From c6d6b8e7cc0682aff184d92e5fc08340541adda4 Mon Sep 17 00:00:00 2001
From: "Daniel J. Magee" <dmagee@lanl.gov>
Date: Wed, 17 Jan 2024 13:38:05 -0700
Subject: [PATCH] Branson roci scaling results with plots and table.

---
 doc/sphinx/01_branson/branson.rst            | 20 +++++++++++++++++++-
 doc/sphinx/01_branson/branson_roci_scale.csv |  8 ++++++++
 doc/sphinx/01_branson/cpu.gp                 |  8 +++++++-
 doc/sphinx/02_amg/amg.rst                    |  2 +-
 4 files changed, 35 insertions(+), 3 deletions(-)
 create mode 100644 doc/sphinx/01_branson/branson_roci_scale.csv

diff --git a/doc/sphinx/01_branson/branson.rst b/doc/sphinx/01_branson/branson.rst
index 72cab122..7a6f4c7f 100644
--- a/doc/sphinx/01_branson/branson.rst
+++ b/doc/sphinx/01_branson/branson.rst
@@ -245,7 +245,8 @@ lose their energy into the material.
 
 
 Crossroads
-------------
+----------
+
 Strong scaling performance of Crossroads 10M Particles is provided within the following table and
 figure.
 
@@ -293,6 +294,23 @@ 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.
+These runs used 32, 64, and 96 nodes with 110 tasks per node.
+
+
+.. figure:: branson_roci_scale.png
+   :align: center
+   :scale: 50%
+   :alt: 
+
+.. csv-table:: Multi Node Scaling problem 1 and 2
+   :file: branson_roci_scale.csv
+   :align: center
+   :widths: 10, 10, 10, 10
+   :header-rows: 1
 
 AMD Epyc + Nvidia A100
 ----------------------
diff --git a/doc/sphinx/01_branson/branson_roci_scale.csv b/doc/sphinx/01_branson/branson_roci_scale.csv
new file mode 100644
index 00000000..08023132
--- /dev/null
+++ b/doc/sphinx/01_branson/branson_roci_scale.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
diff --git a/doc/sphinx/01_branson/cpu.gp b/doc/sphinx/01_branson/cpu.gp
index ca421797..2d669d86 100644
--- a/doc/sphinx/01_branson/cpu.gp
+++ b/doc/sphinx/01_branson/cpu.gp
@@ -20,6 +20,7 @@ set key autotitle columnheader
 
 set style line 1 linetype 6 dashtype 1 linecolor rgb "#FF0000" linewidth 2 pointtype 6 pointsize 3
 set style line 2 linetype 1 dashtype 2 linecolor rgb "#FF0000" linewidth 2
+set style line 3 linetype 6 dashtype 1 linecolor rgb "#0000FF" linewidth 2 pointtype 6 pointsize 3
 
 plot "cpu_10M.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2
 
@@ -27,9 +28,14 @@ set output "cpu_66M.png"
 #set title "Branson Strong Scaling Performance on Crossroads, 66M particles" font "serif,22"
 plot "cpu_66M.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2
 
-
 set output "cpu_200M.png"
 #set title "Branson Strong Scaling Performance on Crossroads, 200M particles" font "serif,22"
 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 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
 
diff --git a/doc/sphinx/02_amg/amg.rst b/doc/sphinx/02_amg/amg.rst
index 086c82c9..86db5194 100644
--- a/doc/sphinx/02_amg/amg.rst
+++ b/doc/sphinx/02_amg/amg.rst
@@ -350,7 +350,7 @@ Approximate results of the FOM for varying memory usages on Crossroads are provi
 Multi-node scaling on Crossroads
 ================================
 
-The results of the scaling runs performed on rocinante hbm partition nodesare presented below.
+The results of the scaling runs performed on rocinante hbm partition nodes are presented below.
 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 of 25,25,50 and 36,36,72 respectively.
 The product of the x,y,z process topology must equal the number of processors.