trunk/ff30875f25530b355ab830bbde00b7a5363bafa4: [inductor] Extend partitioned scatter to additional ops (#194078)
- PyTorch: 2197 events in the last 90 days
- PyTorch: 2168th Release in the last 90 days
- Previous: earlier the same day · trunk/1b37948b338574242245d8dfa0ea3365c24503bc: Add XPU IPC support for c10::Event (#193165)
What happened
The partitioned scatter pass only matched aten.index_put / aten.index_put_ , so it missed ops that emit the exact same contended atomic_add store. This extends the pass to cover them and tightens the partition cap so the rewrite cannot cost more memory traffic than the scatter it replaces. Adds support for: _unsafe_masked_index_put_accumulate lowering aten.scatter_add , aten.scatter_reduce.two , aten.scatter.reduce…
Summary assembled by rule from the sources below