GlobalISelEmitter was skipping these patterns when its predicates were
checked. This patch should allow us to select d16_hi stores in
GlobalISel.
Details
Details
- Reviewers
arsenm foad - Commits
- rGd8b690409dae: [AMDGPU] Set MemoryVT for truncstores in tblgen.
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Event Timeline
Comment Actions
LGTM. It would be nice to improve the codegen as noted inline but I'm not sure how to implement that.
llvm/test/CodeGen/AMDGPU/GlobalISel/load-unaligned.ll | ||
---|---|---|
268 | Now the only use of v5 is in v_lshrrev_b16 v1, 8, v5 below, so we really ought to fold that somehow. |
Now the only use of v5 is in v_lshrrev_b16 v1, 8, v5 below, so we really ought to fold that somehow.