Files
cutlass/python/CuTeDSL
Johnsonms e5fcd125a5 [fix] Boolean.__dsl_and__ emits arith.andi directly for i1 operands (#3087)
Before this fix, combining two Boolean (i1) DSL values with Python `and`
triggered a verbose i1→i32→i1 round-trip in __dsl_and__:
  arith.extui  (×3), arith.select, arith.cmpi ne (×2) — 6 extra MLIR ops.

Add a fast path: when both operands are Boolean, delegate directly to
__and__, emitting a single arith.andi %a, %b : i1 — identical to `&`.

Both operators were already semantically equivalent; this fix makes the
generated MLIR identical as well.

Includes:
- repro_dsl_and_bool.py  — minimal standalone reproducer / bug-report script
- test_dsl_and_fix.py    — pytest tests verifying the fixed behaviour
2026-03-05 17:20:26 +08:00
..
2025-05-13 15:55:29 -04:00
2026-02-27 13:59:21 -05:00
2026-02-27 13:59:21 -05:00
2026-02-13 23:27:58 -05:00