diff --git a/.tmp/README.md b/.tmp/README.md
new file mode 100644
index 00000000..db4f22c5
--- /dev/null
+++ b/.tmp/README.md
@@ -0,0 +1 @@
+This directory is being used for storing nightly test logs.
diff --git a/.tmp/cffi_vs_cython_pingpong.png b/.tmp/cffi_vs_cython_pingpong.png
new file mode 100644
index 00000000..ecc3d390
Binary files /dev/null and b/.tmp/cffi_vs_cython_pingpong.png differ
diff --git a/.tmp/cffi_vs_cython_task-bench.png b/.tmp/cffi_vs_cython_task-bench.png
new file mode 100644
index 00000000..1abd3e20
Binary files /dev/null and b/.tmp/cffi_vs_cython_task-bench.png differ
diff --git a/.tmp/compare_pingpong.py b/.tmp/compare_pingpong.py
new file mode 100644
index 00000000..ff4102ff
--- /dev/null
+++ b/.tmp/compare_pingpong.py
@@ -0,0 +1,39 @@
+from os import listdir
+import numpy as np
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+def parsefile(file, data):
+    f = open(file, 'r')
+    lines = f.readlines()
+    length = 0
+    time = 0
+    for l in lines:
+        if "RES:: [plain] " in l:
+            length = int(l.split()[2])
+            time = float(l.split()[-1])
+            d = {
+                'file':file,
+                'msg length':length,
+                'Elapsed Time':time
+            }
+            data = data.append(d,  ignore_index=True)
+    return data
+  
+data = pd.DataFrame(columns =["file", "msg length", "Elapsed Time"])
+data = parsefile("udp-cffi-pingpong.log", data)
+data = parsefile("udp-cython-pingpong.log", data)
+
+sns.set_theme(style="whitegrid")
+df = data
+
+# Draw a pointplot to show pulse as a function of three categorical factors
+g = sns.lineplot(x="msg length", y="Elapsed Time", hue="file", data=df,ci=99, linewidth=3, markersize=10, alpha  = 0.5)
+g.set(ylabel='Elapsed Time')
+g.set(xlabel='msg length (ms)')
+g.set_xscale('log', base=2)
+g.set(title="cffi vs cython with the pingpong benchmark")
+plt.subplots_adjust(bottom=0.15)
+plt.savefig('cffi_vs_cython_pingpong.png')
+print("Created cffi_vs_cython_pingpong.png")
diff --git a/.tmp/compare_task_bench.py b/.tmp/compare_task_bench.py
new file mode 100644
index 00000000..c6e04a5f
--- /dev/null
+++ b/.tmp/compare_task_bench.py
@@ -0,0 +1,42 @@
+from os import listdir
+import numpy as np
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+def parsefile(file, data):
+    f = open(file, 'r')
+    lines = f.readlines()
+    length = 0
+    time = 0
+    for l in lines:
+        if "Iterations: " in l:
+#             print(l.split())
+            length = int(l.split()[-1])
+        if "Elapsed Time " in l:
+#             print(l.split())
+            time = float(l.split()[-2])
+            d = {
+                'file':file,
+                'Iterations':length,
+                'Elapsed Time':time
+            }
+            data = data.append(d,  ignore_index=True)
+    return data
+  
+data = pd.DataFrame(columns =["file", "Iterations", "Elapsed Time"])
+data = parsefile("udp-cffi-task-bench.log", data)
+data = parsefile("udp-cython-task-bench.log", data)
+
+sns.set_theme(style="whitegrid")
+df = data
+
+# Draw a pointplot to show pulse as a function of three categorical factors
+g = sns.lineplot(x="Iterations", y="Elapsed Time", hue="file", data=df,ci=99, linewidth=3, markersize=10, alpha  = 0.5)
+g.set(ylabel='Elapsed Time')
+g.set(xlabel='Iterations')
+g.set_xscale('log', base=2)
+g.set(title="cffi vs cython with the task-bench benchmark")
+plt.subplots_adjust(bottom=0.15)
+plt.savefig('cffi_vs_cython_task-bench.png')
+print("Created cffi_vs_cython_task-bench.png")
diff --git a/.tmp/udp-cffi-pingpong.log b/.tmp/udp-cffi-pingpong.log
new file mode 100644
index 00000000..66d80ae1
--- /dev/null
+++ b/.tmp/udp-cffi-pingpong.log
@@ -0,0 +1,235 @@
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.133 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.001 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7517490>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7517d30>
+Array length = 1
+RES:: [plain] 1  40.15648365020752
+Array length = 2
+RES:: [plain] 2  39.112091064453125
+Array length = 4
+RES:: [plain] 4  38.93387317657471
+Array length = 8
+RES:: [plain] 8  41.063129901885986
+Array length = 16
+RES:: [plain] 16  41.2411093711853
+Array length = 32
+RES:: [plain] 32  41.03374481201172
+Array length = 64
+RES:: [plain] 64  37.12218999862671
+Array length = 128
+RES:: [plain] 128  39.837539196014404
+Array length = 256
+RES:: [plain] 256  40.46440124511719
+Array length = 512
+RES:: [plain] 512  44.843971729278564
+Array length = 1024
+RES:: [plain] 1024  45.204877853393555
+Array length = 2048
+RES:: [plain] 2048  43.63143444061279
+Array length = 4096
+RES:: [plain] 4096  57.63280391693115
+Array length = 8192
+RES:: [plain] 8192  76.37739181518555
+Array length = 16384
+RES:: [plain] 16384  114.97676372528076
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.138 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.001 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516490>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516d30>
+Array length = 1
+RES:: [plain] 1  39.1005277633667
+Array length = 2
+RES:: [plain] 2  38.743793964385986
+Array length = 4
+RES:: [plain] 4  43.201565742492676
+Array length = 8
+RES:: [plain] 8  38.9094352722168
+Array length = 16
+RES:: [plain] 16  41.18305444717407
+Array length = 32
+RES:: [plain] 32  40.7448410987854
+Array length = 64
+RES:: [plain] 64  42.01465845108032
+Array length = 128
+RES:: [plain] 128  45.90874910354614
+Array length = 256
+RES:: [plain] 256  45.57478427886963
+Array length = 512
+RES:: [plain] 512  50.64809322357178
+Array length = 1024
+RES:: [plain] 1024  55.482685565948486
+Array length = 2048
+RES:: [plain] 2048  49.16834831237793
+Array length = 4096
+RES:: [plain] 4096  54.6494722366333
+Array length = 8192
+RES:: [plain] 8192  82.3284387588501
+Array length = 16384
+RES:: [plain] 16384  112.06519603729248
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.152 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.001 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516490>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516d30>
+Array length = 1
+RES:: [plain] 1  45.69602012634277
+Array length = 2
+RES:: [plain] 2  43.62159967422485
+Array length = 4
+RES:: [plain] 4  45.28534412384033
+Array length = 8
+RES:: [plain] 8  42.55479574203491
+Array length = 16
+RES:: [plain] 16  41.91511869430542
+Array length = 32
+RES:: [plain] 32  41.01341962814331
+Array length = 64
+RES:: [plain] 64  40.20887613296509
+Array length = 128
+RES:: [plain] 128  40.787458419799805
+Array length = 256
+RES:: [plain] 256  43.34598779678345
+Array length = 512
+RES:: [plain] 512  41.78130626678467
+Array length = 1024
+RES:: [plain] 1024  41.22030735015869
+Array length = 2048
+RES:: [plain] 2048  46.240150928497314
+Array length = 4096
+RES:: [plain] 4096  46.45693302154541
+Array length = 8192
+RES:: [plain] 8192  73.711097240448
+Array length = 16384
+RES:: [plain] 16384  95.82799673080444
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.132 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.001 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516490>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516d30>
+Array length = 1
+RES:: [plain] 1  41.44507646560669
+Array length = 2
+RES:: [plain] 2  44.38084363937378
+Array length = 4
+RES:: [plain] 4  43.155670166015625
+Array length = 8
+RES:: [plain] 8  39.33978080749512
+Array length = 16
+RES:: [plain] 16  39.40623998641968
+Array length = 32
+RES:: [plain] 32  41.42165184020996
+Array length = 64
+RES:: [plain] 64  40.746212005615234
+Array length = 128
+RES:: [plain] 128  40.216803550720215
+Array length = 256
+RES:: [plain] 256  40.44085741043091
+Array length = 512
+RES:: [plain] 512  43.04009675979614
+Array length = 1024
+RES:: [plain] 1024  42.25742816925049
+Array length = 2048
+RES:: [plain] 2048  43.71988773345947
+Array length = 4096
+RES:: [plain] 4096  50.69148540496826
+Array length = 8192
+RES:: [plain] 8192  74.50670003890991
+Array length = 16384
+RES:: [plain] 16384  108.46364498138428
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.149 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.001 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516490>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516d30>
+Array length = 1
+RES:: [plain] 1  63.12370300292969
+Array length = 2
+RES:: [plain] 2  44.25305128097534
+Array length = 4
+RES:: [plain] 4  47.86252975463867
+Array length = 8
+RES:: [plain] 8  49.58748817443848
+Array length = 16
+RES:: [plain] 16  45.912861824035645
+Array length = 32
+RES:: [plain] 32  52.34187841415405
+Array length = 64
+RES:: [plain] 64  45.03321647644043
+Array length = 128
+RES:: [plain] 128  45.86869478225708
+Array length = 256
+RES:: [plain] 256  47.442495822906494
+Array length = 512
+RES:: [plain] 512  46.772122383117676
+Array length = 1024
+RES:: [plain] 1024  48.66296052932739
+Array length = 2048
+RES:: [plain] 2048  49.2098331451416
+Array length = 4096
+RES:: [plain] 4096  52.45620012283325
+Array length = 8192
+RES:: [plain] 8192  78.18669080734253
+Array length = 16384
+RES:: [plain] 16384  103.56521606445312
+[Partition 0][Node 0] End of program
diff --git a/.tmp/udp-cffi-task-bench.log b/.tmp/udp-cffi-task-bench.log
new file mode 100644
index 00000000..d4758d91
--- /dev/null
+++ b/.tmp/udp-cffi-task-bench.log
@@ -0,0 +1,656 @@
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.174 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 64
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.0097006599999645
+Time for last run: 0.0005995039999788787
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 132096
+Total Bytes 0
+Elapsed Time 5.995040e-04 seconds
+FLOP/s 2.203421e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.174 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 128
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008754253999995854
+Time for last run: 0.0005851040000379726
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 263168
+Total Bytes 0
+Elapsed Time 5.851040e-04 seconds
+FLOP/s 4.497799e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.174 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 256
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.00867615399999977
+Time for last run: 0.0005850040000154877
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 525312
+Total Bytes 0
+Elapsed Time 5.850040e-04 seconds
+FLOP/s 8.979631e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.173 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 512
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008673054000041702
+Time for last run: 0.0006215039999801775
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 1049600
+Total Bytes 0
+Elapsed Time 6.215040e-04 seconds
+FLOP/s 1.688807e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.173 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 1024
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008711155000014514
+Time for last run: 0.000591804000009688
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 2098176
+Total Bytes 0
+Elapsed Time 5.918040e-04 seconds
+FLOP/s 3.545390e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.172 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 2048
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008710554000003867
+Time for last run: 0.0006275039999650289
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 4195328
+Total Bytes 0
+Elapsed Time 6.275040e-04 seconds
+FLOP/s 6.685739e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.173 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 4096
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008808055000031345
+Time for last run: 0.0006666049999921597
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 8389632
+Total Bytes 0
+Elapsed Time 6.666050e-04 seconds
+FLOP/s 1.258561e+10
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.174 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 8192
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008760154000015064
+Time for last run: 0.0007135039999752735
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 16778240
+Total Bytes 0
+Elapsed Time 7.135040e-04 seconds
+FLOP/s 2.351527e+10
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.188 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 64
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.009781355000029635
+Time for last run: 0.0009580060000189405
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 132096
+Total Bytes 0
+Elapsed Time 9.580060e-04 seconds
+FLOP/s 1.378864e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.185 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 128
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.010087557000019842
+Time for last run: 0.0009556059999908939
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 263168
+Total Bytes 0
+Elapsed Time 9.556060e-04 seconds
+FLOP/s 2.753938e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.183 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 256
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.00945535400001063
+Time for last run: 0.0009060049999902731
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 525312
+Total Bytes 0
+Elapsed Time 9.060050e-04 seconds
+FLOP/s 5.798114e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.182 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.003 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 512
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.0095319540000105
+Time for last run: 0.0008442040000318229
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 1049600
+Total Bytes 0
+Elapsed Time 8.442040e-04 seconds
+FLOP/s 1.243301e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.176 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.008 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 1024
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.009661155000003419
+Time for last run: 0.0009981059999972786
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 2098176
+Total Bytes 0
+Elapsed Time 9.981060e-04 seconds
+FLOP/s 2.102157e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.188 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.004 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 2048
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.01043335899998965
+Time for last run: 0.0009620060000088415
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 4195328
+Total Bytes 0
+Elapsed Time 9.620060e-04 seconds
+FLOP/s 4.361021e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.187 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 4096
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.010313959000029627
+Time for last run: 0.0012098069999524341
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 8389632
+Total Bytes 0
+Elapsed Time 1.209807e-03 seconds
+FLOP/s 6.934686e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.194 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 8192
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.010317658000019492
+Time for last run: 0.001109207000013157
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 16778240
+Total Bytes 0
+Elapsed Time 1.109207e-03 seconds
+FLOP/s 1.512634e+10
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
diff --git a/.tmp/udp-cython-pingpong.log b/.tmp/udp-cython-pingpong.log
new file mode 100644
index 00000000..e5155a40
--- /dev/null
+++ b/.tmp/udp-cython-pingpong.log
@@ -0,0 +1,235 @@
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.160 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.001 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff75ba610>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff75e3970>
+Array length = 1
+RES:: [plain] 1  43.888092041015625
+Array length = 2
+RES:: [plain] 2  43.76024007797241
+Array length = 4
+RES:: [plain] 4  43.49935054779053
+Array length = 8
+RES:: [plain] 8  44.67439651489258
+Array length = 16
+RES:: [plain] 16  47.05125093460083
+Array length = 32
+RES:: [plain] 32  47.47962951660156
+Array length = 64
+RES:: [plain] 64  46.534717082977295
+Array length = 128
+RES:: [plain] 128  47.661781311035156
+Array length = 256
+RES:: [plain] 256  47.47897386550903
+Array length = 512
+RES:: [plain] 512  48.288166522979736
+Array length = 1024
+RES:: [plain] 1024  50.57644844055176
+Array length = 2048
+RES:: [plain] 2048  54.69226837158203
+Array length = 4096
+RES:: [plain] 4096  57.62690305709839
+Array length = 8192
+RES:: [plain] 8192  84.42598581314087
+Array length = 16384
+RES:: [plain] 16384  106.35274648666382
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.131 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.001 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516460>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516d00>
+Array length = 1
+RES:: [plain] 1  38.94263505935669
+Array length = 2
+RES:: [plain] 2  43.44892501831055
+Array length = 4
+RES:: [plain] 4  39.50059413909912
+Array length = 8
+RES:: [plain] 8  52.47640609741211
+Array length = 16
+RES:: [plain] 16  38.996338844299316
+Array length = 32
+RES:: [plain] 32  45.6354022026062
+Array length = 64
+RES:: [plain] 64  39.72911834716797
+Array length = 128
+RES:: [plain] 128  40.835022926330566
+Array length = 256
+RES:: [plain] 256  38.59835863113403
+Array length = 512
+RES:: [plain] 512  40.82232713699341
+Array length = 1024
+RES:: [plain] 1024  43.23399066925049
+Array length = 2048
+RES:: [plain] 2048  41.06622934341431
+Array length = 4096
+RES:: [plain] 4096  49.25590753555298
+Array length = 8192
+RES:: [plain] 8192  74.65660572052002
+Array length = 16384
+RES:: [plain] 16384  100.98874568939209
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.134 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.003 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516460>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516d00>
+Array length = 1
+RES:: [plain] 1  39.76237773895264
+Array length = 2
+RES:: [plain] 2  40.10319709777832
+Array length = 4
+RES:: [plain] 4  40.839552879333496
+Array length = 8
+RES:: [plain] 8  37.33038902282715
+Array length = 16
+RES:: [plain] 16  40.25566577911377
+Array length = 32
+RES:: [plain] 32  41.12619161605835
+Array length = 64
+RES:: [plain] 64  38.93637657165527
+Array length = 128
+RES:: [plain] 128  41.21506214141846
+Array length = 256
+RES:: [plain] 256  38.67143392562866
+Array length = 512
+RES:: [plain] 512  42.545437812805176
+Array length = 1024
+RES:: [plain] 1024  49.97760057449341
+Array length = 2048
+RES:: [plain] 2048  48.38055372238159
+Array length = 4096
+RES:: [plain] 4096  53.62778902053833
+Array length = 8192
+RES:: [plain] 8192  84.78057384490967
+Array length = 16384
+RES:: [plain] 16384  116.44357442855835
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.155 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.001 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516460>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516d00>
+Array length = 1
+RES:: [plain] 1  48.63160848617554
+Array length = 2
+RES:: [plain] 2  46.269893646240234
+Array length = 4
+RES:: [plain] 4  47.40065336227417
+Array length = 8
+RES:: [plain] 8  45.58128118515015
+Array length = 16
+RES:: [plain] 16  42.2205924987793
+Array length = 32
+RES:: [plain] 32  43.89834403991699
+Array length = 64
+RES:: [plain] 64  40.28666019439697
+Array length = 128
+RES:: [plain] 128  40.53777456283569
+Array length = 256
+RES:: [plain] 256  45.09943723678589
+Array length = 512
+RES:: [plain] 512  40.409207344055176
+Array length = 1024
+RES:: [plain] 1024  42.40846633911133
+Array length = 2048
+RES:: [plain] 2048  45.08596658706665
+Array length = 4096
+RES:: [plain] 4096  50.440847873687744
+Array length = 8192
+RES:: [plain] 8192  76.10297203063965
+Array length = 16384
+RES:: [plain] 16384  97.93758392333984
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.137 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-114-ge1a85fbae
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.001 seconds.
+My PE:  0
+[0] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516460>
+My PE:  1
+[1] neighbor =  <__main__.PingArrayProxy object at 0x7ffff7516d00>
+Array length = 1
+RES:: [plain] 1  37.310123443603516
+Array length = 2
+RES:: [plain] 2  38.25861215591431
+Array length = 4
+RES:: [plain] 4  40.13127088546753
+Array length = 8
+RES:: [plain] 8  40.22252559661865
+Array length = 16
+RES:: [plain] 16  39.460837841033936
+Array length = 32
+RES:: [plain] 32  38.31470012664795
+Array length = 64
+RES:: [plain] 64  40.29017686843872
+Array length = 128
+RES:: [plain] 128  38.038671016693115
+Array length = 256
+RES:: [plain] 256  37.92917728424072
+Array length = 512
+RES:: [plain] 512  40.43787717819214
+Array length = 1024
+RES:: [plain] 1024  42.65230894088745
+Array length = 2048
+RES:: [plain] 2048  43.689846992492676
+Array length = 4096
+RES:: [plain] 4096  48.7285852432251
+Array length = 8192
+RES:: [plain] 8192  73.81588220596313
+Array length = 16384
+RES:: [plain] 16384  101.6358733177185
+[Partition 0][Node 0] End of program
diff --git a/.tmp/udp-cython-task-bench.log b/.tmp/udp-cython-task-bench.log
new file mode 100644
index 00000000..c2b7a9dd
--- /dev/null
+++ b/.tmp/udp-cython-task-bench.log
@@ -0,0 +1,656 @@
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.201 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 64
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008624055000041153
+Time for last run: 0.0005591039999899294
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 132096
+Total Bytes 0
+Elapsed Time 5.591040e-04 seconds
+FLOP/s 2.362637e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.175 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 128
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008715055999971355
+Time for last run: 0.0005877039999973022
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 263168
+Total Bytes 0
+Elapsed Time 5.877040e-04 seconds
+FLOP/s 4.477900e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.175 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 256
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.00856105499997284
+Time for last run: 0.0006010039999750916
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 525312
+Total Bytes 0
+Elapsed Time 6.010040e-04 seconds
+FLOP/s 8.740574e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.174 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 512
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008673455999996804
+Time for last run: 0.0006210040000382833
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 1049600
+Total Bytes 0
+Elapsed Time 6.210040e-04 seconds
+FLOP/s 1.690166e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.175 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 1024
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008787357000016982
+Time for last run: 0.0006138039999541434
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 2098176
+Total Bytes 0
+Elapsed Time 6.138040e-04 seconds
+FLOP/s 3.418316e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.173 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 2048
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008677954999996018
+Time for last run: 0.0005995040000357221
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 4195328
+Total Bytes 0
+Elapsed Time 5.995040e-04 seconds
+FLOP/s 6.997998e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.172 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 4096
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008611556000005294
+Time for last run: 0.0006403040000009241
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 8389632
+Total Bytes 0
+Elapsed Time 6.403040e-04 seconds
+FLOP/s 1.310258e+10
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.173 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 8192
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.008716956000000664
+Time for last run: 0.0006808040000123583
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 16778240
+Total Bytes 0
+Elapsed Time 6.808040e-04 seconds
+FLOP/s 2.464474e+10
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.212 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 64
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.011686076999978923
+Time for last run: 0.001018707000014274
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 132096
+Total Bytes 0
+Elapsed Time 1.018707e-03 seconds
+FLOP/s 1.296703e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.194 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 128
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.009927465000032498
+Time for last run: 0.000985606000028838
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 263168
+Total Bytes 0
+Elapsed Time 9.856060e-04 seconds
+FLOP/s 2.670114e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.192 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 256
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.010256968000021516
+Time for last run: 0.001045707000002949
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 525312
+Total Bytes 0
+Elapsed Time 1.045707e-03 seconds
+FLOP/s 5.023510e+08
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.193 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 512
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.010232867000013357
+Time for last run: 0.0010051070000258733
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 1049600
+Total Bytes 0
+Elapsed Time 1.005107e-03 seconds
+FLOP/s 1.044267e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.181 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 1024
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.009402862000001733
+Time for last run: 0.0009570059999646219
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 2098176
+Total Bytes 0
+Elapsed Time 9.570060e-04 seconds
+FLOP/s 2.192438e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.179 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 2048
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.009789064000017333
+Time for last run: 0.00100620699998899
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 4195328
+Total Bytes 0
+Elapsed Time 1.006207e-03 seconds
+FLOP/s 4.169448e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.190 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 4096
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.015119499999968866
+Time for last run: 0.0009688070000493099
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 8389632
+Total Bytes 0
+Elapsed Time 9.688070e-04 seconds
+FLOP/s 8.659756e+09
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program
+Charmrun> scalable start enabled. 
+Charmrun> started all node programs in 0.181 seconds.
+Charm++> Running in non-SMP mode: 2 processes (PEs)
+Converse/Charm++ Commit ID: v7.1.0-devel-115-ga4b8220a7
+Charm++ built with internal error checking enabled.
+Do not use for performance benchmarking (build without --enable-error-checking to do so).
+Isomalloc> Synchronized global address space.
+Charm++> scheduler running in netpoll mode.
+CharmLB> Load balancer assumes all CPUs are same.
+Charm4py> Running Charm4py version 1.0 on Python 3.8.10 (CPython). Using 'cython' interface to access Charm++
+Charm++> Running on 1 hosts (1 sockets x 2 cores x 1 PUs = 2-way SMP)
+Charm++> cpu topology info is gathered in 0.000 seconds.
+Running Task Benchmark
+  Configuration:
+    Task Graph 1:
+      Time Steps: 4
+      Max Width: 4
+      Dependence Type: stencil_1d
+      Radix: 3
+      Period: 0
+      Fraction Connected: 0.250000
+      Kernel:
+        Type: compute_bound
+        Iterations: 8192
+        Samples: 16
+        Imbalance: 0.000000
+      Output Bytes: 16
+      Scratch Bytes: 0
+Time for last run: 0.009021359000030316
+Time for last run: 0.0011290080000208036
+Total Tasks 16
+Total Dependencies 30
+  Unable to estimate local/nonlocal dependencies
+Total FLOPs 16778240
+Total Bytes 0
+Elapsed Time 1.129008e-03 seconds
+FLOP/s 1.486105e+10
+B/s 0.000000e+00
+Transfer (estimated):
+  Unable to estimate local/nonlocal transfer
+[Partition 0][Node 0] End of program