projects
/
oota-llvm.git
/ history
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
first ⋅ prev ⋅ next
X86: Promote i8 cmov when both operands are coming from truncates of the same width.
[oota-llvm.git]
/
test
/
CodeGen
/
X86
/
sse41-blend.ll
2012-06-04
Nadav Rotem
Remove the "-promote-elements" flag. This flag is now...
blob
|
commitdiff
|
raw
2012-04-15
Nadav Rotem
When emulating vselect using OR/AND/XOR make sure to...
blob
|
commitdiff
|
raw
|
diff to current
2012-01-03
Nadav Rotem
Revert 147426 because it caused pr11696.
blob
|
commitdiff
|
raw
|
diff to current
2012-01-02
Nadav Rotem
Optimize the sequence blend(sign_extend(x)) to blend...
blob
|
commitdiff
|
raw
|
diff to current
2011-09-17
Duncan Sands
Synthesize x86 max/min instructions also for vectors...
blob
|
commitdiff
|
raw
|
diff to current
2011-09-14
Nadav Rotem
Add integer promotion support for vselect
blob
|
commitdiff
|
raw
|
diff to current
2011-09-12
Bruno Cardoso Lopes
Change testcase commandline to be more strict and silen...
blob
|
commitdiff
|
raw
|
diff to current
2011-09-12
Bruno Cardoso Lopes
Revert the wrong part of r139528, and fix testcases.
blob
|
commitdiff
|
raw
|
diff to current
2011-09-12
Bruno Cardoso Lopes
Not sure how CMPPS and CMPPD had already ever worked...
blob
|
commitdiff
|
raw
|
diff to current
2011-09-08
Bruno Cardoso Lopes
Add AVX versions of blend vector operations and fix...
blob
|
commitdiff
|
raw
|
diff to current