diff options
| author | Craig Topper <craig.topper@intel.com> | 2018-03-02 18:16:51 +0000 |
|---|---|---|
| committer | Craig Topper <craig.topper@intel.com> | 2018-03-02 18:16:51 +0000 |
| commit | 18799f4c07fdef192ab8b42b9e954baad97a23f5 (patch) | |
| tree | 55117e77977b6a3809f87f4435ee8a3775ae7439 /llvm/test/CodeGen/X86/vector-idiv-udiv-512.ll | |
| parent | 20cf67c233beab21cccbdc23d8b35397fc6cb321 (diff) | |
| download | bcm5719-llvm-18799f4c07fdef192ab8b42b9e954baad97a23f5.tar.gz bcm5719-llvm-18799f4c07fdef192ab8b42b9e954baad97a23f5.zip | |
[InstCombine] Allow fptrunc (fpext X)) to be reduced to a single fpext/ftrunc
If we are only truncating bits from the extend we should be able to just use a smaller extend.
If we are truncating more than the extend we should be able to just use a fptrunc since the presense of the fpextend shouldn't affect rounding.
Differential Revision: https://reviews.llvm.org/D43970
llvm-svn: 326595
Diffstat (limited to 'llvm/test/CodeGen/X86/vector-idiv-udiv-512.ll')
0 files changed, 0 insertions, 0 deletions
