diff --git a/tinygrad/renderer/ptx.py b/tinygrad/renderer/ptx.py index 5f957fbdcc..1fd63ee8d9 100644 --- a/tinygrad/renderer/ptx.py +++ b/tinygrad/renderer/ptx.py @@ -38,6 +38,7 @@ doesnt_support_half: tuple[Ops, ...] = tuple(op for op in asm_for_op.keys() if o ptx_matcher = PatternMatcher([ # bool CMPNE is XOR, bool CMPLT is XOR+AND (universal makes this slow, this is for renderer only) (UPat.var('x', dtype=dtypes.bool).ne(UPat.var('y')), lambda x,y: x^y), + (UPat.var('x', dtype=dtypes.bool).alu(Ops.CMPEQ, UPat.var('y')), lambda x,y: (x^y)^True), (UPat.var('x', dtype=dtypes.bool)