smyalygames/FiniteVolumeGPU
1
0
Fork 0
mirror of https://github.com/smyalygames/FiniteVolumeGPU.git synced 2025-05-18 14:34:13 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

Compare commits

base: smyalygames:c485b3721943444b66e45068f6e8dd7b7d8b7b6c
Branches Tags
smyalygames:master
smyalygames:euler
smyalygames:cleanup
smyalygames:waf_exp
smyalygames:mpi_test
...
compare: smyalygames:e7cd6ae34a18bbbb314f72e63b8660c6e55391f6
Branches Tags
smyalygames:master
smyalygames:euler
smyalygames:cleanup
smyalygames:waf_exp
smyalygames:mpi_test

2 Commits
c485b37219 ... e7cd6ae34a

Author SHA1 Message Date
Anthony Berg
e7cd6ae34a feat: add progress bar for Autotuner 2025-03-26 00:28:16 +01:00
Anthony Berg
079bad08b8 feat: add having run jupyter notebooks with fixes 2025-03-25 23:25:23 +01:00
8 changed files with 141068 additions and 538182 deletions
Show Stats Expand all files Collapse all files

154
Autotuning.ipynb
View File

File diff suppressed because one or more lines are too long

678674
EulerTesting.ipynb
View File

File diff suppressed because one or more lines are too long

107
Figures_Saga.ipynb
View File

@ -75,79 +75,15 @@
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "ename": "FileNotFoundError",
"output_type": "stream", "evalue": "[Errno 2] No such file or directory: 'output_saga/weak_scaling/2022-06-21T235600/'",
"text": [ "output_type": "error",
" t_init t_total outfile \\\n", "traceback": [
"0 13.151470 187.123114 /cluster/work/jobs/5995581/ShallowWaterGPU/mpi... \n", "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"1 17.898452 210.700137 /cluster/work/jobs/6040817/ShallowWaterGPU/mpi... \n", "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
"2 19.701864 208.722497 /cluster/work/jobs/5995583/ShallowWaterGPU/mpi... \n", "Cell \u001b[0;32mIn[5], line 12\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# DGX-2\u001b[39;00m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;66;03m#weak_scaling_profiling_data = read_profiling_files(\"output_dgx-2/weak_scaling/2022-06-09T134809/\")\u001b[39;00m\n\u001b[1;32m 3\u001b[0m \u001b[38;5;66;03m#weak_scaling_profiling_data = read_profiling_files(\"output_dgx-2/weak_scaling/2022-06-23T154025/\")\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[38;5;66;03m#singlenode_weak_scaling_profiling_data = read_profiling_files(\"output_saga/weak_scaling/2022-06-16T151516/\", drop_multinode=True)\u001b[39;00m\n\u001b[1;32m 11\u001b[0m \u001b[38;5;66;03m#multinode_weak_scaling_profiling_data = read_profiling_files(\"output_saga/weak_scaling/2022-06-16T151516/\", drop_singlenode=True)\u001b[39;00m\n\u001b[0;32m---> 12\u001b[0m singlenode_weak_scaling_profiling_data \u001b[38;5;241m=\u001b[39m \u001b[43mread_profiling_files\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43moutput_saga/weak_scaling/2022-06-21T235600/\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdrop_multinode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 13\u001b[0m multinode_weak_scaling_profiling_data \u001b[38;5;241m=\u001b[39m read_profiling_files(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124moutput_saga/weak_scaling/2022-06-21T235600/\u001b[39m\u001b[38;5;124m\"\u001b[39m, drop_singlenode\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28mprint\u001b[39m(singlenode_weak_scaling_profiling_data)\n",
"3 22.790222 218.337566 /cluster/work/jobs/5995584/ShallowWaterGPU/mpi... \n", "Cell \u001b[0;32mIn[4], line 4\u001b[0m, in \u001b[0;36mread_profiling_files\u001b[0;34m(profile_dir_path, drop_multinode, drop_singlenode)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mread_profiling_files\u001b[39m(profile_dir_path\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m, drop_multinode\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, drop_singlenode\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[1;32m 2\u001b[0m profiling_data \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mDataFrame()\n\u001b[0;32m----> 4\u001b[0m json_filenames \u001b[38;5;241m=\u001b[39m [file \u001b[38;5;28;01mfor\u001b[39;00m file \u001b[38;5;129;01min\u001b[39;00m \u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlistdir\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprofile_dir_path\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m file\u001b[38;5;241m.\u001b[39mendswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_profiling.json\u001b[39m\u001b[38;5;124m\"\u001b[39m)]\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m(drop_singlenode):\n\u001b[1;32m 7\u001b[0m json_filenames \u001b[38;5;241m=\u001b[39m [file \u001b[38;5;28;01mfor\u001b[39;00m file \u001b[38;5;129;01min\u001b[39;00m json_filenames \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m1_nodes\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m file]\n",
"\n", "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'output_saga/weak_scaling/2022-06-21T235600/'"
" t_sim_init t_nc_write t_full_step t_mpi_halo_exchange \\\n",
"0 12.316193 92.680975 67.334274 0.0 \n",
"1 24.190988 97.482013 67.381501 0.0 \n",
"2 21.237509 98.550311 67.510278 0.0 \n",
"3 24.143164 102.122138 67.474521 0.0 \n",
"\n",
" t_mpi_halo_exchange_download t_mpi_halo_exchange_upload \\\n",
"0 66.403320 0.039551 \n",
"1 66.379639 0.048828 \n",
"2 66.364868 0.041748 \n",
"3 66.378784 0.043457 \n",
"\n",
" t_mpi_halo_exchange_sendreceive t_mpi_step nx ny dt \\\n",
"0 0.111572 0.025024 20480.0 20480.0 0.000001 \n",
"1 0.247070 0.032532 20480.0 20480.0 0.000001 \n",
"2 0.428223 0.029236 20480.0 20480.0 0.000001 \n",
"3 0.330811 0.030945 20480.0 20480.0 0.000001 \n",
"\n",
" n_time_steps slurm_job_id n_cuda_devices n_processes \\\n",
"0 200.0 5995581.0 1 1 \n",
"1 200.0 6040817.0 2 2 \n",
"2 200.0 5995583.0 3 3 \n",
"3 200.0 5995584.0 4 4 \n",
"\n",
" git_hash \\\n",
"0 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"1 a7a723aca682be4b3c12e6e1f982042aecaa5486\\n \n",
"2 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"3 528b738dda0dbbc4d61db24ef86811d246c47836\\n \n",
"\n",
" git_status \n",
"0 M Figures.ipynb\\n M conda_environment_hpc.yml... \n",
"1 M conda_environment_hpc.yml\\n \n",
"2 M Figures.ipynb\\n M conda_environment_hpc.yml... \n",
"3 M Figures.ipynb\\n M conda_environment_hpc.yml... \n",
" t_init t_total outfile \\\n",
"0 16.962855 204.441923 /cluster/work/jobs/5995585/ShallowWaterGPU/mpi... \n",
"1 17.445864 203.642585 /cluster/work/jobs/5995586/ShallowWaterGPU/mpi... \n",
"2 16.334049 201.706250 /cluster/work/jobs/5995587/ShallowWaterGPU/mpi... \n",
"\n",
" t_sim_init t_nc_write t_full_step t_mpi_halo_exchange \\\n",
"0 18.412322 96.080178 71.158770 0.0 \n",
"1 19.265495 93.089388 72.148323 0.0 \n",
"2 15.037347 94.247609 74.494262 0.0 \n",
"\n",
" t_mpi_halo_exchange_download t_mpi_halo_exchange_upload \\\n",
"0 66.372192 0.051147 \n",
"1 66.372192 0.045532 \n",
"2 66.035767 0.051880 \n",
"\n",
" t_mpi_halo_exchange_sendreceive t_mpi_step nx ny dt \\\n",
"0 4.722656 0.033875 20480.0 20480.0 0.000001 \n",
"1 5.855469 0.027893 20480.0 20480.0 0.000001 \n",
"2 8.360107 0.035767 20480.0 20480.0 0.000001 \n",
"\n",
" n_time_steps slurm_job_id n_cuda_devices n_processes \\\n",
"0 200.0 5995585.0 1 2 \n",
"1 200.0 5995586.0 1 3 \n",
"2 200.0 5995587.0 1 4 \n",
"\n",
" git_hash git_status \n",
"0 a7a723aca682be4b3c12e6e1f982042aecaa5486\\n M conda_environment_hpc.yml\\n \n",
"1 a7a723aca682be4b3c12e6e1f982042aecaa5486\\n M conda_environment_hpc.yml\\n \n",
"2 a7a723aca682be4b3c12e6e1f982042aecaa5486\\n M conda_environment_hpc.yml\\n \n"
] ]
} }
], ],
@ -179,7 +115,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -190,7 +126,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -201,7 +137,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -297,7 +233,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 43, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -429,7 +365,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -509,7 +445,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 18, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -550,7 +486,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -591,7 +527,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 22, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -646,7 +582,7 @@
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "Python 3.7.12 ('ShallowWaterGPU_HPC')", "display_name": "ShallowWaterGPU",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -660,12 +596,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.7.12" "version": "3.9.19"
},
"vscode": {
"interpreter": {
"hash": "cb8fa661d82d1ec49918052345889e962ab1d5f5f5cbd9596ba31c436e222a26"
}
} }
}, },
"nbformat": 4, "nbformat": 4,

170
Figures_Simula.ipynb
View File

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 7,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -17,7 +17,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 8,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -26,7 +26,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 9,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -36,7 +36,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 10,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -71,138 +71,19 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 11,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "ename": "FileNotFoundError",
"output_type": "stream", "evalue": "[Errno 2] No such file or directory: 'output_dgx-2/weak_scaling/2022-06-23T154025/'",
"text": [ "output_type": "error",
" t_init t_total outfile \\\n", "traceback": [
"0 14.511714 181.754037 /work/martinls/232557/ShallowWaterGPU/mpi_out_... \n", "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"1 15.153404 188.838794 /work/martinls/232558/ShallowWaterGPU/mpi_out_... \n", "\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
"2 15.607471 190.535054 /work/martinls/232589/ShallowWaterGPU/mpi_out_... \n", "Cell \u001b[0;32mIn[11], line 3\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# DGX-2\u001b[39;00m\n\u001b[1;32m 2\u001b[0m \u001b[38;5;66;03m#weak_scaling_profiling_data = read_profiling_files(\"output_dgx-2/weak_scaling/2022-06-09T134809/\")\u001b[39;00m\n\u001b[0;32m----> 3\u001b[0m weak_scaling_profiling_data \u001b[38;5;241m=\u001b[39m \u001b[43mread_profiling_files\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43moutput_dgx-2/weak_scaling/2022-06-23T154025/\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[38;5;66;03m# HGX\u001b[39;00m\n\u001b[1;32m 6\u001b[0m \u001b[38;5;66;03m#weak_scaling_profiling_data = read_profiling_files(\"output_hgx/weak_scaling/2022-06-16T162931/\")\u001b[39;00m\n\u001b[1;32m 7\u001b[0m \u001b[38;5;66;03m##weak_scaling_profiling_data = read_profiling_files(\"output_hgx/weak_scaling/2022-06-16T170630/\")\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[38;5;66;03m#singlenode_weak_scaling_profiling_data = read_profiling_files(\"output_saga/weak_scaling/2022-06-16T151516/\", drop_multinode=True)\u001b[39;00m\n\u001b[1;32m 11\u001b[0m \u001b[38;5;66;03m#multinode_weak_scaling_profiling_data = read_profiling_files(\"output_saga/weak_scaling/2022-06-16T151516/\", drop_singlenode=True)\u001b[39;00m\n\u001b[1;32m 13\u001b[0m \u001b[38;5;28mprint\u001b[39m(weak_scaling_profiling_data)\n",
"3 15.332916 188.146165 /work/martinls/232590/ShallowWaterGPU/mpi_out_... \n", "Cell \u001b[0;32mIn[10], line 4\u001b[0m, in \u001b[0;36mread_profiling_files\u001b[0;34m(profile_dir_path, drop_multinode, drop_singlenode)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mread_profiling_files\u001b[39m(profile_dir_path\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m, drop_multinode\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, drop_singlenode\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[1;32m 2\u001b[0m profiling_data \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mDataFrame()\n\u001b[0;32m----> 4\u001b[0m json_filenames \u001b[38;5;241m=\u001b[39m [file \u001b[38;5;28;01mfor\u001b[39;00m file \u001b[38;5;129;01min\u001b[39;00m \u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlistdir\u001b[49m\u001b[43m(\u001b[49m\u001b[43mprofile_dir_path\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mif\u001b[39;00m file\u001b[38;5;241m.\u001b[39mendswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_profiling.json\u001b[39m\u001b[38;5;124m\"\u001b[39m)]\n\u001b[1;32m 6\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m(drop_singlenode):\n\u001b[1;32m 7\u001b[0m json_filenames \u001b[38;5;241m=\u001b[39m [file \u001b[38;5;28;01mfor\u001b[39;00m file \u001b[38;5;129;01min\u001b[39;00m json_filenames \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m1_nodes\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m file]\n",
"4 15.941363 193.263406 /work/martinls/232591/ShallowWaterGPU/mpi_out_... \n", "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'output_dgx-2/weak_scaling/2022-06-23T154025/'"
"5 16.805506 194.776481 /work/martinls/232592/ShallowWaterGPU/mpi_out_... \n",
"6 18.009921 198.615131 /work/martinls/232593/ShallowWaterGPU/mpi_out_... \n",
"7 17.990572 199.018155 /work/martinls/232594/ShallowWaterGPU/mpi_out_... \n",
"8 19.366701 202.898836 /work/martinls/232595/ShallowWaterGPU/mpi_out_... \n",
"9 19.890607 205.122811 /work/martinls/232596/ShallowWaterGPU/mpi_out_... \n",
"10 20.974516 207.287065 /work/martinls/232597/ShallowWaterGPU/mpi_out_... \n",
"11 21.358601 209.105944 /work/martinls/232598/ShallowWaterGPU/mpi_out_... \n",
"12 22.813077 211.172879 /work/martinls/232599/ShallowWaterGPU/mpi_out_... \n",
"13 23.636758 212.722331 /work/martinls/232600/ShallowWaterGPU/mpi_out_... \n",
"14 23.983026 214.176335 /work/martinls/232601/ShallowWaterGPU/mpi_out_... \n",
"15 24.996966 216.951382 /work/martinls/232602/ShallowWaterGPU/mpi_out_... \n",
"\n",
" t_sim_init t_nc_write t_full_step t_mpi_halo_exchange \\\n",
"0 10.661480 113.172576 42.137838 0.0 \n",
"1 11.083883 118.234985 43.038861 0.0 \n",
"2 11.338173 118.849141 43.378157 0.0 \n",
"3 11.166394 116.970772 43.362903 0.0 \n",
"4 11.167876 121.090511 43.696337 0.0 \n",
"5 11.125732 122.019746 43.435468 0.0 \n",
"6 11.410769 124.265493 43.508696 0.0 \n",
"7 11.951049 123.907622 43.785883 0.0 \n",
"8 11.861801 126.177618 44.059032 0.0 \n",
"9 12.045421 127.249941 44.542234 0.0 \n",
"10 12.357193 128.412160 44.133266 0.0 \n",
"11 12.668238 129.337771 44.327086 0.0 \n",
"12 12.733378 129.754346 44.384927 0.0 \n",
"13 12.836023 130.674045 44.157766 0.0 \n",
"14 13.105231 131.080429 44.535530 0.0 \n",
"15 13.106097 133.506058 43.892579 0.0 \n",
"\n",
" t_mpi_halo_exchange_download t_mpi_halo_exchange_upload \\\n",
"0 41.482056 0.042358 \n",
"1 41.775146 0.042603 \n",
"2 41.762573 0.041992 \n",
"3 41.740112 0.041138 \n",
"4 41.728638 0.043213 \n",
"5 41.725586 0.044678 \n",
"6 41.731934 0.044067 \n",
"7 41.630493 0.043823 \n",
"8 41.810547 0.044678 \n",
"9 41.643677 0.044678 \n",
"10 41.851196 0.045288 \n",
"11 41.774414 0.046509 \n",
"12 41.790405 0.046509 \n",
"13 41.642212 0.046387 \n",
"14 41.643066 0.045044 \n",
"15 41.756714 0.047485 \n",
"\n",
" t_mpi_halo_exchange_sendreceive t_mpi_step nx ny dt \\\n",
"0 0.059082 0.025330 22528.0 22528.0 0.000001 \n",
"1 0.402832 0.026062 22528.0 22528.0 0.000001 \n",
"2 0.779541 0.026123 22528.0 22528.0 0.000001 \n",
"3 1.217041 0.025879 22528.0 22528.0 0.000001 \n",
"4 1.111328 0.026855 22528.0 22528.0 0.000001 \n",
"5 0.885742 0.027466 22528.0 22528.0 0.000001 \n",
"6 0.954346 0.027405 22528.0 22528.0 0.000001 \n",
"7 1.984375 0.028320 22528.0 22528.0 0.000001 \n",
"8 1.729980 0.027954 22528.0 22528.0 0.000001 \n",
"9 1.878174 0.028931 22528.0 22528.0 0.000001 \n",
"10 1.613525 0.029053 22528.0 22528.0 0.000001 \n",
"11 1.831299 0.028137 22528.0 22528.0 0.000001 \n",
"12 1.806152 0.029480 22528.0 22528.0 0.000001 \n",
"13 1.662354 0.030518 22528.0 22528.0 0.000001 \n",
"14 1.943604 0.029297 22528.0 22528.0 0.000001 \n",
"15 0.937256 0.030579 22528.0 22528.0 0.000001 \n",
"\n",
" n_time_steps slurm_job_id n_cuda_devices n_processes \\\n",
"0 200.0 232557.0 1 1 \n",
"1 200.0 232558.0 2 2 \n",
"2 200.0 232589.0 3 3 \n",
"3 200.0 232590.0 4 4 \n",
"4 200.0 232591.0 5 5 \n",
"5 200.0 232592.0 6 6 \n",
"6 200.0 232593.0 7 7 \n",
"7 200.0 232594.0 8 8 \n",
"8 200.0 232595.0 9 9 \n",
"9 200.0 232596.0 10 10 \n",
"10 200.0 232597.0 11 11 \n",
"11 200.0 232598.0 12 12 \n",
"12 200.0 232599.0 13 13 \n",
"13 200.0 232600.0 14 14 \n",
"14 200.0 232601.0 15 15 \n",
"15 200.0 232602.0 16 16 \n",
"\n",
" git_hash \\\n",
"0 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"1 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"2 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"3 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"4 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"5 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"6 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"7 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"8 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"9 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"10 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"11 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"12 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"13 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"14 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"15 aa693a9a468e3d591417342d96128d90c9df7884\\n \n",
"\n",
" git_status \n",
"0 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"1 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"2 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"3 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"4 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"5 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"6 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"7 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"8 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"9 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"10 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"11 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"12 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"13 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"14 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n",
"15 M Figures.ipynb\\n M dgx-2_scaling_benchmark.j... \n"
] ]
} }
], ],
@ -233,7 +114,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -244,7 +125,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -255,7 +136,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -395,7 +276,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -531,7 +412,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 34, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -606,7 +487,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 18, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -647,7 +528,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 19, "execution_count": null,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
@ -694,7 +575,7 @@
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "Python 3.7.12 ('ShallowWaterGPU')", "display_name": "ShallowWaterGPU",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -708,12 +589,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.7.12" "version": "3.9.19"
},
"vscode": {
"interpreter": {
"hash": "5ec8a684eb355694b427c525a814c01edbb663f485e9b356374be21a7726d858"
}
} }
}, },
"nbformat": 4, "nbformat": 4,

5
GPUSimulators/Autotuner.py
View File

@ -25,6 +25,7 @@ import gc
import numpy as np import numpy as np
import logging import logging
from socket import gethostname from socket import gethostname
from tqdm.auto import tqdm
import pycuda.driver as cuda import pycuda.driver as cuda
@ -155,9 +156,9 @@ class Autotuner:
sim_arguments = arguments.copy() sim_arguments = arguments.copy()
with Common.Timer(simulator.__name__) as t: with Common.Timer(simulator.__name__) as t:
for j, block_height in enumerate(block_heights): for j, block_height in enumerate(tqdm(block_heights, desc='Autotuner Progress')):
sim_arguments.update({'block_height': block_height}) sim_arguments.update({'block_height': block_height})
for i, block_width in enumerate(block_widths): for i, block_width in enumerate(tqdm(block_widths, desc=f'Iteration {j} Progress', leave=False)):
sim_arguments.update({'block_width': block_width}) sim_arguments.update({'block_width': block_width})
megacells[j, i] = Autotuner.run_benchmark(simulator, sim_arguments) megacells[j, i] = Autotuner.run_benchmark(simulator, sim_arguments)

124
TestSchemes.ipynb
View File

File diff suppressed because one or more lines are too long

1
conda_environment.yml
View File

@ -18,6 +18,7 @@ dependencies:
- pycuda - pycuda
- ipyparallel - ipyparallel
- line_profiler - line_profiler
- tqdm
# Install conda environment (one-time operation): # Install conda environment (one-time operation):
# $ conda env create -f conda_environment.yml # $ conda env create -f conda_environment.yml

1
conda_environment_hpc.yml
View File

@ -12,6 +12,7 @@ dependencies:
- pytools - pytools
- netcdf4 - netcdf4
- scipy - scipy
- tqdm
# Install conda environment (one-time operation): # Install conda environment (one-time operation):
# $ conda env create -f conda_environment_hpc.yml # $ conda env create -f conda_environment_hpc.yml