diff --git a/_sources/olcf-workflow.rst.txt b/_sources/olcf-workflow.rst.txt index 615a44f..3b78ff6 100644 --- a/_sources/olcf-workflow.rst.txt +++ b/_sources/olcf-workflow.rst.txt @@ -541,7 +541,7 @@ Setup the environment: .. prompt:: bash - module load PrgEnv-cray + module load PrgEnv-gnu module load cray-mpich/8.1.27 module load craype-accel-amd-gfx90a module load amd-mixed/5.6.0 @@ -559,16 +559,36 @@ Startup an interactive session: salloc -A ast106 -J mz -t 0:30:00 -p batch -N 1 -This will automatically log you onto the compute now. Now set the following -environment variables: +This will automatically log you onto the compute now. + +.. note:: + + It's a good idea to do: + + .. prompt:: bash + + module restore + + and then reload *the same* modules used for compiling in the interactive shell. + +Now set the following environment variables: .. prompt:: bash export HIP_ENABLE_DEFERRED_LOADING=0 - export AMD_LOG_LEVEL=3 export AMD_SERIALIZE_KERNEL=3 export AMD_SERIALIZE_COPY=3 +.. note:: + + You can also set + + .. prompt:: bash + + export AMD_LOG_LEVEL=3 + + to get *a lot* of information about the GPU calls. + Run the debugger: .. prompt:: bash diff --git a/olcf-workflow.html b/olcf-workflow.html index f3d37dd..1c83143 100644 --- a/olcf-workflow.html +++ b/olcf-workflow.html @@ -618,7 +618,7 @@
Debugging is done with rocgdb
. Here’s a workflow that works:
Setup the environment:
-module load PrgEnv-cray
+module load PrgEnv-gnu
module load cray-mpich/8.1.27
module load craype-accel-amd-gfx90a
module load amd-mixed/5.6.0
@@ -627,13 +627,24 @@ Debuggingmake USE_HIP=TRUE TEST=TRUE USE_MPI=FALSE -j 4
Startup an interactive session:
salloc -A ast106 -J mz -t 0:30:00 -p batch -N 1
-
This will automatically log you onto the compute now. Now set the following
-environment variables:
+
This will automatically log you onto the compute now.
+Note
+It’s a good idea to do:
+module restore
+
and then reload the same modules used for compiling in the interactive shell.
+Now set the following environment variables:
export HIP_ENABLE_DEFERRED_LOADING=0
-export AMD_LOG_LEVEL=3
export AMD_SERIALIZE_KERNEL=3
export AMD_SERIALIZE_COPY=3
-
Run the debugger:
+Note
+You can also set
+export AMD_LOG_LEVEL=3
+
to get a lot of information about the GPU calls.
+Run the debugger:
rocgdb ./Castro2d.hip.x86-trento.HIP.ex
Set the following inside of the debugger: