Reland "Arm backend: Rerun duplicate-user fusion after TOSA lowering" (#21380)
Late TOSA transformations can introduce equivalent operations after the first FuseDuplicateUsersPass invocation. Rerun it after TOSA and shape transformations, before output nodes are made unique. Run InsertRescalePass after the final FuseDuplicateUsersPass. Fusing generated RESCALE users can merge distinct quantized paths and produce incorrect results. TOSA-FP operator comparisons: | Model | Before | After | Reduction | |--------------------|-------:|------:|----------:| | SD3 | 1,591 | 1,527 | 64 (4.0%) | | Conformer delegate | 544 | 498 | 46 (8.5%) | Reference-output tests pass with late fusion enabled. Add regression coverage for late fusion, rescale insertion, and output uniqueness pass ordering. Change-Id: Ia4e2335e05b18d16b93c7e035a5502b8f050855c Signed-off-by: Yufeng Shi <yufeng.shi@arm.com>
Y
Yufeng Shi committed
fb5b788e012305d8d3f7f462d4af87d96a28fc27
Parent: 3aeaa80
Committed by GitHub <noreply@github.com>
on 7/27/2026, 10:57:46 AM