projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 79d189f) | patch
[X86] Simplify the ReplaceNodeResults code for X86ISD::AVG.
authorCraig Topper <craig.topper@intel.com>
Mon, 26 Feb 2018 02:16:33 +0000 (02:16 +0000)
committerCraig Topper <craig.topper@intel.com>
Mon, 26 Feb 2018 02:16:33 +0000 (02:16 +0000)
commit2bf8e3e0e191bd434b867133d0ee093eec63edfb
treeb95ac185dcb44cca0ecbe8ea7e44a33a020494d1tree | snapshot
parent79d189f5970e43cac372403cdf329d6ba04e6bf1commit | diff
[X86] Simplify the ReplaceNodeResults code for X86ISD::AVG.

This code seemed to try to widen to 128, 256, or 512 bit vectors, but we only create X86ISD::AVG with a power of 2 number of elements. This means the only nodes that need to be legalized are less than 128-bits and need to be widened up to 128 bits.

llvm-svn: 326064
llvm/lib/Target/X86/X86ISelLowering.cpp diff | blob | history
Domain: System / Toolchain;