add gnn dataset download script

script/get-dataset-mlperf-inference-gnn/_cm.yaml

@@ -0,0 +1,46 @@
+alias: get-dataset-mlperf-inference-gnn
+automation_alias: script
+automation_uid: 5b4e0237da074764
+cache: true
+tags:
+- get
+- dataset
+- mlperf
+- gnn
+- icbh
+- inference
+uid: 824e61316c074253
+# new_env_keys:
+input_mapping:
+  out_path: CM_IGBH_DATASET_OUT_PATH
+deps:
+  - tags: mlperf,inference,source
+    names:
+      - inference-src
+  - tags: get,python
+    names:
+      - get-python
+variations:
+  debug:
+    default: true
+    group: dataset-type
+    env:
+      CM_IGBH_DATASET_TYPE: debug
+      CM_IGBH_DATASET_SIZE: tiny
+  full:
+    group: dataset-type
+    env:
+      CM_IGBH_DATASET_TYPE: full
+      CM_IGBH_DATASET_SIZE: full
+  glt:
+    env:
+      CM_IGBH_GRAPH_COMPRESS: yes
+  csc:
+    group: compressed-layout
+    default: true
+    env:
+      CM_IGBH_GRAPH_COMPRESS_LAYOUT: csc
+  csr:
+    group: compressed-layout
+    env:
+      CM_IGBH_GRAPH_COMPRESS_LAYOUT: csr

script/get-dataset-mlperf-inference-gnn/customize.py

@@ -0,0 +1,49 @@
+from cmind import utils
+import os
+
+def preprocess(i):
+
+    os_info = i['os_info']
+
+    env = i['env']
+
+    if os_info['platform'] == "windows":
+        return {'return':1, 'error': 'Script not supported in windows yet!'}
+
+    print("Using MLCommons Inference source from '" + env['CM_MLPERF_INFERENCE_SOURCE'] +"'")
+
+    #run cmd
+    run_cmd = ""
+    graph_folder = os.path.join(env['CM_MLPERF_INFERENCE_SOURCE'], 'graph', 'R-GAT')
+
+    download_loc = env.get('CM_IGBH_DATASET_OUT_PATH', os.getcwd())
+
+    run_cmd += f"cd {graph_folder} "
+    x_sep = " && "
+
+    # download the model
+    if env['CM_IGBH_DATASET_TYPE'] == "debug":
+        run_cmd += x_sep + env['CM_PYTHON_BIN_WITH_PATH'] + f" tools/download_igbh_test.py --target-path {download_loc}"
+    else:
+        run_cmd += x_sep + f"./tools/download_igbh_full.sh {download_loc}"
+
+    # split seeds
+    run_cmd += x_sep + f"{env['CM_PYTHON_BIN_WITH_PATH']} tools/split_seeds.py --path {download_loc} --dataset_size {env['CM_IGBH_DATASET_SIZE']}"
+
+    # compress graph(for glt implementation)
+    if env.get('CM_IGBH_GRAPH_COMPRESS', '') == "yes":
+        run_cmd += x_sep + f"{env['CM_PYTHON_BIN_WITH_PATH']} tools/compress_graph.py --path {download_loc} --dataset_size {env['CM_IGBH_DATASET_SIZE']} --layout {env['CM_IGBH_GRAPH_COMPRESS_LAYOUT']}"
+
+    env['CM_RUN_CMD'] = run_cmd
+
+    return {'return':0}
+
+def postprocess(i):
+
+    env = i['env']
+
+    env['CM_IGBH_DATASET_PATH'] = env.get('CM_IGBH_DATASET_OUT_PATH', os.getcwd())
+
+    print(f"Path to the IGBH dataset: {os.path.join(env['CM_IGBH_DATASET_PATH'], env['CM_IGBH_DATASET_SIZE'])}")
+
+    return {'return':0}

script/get-dataset-mlperf-inference-gnn/run.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+#CM Script location: ${CM_TMP_CURRENT_SCRIPT_PATH}
+
+#To export any variable
+#echo "VARIABLE_NAME=VARIABLE_VALUE" >>tmp-run-env.out
+
+#${CM_PYTHON_BIN_WITH_PATH} contains the path to python binary if "get,python" is added as a dependency
+
+
+
+function exit_if_error() {
+  test $? -eq 0 || exit $?
+}
+
+function run() {
+  echo "Running: "
+  echo "$1"
+  echo ""
+  eval "$1"
+  exit_if_error
+}
+
+run "$CM_RUN_CMD"