]> granicus.if.org Git - llvm/commit
projects / llvm / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: e8b19ac) | patch
Allow vector fsub ops with constants to get the same optimizations as scalars.
authorSanjay Patel <spatel@rotateright.com>
Fri, 5 Sep 2014 22:26:22 +0000 (22:26 +0000)
committerSanjay Patel <spatel@rotateright.com>
Fri, 5 Sep 2014 22:26:22 +0000 (22:26 +0000)
commit52af82df95e656434b89638bbd095cd4252b880e
tree6c4b5af0aa001032c038768a526d26fd9cf48ad0tree | snapshot
parente8b19acded1d944918a35c6196d8336916dde735commit | diff
Allow vector fsub ops with constants to get the same optimizations as scalars.

This problem is bigger than just fsub, but this is the minimum fix to solve
fneg for PR20556 ( http://llvm.org/bugs/show_bug.cgi?id=20556 ), and we solve
zero subtraction with the same change.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217286 91177308-0d34-0410-b5e6-96231b3b80d8
lib/CodeGen/SelectionDAG/DAGCombiner.cpp diff | blob | history
test/CodeGen/X86/vec_unsafe-fp-math.ll [new file with mode: 0644] blob
Unnamed repository; edit this file 'description' to name the repository.