diff --git a/examples/qed_bench_tape.jl b/examples/qed_bench_tape.jl
index 01e80e6..223828a 100644
--- a/examples/qed_bench_tape.jl
+++ b/examples/qed_bench_tape.jl
@@ -200,7 +200,7 @@ bench_qed("ke->kkke")
 bench_qed("ke->kkkke")
 bench_qed("ke->kkkkke")
 bench_qed("ke->kkkkkke")
-bench_qed("ke->kkkkkkke", true)
+bench_qed("ke->kkkkkkke")
 
 bench_abc("AB->AB")
 bench_abc("AB->ABBB")
diff --git a/examples/qed_gen_bench.jl b/examples/qed_gen_bench.jl
index 71827df..ed512da 100644
--- a/examples/qed_gen_bench.jl
+++ b/examples/qed_gen_bench.jl
@@ -4,7 +4,7 @@ using CSV
 using BenchmarkTools
 using StatsBase
 
-results_filename = "qed_gen_results.csv"
+results_filename = "qed_gen_results_$(Threads.nthreads()).csv"
 
 df = DataFrame(
     process_name = String[],
@@ -29,26 +29,10 @@ df = DataFrame(
     graph_edges_reduced = Int[],
     graph_mem = Float64[],
     graph_mem_reduced = Float64[],
+    graph_elapsed_reduce = Float64[],
 )
 
-# if they exist, read existing results and append new ones
-if isfile(results_filename)
-    df = CSV.read(results_filename, DataFrame)
-end
-
-processes = [
-    "ke->ke",
-    "ke->kke",
-    "ke->kkke",
-    "ke->kkkke",
-    "ke->kkkkke",
-    "ke->kkkkkke",
-    "ke->kkkkkkke",
-    "ke->kkkkkkkke",
-    #"ke->kkkkkkkkke",
-]
-
-function bench_process(process::AbstractString)
+function bench_process(process::AbstractString; warmup = false, optimize = true)
     println("Benchmarking $process...")
     model = QEDModel()
 
@@ -62,12 +46,21 @@ function bench_process(process::AbstractString)
     node_dict = countmap(typeof.(graph.nodes))
     graph_size = Base.summarysize(graph)
 
-    optim = ReductionOptimizer()
-    optimize_to_fixpoint!(optim, graph)
+    reduce_elapsed = -1.0
+    node_dict_reduced = Dict()
+    graph_size_reduced = -1.0
+    props_reduced = GraphProperties()
+    if optimize
+        reduce_elapsed = @elapsed optimize_to_fixpoint!(ReductionOptimizer(), graph)
 
-    props_reduced = GraphProperties(graph)
-    node_dict_reduced = countmap(typeof.(graph.nodes))
-    graph_size_reduced = Base.summarysize(graph)
+        props_reduced = GraphProperties(graph)
+        node_dict_reduced = countmap(typeof.(graph.nodes))
+        graph_size_reduced = Base.summarysize(graph)
+    end
+
+    if warmup
+        return nothing
+    end
 
     push!(
         df,
@@ -94,13 +87,58 @@ function bench_process(process::AbstractString)
             :graph_edges_reduced => props_reduced.noEdges,
             :graph_mem => graph_size,
             :graph_mem_reduced => graph_size_reduced,
+            :graph_elapsed_reduce => reduce_elapsed,
         ),
     )
     return nothing
 end
 
-for process in processes
-    bench_process(process)
+processes = [
+    ("ke->ke", true),
+    ("ke->kke", true),
+    ("ke->kkke", true),
+    ("ke->kkkke", true),
+    ("ke->kkkkke", true),
+    ("ke->kkkkkke", true),
+    ("ke->kkkkkkke", true),
+    ("ke->kkkkkkkke", false),
+    ("ke->kkkkkkkkke", false),
+]
+
+df = DataFrame(
+    process_name = String[],
+    cpu_threads = Int[],
+    graph_gen_samples = Int[],
+    graph_gen_mean = Float64[],
+    graph_gen_std = Float64[],
+    graph_gen_median = Float64[],
+    graph_nodes = Int[],
+    graph_data_nodes = Int[],
+    graph_u_nodes = Int[],
+    graph_v_nodes = Int[],
+    graph_s1_nodes = Int[],
+    graph_s2_nodes = Int[],
+    graph_edges = Int[],
+    graph_nodes_reduced = Int[],
+    graph_data_nodes_reduced = Int[],
+    graph_u_nodes_reduced = Int[],
+    graph_v_nodes_reduced = Int[],
+    graph_s1_nodes_reduced = Int[],
+    graph_s2_nodes_reduced = Int[],
+    graph_edges_reduced = Int[],
+    graph_mem = Float64[],
+    graph_mem_reduced = Float64[],
+    graph_elapsed_reduce = Float64[],
+)
+
+# if they exist, read existing results and append new ones
+if isfile(results_filename)
+    df = CSV.read(results_filename, DataFrame)
 end
 
-CSV.write(results_filename, df)
+bench_process("ke->kke", warmup = true)
+
+for (process, opt) in processes
+    bench_process(process, optimize = opt)
+    CSV.write(results_filename, df)
+end
diff --git a/experiments/gen_diagram_hemera.sh b/experiments/gen_diagram_hemera.sh
new file mode 100755
index 0000000..a4ab449
--- /dev/null
+++ b/experiments/gen_diagram_hemera.sh
@@ -0,0 +1,17 @@
+#!/bin/bash
+#SBATCH --array=1-8
+#SBATCH --job-name=qed_diag_gen
+#SBATCH --partition=intel
+#SBATCH --time=4:00:00
+#SBATCH --nodes=1
+#SBATCH --ntasks=1
+#SBATCH --cpus-per-task=8
+#SBATCH --mem=64GB
+#SBATCH --output=simulation-%A-%a.out
+#SBATCH --error=simulation-%A-%a.err
+
+cd $HOME/repos/metagraph_optimization
+
+module load singularity
+
+singularity exec experiments/CUDA_container.sif ./experiments/run_gen_diagram.sh $SLURM_ARRAY_TASK_ID
diff --git a/experiments/run.sh b/experiments/run.sh
deleted file mode 100755
index 65ab1f8..0000000
--- a/experiments/run.sh
+++ /dev/null
@@ -1,27 +0,0 @@
-#!/bin/bash
-
-SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-LOG_FILE="$SCRIPT_DIR/../julia.log"
-
-cd $SCRIPT_DIR/..
-
-echo "Initiating julia..."
-julia --project=./ -e 'using Pkg; Pkg.instantiate(); Pkg.add(url="https://github.com/QEDjl-project/QEDprocesses.jl/")' > $LOG_FILE 2>&1 || exit 1    # need current dev version of QEDprocesses
-julia -e 'using Pkg; Pkg.add("CSV"); Pkg.add("DataFrames"); Pkg.add("LIKWID"); Pkg.add("CUDA"); Pkg.add("Random")' >> $LOG_FILE 2>&1 || exit 1        # add requirements for the bench script
-
-echo "Benchmarking..."
-
-#
-#for i in {1..20}
-#do
-#    echo "$i Threads"
-#    julia --project --threads=$i examples/qed_bench.jl >> $LOG_FILE 2>&1 || echo "-- Something went wrong, check logs --"
-#done
-
-echo "Benchmarking Tape variant..."
-
-for i in {1..20}
-do
-    echo "$i Threads"
-    julia --project --threads=$i examples/qed_bench_tape.jl >> $LOG_FILE 2>&1 || echo "-- Something went wrong, check logs --"
-done
diff --git a/experiments/run_gen_diagram.sh b/experiments/run_gen_diagram.sh
new file mode 100755
index 0000000..de9bdc7
--- /dev/null
+++ b/experiments/run_gen_diagram.sh
@@ -0,0 +1,30 @@
+#!/bin/bash
+
+# first arg = number of threads
+i=$1
+
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+LOG_FILE="$SCRIPT_DIR/../julia.log"
+
+cd $SCRIPT_DIR/..
+
+echo "Writing system info..."
+
+printf "Current git commit hash: " > $LOG_FILE
+git rev-parse HEAD >> $LOG_FILE
+git status >> $LOG_FILE
+
+# collect some information of the used node and system
+uname -a > results/system.txt
+julia --version > results/julia.txt
+lscpu > results/cpu.txt
+lsblk > results/storage.txt
+lspci > results/pci.txt
+
+echo "Initiating julia..."
+julia --threads=8 --project=./ -e 'using Pkg; Pkg.instantiate(); Pkg.add(url="https://github.com/QEDjl-project/QEDprocesses.jl/")' >> $LOG_FILE 2>&1 || exit 1    # need current dev version of QEDprocesses
+julia --threads=8 -e 'using Pkg; Pkg.add("CSV"); Pkg.add("DataFrames"); Pkg.add("BenchmarkTools"); Pkg.add("StatsBase")' >> $LOG_FILE 2>&1 || exit 1        # add requirements for the bench script
+
+echo "Benchmarking with $i threads..."
+
+julia --project --threads=$i examples/qed_gen_bench.jl >> $LOG_FILE 2>&1 || echo "-- Something went wrong, check logs --"
diff --git a/experiments/run_qed_exec.sh b/experiments/run_qed_exec.sh
new file mode 100755
index 0000000..885ba51
--- /dev/null
+++ b/experiments/run_qed_exec.sh
@@ -0,0 +1,35 @@
+#!/bin/bash
+
+# first arg = number of threads
+$i = $1
+
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+LOG_FILE="$SCRIPT_DIR/../julia.log"
+
+cd $SCRIPT_DIR/..
+
+echo "Writing system info..."
+
+printf "Current git commit hash: " > $LOG_FILE
+git rev-parse HEAD >> $LOG_FILE
+git status >> $LOG_FILE
+
+# collect some information of the used node and system
+uname -a > results/system.txt
+julia --version > results/julia.txt
+lscpu > results/cpu.txt
+nvidia-smi > results/cuda_gpu.txt
+lsblk > results/storage.txt
+lspci > results/pci.txt
+
+echo "Initiating julia..."
+julia --project=./ -e 'using Pkg; Pkg.instantiate(); Pkg.add(url="https://github.com/QEDjl-project/QEDprocesses.jl/")' >> $LOG_FILE 2>&1 || exit 1    # need current dev version of QEDprocesses
+julia -e 'using Pkg; Pkg.add("CSV"); Pkg.add("DataFrames"); Pkg.add("LIKWID"); Pkg.add("CUDA"); Pkg.add("Random")' >> $LOG_FILE 2>&1 || exit 1        # add requirements for the bench script
+
+echo "Benchmarking..."
+echo "$i Threads"
+julia --project --threads=$i examples/qed_bench.jl >> $LOG_FILE 2>&1 || echo "-- Something went wrong, check logs --"
+
+echo "Benchmarking Tape variant..."
+echo "$i Threads"
+julia --project --threads=$i examples/qed_bench_tape.jl >> $LOG_FILE 2>&1 || echo "-- Something went wrong, check logs --"