
Block
(4,2)
CUDA
kernel 1
launch
CPU serial
code
CPU
kernel 2
launch
Per-block
shared memory
Data grid 1
Data grid 2
Inter-grid synchronization
barrier
Constant/texture memory
Global device memory (DRAM)
Block
(0,0)
Block
(1,0)
Block
(2,0)
Block
(3,0)
Block
(0,1)
Block
(1,1)
Block
(2,1)
Block
(3,1)
Block
(0,0)
Block
(1,0)
Block
(2,0)
Block
(3,0)
Block
(4,1)
Block
(4,2)
Block
(4,0)
Block
(0,2)
Block
(1,2)
Block
(2,2)
Block
(3,2)
Block
(2,1)
Block
(2,1)
Block
(0,1)
Block
(1,1)
Thread
(0,0)
Thread
(1,0)
Thread
(2,0)
Thread
(0,1)
Thread
(0,2) ...