Add the newly added "run_frequency" parameter to the README.md.

PiperOrigin-RevId: 343989439
Change-Id: Id4b611d4cad49a87db630250cccf6936fa9fc624
This commit is contained in:
Chao Mei 2020-11-23 22:04:21 -08:00 committed by TensorFlower Gardener
parent 93d37e183b
commit 6e10cbf9e2

View File

@ -34,6 +34,12 @@ and the following optional parameters:
* `run_delay`: `float` (default=-1.0) \
The delay in seconds between subsequent benchmark runs. Non-positive values
mean use no delay.
* `run_frequency`: `float` (default=-1.0) \
The frequency of running a benchmark run as the number of prorated runs per
second. If the targeted rate per second cannot be reached, the benchmark
would start the next run immediately, trying its best to catch up. If set,
this will override the `run_delay` parameter. A non-positive value means
there is no delay between subsequent runs.
* `enable_op_profiling`: `bool` (default=false) \
Whether to enable per-operator profiling measurement.
* `profiling_output_csv_file`: `str` (default="") \