Minor fixes, lscpu grep, thread number calculation, etc...

GIGI_1_setup.sh

@@ -25,8 +25,8 @@ echo "System Info: " $(uname)
 echo "Hostname: " $(hostname)
 echo "Host ID: " $(hostid)
 echo "Uptime: " $(uptime)
-cores=$(lscpu | grep Core | tail -c 2)
-sockets=$(lscpu | grep Socket | tail -c 2)
+cores=$(lscpu | grep "Core(s)" | tail -c 2)
+sockets=$(lscpu | grep "Socket(s)" | tail -c 2)
 cores_total=$(($cores*$sockets))
 threads_per_core=$(lscpu | grep Thread | tail -c 2)
 threads_total=$(($cores_total*$threads_per_core))
@@ -36,10 +36,15 @@ echo "Number of Threads: " ${threads_total}
 export num_chunks=$(($threads_total - $threads_per_core))
 
 #Compare with num_threads 
-if [ "$num_threads" ]
+if [ "$num_threads" -lt "$num_chunks" ]
 then
   export num_chunks="$num_threads"
 fi
+if [ "$num_chunks" -lt 1 ]
+then
+  export num_chunks=1
+  echo "Trouble determining number of threads correctly, using 1 as a failsafe."
+fi
 echo "Number of chunks to split into: " ${num_chunks}
 echo
 

GIGI_2_split.sh

 #!/bin/bash
 
+export timecmd="$(which time)"
+
 cd ${input_folder}
 find "${gigi_split_prefix%/*}" -name "chunk_0*"
 if [[ -n $(find "${gigi_split_prefix%/*}" -name "chunk_0*") ]]
 then
   echo "chunk_0.geno exists, file is most likely already split, if it is not, then remove the existing chunks from ${gigi_split_prefix%/*} and try again"
 else
-  ${gigi_split} "${param_file##*/}" "${num_chunks}" "${gigi_split_prefix}"
+  mkdir -p "${output_folder}/${run_name}/STATS"
+  $timecmd -o "${output_folder}/${run_name}/STATS/time${i}.log" -f'memory in kilobytes %M real %e user %U sys %S command %C' "${gigi_split}" "${param_file##*/}" "${num_chunks}" "${gigi_split_prefix}"
   echo "Split exit status: " "$?"  
 fi
 cd "$parent_path"

GIGI_3_gigi.sh

 #!/bin/bash
 
-timecmd="$(which time)"
-
 cd "${input_folder}"
 #cd "${gigi_split_chunks_folder}"
 
@@ -19,7 +17,6 @@ do
     echo "file ${output_folder}/${run_name}/gigi_output/${i}/impute.geno already exists."
   else
     mkdir -p "${output_folder}/${run_name}/gigi_output/${i}"
-    mkdir -p "${output_folder}/${run_name}/STATS"
     echo $(pwd)
     $timecmd -o "${output_folder}/${run_name}/STATS/time${i}.log" -f'memory in kilobytes %M real %e user %U sys %S command %C' "${gigi}" "${file}" -outD="${output_folder}/${run_name}/gigi_output/${i}" & pids+=("$!")
     echo "$!"

GIGI_4_merge.sh

@@ -16,8 +16,8 @@ if [ "$merge_status" -eq 0 ]
 then
   echo "COMPLETED SUCCESSFULLY!"
   echo "Merged files are located at: " "${output_folder}/${run_name}/gigi_output"
-  rm -R "${output_folder}"/"${run_name}"/gigi_output/*/
-  rm -R "${output_folder}"/"${run_name}"/split_output/
+#  rm -R "${output_folder}"/"${run_name}"/gigi_output/*/
+#  rm -R "${output_folder}"/"${run_name}"/split_output/
   cat "${output_folder}"/"${run_name}"/STATS/time* > "${output_folder}"/"${run_name}"/STATS/stats
   rm "${output_folder}"/"${run_name}"/STATS/time*
 else

README.md

-Scripts to run GIGI with multiple threads by splitting the input and mergin the output.  
+# Run GIGI Split and MergeScripts 
+
+
+#### Runs GIGI with multiple threads by splitting the input and merging the output.  
+
+
 Usage: run_GIGI parameter_file -o [OUTPUT FOLDER] -n [RUN NAME] -t [THREADS] -m [MEMORY IN MB]
+
+
 Examples: 
+```bash
   run_GIGI ./INPUTS/Sample_Input/param-v1_06.txt    #Output in the current folder with no run name identifying subfolder, threads and memory determined automatically
   run_GIGI ./INPUTS/Sample_Input/param-v1_06.txt -o ./OUTPUTS -n test_run    #Output in ./OUTPUTS/test_run 
   run_GIGI ./INPUTS/Sample_Input/param-v1_06.txt -t 2    #Limit to only 2 threads (and hence two chunks)
   run_GIGI ./INPUTS/Sample_Input/param-v1_06.txt -m 1000    #Limit memory use to 1 GB, not yet implemented, asking for both thread and memory limits may result in impossible scenarios.  
+  run_GIGI ./INPUTS/Sample_Input/param-v1_06.txt -mt 1000 2   #Limit memory use to 1 GB and 2 threads, not yet implemented, asking for both thread and memory limits may result in impossible scenarios.  
+
+```