[Relay] Add pass for getting calibration data from a relay module

[seanlatias]

RFC discussion: https://discuss.tvm.ai/t/rfc-byoc-data-calibration-flow/7099/15

This PR implements the analysis pass get_calibration_data mentioned in the RFC. The main functionality of this analysis pass is allowing users to easily get the calibration data from any Relay module. The calibration data includes the input and output tensor values of each subgraph in the module. Following is an example.

The input relay graph that contains two subgraphs:

def @dnnl0(%dnnl0_i0: Tensor[(3, 3), float32], %dnnl0_i1: Tensor[(3, 3), float32]) -> Tensor[(3, 3), float32] {
  add(%dnnl0_i0, dnnl0_i1) 
}

def @dnnl1(%dnnl0_i0: Tensor[(3, 3), float32], %dnnl0_i1: Tensor[(3, 3), float32]) -> Tensor[(3, 3), float32] {
  sub(%dnnl0_i0, dnnl0_i1) 
}

def @main(%data0: Tensor[(3, 3), float32], %data1: Tensor[(3, 3), float32], %data2: Tensor[(3, 3), float32]) -> Tensor[(3, 3), float32] {
  %0 = @dnnl0(%data0, %data1)
  @dnnl1(%0, %data2)
}

The Python API

mod = # the above relay graph
data = {"data0": ..., "data1": ..., "data2": ...}

calib_data = relay.analysis.get_calibration_data(mod, data)
print(calib_data)

The expected output

{@dnnl0: {"inputs": [%data0, %data1], "outputs": [%0]},
 @dnnl1: {"inputs": [%0, %data2], "outputs":[%out]}}

As can be seen, the output calibration data is a two-level dictionary. The first level takes in the GlobalVar of a subgraph as a key and the value is the second-level dictionary. The second level always has two keys: inputs and outputs, which map to the real tensor values of each subgraph. For more complex example please refer to the test.

@comaniac @zhiics

[comaniac]

We may need to think of the semantic for the module with control flows, which has to use VM instead of graph runtime.

[comaniac]

Suggested change

	This pass use the graph runtime to get the calibration data of a module, which
	This pass uses the graph runtime to get the calibration data of a module, which

Per offline discussion, please mention that this pass only works for the graph without control flow.

[comaniac]

Suggested change

	This pass use the graph runtime to get the calibration data of a module, which
	This pass uses the graph runtime to get the calibration data of a module, which

Per offline discussion, please mention that this pass only works for the graph without control flow.

[comaniac]

LGTM

[zhiics]

LGTM

[zhiics]

Thanks @seanlatias @comaniac