From a0ce607aea5e4dc408444b0edc89499af6298103 Mon Sep 17 00:00:00 2001 From: Galen Shipman Date: Wed, 20 Sep 2023 15:22:01 -0700 Subject: [PATCH] update branson results to Crossroads --- doc/sphinx/1_branson/branson.rst | 61 ++++++++++++++++----------- doc/sphinx/1_branson/cpu.gp | 16 +++---- doc/sphinx/1_branson/cpu_10M.csv | 6 +++ doc/sphinx/1_branson/cpu_200M.csv | 12 +++--- doc/sphinx/1_branson/cpu_200M_bdw.csv | 6 +++ doc/sphinx/1_branson/cpu_66M.csv | 12 +++--- doc/sphinx/1_branson/cpu_66M_bdw.csv | 6 +++ 7 files changed, 74 insertions(+), 45 deletions(-) create mode 100644 doc/sphinx/1_branson/cpu_10M.csv create mode 100644 doc/sphinx/1_branson/cpu_200M_bdw.csv create mode 100644 doc/sphinx/1_branson/cpu_66M_bdw.csv diff --git a/doc/sphinx/1_branson/branson.rst b/doc/sphinx/1_branson/branson.rst index a12fe026..e185ed55 100644 --- a/doc/sphinx/1_branson/branson.rst +++ b/doc/sphinx/1_branson/branson.rst @@ -103,68 +103,79 @@ Running .. -For strong scaling on a CPU the memory footprint of Branson must be between 28% and 34% of the computational device's main memory. -The memory footprint can be controlled by editing "photons" in the input file. -On a dual socket Intel Haswell (E5-2695 v4 2.10GHz) with 128GByte of total system memory using 120000000 photons is ~41.1GByte (Resident set size) or approximately %32.7. +For strong scaling on a CPU the Branson should be run with three different problem sizes such that the memory +footprint at the smallest process count per node is approximately 4 to 5%, 8 to 10%, and 20 to 22% during step 2 of the simulation. +Memory footprint is the sum of all Branson processes resident set size (or equivalent) on the node. +This can be obtained on a CPU system using the following (while the application is in step 2): + +.. code-block:: bash + + ps -C BRANSON -o euser,c,pid,ppid,cmd,%cpu,%mem,rss --sort=-rss + + ps -C BRANSON -o rss | awk '{sum+=$1;} END{print sum/1024/1024;}' +.. -For throughput curves on a GPU the memory footprint of Branson must vary between 5% and 90% in increments of at most 5% of the computational device's main memory. + + + +For throughput curves on a GPU the memory footprint of Branson must vary between ~5% and ~60% in increments of at most 5% of the computational device's main memory. The memory footprint can be controlled by editing "photons" in the input file. Results from Branson are provided on the following systems: -* Commodity Technology System 1 (CTS-1) with Intel Broadwell processors, +* Crossroads, * IBM Power9 with Nvidia V100 GPU, -CTS-1 +Crossroads ------------ -Strong scaling performance of Branson CTS-1 66M Particles is provided within the following table and +Strong scaling performance of Crossroads 66M Particles is provided within the following table and figure. -.. csv-table:: Branson Strong Scaling Performance on CTS-1 66M particles - :file: cpu_66M.csv +.. csv-table:: Branson Strong Scaling Performance on Crossroads 10M particles + :file: cpu_10M.csv :align: center - :widths: 10, 10, 10 + :widths: 10, 10, 10, 10, 10 :header-rows: 1 -.. figure:: cpu_66M.png +.. figure:: cpu_10M.png :align: center :scale: 50% - :alt: Branson Strong Scaling Performance on CTS-1 66M particles + :alt: Branson Strong Scaling Performance on Crossroads 10M particles -Branson Strong Scaling Performance on CTS-1 66M particles +Branson Strong Scaling Performance on Crossroads 10M particles -Strong scaling performance of Branson CTS-1 133M Particles is provided within the following table and +Strong scaling performance of Branson Crossroads 66M Particles is provided within the following table and figure. -.. csv-table:: Branson Strong Scaling Performance on CTS-1 133M particles - :file: cpu_133M.csv +.. csv-table:: Branson Strong Scaling Performance on Crossroads 66M particles + :file: cpu_66M.csv :align: center - :widths: 10, 10, 10 + :widths: 10, 10, 10, 10, 10 :header-rows: 1 -.. figure:: cpu_133M.png +.. figure:: cpu_10M.png :align: center :scale: 50% - :alt: Branson Strong Scaling Performance on CTS-1 133M particles + :alt: Branson Strong Scaling Performance on Crossroads 66M particles -Branson Strong Scaling Performance on CTS-1 133M particles +Branson Strong Scaling Performance on Crossroads 66M particles -Strong scaling performance of Branson CTS-1 200M Particles is provided within the following table and +Strong scaling performance of Branson Crossroads 200M Particles is provided within the following table and figure. -.. csv-table:: Branson Strong Scaling Performance on CTS-1 200M particles +.. csv-table:: Branson Strong Scaling Performance on Crossroads 200M particles :file: cpu_200M.csv :align: center - :widths: 10, 10, 10 + :widths: 10, 10, 10, 10, 10 :header-rows: 1 .. figure:: cpu_200M.png :align: center :scale: 50% - :alt: Branson Strong Scaling Performance on CTS-1 200M particles + :alt: Branson Strong Scaling Performance on Crossroads 200M particles -Branson Strong Scaling Performance on CTS-1 200M particles +Branson Strong Scaling Performance on Crossroads 200M particles Power9+V100 ------------ diff --git a/doc/sphinx/1_branson/cpu.gp b/doc/sphinx/1_branson/cpu.gp index e4bb7155..47cccd33 100644 --- a/doc/sphinx/1_branson/cpu.gp +++ b/doc/sphinx/1_branson/cpu.gp @@ -1,12 +1,12 @@ #!/usr/bin/gnuplot set terminal pngcairo enhanced size 1024, 768 dashed font 'Helvetica,18' -set output "cpu_66M.png" +set output "cpu_10M.png" -set title "Branson Strong Scaling Performance on CTS-1, 66M particles" font "serif,22" +set title "Branson Strong Scaling Performance on Crossroads, 10M particles" font "serif,22" set xlabel "No. Processing Elements" set ylabel "Figure of Merit (particles/sec)" -set xrange [1:64] +set xrange [8:112] set key left top set logscale x 2 @@ -21,15 +21,15 @@ 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 -plot "cpu_66M.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2 +plot "cpu_10M.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2 -set output "cpu_133M.png" -set title "Branson Strong Scaling Performance on CTS-1, 133M particles" font "serif,22" -plot "cpu_133M.csv" using 1:2 with linespoints linestyle 1, "" using 1:3 with line linestyle 2 +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 CTS-1, 200M particles" font "serif,22" +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 diff --git a/doc/sphinx/1_branson/cpu_10M.csv b/doc/sphinx/1_branson/cpu_10M.csv new file mode 100644 index 00000000..b534ef70 --- /dev/null +++ b/doc/sphinx/1_branson/cpu_10M.csv @@ -0,0 +1,6 @@ +No. Cores, Actual, Ideal, Memory (GB), Memory (%) +8,8.85e+04,8.85e+04, 4.8, 3.75 +32,3.48e+05,3.54e+05, --, -- +56,5.61e+05,6.19e+05, --, -- +88,7.52e+05,9.73e+05, --, -- +112,9.08e+05,1.24e+06, 52.27, 40.8 diff --git a/doc/sphinx/1_branson/cpu_200M.csv b/doc/sphinx/1_branson/cpu_200M.csv index 33e958cb..fd0767f6 100644 --- a/doc/sphinx/1_branson/cpu_200M.csv +++ b/doc/sphinx/1_branson/cpu_200M.csv @@ -1,6 +1,6 @@ -No. Cores, Actual, Ideal -4,2.684683e+04,2.684683e+04 -8,5.046809e+04,5.369366e+04 -18,9.855907e+04,1.20810735e+05 -26,1.413827e+05,1.74504395e+05 -36,1.915213e+05,2.4162147e+05 \ No newline at end of file +No. Cores, Actual, Ideal, Memory (GB) +8,9.27E+04,9.27e+04, 26.026, 20.3 +32,3.80E+05,3.80E+05, --, -- +56,5.80E+05,6.44E+05, --, -- +88,7.90E+05,1.01E+06, --, -- +112,9.59E+05,1.29E+06, 73.46, 57.3 diff --git a/doc/sphinx/1_branson/cpu_200M_bdw.csv b/doc/sphinx/1_branson/cpu_200M_bdw.csv new file mode 100644 index 00000000..33e958cb --- /dev/null +++ b/doc/sphinx/1_branson/cpu_200M_bdw.csv @@ -0,0 +1,6 @@ +No. Cores, Actual, Ideal +4,2.684683e+04,2.684683e+04 +8,5.046809e+04,5.369366e+04 +18,9.855907e+04,1.20810735e+05 +26,1.413827e+05,1.74504395e+05 +36,1.915213e+05,2.4162147e+05 \ No newline at end of file diff --git a/doc/sphinx/1_branson/cpu_66M.csv b/doc/sphinx/1_branson/cpu_66M.csv index 6f0c7095..5187577f 100644 --- a/doc/sphinx/1_branson/cpu_66M.csv +++ b/doc/sphinx/1_branson/cpu_66M.csv @@ -1,6 +1,6 @@ -No. Cores, Actual, Ideal -4,2.672975e+04,2.672975e+04 -8,5.039091e+04,5.34595e+04 -18,9.831885e+04,1.20283875e+05 -26,1.398838e+05,1.73743375e+05 -36,1.916970e+05,2.4056775e+05 +No. Cores, Actual, Ideal, Memory +8,9.20E+04,2.672975e+04, 11.04 +32,3.62E+05,3.68E+05, -- +56,5.76E+05,6.44E+05, -- +88,7.74E+05,1.01E+06, -- +112,9.52E+05,1.29E+06, 58.44 diff --git a/doc/sphinx/1_branson/cpu_66M_bdw.csv b/doc/sphinx/1_branson/cpu_66M_bdw.csv new file mode 100644 index 00000000..6f0c7095 --- /dev/null +++ b/doc/sphinx/1_branson/cpu_66M_bdw.csv @@ -0,0 +1,6 @@ +No. Cores, Actual, Ideal +4,2.672975e+04,2.672975e+04 +8,5.039091e+04,5.34595e+04 +18,9.831885e+04,1.20283875e+05 +26,1.398838e+05,1.73743375e+05 +36,1.916970e+05,2.4056775e+05