Jakob Stoklund Olesen 4c1c395789 Tweak hash function and compress hash tables. ... Make the hash tables as small as possible while ensuring that all lookups can be done in less than 8 probes. Cut the aliases hash table in half by only storing a < b pairs - it is a symmetric relation. Use larger multipliers on the initial hash function to ensure that it properly covers the whole table, and to resolve some clustering in the very regular ARM register bank. This reduces the size of most of these tables by 4x - 8x. For instance, the ARM tables shrink from 48 KB to 8 KB. llvm-svn: 132888		2011-06-12 07:04:32 +00:00
..
bugpoint
buildit
count
crosstool
emacs
FileCheck
FileUpdate
fpcmp
git
jedit
kate
KillTheDoctor
lint
lit
llvm-lit
Misc
not
PerfectShuffle	In r131488 I misunderstood how VREV works. It splits the vector in half and splits each half. Therefore, the real problem was that we were using a VREV64 for a 4xi16, when we should have been using a VREV32.	2011-05-18 06:42:21 +00:00
release
TableGen	Tweak hash function and compress hash tables.	2011-06-12 07:04:32 +00:00
Target/ARM
unittest
valgrind
vim
cgiplotNLT.pl
check-each-file
codegen-diff
countloc.sh
DSAclean.py
DSAextract.py
findmisopt
findoptdiff
findsym.pl
GenLibDeps.pl
GetRepositoryPath
GetSourceVersion
getsrcs.sh
importNLT.pl
llvm-native-gcc
llvm-native-gxx
llvm.grm
llvmbuild
llvmdo
llvmgrep
Makefile
makellvm
NewNightlyTest.pl
NightlyTest.gnuplot
NightlyTestTemplate.html
NLT.schema
parseNLT.pl
plotNLT.pl
profile.pl
show-diagnostics
test_debuginfo.pl
UpdateCMakeLists.pl
webNLT.pl