Add stuff for strong scaling measurements

2024-02-05 13:21:34 +01:00
parent 7e3778757c
commit fb08f0af77
6 changed files with 241 additions and 0 deletions
@@ -0,0 +1,77 @@
+import copy
+import json
+
+from dataclasses import dataclass
+from typing import Tuple
+
+@dataclass
+class Configuration:
+    nodes: int
+    tasks: int
+    gpus_per_node: int
+    blockcount: Tuple[int, int, int]
+    blocksize: Tuple[int, int, int]
+
+    def get_domain_size(self) -> int:
+        return self.blockcount[0] * self.blocksize[0] * self.blockcount[1] * self.blocksize[1] * self.blockcount[2] * self.blocksize[2]
+
+configurations = [
+    Configuration( 1,   12,   1, ( 1,  4, 3), (400, 100, 134)),
+    Configuration( 1,   24,   2, ( 2,  4, 3), (200, 100, 134)),
+    Configuration( 1,   48,   4, ( 4,  4, 3), (100, 100, 134)),
+    Configuration( 2,   96,   4, ( 4,  4, 6), (100, 100,  67)),
+    Configuration( 4,  192,   4, ( 4,  8, 6), (100,  50,  67)),
+    Configuration( 8,  384,   4, ( 8,  8, 6), ( 50,  50,  67)),
+    Configuration(16,  768,   4, ( 8, 16, 6), ( 50,  25,  67)),
+    Configuration(32, 1536,   4, (16, 16, 6), ( 25,  25,  67))
+]
+
+with open("templates/spheroid.json") as template_file:
+    template = json.load(template_file)
+
+for c in configurations:
+    print(c)
+    assert(c.get_domain_size() == configurations[0].get_domain_size())
+
+    nastja_config = copy.deepcopy(template)
+
+    nastja_config["Geometry"]["blockcount"] = c.blockcount
+    nastja_config["Geometry"]["blocksize"] = c.blocksize
+
+    label = f"{c.nodes:02}"
+
+    if c.gpus_per_node < 4:
+        label += f"g{c.gpus_per_node}"
+
+    with open(f"configs/measurements/strong/spheroid_{label}.json", "w") as config_file:
+        json.dump(nastja_config, config_file, indent=2)
+
+    batch_config = f"""#!/usr/bin/env bash
+
+#SBATCH --job-name=strong-{label}
+#SBATCH --account=hkf6
+#SBATCH --partition=booster
+#SBATCH --nodes={c.nodes}
+#SBATCH --ntasks={c.tasks}
+# Counted per node
+#SBATCH --gres=gpu:{c.gpus_per_node}
+#SBATCH --time=06:00:00
+#SBATCH --output=logs/strong-{label}-%A_%a.log
+#SBATCH --error=logs/strong-{label}-%A_%a.log
+#SBATCH --array=1-5
+
+SOURCE_DIR=/p/project/cellsinsilico/paulslustigebude
+OUTPUT_DIR="/p/scratch/cellsinsilico/paul/nastja-out/strong-{label}-${{SLURM_ARRAY_TASK_ID}}"
+
+echo "${{OUTPUT_DIR}}"
+
+mkdir -p "${{OUTPUT_DIR}}"
+source "${{SOURCE_DIR}}/activate-nastja-modules"
+
+srun --unbuffered "${{SOURCE_DIR}}/nastja/build-cuda/nastja" \\
+  -c "${{SOURCE_DIR}}/ma/experiments/configs/measurements/strong/spheroid_{c.nodes:02}.json" \\
+  -o "${{OUTPUT_DIR}}"
+"""
+
+    with open(f"batch/measurements/strong/strong-{label}", "w", encoding="utf8") as batch_config_file:
+        batch_config_file.write(batch_config)