requested changes

Author: wilfonba

docs/documentation/expectedPerformance.md

@@ -11,9 +11,10 @@ The following table outlines expected performance in terms of number of time-ste
 | Hardware             | # Ranks | 1M Cells       | 4M Cells       | 8M Cells     | Compiler    | Computer      |
 | ---:                 | :----:  |    :----:      |  :---:         | :---:        | :----:      | :---          |
 | Nvidia V100          | 1       | 88.5k          | 18.7k          | N/A          | NVHPC 22.11 | PACE Phoenix  |
+| Nvidia V100          | 1       | 78.8k          | 18.8k          | N/A          | NVHPC 22.11 | OLCF Summit   |
 | Nvidia A100          | 1       | 114.4k         | 34.6k          | 16.5k        | NVHPC 23.5  | Wingtip       |
 | AMD MI250x           | 1       | 77.5k          | 22.3k          | 11.2k        | CCE 16.0.1  | OLCF Frontier |
-| Intel Xeon Gold 6226 | 12      | 2.5k           | 0.7k           | 0.4k         | GNU 10.3.0  | Pace Phoenix  |
+| Intel Xeon Gold 6226 | 12      | 2.5k           | 0.7k           | 0.4k         | GNU 10.3.0  | PACE Phoenix  |
 | Apple Silicon M2     | 6       | 2.8k           | 0.6k           | 0.2k         | GNU 13.2.0  | N/A           |
 
 If `'model_eqns' : 3` is replaced by `'model_eqns' : 2`, an inviscid 5-equation model is used.
@@ -23,10 +24,11 @@ The following table outlines expected performance in terms of number of time-ste
 
 | Hardware             | # Ranks | 1M Cells       | 4M Cells       | 8M Cells     | Compiler    | Computer      |
 | ---:                 | :----:  |    :----:      |  :---:         | :---:        | :----:      | :---          |
-| Nvidia V100          | 1       | 113.4k         | 26.2k          | N/A          | NVHPC 22.11 | PACE Phoenix  |
+| Nvidia V100          | 1       | 113.4k         | 26.2k          | 13.0k        | NVHPC 22.11 | PACE Phoenix  |
+| Nvidia V100          | 1       | 107.7k         | 26.3k          | 13.1k        | NVHPC 22.11 | OLCF Summit   |
 | Nvidia A100          | 1       | 153.5k         | 48.0k          | 22.5k        | NVHPC 23.5  | Wingtip       |
 | AMD MI250x           | 1       | 104.2k         | 31.0k          | 14.8k        | CCE 16.0.1  | OLCF Frontier |
-| Intel Xeon Gold 6226 | 12      | 5.4k           | 1.6k           | 0.8k         | GNU 10.3.0  | Pace Phoenix  |
+| Intel Xeon Gold 6226 | 12      | 5.4k           | 1.6k           | 0.8k         | GNU 10.3.0  | PACE Phoenix  |
 | Apple Silicon M2     | 6       | 3.7k           | 11.0k          | 0.3k         | GNU 13.2.0  | N/A           |
 
 ## Weak scaling
@@ -35,17 +37,17 @@ Strong scaling results are obtained by increasing the problem size with the numb
 so that work per process remains constant.
 
 ### AMD MI250X GPU
-MFC weask scales to 65,536 AMD MI250X GPUs on OLCF Frontier with 96% efficiency.
+MFC weask scales to 65,536 AMD MI250X GPUs on OLCF Frontier with 96% efficiency. This corresponds to 87% of the entire machine.
 
 <img src="../res/weakScaling/frontier.svg" style="height: 50%; width:50%; border-radius: 10pt"/>
 
 ### Nvidia V100 GPU
-MFC weak scales to 13,824 V100 Nvidia V100 GPUs on OLCF Summit with 97% efficiency.
+MFC weak scales to 13,824 V100 Nvidia V100 GPUs on OLCF Summit with 97% efficiency. This corresponds to 50% of the entire machine.
 
 <img src="../res/weakScaling/summit.svg" style="height: 50%; width:50%; border-radius: 10pt"/>
 
 ### IMB Power9 CPU
-MFC Weak scales to 13,824 Power9 CPU cores on OLCF Summit with 1% of ideal scaling.
+MFC Weak scales to 13,824 Power9 CPU cores on OLCF Summit to within 1% of ideal scaling.
 
 <img src="../res/weakScaling/cpuScaling.svg" style="height: 50%; width:50%; border-radius: 10pt"/>
 

docs/res/strongScaling/S01.95

@@ -295,7 +295,7 @@ contains
         flux_lim = dflt_int
         flux_wrt = .false.
         parallel_io = .false.
-        file_per_process = .true.
+        file_per_process = .false.
         E_wrt = .false.
         pres_wrt = .false.
         alpha_wrt = .false.

src/post_process/m_global_parameters.fpp

@@ -251,7 +251,7 @@ contains
         bc_z%beg = dflt_int; bc_z%end = dflt_int
 
         parallel_io = .false.
-        file_per_process = .true.
+        file_per_process = .false.
         precision = 2
         vel_profile = .false.
         instability_wave = .false.

src/pre_process/m_global_parameters.fpp

@@ -374,7 +374,7 @@ contains
         null_weights = .false.
         mixture_err = .false.
         parallel_io = .false.
-        file_per_process = .true.
+        file_per_process = .false.
         precision = 2
         hypoelasticity = .false.
         weno_flat = .true.