Change parallelization strategy

Makefile

@@ -37,6 +37,6 @@ yadage-run: yadage-clean
 	@echo "Launching Yadage..."
 	@yadage-run $(YADAGE_WORK_DIR) "workflow.yml" \
 		-p input_file="input.yml" \
-		-p num_generation_jobs="6" \
+		-p num_procs_per_job="1" \
 		-d initdir=$(YADAGE_INPUT_DIR) \
 		--toplevel $(YADAGE_SPEC_DIR)

VERSION

@@ -1 +1 @@
-0.4.0
+0.5.0

code/cards/me5_configuration.txt

@@ -0,0 +1,223 @@
+################################################################################
+#
+# Copyright (c) 2009 The MadGraph5_aMC@NLO Development team and Contributors
+#
+# This file is a part of the MadGraph5_aMC@NLO project, an application which
+# automatically generates Feynman diagrams and matrix elements for arbitrary
+# high-energy processes in the Standard Model and beyond.
+#
+# It is subject to the MadGraph5_aMC@NLO license which should accompany this
+# distribution.
+#
+# For more information, visit madgraph.phys.ucl.ac.be and amcatnlo.web.cern.ch
+#
+################################################################################
+#
+# This File contains some configuration variable for MadGraph/MadEvent
+#
+# Line starting by #! are comment and should remain commented
+# Line starting with # should be uncommented if you want to modify the default
+#    value.
+# Current value for all options can seen by typing "display options"
+#    after either ./bin/mg5_aMC or ./bin/madevent
+#
+# You can place this files in ~/.mg5/mg5_configuration.txt if you have more than
+#    one version of MG5.
+#
+################################################################################
+#! Prefered Fortran Compiler
+#! If None: try to find g77 or gfortran on the system
+#!
+# fortran_compiler = None
+# f2py_compiler_py2 = None
+# f2py_compiler_py3 = None
+
+
+#! Prefered C++ Compiler
+#! If None: try to find g++ or clang on the system
+#!
+# cpp_compiler = None
+
+#! Prefered Text Editor
+#!  Default: use the shell default Editor
+#!           or try to find one available on the system
+#!  Be careful: Only shell based editor are allowed
+# text_editor = None
+
+#! Prefered Web Browser
+#! If None: try to find one available on the system
+# web_browser = None
+
+#! Prefered PS viewer
+#!  If None: try to find one available on the system
+# eps_viewer = None
+
+#! Time allowed to answer question (if no answer takes default value)
+#!  0: No time limit
+# timeout = 60
+
+#! Pythia8 path.
+#!  Defines the path to the pythia8 installation directory (i.e. the
+#!  on containing the lib, bin and include directories) .
+#!  If using a relative path, that starts from the mg5 directory
+# pythia8_path = ./HEPTools/pythia8
+
+#! MG5aMC_PY8_interface path
+#!  Defines the path of the C++ driver file that is used by MG5_aMC to
+#!  steer the Pythia8 shower.
+#!  Can be installed directly from within MG5_aMC with the following command:
+#!     MG5_aMC> install mg5amc_py8_interface
+# mg5amc_py8_interface_path = ./HEPTools/MG5aMC_PY8_interface
+
+#! Herwig++/Herwig7 paths
+#!  specify here the paths also to HepMC ant ThePEG
+#!  define the path to the herwig++, thepeg and hepmc directories.
+#!  paths can be absolute or relative from mg5 directory
+#!  WARNING: if Herwig7 has been installed with the bootstrap script,
+#!  then please set thepeg_path and hepmc_path to the same value as
+#!  hwpp_path
+# hwpp_path =
+# thepeg_path =
+# hepmc_path =
+
+#! Control when MG5 checks if he is up-to-date.
+#! Enter the number of day between two check (0 means never)
+#! A question is always asked before any update
+# auto_update = 7
+
+################################################################################
+#  INFO FOR MADEVENT / aMC@NLO
+################################################################################
+# If this file is in a MADEVENT Template. 'main directory' is the directory
+# containing the SubProcesses directory. Otherwise this is the MadGraph5_aMC@NLO main
+# directory (containing the directories madgraph and Template)
+
+#! Allow/Forbid the automatic opening of the web browser  (on the status page)
+#!  when launching MadEvent [True/False]
+# automatic_html_opening = True
+#! allow notification of finished job in the notification center (Mac Only)
+# notification_center = True
+
+
+#! Default Running mode
+#!  0: single machine/ 1: cluster / 2: multicore
+run_mode = 2
+
+#! Cluster Type [pbs|sge|condor|lsf|ge|slurm|htcaas|htcaas2] Use for cluster run only
+#!  And cluster queue (or partition for slurm)
+#!  And size of the cluster (some part of the code can adapt splitting accordingly)
+# cluster_type = condor
+# cluster_queue = madgraph
+# cluster_size = 150
+
+#! Path to a node directory to avoid direct writing on the central disk
+#!  Note that condor clusters avoid direct writing by default (therefore this
+#!  option does not affect condor clusters)
+# cluster_temp_path = None
+
+#! path to a node directory where local file can be found (typically pdf)
+#! to avoid to send them to the node (if cluster_temp_path is on True or condor)
+# cluster_local_path =  None # example: /cvmfs/cp3.uclouvain.be/madgraph/
+
+#! Cluster waiting time for status update
+#!  First number is when the number of waiting job is higher than the number
+#!  of running one (time in second). The second number is in the second case.
+# cluster_status_update = 600 30
+
+#! How to deal with failed submission (can occur on cluster mode)
+#!  0: crash, -1: print error, hangs the program up to manual instructions, N(>0) retry up to N times.
+# cluster_nb_retry = 1
+
+#! How much time to wait for the output file before resubmission/crash (filesystem can be very slow)
+# cluster_retry_wait = 300
+
+#! Nb_core to use (None = all) This is use only for multicore run
+#!  This correspond also to the number core used for code compilation for cluster mode
+nb_core = None
+
+#! Pythia-PGS Package
+#!  relative path start from main directory
+# pythia-pgs_path = ./pythia-pgs
+
+#! Delphes Package
+#!  relative path start from main directory
+# delphes_path = ./Delphes
+
+#! MadAnalysis4 fortran-based package [for basic analysis]
+#!  relative path start from main directory
+# madanalysis_path = ./MadAnalysis
+
+#! MadAnalysis5 python-based Package [For advanced analysis]
+#!  relative path start from main directory
+# madanalysis5_path = ./HEPTools/madanalysis5/madanalysis5
+
+#! ExRootAnalysis Package
+#!  relative path start from main directory
+# exrootanalysis_path = ./ExRootAnalysis
+
+#! TOPDRAWER PATH
+#!  Path to the directory containing td executables
+#!  relative path start from main directory
+# td_path = ./td
+
+#! lhapdf-config --can be specified differently depending on your python version
+#!  If None: try to find one available on the system
+# lhapdf_py2 = lhapdf-config
+# lhapdf_py3 = lhapdf-config
+
+#! fastjet-config
+#!  If None: try to find one available on the system
+# fastjet = fastjet-config
+
+#! MCatNLO-utilities
+#!  relative path starting from main directory
+# MCatNLO-utilities_path = ./MCatNLO-utilities
+
+#! Set what OLP to use for the loop ME generation
+# OLP = MadLoop
+
+#! Set the PJFRy++ directory containing pjfry's library
+#! if auto: try to find it automatically on the system (default)
+#! if '' or None: disabling pjfry
+#! if pjfry=/PATH/TO/pjfry/lib: use that specific installation path for PJFry++
+# pjfry = auto
+
+#! Set the Golem95 directory containing golem's library
+#! It only supports version higher than 1.3.0
+#! if auto: try to find it automatically on the system (default)
+#! if '' or None: disabling Golem95
+#! if golem=/PATH/TO/golem/lib: use that specific installation path for Golem95
+# golem = auto
+
+#! Set the samurai directory containing samurai's library
+#! It only supports version higher than 2.0.0
+#! if auto: try to find it automatically on the system (default)
+#! if '' or None: disabling samurai
+#! if samurai=/PATH/TO/samurai/lib: use that specific installation path for samurai
+# samurai = None
+
+#! Set the Ninja directory containing ninja's library
+#! if '' or None: disabling ninja
+#! if ninja=/PATH/TO/ninja/lib: use that specific installation path for ninja
+# ninja = ./HEPTools/lib
+
+#! Set the COLLIER directory containing COLLIER's library
+#! if '' or None: disabling COLLIER
+#! if ninja=/PATH/TO/ninja/lib: use that specific installation path for COLLIER
+# Note that it is necessary that you have generated a static library for COLLIER
+# collier = ./HEPTools/lib
+
+#! Set how MadLoop dependencies (such as CutTools) should be handled
+#!  > external : ML5 places a link to the MG5_aMC-wide libraries
+#!  > internal : ML5 copies all dependencies in the output so that it is independent
+#!  > environment_paths : ML5 searches for the dependencies in your environment path
+# output_dependencies = external
+
+#! SysCalc PATH
+#! Path to the directory containing syscalc executables
+#! relative path start from main directory
+# syscalc_path = ./SysCalc
+
+#! Absolute paths to config scripts in the bin directories for APPLgrid and aMCFast.
+# applgrid = applgrid-config
+# amcfast = amcfast-config

code/generate.py

@@ -10,9 +10,8 @@
 ##########################
 
 config_file = str(sys.argv[1])
-number_jobs = int(sys.argv[2])
-madgraph_dir = str(sys.argv[3])
-output_dir = str(sys.argv[4])
+madgraph_dir = str(sys.argv[2])
+output_dir = str(sys.argv[3])
 
 project_path = Path(__file__).parent.parent
 output_path = Path(output_dir)
@@ -30,7 +29,6 @@
 miner.load(config_file)
 
 benchmarks = [str(i) for i in miner.benchmarks]
-num_benchmarks = len(benchmarks)
 
 
 ##########################
@@ -54,46 +52,46 @@ def madminer_run_wrapper(sample_benchmarks, run_type):
         raise ValueError("Invalid run type")
 
     miner.run_multiple(
-        is_background=is_background,
-        only_prepare_script=True,
-        sample_benchmarks=sample_benchmarks,
         mg_directory=madgraph_dir,
-        mg_process_directory=f"{proc_dir}/{run_type}",
         proc_card_file=f"{card_dir}/proc_card_{run_type}.dat",
-        param_card_template_file=f"{card_dir}/param_card_template.dat",
         run_card_files=[f"{card_dir}/run_card_{run_type}.dat"],
+        param_card_template_file=f"{card_dir}/param_card_template.dat",
+        mg_process_directory=f"{proc_dir}/{run_type}",
         pythia8_card_file=f"{card_dir}/pythia8_card.dat",
+        configuration_file=f"{card_dir}/me5_configuration.txt",
         log_directory=f"{logs_dir}/{run_type}",
+        sample_benchmarks=sample_benchmarks,
+        is_background=is_background,
+        only_prepare_script=True,
         python_executable="python3",
     )
 
     # Create files to link benchmark_i to run_i.sh
-    for i in range(number_jobs):
-        index = i % num_benchmarks
+    for i, benchmark in enumerate(benchmarks):
         file_path = f"{proc_dir}/{run_type}/madminer/cards/benchmark_{i}.dat"
 
         with open(file_path, "w+") as f:
-            f.write(benchmarks[index])
+            f.write(benchmark)
 
-        print("generate.py", i, benchmarks[index])
+        print("Benchmark:", i, benchmark)
 
 
 ###########################
 ##### Run with signal #####
 ###########################
 
-# Sample benchmarks from already stablished benchmarks in a democratic way
-initial_list = benchmarks[0 : (number_jobs % num_benchmarks)]
-others_list = benchmarks * (number_jobs // num_benchmarks)
-sample_list = initial_list + others_list
-
-madminer_run_wrapper(sample_benchmarks=sample_list, run_type="signal")
+madminer_run_wrapper(
+    sample_benchmarks=benchmarks,
+    run_type="signal",
+)
 
 
 ###########################
 ### Run with background ###
 ###########################
 
 # Currently not used
-# sample_list = ['sm' for i in range(number_jobs)]
-# madminer_run_wrapper(sample_benchmarks=sample_list, run_type='background')
+# madminer_run_wrapper(
+#     sample_benchmarks=["sm"] * len(benchmarks),
+#     run_type="background",
+# )

scripts/2_generate.sh

@@ -11,7 +11,7 @@ while [ "$#" -gt 0 ]; do
         -p|--project_path)  project_path="$2";  shift  ;;
         -m|--madgraph_dir)  madgraph_dir="$2";  shift  ;;
         -c|--config_file)   config_file="$2";   shift  ;;
-        -j|--number_jobs)   number_jobs="$2";   shift  ;;
+        -j|--number_procs)  number_procs="$2";  shift  ;;
         -o|--output_dir)    output_dir="$2";    shift  ;;
         *) echo "Unknown parameter passed: $1"; exit 1 ;;
     esac
@@ -33,10 +33,27 @@ SIGNAL_ABS_PATH="${output_dir}/mg_processes/signal"
 ### translation file called "py.py" which needs to be written on disk.
 (
     cd "${output_dir}" && \
-    python3 "${project_path}/code/generate.py" "${config_file}" "${number_jobs}" "${MADGRAPH_ABS_PATH}" "${output_dir}"
+    python3 "${project_path}/code/generate.py" "${config_file}" "${MADGRAPH_ABS_PATH}" "${output_dir}"
 )
 
-for i in $(seq 0 $((number_jobs-1))); do
+
+# Parametrize number of parallel processes per job
+default_spec="nb_core = None"
+custom_spec="nb_core = ${number_procs}"
+
+
+# Count the number of benchmarks
+run_cards_path="${SIGNAL_ABS_PATH}/madminer/scripts"
+num_benchmarks=$(find "${run_cards_path}" -maxdepth 1 -name "run_*.sh" | wc -l)
+
+for i in $(seq 0 $((num_benchmarks-1))); do
+
+    # Inject the number of processes in the configuration
+    sed -i \
+        -e "s/${default_spec}/${custom_spec}/" \
+        "${SIGNAL_ABS_PATH}/madminer/cards/me5_configuration_${i}.txt"
+
+    # Create the zip files
     tar -czf "${output_dir}/folder_${i}.tar.gz" \
         -C "${SIGNAL_ABS_PATH}" \
         "bin" \
@@ -45,6 +62,7 @@ for i in $(seq 0 $((number_jobs-1))); do
         "lib" \
         "madminer/scripts/run_${i}.sh" \
         "madminer/cards/benchmark_${i}.dat" \
+        "madminer/cards/me5_configuration_${i}.txt" \
         "madminer/cards/mg_commands_${i}.dat" \
         "madminer/cards/param_card_${i}.dat" \
         "madminer/cards/pythia8_card_${i}.dat" \

workflow/yadage/steps.yml

@@ -5,7 +5,7 @@
 common_env_physics: &common_env_physics
     environment_type: 'docker-encapsulated'
     image: 'madminertool/madminer-workflow-ph'
-    imagetag: '0.4.0'
+    imagetag: '0.5.0'
 
 
 ########################################
@@ -26,7 +26,7 @@ generate:
   environment: *common_env_physics
   process:
     process_type: string-interpolated-cmd
-    cmd: /madminer/scripts/2_generate.sh -p /madminer -m {mg5amc_dir} -c {config_file} -j {number_jobs} -o {output_dir}
+    cmd: /madminer/scripts/2_generate.sh -p /madminer -m {mg5amc_dir} -c {config_file} -j {number_procs} -o {output_dir}
   publisher:
     publisher_type: 'fromglob-pub'
     outputkey: script_files

workflow/yadage/workflow.yml

@@ -15,7 +15,7 @@ stages:
       scheduler_type: singlestep-stage
       parameters:
         config_file: {step: configure, output: config_file}
-        number_jobs: {step: init, output: num_generation_jobs}
+        number_procs: {step: init, output: num_procs_per_job}
         mg5amc_dir: 'software/MG5_aMC_v2_9_4'
         output_dir: '{workdir}'
       step: {$ref: 'steps.yml#/generate'}