summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/AMDGPU/scalar_to_vector_v2x16.ll
Commit message (Collapse)AuthorAgeFilesLines
* [AMDGPU] Restored selection of scalar_to_vector (v2x16)Stanislav Mekhanoshin2018-11-191-0/+26
This works if DAG combiner is enabled, but without combining we cannot select scalar_to_vector of <2 x half> and <2 x i16>. Differential Revision: https://reviews.llvm.org/D54718 llvm-svn: 347259
OpenPOWER on IntegriCloud