
DRAM [ Inputs:41472 (41472) Outputs:32768 (32768) ] 
---------------------------------------------------
| for Q in [0:16)

shared_glb [ Inputs:6912 (6912) Outputs:2048 (2048) ] 
-----------------------------------------------------
|   for Q in [0:1)
|     for S in [0:3) (Spatial-X)
|       for R in [0:3) (Spatial-X)

input_buffer [ Inputs:2048 (2048) ] 
-----------------------------------
|         for P in [0:16)

dummy_buffer [ ] 
----------------
|           for Q in [0:1)
|             for M in [0:128) (Spatial-Y)
|               for C in [0:128) (Spatial-X)

scratchpad [ Weights:1 (1) ] 
----------------------------
|                 for Q in [0:1)

