Add strong scaling GPU actions table

experiments/eval/Makefile

@@ -4,6 +4,9 @@ generate-batch-strong-cpu:
 generate-batch-strong-gpu:
 	python scripts/substitute.py strong-batch.j2 < strong-gpu.json
 
+generate-batch-strong-booster:
+	python scripts/substitute.py strong-batch.j2 < strong-booster.json
+
 clean-logs:
 	rm logs/*
 

experiments/eval/data/actions-normalized.csv

@@ -0,0 +1,4 @@
+label,BC:cells,BC:dynamicecm,Sweep:Cells,Sweep:DynamicECM,Sweep:DynamicECMDampers,Filling,Other
+CPU,0.04629667717328299,3.88243023434036,0.002164069189058585,82.18255346583861,13.842310640806883,0.005797982839735358,0.03844692981207934
+GPU,0.034897486509106485,41.227398706349675,13.180664898871365,22.432483220415783,19.749714111977486,1.9939606413394697,1.3808809345371023
+Booster,0.09128030041871667,42.736382370072874,12.260298369798207,22.36492489089858,16.070196185259338,4.364304866307413,2.1126130172448816

experiments/eval/data/actions.csv

@@ -0,0 +1,4 @@
+label,BC:cells,BC:dynamicecm,Sweep:Cells,Sweep:DynamicECM,Sweep:DynamicECMDampers,Other
+CPU,0.9047934333333334,75.87579921250001,0.04229322083333333,1606.12465625,270.5255006333333,0.8646950250000001
+GPU,0.11372260000000001,134.35027680000002,42.952648800000006,73.102122,64.3596162,10.9978052
+Booster,0.155221,72.67267939999999,20.848482800000003,38.0312728,27.327165999999995,11.013917200000002

experiments/eval/data/strong-booster.tsv

@@ -0,0 +1,9 @@
+label	nodes	tasks	mean_time	std_time	speedup	speedup_std	speedup_error
+1	1	1	161.08257980000002	1.0725827874500897	1.0	0.0066585895804611986	0.004614167168572558
+1	1	2	109.2771463	1.3498701967829918	1.474073813730255	0.018208823861030076	0.012618071172974463
+1	1	4	94.5763083	2.921107861707173	1.7032022363258181	0.052605536545441436	0.03645377698685362
+2	2	8	75.06436665	5.345617315509918	2.145926049720424	0.15281950626022228	0.10589851499069955
+4	4	16	42.842002025	1.5314070839490197	3.759921856733072	0.13440013758310768	0.09313454370387199
+8	8	32	16.40522446875	4.395440141154071	9.818980539208297	2.6307924825691393	1.823046180232846
+16	16	64	9.361684956249999	5.010216046116417	17.206579857449583	9.208671612370724	6.381283859970849
+32	32	128	5.214438346875	0.113661681579046	30.891645290338204	0.6733604113945479	0.4666149588180552

experiments/eval/data/strong-cpu.tsv

@@ -1,10 +1,10 @@
-label	nodes	mean_time	std_time	speedup	speedup_std
+label	nodes	tasks	mean_time	std_time	speedup	speedup_std	speedup_error
-1	1	1132.1093720291667	18.428644622186628	1.0	0.016278148629010596
+1	1	48	1953.3832839708334	14.087268287606769	1.0	0.007211727674340593	0.004711662080569187
-2	2	619.9614289104168	7.890810670766857	1.8260964621925766	0.029725469622481192
+2	2	96	1046.3540047312501	6.0880471399828595	1.866847429396085	0.010861959816590314	0.007096480413505672
-4	4	348.657283046875	3.3739994706945122	3.247054993762918	0.052856043795043856
+4	4	192	566.0709002166666	5.005298021298787	3.4507749527897755	0.030512356378918384	0.019934739500893344
-8	8	200.79244575312498	1.259910347938215	5.63820699420684	0.09177957145282603
+8	8	384	318.1225953708333	9.706195475255436	6.1403475024896865	0.18734731205020752	0.12240024387280224
-16	16	111.37033198671875	0.3943541234366863	10.16526889911915	0.16547175799372044
+16	16	768	178.56471887994792	9.393026972005948	10.939357428631386	0.5754422263707719	0.375955587895571
-32	32	65.69918741145833	0.43464214827532205	17.231710415823503	0.28050034328084494
+32	32	1536	99.82801128216144	1.4413062581268035	19.56748670921274	0.28251330150299214	0.18457535698195485
-64	64	38.56257490957031	0.12227397957602136	29.35772247273364	0.4778893698204027
+64	64	3072	55.75610567220052	1.0303316198245824	35.034428255357376	0.6474103379133267	0.42297475410337343
-128	128	21.433497051595047	0.14016683538819355	52.81962944749218	0.8598057786755426
+128	128	6144	31.589132888118492	0.32226687791817415	61.83719226764697	0.6308523555205254	0.41215687227340997
-256	256	13.247708324598525	0.030540850807946187	85.45699711149668	1.3910817003698723
+256	256	12288	19.11704500200738	0.18528928846832715	102.18018965617955	0.9903672160087601	0.6470399144590566

experiments/eval/data/strong-gpu-actions.csv

@@ -0,0 +1,9 @@
+label,BC:cells,BC:dynamicecm,Sweep:Cells,Sweep:DynamicECM,Sweep:DynamicECMDampers,Filling,Other
+1,0.034897486509106485,41.227398706349675,13.180664898871365,22.432483220415783,19.749714111977486,1.9939606413394697,1.3808809345371023
+2,0.7137918070198439,50.7137377526309,8.923981074147767,19.35772833011394,17.571497161475467,1.320924803923136,1.3983390706889622
+4,0.6647403410134337,58.291944402330074,7.087118055335309,16.67352093599457,15.236952119238136,1.092645293437499,0.953078852650984
+8,0.6788278363464717,65.05900206274784,5.2089254465999275,14.249993130938188,13.176763096049008,0.7851584656500297,0.8413299616685318
+16,1.441574901760373,61.1245906198054,4.832237599492141,16.029377636605524,14.996293924006913,0.716990077435801,0.858935240893841
+32,3.3736940900007966,47.94830950907802,5.622259685491874,21.238716402604393,19.97281149065964,0.8196124452570666,1.0245963769081996
+64,6.284545018581091,45.28808866195176,4.502683326147901,21.66574860147326,20.522789117514915,0.6460791296539419,1.0900661446771265
+128,11.788574344478201,40.04977497065291,3.2677482351392375,22.1995263401806,21.209134936528987,0.4598839494487746,1.0253572235712836

experiments/eval/data/strong-gpu.tsv

@@ -1,8 +1,9 @@
-label	nodes	tasks	mean_time	std_time	speedup	speedup_std
+label	nodes	tasks	mean_time	std_time	speedup	speedup_std	speedup_error
-1	1	1	157.5217688	0.5311809049610176	1.0	0.003372111099358209
+1	1	1	316.56674059999995	1.3298279828832311	1.0	0.004200782370133899	0.002910993666206366
-1	1	2	120.15237200000001	0.299200156243067	1.3110167213344732	0.004420894037456185
+1	1	2	239.7297573	1.3705192585818793	1.3205150005797797	0.007549297425250635	0.00523139621453709
-1	1	4	75.69762635	0.5769735213369493	2.0809340582447473	0.007017140834839633
+1	1	4	150.86725470000002	1.463195211854327	2.098313124537819	0.020350616990413285	0.014102258089746373
-2	2	8	52.110670325	0.940887445857671	3.022831366735062	0.010193323203255446
+2	2	8	103.758313	1.3959932139830615	3.051001230137579	0.041049019495199714	0.028445519245192213
-4	4	16	28.215493675000005	0.5598524922936691	5.582811012077745	0.018825858979446598
+4	4	16	56.423368849999996	0.8293394846143929	5.610560784514376	0.08246688711191473	0.057146637198176795
-8	8	32	12.422501156249998	0.31940690526235005	12.680358554102268	0.04275957782413007
+8	8	32	24.168551143749998	0.5503559531334744	13.09829202078025	0.29826872726631265	0.20668968287257275
-16	16	64	7.70770194375	0.04068644910316383	20.43693048194875	0.06891560011499148
+16	16	64	15.05716248125	0.04648043269670786	21.024329185144023	0.06490066896072916	0.044973869063161365
+32	32	128	9.9111531140625	0.08848604506395903	31.940455056721632	0.28516203039001964	0.19760720531719309

experiments/eval/data/weak-booster.tsv

@@ -0,0 +1,9 @@
+nodes	tasks	mean_time	std_time	efficiency	efficiency_error
+1	1	41.98463099999999	1.4067920862965122	1.0	0.023219381860496473
+1	2	49.85189340000001	1.7669363566083227	0.8421872899214694	0.020685165974491628
+1	4	59.9694977	2.209151778903949	0.7000997608822725	0.01787171173813342
+2	8	72.810012625	0.5538313058789631	0.5766326565034021	0.003039461920431096
+4	16	84.718001525	5.20969191162485	0.4955809892140865	0.021118450727088397
+8	32	87.22569569999999	1.7018797711775082	0.4813332890390463	0.0065079080866405825
+16	64	85.36740952500001	1.0197522041876155	0.49181099946232654	0.004071100890302765
+32	128	87.5995021046875	0.8707125543332932	0.47927933368645675	0.003301208459097849

experiments/eval/data/weak-cpu.tsv

@@ -0,0 +1,10 @@
+nodes	tasks	mean_time	std_time	efficiency	efficiency_error
+1	48	234.09125610833334	4.9756238110995765	1.0	0.013886639526655382
+2	96	234.09269640000002	1.9886350551995884	0.9999938473447108	0.005550081636855162
+4	192	239.06532950520833	1.8931447841474947	0.9791936647310181	0.005066063671757703
+8	384	241.32357499479167	0.977728668984766	0.9700306160033705	0.0025676679349660694
+16	768	260.8008324059896	12.802824235961744	0.8975863073317291	0.028787758154736998
+32	1536	266.59983470546877	13.970338204797093	0.8780622702446538	0.03006125980502309
+64	3072	281.61153985800786	25.95560834859075	0.8312559074332151	0.05005532970709546
+128	6144	293.4177162058594	10.8076489888669	0.7978088683101088	0.019198998510810975
+256	12288	310.9775802693196	14.459893325743863	0.7527592693518308	0.022867934404056486

experiments/eval/data/weak-gpu.tsv

@@ -0,0 +1,9 @@
+nodes	tasks	mean_time	std_time	efficiency	efficiency_error
+1	1	60.658062599999994	1.8711952545625232	1.0	0.021376748626269895
+1	2	80.6903592	1.1554429061827625	0.751738661240214	0.007459415624087278
+1	4	89.01234124999999	1.3979557323025515	0.6814567704677693	0.00741639040919915
+2	8	101.357940575	4.784240687736861	0.5984539766286584	0.01957478845779047
+4	16	106.2530252	1.5044057675724636	0.5708831582519497	0.005601211794070455
+8	32	113.70197445	2.069642901549501	0.5334829310873062	0.006729131548114211
+16	64	119.22770070624999	0.7600051865549382	0.5087581345667959	0.00224730403456563
+32	128	121.8124414140625	0.5170666166834136	0.4979627852118346	0.0014647476739746731

experiments/eval/scripts/build-pgf-datafiles.py

@@ -3,6 +3,7 @@
 
 import argparse
 import json
+import math
 
 
 def print_table(data, spec):
@@ -19,18 +20,33 @@ def print_table(data, spec):
 if __name__ == "__main__":
     p = argparse.ArgumentParser(description="Turn files generated by timing.py into pgf datafiles")
     p.add_argument("timing_file")
+    p.add_argument("--weak", action="store_true")
     args = p.parse_args()
 
     with open(args.timing_file, "r", encoding="utf8") as f:
         jobs = json.load(f)
 
-    scaling_spec = {
+    if not args.weak:
-        "label": lambda job: job["accounting"][0]["nodes"]["count"],
+        scaling_spec = {
-        "nodes": lambda job: job["accounting"][0]["nodes"]["count"],
+            "label": lambda job: job["accounting"][0]["nodes"]["count"],
-        "tasks": lambda job: job["accounting"][0]["tasks"]["count"],
+            "nodes": lambda job: job["accounting"][0]["nodes"]["count"],
-        "mean_time": lambda job: job["means"]["TimeStep"],
+            "tasks": lambda job: job["accounting"][0]["tasks"]["count"],
-        "std_time": lambda job: job["stds"]["TimeStep"],
+            "mean_time": lambda job: job["means"]["TimeStep"],
-        "speedup": lambda job: jobs[0]["means"]["TimeStep"] / job["means"]["TimeStep"],
+            "std_time": lambda job: job["stds"]["TimeStep"],
-        "speedup_std": lambda job: jobs[0]["stds"]["TimeStep"] / job["means"]["TimeStep"],
+            "speedup": lambda job: jobs[0]["means"]["TimeStep"] / job["means"]["TimeStep"],
-    }
+            # Standard deviation scaled to speedup
+            "speedup_std": lambda job: (jobs[0]["means"]["TimeStep"] / job["means"]["TimeStep"]) * (job["stds"]["TimeStep"] / job["means"]["TimeStep"]),
+            # 95% confidence interval
+            "speedup_error": lambda job: (jobs[0]["means"]["TimeStep"] / job["means"]["TimeStep"]) * (job["stds"]["TimeStep"] / job["means"]["TimeStep"]) / math.sqrt(len(jobs)) * 1.96,
+        }
+    else:
+        scaling_spec = {
+            "nodes": lambda job: job["accounting"][0]["nodes"]["count"],
+            "tasks": lambda job: job["accounting"][0]["tasks"]["count"],
+            "mean_time": lambda job: job["means"]["TimeStep"],
+            "std_time": lambda job: job["stds"]["TimeStep"],
+            "efficiency": lambda job: jobs[0]["means"]["TimeStep"] / job["means"]["TimeStep"],
+            "efficiency_error": lambda job: (jobs[0]["means"]["TimeStep"] / job["means"]["TimeStep"]) * (job["stds"]["TimeStep"] / job["means"]["TimeStep"]) / math.sqrt(len(jobs)) * 1.96,
+        }
+
     print_table(jobs, scaling_spec)

experiments/eval/scripts/generate-strong-booster-configs.py

@@ -0,0 +1,34 @@
+#!/usr/bin/env python
+
+import copy
+import json
+
+from pathlib import Path
+
+SIZE = [384, 384, 384]
+
+with (Path(__file__).parent.parent / "templates" / "strong-booster.json").open(encoding="utf8") as f:
+    template = json.load(f)
+
+configs = [
+    [  1,  1,  1],
+    [  1,  1,  2],
+    [  1,  2,  2],
+    [  2,  2,  2],
+    [  2,  2,  4],
+    [  2,  4,  4],
+    [  4,  4,  4],
+    [  4,  4,  8],
+]
+
+out_path = Path(__file__).parent.parent / "generated" / "config"
+
+for c in configs:
+    nc = copy.deepcopy(template)
+    nc["Geometry"]["blockcount"] = c
+    nc["Geometry"]["blocksize"] = [bs // bc for bc, bs in zip(c, SIZE)]
+
+    nc_out_path = out_path / f"strong-booster-{c[0]:02}-{c[1]:02}-{c[2]:02}.json"
+    print(f"Dumping {(c[0] * c[1] * c[2])} to {nc_out_path}")
+    with nc_out_path.open("w", encoding="utf8") as f:
+        json.dump(nc, f)

experiments/eval/scripts/generate-weak-configs.py

@@ -0,0 +1,207 @@
+#!/usr/bin/env python
+
+
+import jinja2
+import json
+import sys
+
+
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Tuple
+
+
+SIZE = (192, 192, 192)
+
+
+templates_env = jinja2.Environment(
+    loader=jinja2.FileSystemLoader(Path(__file__).parent.parent / "templates"),
+    autoescape=jinja2.select_autoescape()
+)
+        
+
+@dataclass
+class Experiment:
+    job_name: str
+    account: str
+    partition: str
+    nastja_binary_path: str
+    nodes: int
+    tasks: int
+    num_blocks: Tuple[int, int, int]
+    domain_scale: Tuple[int, int, int]
+    time: str = "00:15:00"
+    extra_sbatch_line: str = ""
+    logfile_path: str = "/p/project/cellsinsilico/paulslustigebude/ma/experiments/eval/logs/%x-%A.%a"
+    config_path: str = "/p/project/cellsinsilico/paulslustigebude/ma/experiments/eval/generated/config/${SLURM_JOB_NAME}.json"
+    output_dir_path: str = "/p/scratch/cellsinsilico/paul/nastja-out/${SLURM_JOB_NAME}-${SLURM_ARRAY_JOB_ID}.${SLURM_ARRAY_TASK_ID}"
+
+    def get_config(self):
+        with (Path(__file__).parent.parent / "templates" / "weak.json").open(encoding="utf8") as f:
+            config = json.load(f)
+
+        size = (
+            SIZE[0] * self.domain_scale[0],
+            SIZE[1] * self.domain_scale[1],
+            SIZE[2] * self.domain_scale[2],
+        )
+        blocksize = (
+            size[0] // self.num_blocks[0],
+            size[1] // self.num_blocks[1],
+            size[2] // self.num_blocks[2],
+        )
+        config["Geometry"] = {
+            "blockcount": list(self.num_blocks),
+            "blocksize": list(blocksize),
+        }
+
+        cells_filling = [{
+            "box": [
+                [0, 0, 0],
+                list(size)
+            ],
+            "celltype": 0,
+            "component": 0,
+            "pattern": "const",
+            "seed": 0,
+            "shape": "cube",
+            "value": 0,
+        }]
+        for z in range(self.domain_scale[2]):
+            for y in range(self.domain_scale[1]):
+                for x in range(self.domain_scale[0]):
+                    cx = x * SIZE[0] + SIZE[0] // 2
+                    cy = y * SIZE[1] + SIZE[1] // 2
+                    cz = z * SIZE[2] + SIZE[2] // 2
+                    cells_filling.append({
+                        "shape": "sphere",
+                        "pattern": "voronoi",
+                        "count": 715,
+                        "radius": 38,
+                        "center": [cx, cy, cz],
+                        "box": [
+                            [cx - 38, cy - 38, cz - 38],
+                            [cx + 38, cy + 38, cz + 38]
+                        ],
+                        "celltype": 9,
+                        "seed": 758960,
+                    })
+
+        config["Filling"]["cells"] = cells_filling
+
+        return config
+    
+    def write_batch_file(self, out_path: Path):
+        t = templates_env.get_template("strong-batch.j2")
+        t.stream(
+            name=self.job_name,
+            account=self.account,
+            partition=self.partition,
+            nodes=self.nodes,
+            tasks=self.tasks,
+            extra_sbatch_line=self.extra_sbatch_line,
+            time=self.time,
+            logfile_path=self.logfile_path,
+            nastja_binary_path=self.nastja_binary_path,
+            config_path=self.config_path,
+            output_dir_path=self.output_dir_path,
+        ).dump(str(out_path))
+
+
+def make_cpu_ex(x: int, y: int, z: int) -> Experiment:
+    num_blocks = x * y * z
+    assert num_blocks % 48 == 0
+    num_nodes = num_blocks // 48
+
+    assert x % 4 == 0
+    assert y % 4 == 0
+    assert z % 3 == 0
+
+    return Experiment(
+        job_name=f"weak-cpu-{x:02}-{y:02}-{z:02}",
+        account="cellsinsilico",
+        partition="batch",
+        nastja_binary_path="/p/project/cellsinsilico/paulslustigebude/nastja/build-nocuda/nastja",
+        nodes=num_nodes,
+        tasks=num_blocks,
+        num_blocks=(x, y, z),
+        domain_scale=(x // 4, y // 4, z // 3),
+    )
+
+
+def make_gpu_ex(x: int, y: int, z: int) -> Experiment:
+    num_blocks = x * y * z
+    gpus_per_node = num_blocks if num_blocks <= 4 else 4
+    num_nodes = 1 if num_blocks <= 4 else num_blocks // 4
+
+    return Experiment(
+        job_name=f"weak-gpu-{x:02}-{y:02}-{z:02}",
+        account="cellsinsilico",
+        partition="gpus",
+        extra_sbatch_line=f"#SBATCH --gres=gpu:{gpus_per_node}",
+        nastja_binary_path="/p/project/cellsinsilico/paulslustigebude/nastja/build-cuda/nastja",
+        nodes=num_nodes,
+        tasks=num_blocks,
+        num_blocks=(x, y, z),
+        domain_scale=(x, y, z),
+    )
+
+
+def make_booster_ex(x: int, y: int, z: int) -> Experiment:
+    num_blocks = x * y * z
+    gpus_per_node = num_blocks if num_blocks <= 4 else 4
+    num_nodes = 1 if num_blocks <= 4 else num_blocks // 4
+
+    return Experiment(
+        job_name=f"weak-booster-{x:02}-{y:02}-{z:02}",
+        account="hkf6",
+        partition="booster",
+        extra_sbatch_line=f"#SBATCH --gres=gpu:{gpus_per_node}",
+        nastja_binary_path="/p/project/cellsinsilico/paulslustigebude/nastja/build-cuda/nastja",
+        nodes=num_nodes,
+        tasks=num_blocks,
+        num_blocks=(x, y, z),
+        domain_scale=(x, y, z),
+    )
+
+
+experiments = [
+    make_cpu_ex(4, 4, 3),
+    make_cpu_ex(4, 4, 6),
+    make_cpu_ex(4, 4, 12),
+    make_cpu_ex(4, 8, 12),
+    make_cpu_ex(8, 8, 12),
+    make_cpu_ex(8, 8, 24),
+    make_cpu_ex(8, 16, 24),
+    make_cpu_ex(16, 16, 24),
+    make_cpu_ex(16, 16, 48),
+
+    make_gpu_ex(1, 1, 1),
+    make_gpu_ex(1, 1, 2),
+    make_gpu_ex(1, 2, 2),
+    make_gpu_ex(2, 2, 2),
+    make_gpu_ex(2, 2, 4),
+    make_gpu_ex(2, 4, 4),
+    make_gpu_ex(4, 4, 4),
+    make_gpu_ex(4, 4, 8),
+
+    make_booster_ex(1, 1, 1),
+    make_booster_ex(1, 1, 2),
+    make_booster_ex(1, 2, 2),
+    make_booster_ex(2, 2, 2),
+    make_booster_ex(2, 2, 4),
+    make_booster_ex(2, 4, 4),
+    make_booster_ex(4, 4, 4),
+    make_booster_ex(4, 4, 8),
+]
+
+if __name__ == "__main__":
+    outdir = Path(__file__).parent.parent / "generated"
+
+    for e in experiments:
+        print(f"Generating config for {e.job_name}", file=sys.stderr)
+        config_path = (outdir / "config" / e.job_name).with_suffix(".json")
+        with config_path.open("w", encoding="utf8") as f:
+            json.dump(e.get_config(), f, indent=2)
+        print(f"Generating batch file for {e.job_name}", file=sys.stderr)
+        e.write_batch_file(outdir / "batch" / e.job_name)

experiments/eval/scripts/make-latex-table.py

@@ -0,0 +1,24 @@
+#!/usr/bin/env python
+
+
+import argparse
+import pandas
+
+
+def show_seconds(s: float) -> str:
+    return f"{s:.2f}s"
+
+
+if __name__ == '__main__':
+    p = argparse.ArgumentParser(description="Make a latex table from a timings tsv")
+    p.add_argument("timingfile")
+    p.add_argument("--weak", action="store_true")
+    args = p.parse_args()
+
+    df = pandas.read_csv(args.timingfile, sep="\t")
+
+    for i in range(len(df)):
+        if not args.weak:
+            print(f"{df['nodes'][i]} & {df['tasks'][i]} & {show_seconds(df['mean_time'][i])} & {show_seconds(df['std_time'][i])} & {df['speedup'][i]:.02f} & {df['speedup_error'][i]:.02f} \\\\")
+        else:
+            print(f"{df['nodes'][i]} & {df['tasks'][i]} & {show_seconds(df['mean_time'][i])} & {show_seconds(df['std_time'][i])} & {df['efficiency'][i]:.02f} & {df['efficiency_error'][i]:.02f} \\\\")

experiments/eval/scripts/timing-actions.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python
+
+
+import argparse
+import sys
+
+
+import timing
+
+
+ignore = ["TimeStep"]
+
+
+if __name__ == "__main__":
+    p = argparse.ArgumentParser()
+    p.add_argument("jobs", nargs="+")
+    p.add_argument("--normalize", action="store_true")
+    p.add_argument("--extra-columns", nargs="*")
+    args = p.parse_args()
+
+    columns = [
+        "BC:cells",
+        "BC:dynamicecm",
+        "Sweep:Cells",
+        "Sweep:DynamicECM",
+        "Sweep:DynamicECMDampers",
+    ] + (args.extra_columns or [])
+
+    dfs = dict()
+    labels = []
+    for label, jobid in [jobarg.split(":") for jobarg in args.jobs]:
+        jobs, excluded_array_indices = timing.get_jobs(jobid)
+        df = timing.load_array_mean_timings(jobid, excluded_array_indices).mean()
+        dfs[label] = df
+        labels.extend(df.index)
+
+    labels = set(labels)
+    print(",".join(["label"] + columns + ["Other"]))
+
+    values_by_label = dict()
+    for label, df in dfs.items():
+        values = {"Other": 0}
+        for c in df.index:
+            if c in ignore:
+                continue
+            elif c not in columns:
+                values["Other"] += df[c]
+                print(f"Others+= {c}={df[c]}", file=sys.stderr)
+            else:
+                values[c] = df[c]
+        values_by_label[label] = values
+
+    if args.normalize:
+        print("Normalizing data to 100%...", file=sys.stderr)
+        for values in values_by_label.values():
+            row_length = sum(values.values())
+            for c in values.keys():
+                values[c] *= 100 / row_length
+
+    for label, values in values_by_label.items():
+        print(label + "," + ",".join(f"{values[c]}" for c in columns + ["Other"]))

experiments/eval/scripts/timing.py

@@ -44,12 +44,13 @@ def get_outdirs(jobid: str):
     return sorted(Path("/p/scratch/cellsinsilico/paul/nastja-out").glob(f"*{jobid}*"))
 
 
-def load_array_mean_timings(jobid: str):
+def load_array_mean_timings(jobid: str, excluded_array_indices):
-    mts = [
+    mts = []
-        load_mean_timings(outdir_path)
+    for outdir_path in get_outdirs(jobid):
-        for outdir_path
+        if any(str(outdir_path).endswith(str(i)) for i in excluded_array_indices):
-        in get_outdirs(jobid)
+            print(f"Not loading timings for {outdir_path} because it was excluded.", file=sys.stderr)
-    ]
+            continue
+        mts.append(load_mean_timings(outdir_path))
 
     return pandas.DataFrame(list(mts), columns=mts[0].index)
 
@@ -71,22 +72,45 @@ def get_accounting_data(jobid: str):
     return json.loads(sacct_results.stdout.decode("utf8"))
 
 
+def get_jobs(jobid: str):
+    accounting_data = get_accounting_data(jobid)
+    jobs = []
+    excluded_array_indices = []
+    for array_job in accounting_data["jobs"]:
+        # Get metadata related to array
+        array_main_job = array_job["array"]["job_id"]
+        array_index = array_job["array"]["task_id"]
+        # The last step is the actual job we want the data for
+        # The steps before set up cluster etc.
+        last_step = array_job["steps"][-1]
+        if last_step["state"] != "COMPLETED":
+            print(f"WARNING: {array_main_job}.{array_index} has state {last_step['state']}, excluding it from measurements", file=sys.stderr)
+            excluded_array_indices.append(array_index)
+            continue
+        jobs.append(last_step)
+
+    return jobs, excluded_array_indices
+
+
 if __name__ == "__main__":
     p = argparse.ArgumentParser(description="Load and analzye data from nastja timing files")
     p.add_argument("jobid", nargs="+")
     p.add_argument("--prettify", action="store_true")
+    p.add_argument("--dump-timings", action="store_true")
     args = p.parse_args()
 
     results = []
     for i, jobid in enumerate(args.jobid, 1):
         print(f"({i:2}/{len(args.jobid):2}) Loading accounting data for {jobid}", file=sys.stderr)
-        accounting_data = get_accounting_data(jobid)
+        jobs, excluded_array_indices = get_jobs(jobid)
-        array_mean_timings = load_array_mean_timings(jobid)
+        array_mean_timings = load_array_mean_timings(jobid, excluded_array_indices)
+        if args.dump_timings:
+            print(array_mean_timings, file=sys.stderr)
 
         results.append({
             "jobid": jobid,
             "means": array_mean_timings.mean().to_dict(),
             "stds": array_mean_timings.std().to_dict(),
-            "accounting": [array_job["steps"][-1] for array_job in accounting_data["jobs"]]
+            "accounting": jobs
         })
     print(json.dumps(results, indent=2 if args.prettify else None))

experiments/eval/strong-booster.json

@@ -0,0 +1,63 @@
+{
+  "common": {
+    "account": "hkf6",
+    "partition": "booster",
+    "extra_sbatch_line": "#SBATCH --gres=gpu:4",
+    "logfile_path": "/p/project/cellsinsilico/paulslustigebude/ma/experiments/eval/logs/%x-%A.%a",
+    "nastja_binary_path": "/p/project/cellsinsilico/paulslustigebude/nastja/build-cuda/nastja",
+    "config_path": "/p/project/cellsinsilico/paulslustigebude/ma/experiments/eval/generated/config/${SLURM_JOB_NAME}.json",
+    "output_dir_path": "/p/scratch/cellsinsilico/paul/nastja-out/${SLURM_JOB_NAME}-${SLURM_ARRAY_JOB_ID}.${SLURM_ARRAY_TASK_ID}"
+  },
+  "batches": [
+    {
+      "name": "strong-booster-01-01-01",
+      "nodes": 1,
+      "tasks": 1,
+      "time": "00:15:00",
+      "extra_sbatch_line": "#SBATCH --gres=gpu:1"
+    },
+    {
+      "name": "strong-booster-01-01-02",
+      "nodes": 1,
+      "tasks": 2,
+      "time": "00:15:00",
+      "extra_sbatch_line": "#SBATCH --gres=gpu:2"
+    },
+    {
+      "name": "strong-booster-01-02-02",
+      "nodes": 1,
+      "tasks": 4,
+      "time": "00:15:00"
+    },
+    {
+      "name": "strong-booster-02-02-02",
+      "nodes": 2,
+      "tasks": 8,
+      "time": "00:15:00"
+    },
+    {
+      "name": "strong-booster-02-02-04",
+      "nodes": 4,
+      "tasks": 16,
+      "time": "00:15:00"
+    },
+    {
+      "name": "strong-booster-02-04-04",
+      "nodes": 8,
+      "tasks": 32,
+      "time": "00:15:00"
+    },
+    {
+      "name": "strong-booster-04-04-04",
+      "nodes": 16,
+      "tasks": 64,
+      "time": "00:15:00"
+    },
+    {
+      "name": "strong-booster-04-04-08",
+      "nodes": 32,
+      "tasks": 128,
+      "time": "00:15:00"
+    }
+  ]
+}

experiments/eval/strong-cpu.json

@@ -13,19 +13,19 @@
       "name": "strong-cpu-04-04-03",
       "nodes": 1,
       "tasks": 48,
-      "time": "00:30:00"
+      "time": "01:00:00"
     },
     {
       "name": "strong-cpu-04-04-06",
       "nodes": 2,
       "tasks": 96,
-      "time": "00:30:00"
+      "time": "01:00:00"
     },
     {
       "name": "strong-cpu-04-04-12",
       "nodes": 4,
       "tasks": 192,
-      "time": "00:10:00"
+      "time": "00:20:00"
     },
     {
       "name": "strong-cpu-04-08-12",

experiments/eval/templates/strong-booster.json

@@ -0,0 +1,263 @@
+{
+  "Application": "Cells",
+  "CellsInSilico": {
+    "2D": false,
+    "adhesion": {
+      "matrix": [
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 450.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 450.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 50.0]
+      ],
+      "polarityenabled": false
+    },
+    "centerofmass": {
+      "steps": 1
+    },
+    "cleaner": {
+      "killdistance": 0,
+      "steps": 100
+    },
+    "contactinhibition": {
+      "enabled": false
+    },
+    "division": {
+      "condition": [
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "( volume >= 0.9 * volume0 )  & ( rnd() <= 0.00001 ) & generation < 1"
+      ],
+      "enabled": true,
+      "halveSignals": false
+    },
+    "dynamicecm": {
+      "alpha": 2.0,
+      "beta": 0.5,
+      "c": 4.0,
+      "deltat": 0.10000000149011612,
+      "ecmCellID": 0,
+      "enabled": true,
+      "eta": 0.25,
+      "k0": 0.10000000149011612,
+      "k1": 0.10000000149011612,
+      "lambda": 10.0,
+      "phi": 1.0,
+      "pushSteps": 10,
+      "pushWeight": 0.5,
+      "stepsPerMcs": 100
+    },
+    "ecmdegradation": {
+      "enabled": false
+    },
+    "energyfunctions": [
+      "Volume00",
+      "Surface01",
+      "Motility00",
+      "Adhesion01",
+      "DynamicECM00"
+    ],
+    "liquid": 6,
+    "logcellproperties": {
+      "enabled": false
+    },
+    "orientation": {
+      "enabled": true,
+      "motility": "persistentRandomWalk",
+      "motilityamount": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "numRandomNumbers": 5,
+      "persistenceMagnitude": 0.0,
+      "persistentDecay": 0.8,
+      "recalculationtime": 200
+    },
+    "polarity": {
+      "enabled": false
+    },
+    "signaling": {
+      "constant": false,
+      "enabled": false
+    },
+    "surface": {
+      "default": {
+        "storage": "const",
+        "value": 400.0
+      },
+      "lambda": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        5.625,
+        5.625,
+        1.0
+      ],
+      "sizechange": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        -0.05,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "temperature": 50.0,
+    "visitor": {
+      "checkerboard": "01",
+      "stepwidth": 10
+    },
+    "volume": {
+      "default": {
+        "storage": "const",
+        "value": 500.0
+      },
+      "lambda": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        7.5,
+        7.5,
+        7.5
+      ],
+      "sizechange": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        -0.05,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    }
+  },
+  "DefineFunctions": [
+    "r_angle()=360*rnd()",
+    "r_size()=400*rnd()"
+  ],
+  "Filling": {
+    "cells": [
+      {
+        "box": [
+          [
+            0,
+            0,
+            0
+          ],
+          [
+            384,
+            384,
+            384
+          ]
+        ],
+        "celltype": 0,
+        "component": 0,
+        "pattern": "const",
+        "seed": 0,
+        "shape": "cube",
+        "value": 0
+      },
+      {
+        "box": [
+          [117, 117, 177],
+          [267, 267, 267]
+        ],
+        "celltype": 9,
+        "center": [192, 192, 192],
+        "component": 0,
+        "count": 5500,
+        "pattern": "voronoi",
+        "radius": 75,
+        "seed": 758960,
+        "shape": "sphere",
+        "value": 8
+      }
+    ],
+    "initialoutput": false,
+    "randomseed": 758959
+  },
+  "Geometry": {
+    "blockcount": [
+      4,
+      4,
+      3
+    ],
+    "blockdefault": "fill",
+    "blocksize": [
+      96,
+      96,
+      128
+    ],
+    "blocktype": [
+      [
+        [
+          1
+        ]
+      ]
+    ]
+  },
+  "Settings": {
+    "deltat": 1.0,
+    "deltax": 1.0,
+    "handleFPE": "signal",
+    "logger": {
+      "group": 0,
+      "steps": 100
+    },
+    "randomseed": 42,
+    "statusoutput": 1,
+    "timestepguard": 1,
+    "timesteps": 10,
+    "cuda": {
+      "subblocks": {
+        "blockDim": [8, 8, 8]
+      }
+    }
+  }
+}

experiments/eval/templates/strong-cpu.json

@@ -253,6 +253,6 @@
     "randomseed": 42,
     "statusoutput": 1,
     "timestepguard": 1,
-    "timesteps": 5
+    "timesteps": 10
   }
 }

experiments/eval/templates/strong-gpu.json

@@ -253,7 +253,7 @@
     "randomseed": 42,
     "statusoutput": 1,
     "timestepguard": 1,
-    "timesteps": 5,
+    "timesteps": 10,
     "cuda": {
       "subblocks": {
         "blockDim": [8, 8, 8]

experiments/eval/templates/weak.json

@@ -0,0 +1,193 @@
+{
+  "Application": "Cells",
+  "CellsInSilico": {
+    "2D": false,
+    "adhesion": {
+      "matrix": [
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 450.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
+        [0.0, 450.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 50.0]
+      ],
+      "polarityenabled": false
+    },
+    "centerofmass": {
+      "steps": 1
+    },
+    "cleaner": {
+      "killdistance": 0,
+      "steps": 100
+    },
+    "contactinhibition": {
+      "enabled": false
+    },
+    "division": {
+      "condition": [
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "",
+        "( volume >= 0.9 * volume0 )  & ( rnd() <= 0.00001 ) & generation < 1"
+      ],
+      "enabled": true,
+      "halveSignals": false
+    },
+    "dynamicecm": {
+      "alpha": 2.0,
+      "beta": 0.5,
+      "c": 4.0,
+      "deltat": 0.1,
+      "ecmCellID": 0,
+      "enabled": true,
+      "eta": 0.25,
+      "k0": 0.1,
+      "k1": 0.1,
+      "lambda": 10.0,
+      "phi": 1.0,
+      "pushSteps": 10,
+      "pushWeight": 0.5,
+      "stepsPerMcs": 100
+    },
+    "ecmdegradation": {
+      "enabled": false
+    },
+    "energyfunctions": [
+      "Volume00",
+      "Surface01",
+      "Motility00",
+      "Adhesion01",
+      "DynamicECM00"
+    ],
+    "liquid": 6,
+    "logcellproperties": {
+      "enabled": false
+    },
+    "orientation": {
+      "enabled": true,
+      "motility": "persistentRandomWalk",
+      "motilityamount": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ],
+      "numRandomNumbers": 5,
+      "persistenceMagnitude": 0.0,
+      "persistentDecay": 0.8,
+      "recalculationtime": 200
+    },
+    "polarity": {
+      "enabled": false
+    },
+    "signaling": {
+      "constant": false,
+      "enabled": false
+    },
+    "surface": {
+      "default": {
+        "storage": "const",
+        "value": 400.0
+      },
+      "lambda": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        5.625,
+        5.625,
+        1.0
+      ],
+      "sizechange": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        -0.05,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    },
+    "temperature": 50.0,
+    "visitor": {
+      "checkerboard": "01",
+      "stepwidth": 10
+    },
+    "volume": {
+      "default": {
+        "storage": "const",
+        "value": 500.0
+      },
+      "lambda": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        7.5,
+        7.5,
+        7.5
+      ],
+      "sizechange": [
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        -0.05,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0,
+        0.0
+      ]
+    }
+  },
+  "DefineFunctions": [
+    "r_angle()=360*rnd()",
+    "r_size()=400*rnd()"
+  ],
+  "Filling": {
+    "initialoutput": false,
+    "randomseed": 758959
+  },
+  "Settings": {
+    "randomseed": 42,
+    "statusoutput": 1,
+    "timesteps": 10
+  }
+}