AMG and Branson plots updated for FOM/node

doc/sphinx/01_branson/branson.rst

@@ -294,25 +294,6 @@ Strong scaling performance of Branson Crossroads 200M Particles is provided with
 
    Branson Strong Scaling Performance on Crossroads 200M particles
 
-Multi-node scaling
-------------------
-
-The results of the scaling runs performed on rocinante hbm partition nodes are presented below.
-Branson was built with intel oneapi 2023.1.0 and cray-mpich 8.1.25.
-These runs used 32, 64, and 96 nodes with 110 tasks per node.
-These runs use 85 million photons per node for a problem size using 25% of the total avalable memory across nodes. 
-
-.. figure:: branson_roci_scale.png
-   :align: center
-   :scale: 50%
-   :alt: 
-
-.. csv-table:: Multi Node Scaling Branson
-   :file: branson_roci_scale.csv
-   :align: center
-   :widths: 10, 10, 10, 10
-   :header-rows: 1
-
 AMD Epyc + Nvidia A100
 ----------------------
 Throughput performance of Branson on AMD Epyc + Nvidia A100 (using a single GPU) is provided within the
@@ -331,6 +312,25 @@ following table and figure.
 
    Branson Throughput Performance on AMD Epyc + Nvidia A100
 
+Multi-node scaling on Crossroads
+================================
+
+The results of the scaling runs performed on rocinante hbm partition nodes are presented below.
+Branson was built with intel oneapi 2023.1.0 and cray-mpich 8.1.25.
+These runs used 32, 64, and 96 nodes with 110 tasks per node.
+These runs use 85 million photons per node for a problem size using 25% of the total avalable memory across nodes. 
+
+.. figure:: branson_roci_scale.png
+   :align: center
+   :scale: 50%
+   :alt: 
+
+.. csv-table:: Multi Node Scaling Branson
+   :file: branson_roci_scale.csv
+   :align: center
+   :widths: 10, 10, 10, 10, 10
+   :header-rows: 1
+
 References
 ==========
 

doc/sphinx/01_branson/branson_roci_badnodes_scale.csv

@@ -0,0 +1,4 @@
+Iteration,Photons,Nodes,Photons/s,Photons/s
+1,2720,32,9.19E+07,2.87E+06
+1,5440,64,1.92E+07,3.00E+05
+1,8160,96,2.80E+07,2.91E+05

doc/sphinx/01_branson/branson_roci_scale.csv

@@ -1,8 +1,4 @@
-Photons,32,64,96
-200,1.25e+08,2.42e+08,2.41e+08
-400,1.26e+08,2.39e+08,3.42e+08
-800,1.25e+08,2.39e+08,3.53e+08
-1000,1.26e+08,2.37e+08,3.6e+08
-2000,1.27e+08,2.46e+08,3.58e+08
-4000,1.27e+08,2.52e+08,3.67e+08
-8000,,2.54e+08,3.77e+08
+Iteration,Photons,Nodes,Photons/s,Photons/s
+1,2720,32,9.20E+07,2.87E+06
+1,5440,64,1.89E+08,2.95E+06
+1,8160,96,2.73E+08,2.85E+06

doc/sphinx/01_branson/branson_roci_scale_photonrange.csv

@@ -0,0 +1,8 @@
+Photons,32,64,96
+200,1.25e+08,2.42e+08,2.41e+08
+400,1.26e+08,2.39e+08,3.42e+08
+800,1.25e+08,2.39e+08,3.53e+08
+1000,1.26e+08,2.37e+08,3.6e+08
+2000,1.27e+08,2.46e+08,3.58e+08
+4000,1.27e+08,2.52e+08,3.67e+08
+8000,,2.54e+08,3.77e+08

doc/sphinx/01_branson/cpu.gp

@@ -33,9 +33,23 @@ set output "cpu_200M.png"
 plot "cpu_200M.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2
 
 # Scaling Output
-set output "branson_roci_scale.png"
+set output "branson_roci_scale_range.png"
 set xrange [200:8000]
 unset logscale xy
 set key title "Number of Nodes"
-plot "branson_roci_scale.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2, "" using 1:4 with line linestyle 3
+plot "branson_roci_scale_photonrange.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2, "" using 1:4 with line linestyle 3
+
+# SCALING PLOTS, Y IS FOM PER NODE
+set xrange [32:96]
+set yrange [2.5e6:3.5e6]
+set xlabel "Number of Nodes"
+set format y "%.1e"
+set ylabel "FOM/node"
+unset logscale xy
+set output "branson_roci_scale.png"
+set title "Branson Multi Node Scaling" font "serif,22"
+plot "branson_roci_scale.csv" using 3:5 with linespoints linestyle 1
 
+set output "branson_roci_scale_badnodes.png"
+set title "Branson Multi Node Scaling" font "serif,22"
+plot "branson_roci_badnodes_scale.csv" using 3:5 with linespoints linestyle 1

doc/sphinx/02_amg/amg.rst

@@ -346,28 +346,6 @@ Approximate results of the FOM for varying memory usages on Crossroads are provi
 
    Varying memory usage (estimated) for Problem 1 and 2
 
-
-Multi-node scaling on Crossroads
-================================
-
-The results of the scaling runs performed on rocinante hbm partition are presented below.
-Amg and hypre were built with intel oneapi 2023.1.0 and cray-mpich 8.1.25.
-These runs used 32, 64, and 96 nodes with 108 tasks per node.
-Problems 1 and 2 were run with problem sizes per MPI process, `-n`, of 25,25,125 and 40,40,200 respectively to use 15% of available memory.
-The product of the x,y,z process topology must equal the number of processors.
-In this case, x=y=24 for all node counts and z was set to 6, 12, and 18 for 32, 64, and 96 nodes respectively. 
-
-.. figure:: cpu_scale_roci.png
-   :align: center
-   :scale: 50%
-   :alt: 
-
-.. csv-table:: Multi Node Scaling AMG problem 1 and 2
-   :file: amg_scale_roci.csv
-   :align: center
-   :widths: 10, 10, 10
-   :header-rows: 1
-
 V-100
 =====
 
@@ -413,6 +391,26 @@ The FOMs of AMG2023 on V100 for Problem 2 is provided in the following table and
 
    AMG2023 FOM on V100 for Problem 2 (7-pt stencil, AMG-PCG)
 
+Multi-node scaling on Crossroads
+================================
+
+The results of the scaling runs performed on rocinante hbm partition are presented below.
+Amg and hypre were built with intel oneapi 2023.1.0 and cray-mpich 8.1.25.
+These runs used 32, 64, and 96 nodes with 108 tasks per node.
+Problems 1 and 2 were run with problem sizes per MPI process, `-n`, of 25,25,125 and 40,40,200 respectively to use 15% of available memory.
+The product of the x,y,z process topology must equal the number of processors.
+In this case, x=y=24 for all node counts and z was set to 6, 12, and 18 for 32, 64, and 96 nodes respectively. 
+
+.. figure:: cpu_scale_roci.png
+   :align: center
+   :scale: 50%
+   :alt: 
+
+.. csv-table:: Multi Node Scaling AMG problem 1 and 2
+   :file: amg_scale_roci.csv
+   :align: center
+   :widths: 10, 10, 10, 10, 10
+   :header-rows: 1
 
 References
 ==========

doc/sphinx/02_amg/amg_scale_roci.csv

@@ -1,4 +1,4 @@
-NumNodes,Problem1,Problem2
-96,7.3e+09,3.01e+09
-64,5.44e+09,2.09e+09
-32,3.29e+09,1.19e+09
+NumNodes,Problem1,Problem2,Problem1,Problem2
+96,7.30E+09,3.01E+09,7.60E+07,3.14E+07
+64,5.44E+09,2.09E+09,8.50E+07,3.27E+07
+32,3.29E+09,1.19E+09,1.03E+08,3.72E+07

doc/sphinx/02_amg/cpu.gp

@@ -44,11 +44,13 @@ set output "roci_2_320.png"
 set title "AMG2023 Strong Scaling for Problem 2, 320 x 320 x 320" font "serif,22"
 plot "roci_2_320.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2
 
+# SCALING PLOTS, Y IS FOM PER NODE
 set xrange [32:96]
 set xlabel "Number of Nodes"
 set format y "%.1e"
+set ylabel "FOM/node"
 unset logscale xy
 set output "cpu_scale_roci.png"
 set title "AMG Multi Node Scaling" font "serif,22"
-plot "amg_scale_roci.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2
+plot "amg_scale_roci.csv" using 1:4 with linespoints linestyle 1, "" using 1:5 with line linestyle 2