Yi Jiang 89008539a3 In this patch we are trying to do two things: ... 1) If the width of vectorization list candidate is bigger than vector reg width, we will break it down to fit the vector reg. 2) We do not vectorize the width which is not power of two. The performance result shows it will help some spec benchmarks. mesa improved 6.97% and ammp improved 1.54%. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189830 91177308-0d34-0410-b5e6-96231b3b80d8		2013-09-03 17:26:04 +00:00
..
Analysis
Assembler	Debug Info: add an identifier field to DICompositeType.	2013-08-26 22:39:55 +00:00
Bindings/Ocaml
Bitcode	Add function attribute 'optnone'.	2013-08-23 11:53:55 +00:00
BugPoint
CodeGen	[SystemZ] Add support for TMHH, TMHL, TMLH and TMLL	2013-09-03 15:38:35 +00:00
DebugInfo
ExecutionEngine	llvm interpreter: select, shuffle and insertelement instructions.	2013-09-02 06:40:09 +00:00
Feature
FileCheck
Instrumentation	[msan] Fix handling of select with struct arguments.	2013-09-03 13:05:29 +00:00
Integer	[tests] Cleanup initialization of test suffixes.	2013-08-16 00:37:11 +00:00
JitListener
Linker
MC	Fixed a bug where diassembling an instruction that had a prefix would cause LLVM to identify a 1-byte instruction, but then upon querying it for that 1-byte instruction would cause an undefined opcode.	2013-08-30 21:19:48 +00:00
Object
Other
TableGen
tools	Print string value for DT_RPATH and DT_RUNPATH.	2013-09-03 17:13:53 +00:00
Transforms	In this patch we are trying to do two things:	2013-09-03 17:26:04 +00:00
Unit
Verifier
YAMLParser
CMakeLists.txt
lit.cfg	Restore llvm-ranlib expansion in RUN-lines removed in r184019	2013-08-30 12:53:22 +00:00
lit.site.cfg.in
Makefile
Makefile.tests
TestRunner.sh