We can use riscv_vse intrinsic instead of riscv_vse_mask. The code here
is based on similar code for handling masked.scatter and vp.scatter.
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Differential D110206 Authored by craig.topper on Sep 21 2021, 3:55 PM.
Details Summary We can use riscv_vse intrinsic instead of riscv_vse_mask. The code here
Diff Detail
Event TimelineHerald added subscribers: vkmr, evandro, luismarques and 24 others. · View Herald TranscriptSep 21 2021, 3:55 PM craig.topper added a child revision: D109482: [RISCV] Fold store of vmv.x.s to a vse with VL=1..Sep 21 2021, 4:45 PM This revision is now accepted and ready to land.Sep 22 2021, 1:43 AM This revision was landed with ongoing or failed builds.Sep 22 2021, 9:21 AM Closed by commit rGb33a1cc05b48: [RISCV] Optimize vp.store with an all ones mask to avoid a vmset. (authored by craig.topper). · Explain Why This revision was automatically updated to reflect the committed changes.
Revision Contents
Diff 374061 |