projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: ef484a3) | patch
Add PPC FP rounding instructions fri[mnpz]
authorHal Finkel <hfinkel@anl.gov>
Fri, 29 Mar 2013 08:57:48 +0000 (08:57 +0000)
committerHal Finkel <hfinkel@anl.gov>
Fri, 29 Mar 2013 08:57:48 +0000 (08:57 +0000)
commitf5d5c434606161fb017a34cb656fa4aa5a3e076b
tree4641a3e130c65183f13495d0228b9454e7bf7b60tree | snapshot
parentef484a376cce3729b45ad86eab5724aa83a61823commit | diff
Add PPC FP rounding instructions fri[mnpz]

These instructions are available on the P5x (and later) and on the A2. They
implement the standard floating-point rounding operations (floor, trunc, etc.).
One caveat: frin (round to nearest) does not implement "ties to even", and so
is only enabled in fast-math mode.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178337 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/PowerPC/PPC.td diff | blob | history
lib/Target/PowerPC/PPCISelLowering.cpp diff | blob | history
lib/Target/PowerPC/PPCInstrInfo.td diff | blob | history
lib/Target/PowerPC/PPCSubtarget.cpp diff | blob | history
lib/Target/PowerPC/PPCSubtarget.h diff | blob | history
test/CodeGen/PowerPC/rounding-ops.ll [new file with mode: 0644] blob
test/CodeGen/PowerPC/vec_rounding.ll diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors