DRAM-side
```asm{all|1-8|9,10|11|12|all}{lines:true,at:1}
MOV GRF_A #0, BANK
MOV GRF_A #1, BANK
MOV GRF_A #2, BANK
MOV GRF_A #3, BANK
MOV GRF_A #4, BANK
MOV GRF_A #5, BANK
MOV GRF_A #6, BANK
MOV GRF_A #7, BANK
MAC(AAM) GRF_B, BANK, GRF_A
JUMP -1, 7
FILL BANK, GRF_B #0
EXIT
```
Host-side
```rust {all|7-10|12-17|19-28|30-31|all}{lines:true,maxHeight:'15em',at:1}
pub fn execute(
matrix: &Matrix,
input_vector: &Vector,
output_partial_sum_vector: &mut SVector,
dummy: &impl PimOperand,
) {
// Load input vector into GRF-A registers
for chunk in input_vector.0.iter() {
chunk.execute_read();
}
// Execute the MAC instructions without memory barriers
for sub_matrix in matrix.0.iter() {
for column_block in sub_matrix.fixed_rows::<1>(0).iter() {
column_block.execute_read_async();
}
}
// Verify all memory accesses have finished
barrier::dsb(barrier::SY);
// Copy the partial sums into the bank
for chunk in output_partial_sum_vector
.fixed_rows_with_step_mut::(0, 16)
.iter_mut()
{
chunk.execute_write();
}
// Execute the EXIT instruction
dummy.execute_read();
}
```