| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | [ARM] Split 128-bit vectors in BUILD_VECTOR lowering | Eli Friedman | 2016-12-14 | 1 | -12/+12 |
| | | | | | | | | | | | | | | Given that INSERT_VECTOR_ELT operates on D registers anyway, combining 64-bit vectors into a 128-bit vector is basically free. Therefore, try to split BUILD_VECTOR nodes before giving up and lowering them to a series of INSERT_VECTOR_ELT instructions. Sometimes this allows dramatically better lowerings; see testcases for examples. Inspired by similar code in the x86 backend for AVX. Differential Revision: https://reviews.llvm.org/D27624 llvm-svn: 289706 | ||||
| * | ARM-BE: test files for vector argument passing | Christian Pirker | 2014-05-14 | 1 | -0/+1172 |
| Reviewed at http://reviews.llvm.org/D3766 llvm-svn: 208793 | |||||
 |
index : bcm5719-llvm | |
| Project Ortega BCM5719 LLVM | Raptor Computing Systems |
| summaryrefslogtreecommitdiffstats |
|