projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: e0f5a86) | patch
[AArch64 NEON] Lower SELECT_CC with vector operand.
authorKevin Qin <Kevin.Qin@arm.com>
Wed, 29 Jan 2014 01:57:30 +0000 (01:57 +0000)
committerKevin Qin <Kevin.Qin@arm.com>
Wed, 29 Jan 2014 01:57:30 +0000 (01:57 +0000)
commit79c6a4f3478bd21558e2c779667bec7d69e94ccc
tree4c69979185e3d7da5d820000115dbeb39c1a1944tree | snapshot
parente0f5a8667105ac03c6cd21c0200ba87e94d8d931commit | diff
[AArch64 NEON] Lower SELECT_CC with vector operand.

When the scalar compare is between floating point and operands are
vector, we custom lower SELECT_CC to use NEON SIMD compare for
generating less instructions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@200365 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AArch64/AArch64ISelLowering.cpp diff | blob | history
lib/Target/AArch64/AArch64InstrNEON.td diff | blob | history
test/CodeGen/AArch64/neon-select_cc.ll [new file with mode: 0644] blob
C/C++ LLVM-based compilers that forbids OOTA behaviors