I try to read x into shared memory to accelerate layernorm, script here
but error occurs in pass thread_sorage_sync pass
can anyone help to explain the cause of this error, or it could be better to help solve this problem
I try to read x into shared memory to accelerate layernorm, script here
but error occurs in pass thread_sorage_sync pass
can anyone help to explain the cause of this error, or it could be better to help solve this problem