projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 1baf789) | patch
[x86] allow narrowing of vector UINT_TO_FP
authorSanjay Patel <spatel@rotateright.com>
Fri, 22 Feb 2019 15:47:45 +0000 (15:47 +0000)
committerSanjay Patel <spatel@rotateright.com>
Fri, 22 Feb 2019 15:47:45 +0000 (15:47 +0000)
commita9e289174a1c21698ea0c1f1a43f1f504e5e75ef
tree103fb47d274aba00af6c22098d1e8fdaff08899btree | snapshot
parent1baf7896cc2b48a15ba0590a5ece6143ef1ab552commit | diff
[x86] allow narrowing of vector UINT_TO_FP

As discussed in:
D56864
D58197

Always use the narrow (128-bit) instruction when possible.
We already had the signed int version of this transform.

llvm-svn: 354675
llvm/lib/Target/X86/X86ISelLowering.cpp diff | blob | history
llvm/test/CodeGen/X86/vec_int_to_fp-widen.ll diff | blob | history
llvm/test/CodeGen/X86/vec_int_to_fp.ll diff | blob | history
Domain: System / Toolchain;