remove move_mask from the devectorizer (#9511)

* remove move_mask from the devectorizer

* add (wrong) ptx

* reason

* enable index addition in PTX, we won't have the INDEX anyways

* space
This commit is contained in:
qazal
2025-03-20 11:53:12 +08:00
committed by GitHub
parent 9302738263
commit 0b20f91ce7
10 changed files with 30 additions and 25 deletions

View File

@@ -53,6 +53,7 @@ class TestPTXFailures(unittest.TestCase):
ret = _test_uop_result([], uops, local_size=[4, 1, 1])[0]
np.testing.assert_equal(ret, [0, 1, 1, 1])
@unittest.skip("INDEX can only have a gate ALU parent, not an IF")
def test_gated_store_with_if(self):
a = UOp(Ops.DEFINE_GLOBAL, dtypes.int.ptr(), (), 0)
gate_alu = (lidx0:=UOp(Ops.SPECIAL, dtypes.int, (), ('lidx0', 4))).ne(0)