forked from OSchip/llvm-project
72855e36c5
In general we can't assume flat loads are uniform, and cases where we can prove they are should be handled through infer-address-spaces. Differential Revision: https://reviews.llvm.org/D50991 llvm-svn: 340343 |
||
|---|---|---|
| .. | ||
| atomics.ll | ||
| intrinsics.ll | ||
| kernel-args.ll | ||
| lit.local.cfg | ||
| llvm.amdgcn.buffer.atomic.ll | ||
| llvm.amdgcn.image.atomic.ll | ||
| loads.ll | ||
| no-return-blocks.ll | ||
| phi-undef.ll | ||
| unreachable-loop-block.ll | ||
| workitem-intrinsics.ll | ||