original output from 2060

M = 32, N = 32, K = 32. alpha = 2.000000, beta = 2.000000

gridDim.x = 2, gridDim.y = 2
Running with wmma...
Thread (0, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (1, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (2, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (3, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (4, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (5, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (6, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (7, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (8, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (9, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (10, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (11, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (12, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (13, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (14, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (15, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (16, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (17, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (18, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (19, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (20, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (21, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (22, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (23, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (24, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (25, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (26, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (27, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (28, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (29, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (30, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (31, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 0
Thread (0, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (1, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (2, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (3, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (4, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (5, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (6, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (7, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (8, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (9, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (10, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (11, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (12, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (13, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (14, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (15, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (16, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (17, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (18, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (19, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (20, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (21, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (22, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (23, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (24, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (25, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (26, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (27, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (28, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (29, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (30, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (31, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 16
Thread (0, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (1, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (2, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (3, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (4, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (5, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (6, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (7, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (8, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (9, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (10, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (11, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (12, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (13, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (14, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (15, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (16, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (17, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (18, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (19, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (20, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (21, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (22, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (23, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (24, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (25, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (26, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (27, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (28, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (29, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (30, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (31, 0) working on aRow = 16, aCol = 0, bRow = 0, bCol = 16
Thread (0, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (1, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (2, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (3, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (4, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (5, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (6, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (7, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (8, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (9, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (10, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (11, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (12, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (13, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (14, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (15, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (16, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (17, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (18, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (19, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (20, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (21, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (22, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (23, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (24, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (25, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (26, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (27, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (28, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (29, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (30, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (31, 0) working on aRow = 0, aCol = 0, bRow = 0, bCol = 0
Thread (0, 0) loading A from address 0x7fad19802020
Thread (1, 0) loading A from address 0x7fad19802020
Thread (2, 0) loading A from address 0x7fad19802020
Thread (3, 0) loading A from address 0x7fad19802020
Thread (4, 0) loading A from address 0x7fad19802020
Thread (5, 0) loading A from address 0x7fad19802020
Thread (6, 0) loading A from address 0x7fad19802020
Thread (7, 0) loading A from address 0x7fad19802020
Thread (8, 0) loading A from address 0x7fad19802020
Thread (9, 0) loading A from address 0x7fad19802020
Thread (10, 0) loading A from address 0x7fad19802020
Thread (11, 0) loading A from address 0x7fad19802020
Thread (12, 0) loading A from address 0x7fad19802020
Thread (13, 0) loading A from address 0x7fad19802020
Thread (14, 0) loading A from address 0x7fad19802020
Thread (15, 0) loading A from address 0x7fad19802020
Thread (16, 0) loading A from address 0x7fad19802020
Thread (17, 0) loading A from address 0x7fad19802020
Thread (18, 0) loading A from address 0x7fad19802020
Thread (19, 0) loading A from address 0x7fad19802020
Thread (20, 0) loading A from address 0x7fad19802020
Thread (21, 0) loading A from address 0x7fad19802020
Thread (22, 0) loading A from address 0x7fad19802020
Thread (23, 0) loading A from address 0x7fad19802020
Thread (24, 0) loading A from address 0x7fad19802020
Thread (25, 0) loading A from address 0x7fad19802020
Thread (26, 0) loading A from address 0x7fad19802020
Thread (27, 0) loading A from address 0x7fad19802020
Thread (28, 0) loading A from address 0x7fad19802020
Thread (29, 0) loading A from address 0x7fad19802020
Thread (30, 0) loading A from address 0x7fad19802020
Thread (31, 0) loading A from address 0x7fad19802020
Thread (0, 0) loading A from address 0x7fad19802000
Thread (1, 0) loading A from address 0x7fad19802000
Thread (2, 0) loading A from address 0x7fad19802000
Thread (3, 0) loading A from address 0x7fad19802000
Thread (4, 0) loading A from address 0x7fad19802000
Thread (5, 0) loading A from address 0x7fad19802000
Thread (6, 0) loading A from address 0x7fad19802000
Thread (7, 0) loading A from address 0x7fad19802000
Thread (8, 0) loading A from address 0x7fad19802000
Thread (9, 0) loading A from address 0x7fad19802000
Thread (10, 0) loading A from address 0x7fad19802000
Thread (11, 0) loading A from address 0x7fad19802000
Thread (12, 0) loading A from address 0x7fad19802000
Thread (13, 0) loading A from address 0x7fad19802000
Thread (14, 0) loading A from address 0x7fad19802000
Thread (15, 0) loading A from address 0x7fad19802000
Thread (16, 0) loading A from address 0x7fad19802000
Thread (17, 0) loading A from address 0x7fad19802000
Thread (18, 0) loading A from address 0x7fad19802000
Thread (19, 0) loading A from address 0x7fad19802000
Thread (20, 0) loading A from address 0x7fad19802000
Thread (21, 0) loading A from address 0x7fad19802000
Thread (22, 0) loading A from address 0x7fad19802000
Thread (23, 0) loading A from address 0x7fad19802000
Thread (24, 0) loading A from address 0x7fad19802000
Thread (25, 0) loading A from address 0x7fad19802000
Thread (26, 0) loading A from address 0x7fad19802000
Thread (27, 0) loading A from address 0x7fad19802000
Thread (28, 0) loading A from address 0x7fad19802000
Thread (29, 0) loading A from address 0x7fad19802000
Thread (30, 0) loading A from address 0x7fad19802000
Thread (31, 0) loading A from address 0x7fad19802000
Thread (0, 0) loading A from address 0x7fad19802020
Thread (1, 0) loading A from address 0x7fad19802020
Thread (2, 0) loading A from address 0x7fad19802020
Thread (3, 0) loading A from address 0x7fad19802020
Thread (4, 0) loading A from address 0x7fad19802020
Thread (5, 0) loading A from address 0x7fad19802020
Thread (6, 0) loading A from address 0x7fad19802020
Thread (7, 0) loading A from address 0x7fad19802020
Thread (8, 0) loading A from address 0x7fad19802020
Thread (9, 0) loading A from address 0x7fad19802020
Thread (10, 0) loading A from address 0x7fad19802020
Thread (11, 0) loading A from address 0x7fad19802020
Thread (12, 0) loading A from address 0x7fad19802020
Thread (13, 0) loading A from address 0x7fad19802020
Thread (14, 0) loading A from address 0x7fad19802020
Thread (15, 0) loading A from address 0x7fad19802020
Thread (16, 0) loading A from address 0x7fad19802020
Thread (17, 0) loading A from address 0x7fad19802020
Thread (18, 0) loading A from address 0x7fad19802020
Thread (19, 0) loading A from address 0x7fad19802020
Thread (20, 0) loading A from address 0x7fad19802020
Thread (21, 0) loading A from address 0x7fad19802020
Thread (22, 0) loading A from address 0x7fad19802020
Thread (23, 0) loading A from address 0x7fad19802020
Thread (24, 0) loading A from address 0x7fad19802020
Thread (25, 0) loading A from address 0x7fad19802020
Thread (26, 0) loading A from address 0x7fad19802020
Thread (27, 0) loading A from address 0x7fad19802020
Thread (28, 0) loading A from address 0x7fad19802020
Thread (29, 0) loading A from address 0x7fad19802020
Thread (30, 0) loading A from address 0x7fad19802020
Thread (31, 0) loading A from address 0x7fad19802020
Thread (0, 0) loading A from address 0x7fad19802000
Thread (1, 0) loading A from address 0x7fad19802000
Thread (2, 0) loading A from address 0x7fad19802000
Thread (3, 0) loading A from address 0x7fad19802000
Thread (4, 0) loading A from address 0x7fad19802000
Thread (5, 0) loading A from address 0x7fad19802000
Thread (6, 0) loading A from address 0x7fad19802000
Thread (7, 0) loading A from address 0x7fad19802000
Thread (8, 0) loading A from address 0x7fad19802000
Thread (9, 0) loading A from address 0x7fad19802000
Thread (10, 0) loading A from address 0x7fad19802000
Thread (11, 0) loading A from address 0x7fad19802000
Thread (12, 0) loading A from address 0x7fad19802000
Thread (13, 0) loading A from address 0x7fad19802000
Thread (14, 0) loading A from address 0x7fad19802000
Thread (15, 0) loading A from address 0x7fad19802000
Thread (16, 0) loading A from address 0x7fad19802000
Thread (17, 0) loading A from address 0x7fad19802000
Thread (18, 0) loading A from address 0x7fad19802000
Thread (19, 0) loading A from address 0x7fad19802000
Thread (20, 0) loading A from address 0x7fad19802000
Thread (21, 0) loading A from address 0x7fad19802000
Thread (22, 0) loading A from address 0x7fad19802000
Thread (23, 0) loading A from address 0x7fad19802000
Thread (24, 0) loading A from address 0x7fad19802000
Thread (25, 0) loading A from address 0x7fad19802000
Thread (26, 0) loading A from address 0x7fad19802000
Thread (27, 0) loading A from address 0x7fad19802000
Thread (28, 0) loading A from address 0x7fad19802000
Thread (29, 0) loading A from address 0x7fad19802000
Thread (30, 0) loading A from address 0x7fad19802000
Thread (31, 0) loading A from address 0x7fad19802000
Thread (0, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (1, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (2, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (3, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (4, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (5, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (6, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (7, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (8, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (9, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (10, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (11, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (12, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (13, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (14, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (15, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (16, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (17, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (18, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (19, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (20, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (21, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (22, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (23, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (24, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (25, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (26, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (27, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (28, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (29, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (30, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (31, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 0
Thread (0, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (1, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (2, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (3, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (4, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (5, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (6, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (7, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (8, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (9, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (10, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (11, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (12, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (13, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (14, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (15, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (16, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (17, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (18, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (19, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (20, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (21, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (22, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (23, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (24, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (25, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (26, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (27, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (28, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (29, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (30, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (31, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 16
Thread (0, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (1, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (2, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (3, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (4, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (5, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (6, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (7, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (8, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (9, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (10, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (11, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (12, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (13, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (14, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (15, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (16, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (17, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (18, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (19, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (20, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (21, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (22, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (23, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (24, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (25, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (26, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (27, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (28, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (29, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (30, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (31, 0) working on aRow = 0, aCol = 16, bRow = 16, bCol = 0
Thread (0, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (1, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (2, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (3, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (4, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (5, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (6, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (7, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (8, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (9, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (10, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (11, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (12, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (13, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (14, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (15, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (16, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (17, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (18, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (19, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (20, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (21, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (22, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (23, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (24, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (25, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (26, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (27, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (28, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (29, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (30, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (31, 0) working on aRow = 16, aCol = 16, bRow = 16, bCol = 16
Thread (0, 0) loading A from address 0x7fad19802420
Thread (1, 0) loading A from address 0x7fad19802420
Thread (2, 0) loading A from address 0x7fad19802420
Thread (3, 0) loading A from address 0x7fad19802420
Thread (4, 0) loading A from address 0x7fad19802420
Thread (5, 0) loading A from address 0x7fad19802420
Thread (6, 0) loading A from address 0x7fad19802420
Thread (7, 0) loading A from address 0x7fad19802420
Thread (8, 0) loading A from address 0x7fad19802420
Thread (9, 0) loading A from address 0x7fad19802420
Thread (10, 0) loading A from address 0x7fad19802420
Thread (11, 0) loading A from address 0x7fad19802420
Thread (12, 0) loading A from address 0x7fad19802420
Thread (13, 0) loading A from address 0x7fad19802420
Thread (14, 0) loading A from address 0x7fad19802420
Thread (15, 0) loading A from address 0x7fad19802420
Thread (16, 0) loading A from address 0x7fad19802420
Thread (17, 0) loading A from address 0x7fad19802420
Thread (18, 0) loading A from address 0x7fad19802420
Thread (19, 0) loading A from address 0x7fad19802420
Thread (20, 0) loading A from address 0x7fad19802420
Thread (21, 0) loading A from address 0x7fad19802420
Thread (22, 0) loading A from address 0x7fad19802420
Thread (23, 0) loading A from address 0x7fad19802420
Thread (24, 0) loading A from address 0x7fad19802420
Thread (25, 0) loading A from address 0x7fad19802420
Thread (26, 0) loading A from address 0x7fad19802420
Thread (27, 0) loading A from address 0x7fad19802420
Thread (28, 0) loading A from address 0x7fad19802420
Thread (29, 0) loading A from address 0x7fad19802420
Thread (30, 0) loading A from address 0x7fad19802420
Thread (31, 0) loading A from address 0x7fad19802420
Thread (0, 0) loading A from address 0x7fad19802400
Thread (1, 0) loading A from address 0x7fad19802400
Thread (2, 0) loading A from address 0x7fad19802400
Thread (3, 0) loading A from address 0x7fad19802400
Thread (4, 0) loading A from address 0x7fad19802400
Thread (5, 0) loading A from address 0x7fad19802400
Thread (6, 0) loading A from address 0x7fad19802400
Thread (7, 0) loading A from address 0x7fad19802400
Thread (8, 0) loading A from address 0x7fad19802400
Thread (9, 0) loading A from address 0x7fad19802400
Thread (10, 0) loading A from address 0x7fad19802400
Thread (11, 0) loading A from address 0x7fad19802400
Thread (12, 0) loading A from address 0x7fad19802400
Thread (13, 0) loading A from address 0x7fad19802400
Thread (14, 0) loading A from address 0x7fad19802400
Thread (15, 0) loading A from address 0x7fad19802400
Thread (16, 0) loading A from address 0x7fad19802400
Thread (17, 0) loading A from address 0x7fad19802400
Thread (18, 0) loading A from address 0x7fad19802400
Thread (19, 0) loading A from address 0x7fad19802400
Thread (20, 0) loading A from address 0x7fad19802400
Thread (21, 0) loading A from address 0x7fad19802400
Thread (22, 0) loading A from address 0x7fad19802400
Thread (23, 0) loading A from address 0x7fad19802400
Thread (24, 0) loading A from address 0x7fad19802400
Thread (25, 0) loading A from address 0x7fad19802400
Thread (26, 0) loading A from address 0x7fad19802400
Thread (27, 0) loading A from address 0x7fad19802400
Thread (28, 0) loading A from address 0x7fad19802400
Thread (29, 0) loading A from address 0x7fad19802400
Thread (30, 0) loading A from address 0x7fad19802400
Thread (31, 0) loading A from address 0x7fad19802400
Thread (0, 0) loading A from address 0x7fad19802420
Thread (1, 0) loading A from address 0x7fad19802420
Thread (2, 0) loading A from address 0x7fad19802420
Thread (3, 0) loading A from address 0x7fad19802420
Thread (4, 0) loading A from address 0x7fad19802420
Thread (5, 0) loading A from address 0x7fad19802420
Thread (6, 0) loading A from address 0x7fad19802420
Thread (7, 0) loading A from address 0x7fad19802420
Thread (8, 0) loading A from address 0x7fad19802420
Thread (9, 0) loading A from address 0x7fad19802420
Thread (10, 0) loading A from address 0x7fad19802420
Thread (11, 0) loading A from address 0x7fad19802420
Thread (12, 0) loading A from address 0x7fad19802420
Thread (13, 0) loading A from address 0x7fad19802420
Thread (14, 0) loading A from address 0x7fad19802420
Thread (15, 0) loading A from address 0x7fad19802420
Thread (16, 0) loading A from address 0x7fad19802420
Thread (17, 0) loading A from address 0x7fad19802420
Thread (18, 0) loading A from address 0x7fad19802420
Thread (19, 0) loading A from address 0x7fad19802420
Thread (20, 0) loading A from address 0x7fad19802420
Thread (21, 0) loading A from address 0x7fad19802420
Thread (22, 0) loading A from address 0x7fad19802420
Thread (23, 0) loading A from address 0x7fad19802420
Thread (24, 0) loading A from address 0x7fad19802420
Thread (25, 0) loading A from address 0x7fad19802420
Thread (26, 0) loading A from address 0x7fad19802420
Thread (27, 0) loading A from address 0x7fad19802420
Thread (28, 0) loading A from address 0x7fad19802420
Thread (29, 0) loading A from address 0x7fad19802420
Thread (30, 0) loading A from address 0x7fad19802420
Thread (31, 0) loading A from address 0x7fad19802420
Thread (0, 0) loading A from address 0x7fad19802400
Thread (1, 0) loading A from address 0x7fad19802400
Thread (2, 0) loading A from address 0x7fad19802400
Thread (3, 0) loading A from address 0x7fad19802400
Thread (4, 0) loading A from address 0x7fad19802400
Thread (5, 0) loading A from address 0x7fad19802400
Thread (6, 0) loading A from address 0x7fad19802400
Thread (7, 0) loading A from address 0x7fad19802400
Thread (8, 0) loading A from address 0x7fad19802400
Thread (9, 0) loading A from address 0x7fad19802400
Thread (10, 0) loading A from address 0x7fad19802400
Thread (11, 0) loading A from address 0x7fad19802400
Thread (12, 0) loading A from address 0x7fad19802400
Thread (13, 0) loading A from address 0x7fad19802400
Thread (14, 0) loading A from address 0x7fad19802400
Thread (15, 0) loading A from address 0x7fad19802400
Thread (16, 0) loading A from address 0x7fad19802400
Thread (17, 0) loading A from address 0x7fad19802400
Thread (18, 0) loading A from address 0x7fad19802400
Thread (19, 0) loading A from address 0x7fad19802400
Thread (20, 0) loading A from address 0x7fad19802400
Thread (21, 0) loading A from address 0x7fad19802400
Thread (22, 0) loading A from address 0x7fad19802400
Thread (23, 0) loading A from address 0x7fad19802400
Thread (24, 0) loading A from address 0x7fad19802400
Thread (25, 0) loading A from address 0x7fad19802400
Thread (26, 0) loading A from address 0x7fad19802400
Thread (27, 0) loading A from address 0x7fad19802400
Thread (28, 0) loading A from address 0x7fad19802400
Thread (29, 0) loading A from address 0x7fad19802400
Thread (30, 0) loading A from address 0x7fad19802400
Thread (31, 0) loading A from address 0x7fad19802400

Checking results...