projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 00d3b27) | patch
[PowerPC] Implement combineRepeatedFPDivisors
authorHal Finkel <hfinkel@anl.gov>
Mon, 24 Nov 2014 23:45:21 +0000 (23:45 +0000)
committerHal Finkel <hfinkel@anl.gov>
Mon, 24 Nov 2014 23:45:21 +0000 (23:45 +0000)
commit360f213d039b519ce33c6b553f211e1cc826b976
tree7c749c14b88fce502ee4c501037410d148536931tree | snapshot
parent00d3b279cbdad40d27098754820b5951ff9328d8commit | diff
[PowerPC] Implement combineRepeatedFPDivisors

This does not matter on newer cores (where we can use reciprocal estimates in
fast-math mode anyway), but for older cores this allows us to generate better
fast-math code where we have multiple FDIVs with a common divisor.

llvm-svn: 222710
llvm/lib/Target/PowerPC/PPCISelLowering.cpp diff | blob | history
llvm/lib/Target/PowerPC/PPCISelLowering.h diff | blob | history
llvm/test/CodeGen/PowerPC/fdiv-combine.ll [new file with mode: 0644] blob
Domain: System / Toolchain;