You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
hi,
our device just can compute on device_l1_buffer
if use gpu, one can use .copy_to_device, to indicate that buffer copy from host to device.
however gpu can compute their data at GPU_L2_memory . while in our case, if use copy to device the data only can insert to device_l3_memory, but compute can only happen at device_l1_memory.
how can I inject host->device_l3_memory -> device_l2_memory -> device_l1_memory( pure compute function)
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
hi,
our device just can compute on device_l1_buffer
if use gpu, one can use .copy_to_device, to indicate that buffer copy from host to device.
however gpu can compute their data at GPU_L2_memory . while in our case, if use copy to device the data only can insert to device_l3_memory, but compute can only happen at device_l1_memory.
how can I inject host->device_l3_memory -> device_l2_memory -> device_l1_memory( pure compute function)
thanks for kindly help.
Beta Was this translation helpful? Give feedback.
All reactions