Merge branch 'master' into rdma_mpi

Author: Malmahrouqi3

.github/workflows/frontier/build.sh

@@ -1,7 +1,7 @@
 #!/bin/bash
 
 build_opts=""
-if [ "$1" == "gpu" ]; then
+if [ "$1" = "gpu" ]; then
     build_opts="--gpu"
 fi
 

.github/workflows/frontier/submit.sh

@@ -13,10 +13,10 @@ else
     exit 1
 fi
 
-if [ "$2" == "cpu" ]; then
+if [ "$2" = "cpu" ]; then
     sbatch_device_opts="\
 #SBATCH -n 32                       # Number of cores required"
-elif [ "$2" == "gpu" ]; then
+elif [ "$2" = "gpu" ]; then
     sbatch_device_opts="\
 #SBATCH -n 8                       # Number of cores required"
 else

.github/workflows/frontier/test.sh

@@ -3,7 +3,7 @@
 gpus=`rocm-smi --showid | awk '{print $1}' | grep -Eo '[0-9]+' | uniq | tr '\n' ' '`
 ngpus=`echo "$gpus" | tr -d '[:space:]' | wc -c`
 
-if [ "$job_device" == "gpu" ]; then
+if [ "$job_device" = "gpu" ]; then
     ./mfc.sh test --rdma-mpi --max-attempts 3 -j $ngpus -- -c frontier
 else
     ./mfc.sh test --max-attempts 3 -j 32 -- -c frontier

.github/workflows/phoenix/bench.sh

@@ -2,19 +2,26 @@
 
 n_ranks=12
 
-if [ "$job_device" == "gpu" ]; then
+if [ "$job_device" = "gpu" ]; then
     n_ranks=$(nvidia-smi -L | wc -l)        # number of GPUs on node
     gpu_ids=$(seq -s ' ' 0 $(($n_ranks-1))) # 0,1,2,...,gpu_count-1
     device_opts="--gpu -g $gpu_ids"
 fi
 
-mkdir -p /storage/scratch1/6/sbryngelson3/mytmp_build
-export TMPDIR=/storage/scratch1/6/sbryngelson3/mytmp_build
+tmpbuild=/storage/scratch1/6/sbryngelson3/mytmp_build
+currentdir=$tmpbuild/run-$(( RANDOM % 900 ))
+mkdir -p $tmpbuild
+mkdir -p $currentdir
 
-if ["$job_device" == "gpu"]; then
+export TMPDIR=$currentdir
+
+if [ "$job_device" = "gpu" ]; then
     ./mfc.sh bench --mem 12 -j $(nproc) -o "$job_slug.yaml" -- -c phoenix-bench $device_opts -n $n_ranks
 else
     ./mfc.sh bench --mem 1 -j $(nproc) -o "$job_slug.yaml" -- -c phoenix-bench $device_opts -n $n_ranks
 fi
 
+sleep 10
+rm -rf "$currentdir" || true
+
 unset TMPDIR

.github/workflows/phoenix/submit-bench.sh

@@ -25,9 +25,9 @@ sbatch_gpu_opts="\
 #SBATCH -G2\
 "
 
-if [ "$2" == "cpu" ]; then
+if [ "$2" = "cpu" ]; then
     sbatch_device_opts="$sbatch_cpu_opts"
-elif [ "$2" == "gpu" ]; then
+elif [ "$2" = "gpu" ]; then
     sbatch_device_opts="$sbatch_gpu_opts"
 else
     usage

.github/workflows/phoenix/submit.sh

@@ -25,9 +25,9 @@ sbatch_gpu_opts="\
 #SBATCH -G2\
 "
 
-if [ "$2" == "cpu" ]; then
+if [ "$2" = "cpu" ]; then
     sbatch_device_opts="$sbatch_cpu_opts"
-elif [ "$2" == "gpu" ]; then
+elif [ "$2" = "gpu" ]; then
     sbatch_device_opts="$sbatch_gpu_opts"
 else
     usage

.github/workflows/phoenix/test.sh

@@ -1,15 +1,15 @@
 #!/bin/bash
 
 build_opts=""
-if [ "$job_device" == "gpu" ]; then
+if [ "$job_device" = "gpu" ]; then
     build_opts="--gpu"
 fi
 
 ./mfc.sh test --dry-run -j 8 $build_opts
 
 n_test_threads=8
 
-if [ "$job_device" == "gpu" ]; then
+if [ "$job_device" = "gpu" ]; then
     gpu_count=$(nvidia-smi -L | wc -l)        # number of GPUs on node
     gpu_ids=$(seq -s ' ' 0 $(($gpu_count-1))) # 0,1,2,...,gpu_count-1
     device_opts="-g $gpu_ids"