Skip to content

Commit 60dcf7d

Browse files
nicolemarsagliaNicole Marsaglia
andauthored
Add rocm-smi to GPU docs (#1102)
* Add rocm-smi to gpu docs * spellcheck sampling --------- Co-authored-by: Nicole Marsaglia <marsagli@uoreogn.edu>
1 parent 0e4ad64 commit 60dcf7d

2 files changed

Lines changed: 16 additions & 3 deletions

File tree

src/docs/sphinx/Actions/Binning.rst

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -35,8 +35,8 @@ simulation codes, regardless of the underlying mesh representation.
3535

3636
Sampling and Aggregation
3737
------------------------
38-
When specifying the number of bins on an axis, there will always be over smapling or undersampling.
39-
During spatial binning, each zone is placed into a bin based on it centriod, and as with all
38+
When specifying the number of bins on an axis, there will always be over sampling or undersampling.
39+
During spatial binning, each zone is placed into a bin based on its centriod, and as with all
4040
binning, this is subject to over sampling or under sampling.
4141

4242

@@ -62,7 +62,7 @@ example.
6262

6363
An example of spatial over sampling.
6464

65-
When oversamping data, the default value of an empy bin is 0. That said, the default empty
65+
When oversampling data, the default value of an empty bin is 0. That said, the default empty
6666
value can be overridden by an option named parameter, e.g., `empty_bin_val=100`.
6767
This is often useful when the default value is part of the data range, and setting
6868
the empty bin value to something known, allows the user to filter out empty bins

src/docs/sphinx/GPU_notes.rst

Lines changed: 13 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -16,6 +16,19 @@ By default, each CUDA capable GPU device is queried, and a rank is assigned a de
1616
Collisions could result in a run-time failure or significant delays.
1717
This default behavior can be overridden. Please see the Ascent options for more details.
1818

19+
Using ROCm-SMI on AMD GPUs
20+
--------------------------
21+
ROCm-SMI stands for ROCm System Management Interface and provides an interfaces for applications and users to monitor and control GPU applicatoins.
22+
23+
ROCm-SMI can be used to verify GPU usage.
24+
This is done by launching your application and then using ROCm-SMI on the same node to monitor the running job.
25+
26+
The following call will monitor the usage of GPUs every tenth of a second:
27+
28+
.. code-block:: sh
29+
30+
watch -n 0.1 rocm-smi
31+
1932
Using RocProf on AMD GPUs
2033
-------------------------
2134
RocProf is a command line tool provided by ROCm that is implemented on top of the rocProfiler and rocTracer APIs.

0 commit comments

Comments
 (0)