diff --git a/examples/qed_bench_reduction_steps_gpu.jl b/examples/qed_bench_reduction_steps_gpu.jl
index 9786db5..f542e96 100644
--- a/examples/qed_bench_reduction_steps_gpu.jl
+++ b/examples/qed_bench_reduction_steps_gpu.jl
@@ -4,6 +4,7 @@ using UUIDs
 using BenchmarkTools
 using DataFrames
 using CSV
+using Dates
 
 results_filename = "bench_results_reduction_steps_gpu.csv"
 
@@ -39,7 +40,7 @@ function bench(func, inputs)
     gpu_compile_time = @elapsed func.(inputs[1:2])
 
     gpu_time = @benchmark $func.($inputs)
-    
+
     return (
         cpu_compile_time = 0.0,
         gpu_compile_time = gpu_compile_time,
@@ -59,7 +60,7 @@ processes = [("ke->kke", 50), ("ke->ke", 1), ("ke->kke", 1), ("ke->kkke", 1), ("
 for (process_str, STEPSIZE) in processes
     n = 0
     opt_time_cum = 0
-    
+
     # preparation of graph
     machine = Machine(
         [
diff --git a/experiments/reduce_bench_hemera_gpu.sh b/experiments/reduce_bench_hemera_gpu.sh
index 8d8df41..ed03487 100755
--- a/experiments/reduce_bench_hemera_gpu.sh
+++ b/experiments/reduce_bench_hemera_gpu.sh
@@ -14,9 +14,10 @@ cd $HOME/repos/metagraph_optimization
 
 module load singularity
 module load git 
+module load cuda/12.1
 
 printf "Current git commit hash: " > results/git_reduce_bench_gpu.txt
 git rev-parse HEAD >> results/git_reduce_bench_gpu.txt
 git status >> results/git_reduce_bench_gpu.txt
 
-singularity exec experiments/CUDA_container.sif ./experiments/run_reduce_bench_gpu.sh
+singularity exec --nv experiments/CUDA_container.sif ./experiments/run_reduce_bench_gpu.sh