add simple static mode loading
test=develop

1. bind trt input and output to fluid tensors

BUG: After continuing to input different data, the output cannot be aligned
test=develop

This reverts commit 0446220e.

Reason:

Rerun failed test hides flaky test.
Flaky test can be bugs, for example, race condition.
Test shouldn't be flaky, if a test is flaky, it should be fixed.

* CI: rerun failed tests.

* fix check style error.

We need to figure out if tensorrt
use row-major or col-major for tensor
layerout inorder to do conversion.

* Fix CPPLint issue in test_engine

* Fix CPPLint errors in operators/math

* Fix compilation