tree 0ad812474c0f8a156d07eabd42902572f14bc426
parent b7341d9f7d39b6248389f93cd1e696659adb21f6
author Zhewen Yu <zhewenyu@amd.com> 1756457090 +0100
committer GitHub <noreply@github.com> 1756457090 +0100
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJosWiDCRC1aQ7uu5UhlAAAzYgQACyOvw2OPwiw1z+Dbc6fSUK0
 J+X9XhHDMZQJGc7YOk/xPRfjYsCaFNjbu8z5GE5fCa0MKfg2E1h4RSLPaZ0MVklY
 FyFz5Q3hMVHFX+xlYjFKbYxvuDCWCZOBiPIXMXqcJ8OY4Gbfcl2ItxADoZmMZosj
 x2IJGokkHKmQfRo9j6Kighfa+0NVPDCdVb3qnck8YPwtsDuictMv1rIaDDZDfeb9
 ulQqyUTkDvLy7q0ciZM5ypUdj3E5MguVFofFuwMCsGbOmcVXe4Yg8VZ/TmALvomb
 1GMk2MFZ/SpKsQx1MAV50zJI+nmsuTlNUWNCv4wGhoxtTRi37i/GY1IK1PK6u5Wi
 Azwn8TLCM2aAJlVt8Kp4VcbTZ1XOZgWdydp8mAixcz0MqU7BDRahaPLJmE6h8Ykm
 p/Zo4BJaqqTLmfwjl+LArBrowsRX0nceTBE/WW6/Osk2XPzf4CLYHeuwN11XBlfK
 Oe3vxwCYeONsBIJ+5N5/j9oKTkMUBWEXOjJdsnYdi4lteUzLyEV6KSMa59i25ITA
 FlUoklMwExwncI3j3yBWrqCWM/+1RxD25MjOlKZlVLLBojzc26iWpGx+uORoVLBa
 u6p0pIO/e7HmO14EIpjjQFlvJgSO6AV3S1+WUfUxoTt02IoGFiWuQ9mb5lTqEGPd
 pXTxEU2ln3D0++Bj1UEx
 =DBc0
 -----END PGP SIGNATURE-----
 

[GPU][DT] Fix LHS operand offset calculation for DataTiledMMAAttr (#21808)

`DistributeInnerTiledToLanesPass` creates `AffineDelinearizeIndexOp` to
delinearize the thread index within a workgroup and generate offsets for
slicing the operands of InnerTiled operations.

Currently, the delinearization for `DataTiledMMAAttr` relies solely on
the operand swizzle. However, for the LHS, this swizzle does not include
the subGroupsN dimension, which could result in incorrect offset
calculations.

This PR fixes the issue by inserting a dummy subGroupsN dimension when
delinearizing for LHS, ensuring that offsets are generated correctly
according to the full subGroupsM × subGroupsN thread space.

Note that, no special handling is required for the RHS operand, since
subGroupsM is treated as an implicit leading dimension and therefore
omitted anyway.

Closes #21789

Signed-off-by: Yu-Zhewen <zhewenyu@amd.com>