Add scripts for timing stuff and strong scaling configs

experiments/scripts/gen/strong.py

@@ -1,29 +1,51 @@
 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]
+from toolkit import Configuration
 
-    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]
+SIZE_X = 400
+SIZE_Y = 400
+SIZE_Z = 400
+
+def make_config(gpus: int, blockcount: Tuple[int, int, int]) -> Configuration:
+    assert gpus % 4 == 0
+    assert SIZE_X % blockcount[0] == 0
+    assert SIZE_Y % blockcount[1] == 0
+    assert SIZE_Z % blockcount[2] == 0
+    assert blockcount[0] * blockcount[1] * blockcount[2] == gpus
+
+    return Configuration(
+        gpus // 4,
+        gpus,
+        4,
+        blockcount,
+        (SIZE_X // blockcount[0], SIZE_Y // blockcount[1], SIZE_Z // blockcount[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))
+    Configuration(1, 1, 1, (1, 1, 1), (400, 400, 400)),
+    Configuration(1, 2, 2, (1, 1, 2), (400, 400, 200)),
+    Configuration(1, 2, 2, (1, 2, 1), (400, 200, 400)),
+    Configuration(1, 2, 2, (2, 1, 1), (200, 400, 400)),
+    make_config(4, (1, 1, 4)),
+    make_config(4, (1, 4, 1)),
+    make_config(4, (4, 1, 1)),
+    make_config(4, (1, 2, 2)),
+    make_config(4, (2, 1, 2)),
+    make_config(4, (2, 2, 1)),
+    make_config(8, (2, 2, 2)),
+    make_config(8, (1, 2, 4)),
+    make_config(16, (1, 4, 4)),
+    make_config(16, (2, 2, 4)),
+    make_config(32, (2, 4, 4)),
+    make_config(64, (4, 4, 4)),
+    make_config(128, (4, 4, 8)),
+    make_config(256, (4, 8, 8)),
+    make_config(512, (8, 8, 8)),
+    make_config(1024, (8, 8, 16)),
+    make_config(2048, (8, 16, 16))
 ]
 
 with open("templates/spheroid.json") as template_file:
@@ -38,10 +60,7 @@ for c in configurations:
     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}"
+    label = c.get_label()
 
     with open(f"configs/measurements/strong/spheroid_{label}.json", "w") as config_file:
         json.dump(nastja_config, config_file, indent=2)
@@ -55,7 +74,7 @@ for c in configurations:
 #SBATCH --ntasks={c.tasks}
 # Counted per node
 #SBATCH --gres=gpu:{c.gpus_per_node}
-#SBATCH --time=06:00:00
+#SBATCH --time=00:30:00
 #SBATCH --output=logs/strong-{label}-%A_%a.log
 #SBATCH --error=logs/strong-{label}-%A_%a.log
 #SBATCH --array=1-5
@@ -63,13 +82,13 @@ for c in configurations:
 SOURCE_DIR=/p/project/cellsinsilico/paulslustigebude
 OUTPUT_DIR="/p/scratch/cellsinsilico/paul/nastja-out/strong-{label}-${{SLURM_ARRAY_TASK_ID}}"
 
-echo "${{OUTPUT_DIR}}"
+echo "outdir is ${{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" \\
+  -c "${{SOURCE_DIR}}/ma/experiments/configs/measurements/strong/spheroid_{label}.json" \\
   -o "${{OUTPUT_DIR}}"
 """
 

experiments/scripts/gen/toolkit.py

@@ -0,0 +1,16 @@
+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]
+
+    def get_label(self) -> str:
+        return f"t{self.tasks:04}n{self.nodes:03}g{self.gpus_per_node}x{self.blockcount[0]}y{self.blockcount[1]}z{self.blockcount[2]}"