[Quantization] Calibrated quantized resnet-152 inference slower than no-calib model after rebasing with the master branch

[reminisce]

The quantize and dequantize op are slower in calibrated quantized resnet-152 model than in no-calib model, even though quantize_down_and_shrink range is much faster in calibrated model.

For bugs or installation issues, please provide the following information.
The more information you provide, the more likely people will be able to help you.

Environment info

Operating System:

Compiler:

Package used (Python/R/Scala/Julia):

MXNet version:

Or if installed from source:

MXNet commit hash (git rev-parse HEAD):

If you are using python package, please provide

Python version and distribution:

If you are using R package, please provide

R sessionInfo():

Error Message:

Please paste the full error message, including stack trace.

Minimum reproducible example

if you are using your own code, please provide a short script that reproduces the error.

Steps to reproduce

or if you are running standard examples, please provide the commands you have run that lead to the error.

What have you tried to solve it?