Use CUDA kernels in bench scripts

data/bench_results_32.csv

@@ -0,0 +1,9 @@
+process_name,graph_gen_time,optimization_time,function_generation_time,graph_nodes,graph_edges,graph_mem,cpu_threads,n_inputs,nflops_likwid,cpu_time,cpu_std,cpu_rate,cpu_gflops,gpu_name,gpu_time,gpu_std,gpu_rate,gpu_gflops
+QED Process: 'ke->ke' reduced,0.004851193,0.001290078,0.006093401,26,29,6948.0,32,10000000,0,0.2810178885,0.00909457898005121,3.5584923270818755e7,1.886000933353394,NVIDIA A100-SXM4-80GB,0.4060797745,0.0013320688448668838,2.462570319418851e7,1.305162269291991
+QED Process: 'ke->kke' reduced,0.001065397,0.010432606,0.014287271,59,77,16383.0,32,10000000,0,0.823029796,0.01692859562197734,1.2150228398292398e7,2.223491796887509,NVIDIA A100-SXM4-80GB,2.3333098275,0.0014037935241043983,4.285757460128814e6,0.784293615203573
+QED Process: 'ke->kkke' reduced,0.001348518,0.005210738,0.034243651,188,273,54426.0,32,10000000,0,2.9432864705,0.031053960614444084,3.397562588700793e6,2.497208502695083,NVIDIA A100-SXM4-80GB,10.340032588,0.0028660606476431714,967114.9403924877,0.7108294811884784
+QED Process: 'ke->kkkke' reduced,0.004413783,0.039469525,0.15704043,853,1295,243781.0,32,10000000,0,14.980394603,0.5162977440607073,667539.1580137269,2.4318451526440072,NVIDIA A100-SXM4-80GB,54.2063089555,0.006347197107681703,184480.371246258,0.672061992450118
+QED Process: 'ke->kkkkke' reduced,0.021871728,0.716956567,1.121625045,4982,7655,1.800816e6,32,10000000,0,82.035650126,0.3421310894344223,121898.22332901397,2.6545776094359375,NVIDIA A100-SXM4-80GB,321.789538108,NaN,31076.212293277757,0.6767466751107096
+ABC Process: 'AB->AB' reduced,0.000867035,0.002263493,0.007340721,34,37,9296.0,32,10000000,0,0.1877912925,0.0029540808349122686,5.325060532292784e7,2.8222820821151755,NVIDIA A100-SXM4-80GB,0.0016617045,1.5729813606955104e-5,6.01791714471496e9,318.9496086698929
+ABC Process: 'AB->ABBB' reduced,0.000547175,0.004720326,0.035918118,200,285,57156.0,32,10000000,0,0.257040364,0.007250633041861087,3.8904395575785905e7,28.59473074820264,NVIDIA A100-SXM4-80GB,0.003641165,3.2217340292524716e-5,2.74637375675093e9,2018.5847112119334
+ABC Process: 'AB->ABBBBB' reduced,0.019826198,0.258674017,1.136386232,4998,7671,1.507432e6,32,10000000,0,1.818710381,0.03353568966350073,5.498401562156146e6,119.7386908190744,NVIDIA A100-SXM4-80GB,0.492263776,0.0031065569742746986,2.031431213821429e7,442.38477543389257

data/evaluate_cpu_gpu_exec.jl

@@ -0,0 +1,143 @@
+using CSV
+using DataFrames
+using Plots
+using StatsPlots
+using LaTeXStrings
+
+if (length(ARGS) < 1)
+    println("Please use with \"input_file.csv\"")
+end
+
+processes = [
+    "QED Process: 'ke->ke'",
+    "QED Process: 'ke->kke'",
+    "QED Process: 'ke->kkke'",
+    "QED Process: 'ke->kkkke'",
+    "QED Process: 'ke->kkkkke'",
+    #"QED Process: 'ke->kkkkkke'",
+    #"QED Process: 'ke->kkkkkkke'",
+    "ABC Process: 'AB->AB'",
+    "ABC Process: 'AB->ABBB'",
+    "ABC Process: 'AB->ABBBBB'",
+]
+
+function proc_to_n(str::AbstractString)
+    parts = split(str, "'")
+    parts = split(parts[2], "->")
+    k_count = count(c -> c == 'k', parts[2])
+    return k_count
+end
+
+function abc_proc_to_n(str::AbstractString)
+    parts = split(str, "'")
+    parts = split(parts[2], "->")
+    b_count = count(c -> c == 'B', parts[2])
+    return b_count
+end
+
+function beautify_title(str::AbstractString)
+    parts = split(str, "'")
+
+    preprefix = parts[1]
+    infix = parts[2]
+    sufsuffix = parts[3]
+
+    parts = split(infix, "->")
+
+    prefix = parts[1]
+    suffix = parts[2]
+
+    k_count = count(c -> c == 'k', suffix)
+    B_count = count(c -> c == 'B', suffix)
+
+    if k_count == 1 || B_count == 1
+        new_suffix = suffix
+    elseif k_count >= 1
+        new_suffix = replace(suffix, r"k+" => "k^$k_count")
+    elseif B_count >= 1
+        new_suffix = replace(suffix, r"B+" => "B^$B_count")
+    end
+
+    return preprefix * L"%$prefix \rightarrow %$new_suffix" * sufsuffix
+end
+
+input_file = ARGS[1]
+df = CSV.read(input_file, DataFrame)
+n_inputs = df[:, "n_inputs"][1]
+
+
+
+title_string = "QED N-Photon Compton Scattering\nCalculate 10,000,000 Matrix Elements"
+
+df_filt = filter(:process_name => x -> proc_to_n(x) >= 1, df)
+
+df_filt.process_size = @. proc_to_n(df_filt.process_name)
+
+df_red = filter(:process_name => x -> match(r" reduced$", x) !== nothing, df_filt)
+
+@df df_red scatter(
+    :process_size,
+    :cpu_time,
+    yerror = :cpu_std,
+    label = "CPU execution time, 32 threads (s)",
+    markersize = 6,
+)
+@df df_red scatter!(
+    :process_size,
+    :gpu_time,
+    yerror = :gpu_std,
+    label = "GPU execution time, A100 80GB (s)",
+    markersize = 6,
+)
+
+plot!(
+    title = title_string,
+    yscale = :log10,
+    legend = :outerbottom,
+    legendcolumns = 2,
+    legend_font_pointsize = 10,
+    size = (800, 600),
+    ylabel = "time (s)",
+    xlabel = "process size (#)",
+)
+
+savefig("cpu_vs_gpu_qed.pdf")
+
+
+
+
+title_string = "\$AB\\rightarrow AB^n\$ ABC Processes\nCalculate 10,000,000 Matrix Elements"
+
+df_filt = filter(:process_name => x -> abc_proc_to_n(x) >= 1, df)
+
+df_filt.process_size = @. abc_proc_to_n(df_filt.process_name)
+
+df_red = filter(:process_name => x -> match(r" reduced$", x) !== nothing, df_filt)
+
+@df df_red scatter(
+    :process_size,
+    :cpu_time,
+    yerror = :cpu_std,
+    label = "CPU execution time, 32 threads (s)",
+    markersize = 6,
+)
+@df df_red scatter!(
+    :process_size,
+    :gpu_time,
+    yerror = :gpu_std,
+    label = "GPU execution time, A100 80GB (s)",
+    markersize = 6,
+)
+
+plot!(
+    title = title_string,
+    yscale = :log10,
+    legend = :outerbottom,
+    legendcolumns = 2,
+    legend_font_pointsize = 10,
+    size = (800, 600),
+    ylabel = "time (s)",
+    xlabel = "process size (#)",
+)
+
+savefig("cpu_vs_gpu_abc.pdf")