TMP TensorFlow benchmarking

In order to chart the performance of TensorFlow over time, there must be performance measurements made at regular intervals. These should also cover a range of use cases and machine capabilities to get the best possible coverage.

We will make use of the MLCommons infrastructure to run some of the tests from MLPerf Inference r1.1.

Usable benchmarks

These benchmarks have all been run on recent versions of TensorFlow

https://linaro.atlassian.net/wiki/spaces/TENS/pages/28867560422

https://linaro.atlassian.net/wiki/spaces/TENS/pages/28867560437

https://linaro.atlassian.net/wiki/spaces/TENS/pages/28867560463

Unusable benchmarks

These benchmarks have problems that prevent their use on recent versions of TensorFlow, or even, in one case, on any version.

https://linaro.atlassian.net/wiki/spaces/TENS/pages/28867560480

https://linaro.atlassian.net/wiki/spaces/TENS/pages/28867560493

https://linaro.atlassian.net/wiki/spaces/TENS/pages/28867560504