Merge pull request #13 from EESSI/gpu

Make sure to give EB4 CUDA options it understands, don't include `accel/` in `gpu_arch`

Author: boegel

.github/workflows/docs.yml

@@ -36,16 +36,27 @@ jobs:
           # Set CPU override for the stack to query
           export EESSI_ARCHDETECT_OPTIONS_OVERRIDE="x86_64/intel/icelake"
           # Set GPU overrides for the stack to query (we have no GPU, so also override the GPU check)
-          export EESSI_ACCELERATOR_TARGET_OVERRIDE="accel/nvidia/cc90"
           export EESSI_OVERRIDE_GPU_CHECK=1
           # First do 2023.06 for EB 4
+          export EESSI_ACCELERATOR_TARGET_OVERRIDE="accel/nvidia/cc80"  # Stick to 8.0 for EB4 as options for 9.0 set by EESSI-extend are not understood there
           ( module load EESSI/2023.06 && module load EasyBuild/4 && module load EESSI-extend && python scripts/generate_data_files.py --eessi-version=2023.06 ) &
+          pid1=$!
           # then 2023.06 for EB 5
+          export EESSI_ACCELERATOR_TARGET_OVERRIDE="accel/nvidia/cc90"
           ( module load EESSI/2023.06 && module load EasyBuild/5 && module load EESSI-extend && python scripts/generate_data_files.py --eessi-version=2023.06 ) &
+          pid2=$!
           # then 2025.06 for EB 5 (does not have EB4)
+          export EESSI_ACCELERATOR_TARGET_OVERRIDE="accel/nvidia/cc90"
           ( module load EESSI/2025.06 && module load EasyBuild/5 && module load EESSI-extend && python scripts/generate_data_files.py --eessi-version=2025.06 ) &
+          pid3=$!
+          wait $pid1 || fail=1
+          wait $pid2 || fail=2
+          wait $pid3 || fail=3
+          if [ $fail -ne 0 ]; then
+            echo "One or more jobs failed (at least job $fail)"
+            exit 1
+          fi
           # Merge all these results together
-          wait
           python scripts/merge_data_files.py out.yaml eessi*.yaml
           mv out.yaml docs/data/eessi_software_metadata.yaml
           # Generate json data files and markdown index/description for them

scripts/process_eessi_software_metadata.py

@@ -103,7 +103,8 @@ def get_software_information_by_filename(file_metadata, original_path=None, tool
                     accel_substituted_modulefile = substituted_modulefile.replace(detected_accel_arch, accel_arch)
                     found = subprocess.run(["grep", "-q", accel_substituted_modulefile, substituted_spider_cache]).returncode == 0
                     if found:
-                        base_version_dict["gpu_arch"][arch].append(accel_arch)
+                        # Let's not include the "accel/" part of the accel_arch 
+                        base_version_dict["gpu_arch"][arch].append(accel_arch.replace("accel/", "", 1))
                     else:
                         print(f"No module {accel_substituted_modulefile}...not adding software for architecture {arch}/{accel_arch}")
                         continue