I am going through the VTA tutorial for matrix multiplication given in https://tvm.apache.org/docs/vta/tutorials/matrix_multiply.html
A_2 is the input vector tensor and B_2 is the weight tensor. As we can see in the lowered code below, the last parameter’s value (which corresponds to memory stage) is different for A_2 and B_2. For A_2, the value is 2 (which corresponds to compute stage), and for B_2, the value is 1 (which corresponds to load stage)
tir.call_extern(“VTALoadBuffer2D”, tir.tvm_thread_context(tir.vta.command_handle(, dtype=handle), dtype=handle), A_2, ko, 1, 1, 1, 0, 0, 0, 0, 0, 2, dtype=int32)
tir.call_extern(“VTALoadBuffer2D”, tir.tvm_thread_context(tir.vta.command_handle(, dtype=handle), dtype=handle), B_2, ko, 1, 16, 16, 0, 0, 0, 0, 0, 1, dtype=int32)
Can you please let me know why the values are different although both act as inputs for matrix multiplication.