Specification for UniformQuantizeOp and UniformDequantizeOp

[sdasgup3]

fixes #531
fixes #530

Summary

The PR proposes the specification for uniform.quantize and uniform.dequantize ops.

The specification of uniform.quantize also captures the re-quantization conversions from quantized tensor to quantized tensors.

Please let me know your feedback.

Working notes on following the reference_checklist.md and spec_checkilist.md

uniform_dequantize

We have the following constraints from the spec

(I1)  `operand` is a  quantized tensor
(C1) `shape(operand) = shape(result)`.
(C2) `element_type(result) = expressed_type(operand)`.

These constraints will be comprehensively covered by the following tests:

I1: a) `operand: quantized tensors`. (Covered by ODS).
C1: a) `shape(operand) != shape(result)`. (Covered by ODS)
C2: a) `element_type(result) != expressed_type(operand)`.

If we drop the "Covered by ODS" pieces, this will leave us with the following test cases:

C2: a) `element_type(result) != expressed_type(operand)`.

We already has a type inference test to cover the above.

uniform_quantize

We have the following constraints from the spec

(I1)  `operand: tensor of floating-point or quantized type`.
(C1) `shape(operand) = shape(result)`.
(C2) `expressed_type(result) = is_float(operand) ? element_type(operand) :
  expressed_type(operand)`.

These constraints will be comprehensively covered by the following tests:

I1: a) `operand: quantized tensors`. (Covered by ODS).
C1: a) `shape(operand) != shape(result)`. (Covered by ODS)
C2: a) if_float(operand): `expressed_type(result) != element_type(operand)`.
      b) if_quantized(operand): `expressed_type(result) !=  expressed_type(operand)`.

If we drop the "Covered by ODS" pieces, this will leave us with the following test cases:

C2: a) if_float(operand): `expressed_type(result) != element_type(operand)`.
      b) if_quantized(operand): `expressed_type(result) !=  expressed_type(operand)`.

The above will be covered as part of #1603.

[loganchien]

Overall LGTM, which a few minor comments.

[dominicsymes]

This looks fine to me. I think allowing also QuantizationIntegerScale should be discussed following that PR (#1475).

[sdasgup3]

@dominicsymes
Thanks for the review.

I think allowing also QuantizationIntegerScale should be discussed following that PR

That is right. Once we have #1475 landed, then the quantize/dequantize op will allow that type too.

[sdasgup3]

My proposal is to merge the current PR and consider merging the two ops to convert op at a later point via #1576.