projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 4470f38) | patch
[X86][SSE] Improved support for vector i16 to float conversions.
authorSimon Pilgrim <llvm-dev@redking.me.uk>
Wed, 17 Jun 2015 22:43:34 +0000 (22:43 +0000)
committerSimon Pilgrim <llvm-dev@redking.me.uk>
Wed, 17 Jun 2015 22:43:34 +0000 (22:43 +0000)
commit3aa039a4a8d7b81c6b2a6bacdc6b6fa33665715e
treee2fdfd8eb58460fabdffba6f498e0d71baa0bc17tree | snapshot
parent4470f3826c964e25f8c3a7229640567333fd9119commit | diff
[X86][SSE] Improved support for vector i16 to float conversions.

Added explicit sign extension for v4i16/v8i16 to v4i32/v8i32 before conversion to floats. Matches existing support for v4i8/v8i8.

Follow up to D10433

llvm-svn: 239966
llvm/lib/Target/X86/X86ISelLowering.cpp diff | blob | history
llvm/test/CodeGen/X86/vec_int_to_fp.ll diff | blob | history
Domain: System / Toolchain;