projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 3d906e9) | patch
Allow generation of vmla.f32 instructions when targeting Cortex-A15. The patch also...
authorSilviu Baranga <silviu.baranga@arm.com>
Mon, 29 Jul 2013 09:25:50 +0000 (09:25 +0000)
committerSilviu Baranga <silviu.baranga@arm.com>
Mon, 29 Jul 2013 09:25:50 +0000 (09:25 +0000)
commitfd79485dfa4fee67467299720efac2d0c21d846c
tree0c3ee3a4ee3a79be8c5f48ad650386d4aa60c749tree | snapshot
parent3d906e9846361b494115e7a26625bdc435fdd5b1commit | diff
Allow generation of vmla.f32 instructions when targeting Cortex-A15. The patch also adds the VFP4 feature to Cortex-A15 and fixes the DontUseFusedMAC predicate so that we can still generate vmla.f32 instructions on non-darwin targets with VFP4.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187349 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/ARM/ARM.td diff | blob | history
lib/Target/ARM/ARMISelDAGToDAG.cpp diff | blob | history
lib/Target/ARM/ARMInstrInfo.td diff | blob | history
lib/Target/ARM/ARMTargetMachine.cpp diff | blob | history
test/CodeGen/ARM/a15-mla.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors