projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 18c2671) | patch
[ARM] MVE floating point compares and selects
authorDavid Green <david.green@arm.com>
Wed, 24 Jul 2019 14:28:22 +0000 (14:28 +0000)
committerDavid Green <david.green@arm.com>
Wed, 24 Jul 2019 14:28:22 +0000 (14:28 +0000)
commit4fc78c496eb6e79d6ab273e4cb1ef8dc0fb61737
tree21cccb00504e14ab82d35f23e2c6d38a95da5b2ftree | snapshot
parent18c267135225272e0600b76dec587df660321f67commit | diff
[ARM] MVE floating point compares and selects

Much like integers, this adds MVE floating point compares and select. It
requires a lot more buildvector/shuffle code because we may need to expand the
compares without mve.fp, and requires support for and/or because of the way we
lower llvm condition codes.

Some original code by David Sherwood

Differential Revision: https://reviews.llvm.org/D65054

llvm-svn: 366909
llvm/lib/Target/ARM/ARMISelLowering.cpp diff | blob | history
llvm/lib/Target/ARM/ARMInstrMVE.td diff | blob | history
llvm/test/CodeGen/Thumb2/mve-vcmpf.ll [new file with mode: 0644] blob
llvm/test/CodeGen/Thumb2/mve-vcmpfz.ll [new file with mode: 0644] blob
llvm/test/CodeGen/Thumb2/mve-vpsel.ll diff | blob | history
Domain: System / Toolchain;