and bugzilled failures from UBSan bootstrap	2014-09-17 20:17:52 +00:00
lit.site.cfg.in
Makefile
Makefile.tests
TestRunner.sh