maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/mlir/test/Dialect/Quant/parse-calibrated.mlir

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

11 lines
321 B
MLIR
Raw Normal View History

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
2020-11-18 14:14:02 +08:00
// RUN: mlir-opt -allow-unregistered-dialect %s -split-input-file | FileCheck %s
// -----
// CHECK-LABEL: parseCalibrated
Fix CalibratedQuantizedType's print function to match parser Reviewed By: liufengdb Differential Revision: https://reviews.llvm.org/D92034
2020-11-25 01:34:52 +08:00
// CHECK: !quant.calibrated<f32<-0.998:1.232100e+00>
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
2020-11-18 14:14:02 +08:00
!qalias = type !quant.calibrated<f32<-0.998:1.2321>>
func @parseCalibrated() -> !qalias {
%0 = "foo"() : () -> !qalias
return %0 : !qalias
}