Owen Anderson b0ba0f4170 LoadPRE was not properly checking that the load it was PRE'ing post-dominated the block it was being hoisted to. ... Splitting critical edges at the merge point only addressed part of the issue; it is also possible for non-post-domination to occur when the path from the load to the merge has branches in it. Unfortunately, full anticipation analysis is time-consuming, so for now approximate it. This is strictly more conservative than real anticipation, so we will miss some cases that real PRE would allow, but we also no longer insert loads into paths where they didn't exist before. :-) This is a very slight net positive on SPEC for me (0.5% on average). Most of the benchmarks are largely unaffected, but when it pays off it pays off decently: 181.mcf improves by 4.5% on my machine. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@114785 91177308-0d34-0410-b5e6-96231b3b80d8		2010-09-25 05:26:18 +00:00
..
Analysis	PR7959: Handle negative scales in GEPs correctly in BasicAA for non-64-bit	2010-09-15 20:08:03 +00:00
Archive
Assembler	Basic smoke test for new x86mmx type.	2010-09-13 21:01:36 +00:00
Bindings/Ocaml	tests: XFAIL a handful of tests on the vg_leak builder, so we can get back to	2010-09-09 15:50:19 +00:00
Bitcode	Auto-upgrade the magic ".llvm.eh.catch.all.value" global to	2010-09-10 18:51:56 +00:00
BugPoint
CodeGen	Enable code placement optimization pass for ARM.	2010-09-24 19:07:23 +00:00
DebugInfo	If FE forgot to provide a file name (usually it uses "stdin" as name in such situation) then make one up to ensure that debug info is not malformed.	2010-09-16 20:57:49 +00:00
ExecutionEngine
Feature
FrontendAda
FrontendC	Get rid of the last use of -m64 in FrontendC. This solution	2010-09-09 12:57:29 +00:00
FrontendC++
FrontendFortran
FrontendObjC
FrontendObjC++
Integer
lib
Linker
LLVMC	llvmc: Support '-emit-llvm -S' with -opt.	2010-09-22 09:00:41 +00:00
MC	Reapply 114678 and 114667. Reverting them did not fix the bot:	2010-09-24 21:19:03 +00:00
Other	Fix llvm-extract so that it changes the linkage of all GlobalValues to	2010-09-23 17:25:06 +00:00
Scripts	test: Fix coff-dump section array indicies to 1 based to match file format.	2010-09-15 03:58:51 +00:00
TableGen	tests: XFAIL a handful of tests on the vg_leak builder, so we can get back to	2010-09-09 15:50:19 +00:00
Transforms	LoadPRE was not properly checking that the load it was PRE'ing post-dominated the block it was being hoisted to.	2010-09-25 05:26:18 +00:00
Unit
Verifier
CMakeLists.txt	CMake: Build unittests.	2010-09-24 09:01:13 +00:00
lit.cfg	Spelling fixes in comments.	2010-09-13 13:32:22 +00:00
lit.site.cfg.in
Makefile
Makefile.tests
site.exp.in
TestRunner.sh