Updated docs

Samsung · Aug 24, 2020 · c6382f1 · c6382f1
1 parent 429d50a
commit c6382f1
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 2 deletions.
diff --git a/website/blog/2020-08-10-introducing-QA-Board.md b/website/blog/2020-08-10-introducing-QA-Board.md
@@ -47,7 +47,7 @@ QA-Board has become a key collaborative tool. Our main use-cases are:
 - **Visualizations**: everything can be compared, and thanks to the [many different types of visualizations](https://samsung.github.io/qaboard/docs/visualizations) (images/plots/text/html/video...), users can easily create the reports they need.
 - **Tuning**: QA-Board [distributes runs](https://samsung.github.io/qaboard/docs/celery-integration) to our cluster. Users can easily start tuning experiments that enable feature flags or tweak parameters. We've integrated [scikit-optimize](https://scikit-optimize.github.io/) for black-box optimization.
 - **Regression**: users can check the progress on various metrics, and when needed, identify which commit caused a regression.
-- **Performance engineering**: save [`rr`](https://rr-project.org/)/[`perf`](http://www.brendangregg.com/perf.html) recordings, view [flame graphs](http://www.brendangregg.com/flamegraphs.html) and track metrics for regressions.
+- **Performance engineering**: save [`rr`](https://rr-project.org/)/[`perf`](http://www.brendangregg.com/perf.html) recordings, view [flame graphs](http://www.brendangregg.com/flamegraphs.html), [benchmark drivers](https://github.com/arthur-flam/sysbench-qaboard), and track metrics for regressions.
 
 > Here are some screenshots:
 

diff --git a/website/docs/inputs.md b/website/docs/inputs.md
@@ -15,10 +15,13 @@ Depending on your domain, those will be different. Here are some examples:
 | Domain                 | Input            | Configuration         | Output                             | Metric                            |
 |------------------------|------------------|-----------------------|------------------------------------|-----------------------------------|
 | **Image processing**   | image            | feature flag & params | transformed image, debug data...   | SNR, sharpness, color accuracy... |
-| **Cloud server choice**| integration test | instance type     |                                    | cost, throughput...               |
+| **Cloud server choice**| integration test | instance type         |                                    | cost, throughput...               |
 | **Machine learning**   | database/sample  | hyperparameters       | convergence plots / individual results| loss                           |
 |**Optimization research**| problem         | model type, solver    | solution                           | cost, runtime...                  |
 |**Software performance**| unit test        | feature flag, platform| `perf` recordings, benchmark histograms| runtime, memory, latency, IPC, throughput...|
+|**Hardware/driver perf**| hardware/unit-test | [sysbench config](https://github.com/arthur-flam/sysbench-qaboard)    | latency histogram                           | ops/s, runtime...                  |
+
+
 
 ## How QA-Board looks for inputs
 To make things simple, QA-Board expects that your inputs are existing **paths**.