[all-commits] [llvm/llvm-project] 94e4ec: Add CalibratedQuantizedType to quant dialect

[Taehee Jeong via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 94e4ec6499a237aeec4f1fe8f2cc1e9bcb33f971
      https://github.com/llvm/llvm-project/commit/94e4ec6499a237aeec4f1fe8f2cc1e9bcb33f971
  Author: Tei Jeong <taeheej at google.com>
  Date:   2020-11-17 (Tue, 17 Nov 2020)

  Changed paths:
    M mlir/include/mlir/Dialect/Quant/QuantTypes.h
    M mlir/lib/Dialect/Quant/IR/QuantOps.cpp
    M mlir/lib/Dialect/Quant/IR/QuantTypes.cpp
    M mlir/lib/Dialect/Quant/IR/TypeDetail.h
    M mlir/lib/Dialect/Quant/IR/TypeParser.cpp
    A mlir/test/Dialect/Quant/parse-calibrated-invalid.mlir
    A mlir/test/Dialect/Quant/parse-calibrated.mlir

  Log Message:
  -----------
  Add CalibratedQuantizedType to quant dialect

This type supports a calibrated type with min, max provided.

This will be used for importing calibration values of intermediate tensors (e.g. LSTM) which can't be imported with QuantStats op.

This type was initially suggested in the following RFC: https://llvm.discourse.group/t/rfc-a-proposal-for-implementing-quantization-transformations-in-mlir/655

Reviewed By: stellaraccident

Differential Revision: https://reviews.llvm.org/D91584