Merge pull request #4 from converged-computing/prototype-new-apps

Prototype new apps

Author: vsoch

analysis/amg2023/1-run-analysis.py

@@ -86,14 +86,19 @@ def parse_data(indir, outdir, files):
     Parse filepaths for environment, etc., and results files for data.
     """
     # metrics here will be figures of merit, and seconds runtime
-    p = ps.ResultParser("amg2023")
+    p = ps.ProblemSizeParser("amg2023")
 
     # For flux we can save jobspecs and other event data
     data = {}
 
     # It's important to just parse raw data once, and then use intermediate
     for filename in files:
         exp = ps.ExperimentNameParser(filename, indir)
+        if "compute-engine" in filename:
+            continue
+        mpi = "openmpi"
+        if "intel" in filename:
+            mpi = "intel"
         if exp.prefix not in data:
             data[exp.prefix] = []
 
@@ -112,13 +117,18 @@ def parse_data(indir, outdir, files):
 
         jobs = ps.parse_flux_jobs(item)
         for job, metadata in jobs.items():
-
+            if "log" not in metadata:
+                print(filename)
+                continue
             # Parse the FOM from the item - I see three.
             # This needs to throw an error if we can't find it - indicates the result file is wonky
             # Figure of Merit (FOM): nnz_AP / (Setup Phase Time + 3 * Solve Phase Time) 1.148604e+09
             fom_overall = get_fom_line(metadata['log'], "Figure of Merit (FOM)")
-            p.add_result("fom_overall", fom_overall)
-            p.add_result("duration", metadata['duration'])
+            p.add_result("fom_overall", fom_overall, mpi)
+            if "duration" in metadata:
+                p.add_result("duration", metadata['duration'], mpi)
+            else:
+                print(filename)
 
     print("Done parsing amg2023 results!")
 
@@ -173,13 +183,13 @@ def plot_results(df, outdir, non_anon=False):
             ax=axes[0],
             x="nodes",
             y="value",
-            hue="experiment",
+            hue="problem_size",
             err_kws={"color": "darkred"},
-            hue_order=[
-                "google/gke/cpu",
+            #hue_order=[
+            #    "google/gke/cpu",
     #            "google/compute-engine/cpu",
-            ],
-            palette=cloud_colors,
+           # ],
+            # palette=cloud_colors,
             order=[4, 8, 16, 32],
         )
         if metric == "duration":        

analysis/amg2023/data/amg2023-results.csv

@@ -1,41 +1,85 @@
-,experiment,cloud,env,env_type,nodes,application,metric,value,gpu_count
-0,google/gke/cpu,google,gke,cpu,16,amg2023,fom_overall,480151700.0,0
-1,google/gke/cpu,google,gke,cpu,16,amg2023,duration,152.01309609413147,0
-2,google/gke/cpu,google,gke,cpu,16,amg2023,fom_overall,482046400.0,0
-3,google/gke/cpu,google,gke,cpu,16,amg2023,duration,150.1113781929016,0
-4,google/gke/cpu,google,gke,cpu,16,amg2023,fom_overall,482960600.0,0
-5,google/gke/cpu,google,gke,cpu,16,amg2023,duration,149.70200538635254,0
-6,google/gke/cpu,google,gke,cpu,16,amg2023,fom_overall,482267400.0,0
-7,google/gke/cpu,google,gke,cpu,16,amg2023,duration,150.08514404296875,0
-8,google/gke/cpu,google,gke,cpu,16,amg2023,fom_overall,481757800.0,0
-9,google/gke/cpu,google,gke,cpu,16,amg2023,duration,149.86131691932678,0
-10,google/gke/cpu,google,gke,cpu,32,amg2023,fom_overall,878921000.0,0
-11,google/gke/cpu,google,gke,cpu,32,amg2023,duration,166.38555097579956,0
-12,google/gke/cpu,google,gke,cpu,32,amg2023,fom_overall,875691900.0,0
-13,google/gke/cpu,google,gke,cpu,32,amg2023,duration,166.9042501449585,0
-14,google/gke/cpu,google,gke,cpu,32,amg2023,fom_overall,873602600.0,0
-15,google/gke/cpu,google,gke,cpu,32,amg2023,duration,167.73378896713257,0
-16,google/gke/cpu,google,gke,cpu,32,amg2023,fom_overall,876845100.0,0
-17,google/gke/cpu,google,gke,cpu,32,amg2023,duration,166.47650456428528,0
-18,google/gke/cpu,google,gke,cpu,32,amg2023,fom_overall,874013400.0,0
-19,google/gke/cpu,google,gke,cpu,32,amg2023,duration,167.56161046028137,0
-20,google/gke/cpu,google,gke,cpu,4,amg2023,fom_overall,149912000.0,0
-21,google/gke/cpu,google,gke,cpu,4,amg2023,duration,120.93159031867981,0
-22,google/gke/cpu,google,gke,cpu,4,amg2023,fom_overall,150533300.0,0
-23,google/gke/cpu,google,gke,cpu,4,amg2023,duration,120.01596999168396,0
-24,google/gke/cpu,google,gke,cpu,4,amg2023,fom_overall,150666800.0,0
-25,google/gke/cpu,google,gke,cpu,4,amg2023,duration,119.97674822807312,0
-26,google/gke/cpu,google,gke,cpu,4,amg2023,fom_overall,150211100.0,0
-27,google/gke/cpu,google,gke,cpu,4,amg2023,duration,120.16240978240967,0
-28,google/gke/cpu,google,gke,cpu,4,amg2023,fom_overall,149685600.0,0
-29,google/gke/cpu,google,gke,cpu,4,amg2023,duration,120.9310314655304,0
-30,google/gke/cpu,google,gke,cpu,8,amg2023,fom_overall,257540200.0,0
-31,google/gke/cpu,google,gke,cpu,8,amg2023,duration,138.88910913467407,0
-32,google/gke/cpu,google,gke,cpu,8,amg2023,fom_overall,256498200.0,0
-33,google/gke/cpu,google,gke,cpu,8,amg2023,duration,139.47089266777039,0
-34,google/gke/cpu,google,gke,cpu,8,amg2023,fom_overall,258269200.0,0
-35,google/gke/cpu,google,gke,cpu,8,amg2023,duration,138.14567017555237,0
-36,google/gke/cpu,google,gke,cpu,8,amg2023,fom_overall,258603700.0,0
-37,google/gke/cpu,google,gke,cpu,8,amg2023,duration,138.3945276737213,0
-38,google/gke/cpu,google,gke,cpu,8,amg2023,fom_overall,258313400.0,0
-39,google/gke/cpu,google,gke,cpu,8,amg2023,duration,138.5294554233551,0
+,experiment,cloud,env,env_type,nodes,application,problem_size,metric,value,gpu_count
+0,google/gke/cpu,google,gke,cpu,16,amg2023,intel,fom_overall,479566100.0,0
+1,google/gke/cpu,google,gke,cpu,16,amg2023,intel,duration,150.02887225151062,0
+2,google/gke/cpu,google,gke,cpu,16,amg2023,intel,fom_overall,480194700.0,0
+3,google/gke/cpu,google,gke,cpu,16,amg2023,intel,duration,149.20562863349915,0
+4,google/gke/cpu,google,gke,cpu,16,amg2023,intel,fom_overall,483265400.0,0
+5,google/gke/cpu,google,gke,cpu,16,amg2023,intel,duration,148.83068323135376,0
+6,google/gke/cpu,google,gke,cpu,16,amg2023,intel,fom_overall,483654700.0,0
+7,google/gke/cpu,google,gke,cpu,16,amg2023,intel,duration,148.3491086959839,0
+8,google/gke/cpu,google,gke,cpu,16,amg2023,intel,fom_overall,482457300.0,0
+9,google/gke/cpu,google,gke,cpu,16,amg2023,intel,duration,148.45357942581177,0
+10,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,fom_overall,480151700.0,0
+11,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,duration,152.01309609413147,0
+12,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,fom_overall,482046400.0,0
+13,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,duration,150.1113781929016,0
+14,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,fom_overall,482960600.0,0
+15,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,duration,149.70200538635254,0
+16,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,fom_overall,482267400.0,0
+17,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,duration,150.08514404296875,0
+18,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,fom_overall,481757800.0,0
+19,google/gke/cpu,google,gke,cpu,16,amg2023,openmpi,duration,149.86131691932678,0
+20,google/gke/cpu,google,gke,cpu,2,amg2023,openmpi,fom_overall,63159190.0,0
+21,google/gke/cpu,google,gke,cpu,2,amg2023,openmpi,fom_overall,63236600.0,0
+22,google/gke/cpu,google,gke,cpu,32,amg2023,intel,fom_overall,873366200.0,0
+23,google/gke/cpu,google,gke,cpu,32,amg2023,intel,duration,168.76999402046204,0
+24,google/gke/cpu,google,gke,cpu,32,amg2023,intel,fom_overall,879048800.0,0
+25,google/gke/cpu,google,gke,cpu,32,amg2023,intel,duration,165.79934787750244,0
+26,google/gke/cpu,google,gke,cpu,32,amg2023,intel,fom_overall,885228600.0,0
+27,google/gke/cpu,google,gke,cpu,32,amg2023,intel,duration,163.910582780838,0
+28,google/gke/cpu,google,gke,cpu,32,amg2023,intel,fom_overall,878304300.0,0
+29,google/gke/cpu,google,gke,cpu,32,amg2023,intel,duration,165.0614676475525,0
+30,google/gke/cpu,google,gke,cpu,32,amg2023,intel,fom_overall,874730300.0,0
+31,google/gke/cpu,google,gke,cpu,32,amg2023,intel,duration,166.17630052566528,0
+32,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,fom_overall,878921000.0,0
+33,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,duration,166.38555097579956,0
+34,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,fom_overall,875691900.0,0
+35,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,duration,166.9042501449585,0
+36,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,fom_overall,873602600.0,0
+37,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,duration,167.73378896713257,0
+38,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,fom_overall,876845100.0,0
+39,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,duration,166.47650456428528,0
+40,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,fom_overall,874013400.0,0
+41,google/gke/cpu,google,gke,cpu,32,amg2023,openmpi,duration,167.56161046028137,0
+42,google/gke/cpu,google,gke,cpu,4,amg2023,intel,fom_overall,150054300.0,0
+43,google/gke/cpu,google,gke,cpu,4,amg2023,intel,duration,119.58212518692017,0
+44,google/gke/cpu,google,gke,cpu,4,amg2023,intel,fom_overall,150422500.0,0
+45,google/gke/cpu,google,gke,cpu,4,amg2023,intel,duration,118.81294631958008,0
+46,google/gke/cpu,google,gke,cpu,4,amg2023,intel,fom_overall,151957000.0,0
+47,google/gke/cpu,google,gke,cpu,4,amg2023,intel,duration,117.66585993766785,0
+48,google/gke/cpu,google,gke,cpu,4,amg2023,intel,fom_overall,150265300.0,0
+49,google/gke/cpu,google,gke,cpu,4,amg2023,intel,duration,119.45544004440308,0
+50,google/gke/cpu,google,gke,cpu,4,amg2023,intel,fom_overall,151190900.0,0
+51,google/gke/cpu,google,gke,cpu,4,amg2023,intel,duration,118.32887387275696,0
+52,google/gke/cpu,google,gke,cpu,4,amg2023,intel,fom_overall,149320300.0,0
+53,google/gke/cpu,google,gke,cpu,4,amg2023,intel,duration,121.57392072677612,0
+54,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,fom_overall,149912000.0,0
+55,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,duration,120.93159031867981,0
+56,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,fom_overall,150533300.0,0
+57,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,duration,120.01596999168396,0
+58,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,fom_overall,150666800.0,0
+59,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,duration,119.97674822807312,0
+60,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,fom_overall,150211100.0,0
+61,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,duration,120.16240978240967,0
+62,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,fom_overall,149685600.0,0
+63,google/gke/cpu,google,gke,cpu,4,amg2023,openmpi,duration,120.9310314655304,0
+64,google/gke/cpu,google,gke,cpu,8,amg2023,intel,fom_overall,255527000.0,0
+65,google/gke/cpu,google,gke,cpu,8,amg2023,intel,duration,140.18634748458862,0
+66,google/gke/cpu,google,gke,cpu,8,amg2023,intel,fom_overall,256846400.0,0
+67,google/gke/cpu,google,gke,cpu,8,amg2023,intel,duration,138.2529284954071,0
+68,google/gke/cpu,google,gke,cpu,8,amg2023,intel,fom_overall,256867400.0,0
+69,google/gke/cpu,google,gke,cpu,8,amg2023,intel,duration,137.77160787582397,0
+70,google/gke/cpu,google,gke,cpu,8,amg2023,intel,fom_overall,255484500.0,0
+71,google/gke/cpu,google,gke,cpu,8,amg2023,intel,duration,138.67487406730652,0
+72,google/gke/cpu,google,gke,cpu,8,amg2023,intel,fom_overall,256334100.0,0
+73,google/gke/cpu,google,gke,cpu,8,amg2023,intel,duration,138.12138152122498,0
+74,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,fom_overall,257540200.0,0
+75,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,duration,138.88910913467407,0
+76,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,fom_overall,256498200.0,0
+77,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,duration,139.47089266777039,0
+78,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,fom_overall,258269200.0,0
+79,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,duration,138.14567017555237,0
+80,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,fom_overall,258603700.0,0
+81,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,duration,138.3945276737213,0
+82,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,fom_overall,258313400.0,0
+83,google/gke/cpu,google,gke,cpu,8,amg2023,openmpi,duration,138.5294554233551,0