Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | [AMDGPU] Restored selection of scalar_to_vector (v2x16) | Stanislav Mekhanoshin | 2018-11-19 | 1 | -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 |