diff --git a/ci/perf/gpuc1_bench.csv b/ci/perf/gpuc1_bench.csv
new file mode 100644
index 000000000..1930d270f
--- /dev/null
+++ b/ci/perf/gpuc1_bench.csv
@@ -0,0 +1,85 @@
+test case,benchmark name,samples,iterations,estimated,mean,low mean,high mean,std dev,low std dev,high std dev,raw
+benchmark intrusive graph dependency handling with N nodes - 1,creating nodes,100,5943,2377200,4.7182,4.6863,4.7595,0.1850,0.1498,0.2834,"4.8583,4.7621,4.4908,4.6492,4.5701,4.5396,4.4873,4.8279,4.7722,4.9509,4.6155,4.9561,4.4705,4.9578,4.7251,4.6813,4.6021,4.5665,4.5093,4.9510,4.7839,4.6948,4.6510,4.5766,4.5447,4.4908,4.8346,4.9578,4.9510,4.6019,4.9477,4.8415,4.7839,4.6948,4.9561,4.5464,4.5178,4.8701,4.7723,4.7217,4.6391,4.6004,4.5312,4.5024,4.8566,4.9510,4.6929,4.6120,4.9561,4.4841,4.8262,4.7723,4.9509,4.6155,4.5413,4.5144,4.8667,4.7690,4.7200,4.6357,5.7468,4.8750,4.8146,4.7976,4.7469,4.7385,4.6931,4.6897,4.9510,4.6189,4.5884,4.5953,4.5649,4.5346,4.4824,4.8245,4.9561,4.6643,4.6222,4.5499,4.5193,4.8733,4.7740,4.9578,4.6189,4.5817,4.9275,4.8262,4.7707,4.6828,4.6408,4.5649,4.5346,4.5110,4.8228,4.7673,4.6811,4.9578,4.5312,4.5043"
+benchmark intrusive graph dependency handling with N nodes - 1,creating and adding dependencies,100,1013,2431200,23.9045,23.9016,23.9160,0.0257,0.0040,0.0593,"23.9033,23.9033,24.1500,23.9625,23.9033,23.9033,23.9033,23.9023,23.9023,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.9023,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.8924,23.9033,23.9033,23.9033,23.9033,23.9033,23.9023,23.8934,23.9033,23.9033,23.9033,23.9033,23.9033,23.9023,23.8934,23.9033,23.9033,23.9033,23.9033,23.9033,23.9023,23.8934,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.9023,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.9023,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.8924,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.9033,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.9033,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.9033,23.8934,23.9033,23.9033,23.9033,23.9033,23.9023,23.8934,23.9033"
+benchmark intrusive graph dependency handling with N nodes - 1,adding and removing dependencies,100,1216,2432000,20.5822,20.5398,20.7891,0.4118,0.0131,0.9812,"20.5469,20.5304,20.5880,20.5469,20.5387,20.5304,20.5551,20.5477,20.5387,20.5222,20.5477,20.5551,20.5469,20.5222,20.5387,20.5469,20.5469,20.5304,20.5551,20.5477,20.5387,20.5222,20.5477,20.5469,20.5222,20.5477,20.5469,20.5551,20.5304,20.5551,20.5469,20.5469,20.5222,24.6752,20.5551,20.6793,20.5222,20.5469,20.5304,20.5477,20.5222,20.5469,20.5477,20.5222,20.5469,20.5304,20.5469,20.5222,20.5469,20.5477,20.5222,20.5551,20.5312,20.5551,20.5304,20.5477,20.5469,20.5222,20.5387,20.5304,20.5469,20.5304,20.5395,20.5469,20.5304,20.5395,20.5222,20.5469,20.5469,20.5304,20.5469,20.5222,20.5477,20.5222,20.5387,20.5559,20.5222,20.5551,20.5304,20.5477,20.5222,20.5469,20.5477,20.5304,20.5551,20.5312,20.5469,20.5222,20.5469,20.5469,20.5222,20.5469,20.5230,20.5387,20.5222,20.5477,20.5469,20.5222,20.5387,20.5222"
+benchmark intrusive graph dependency handling with N nodes - 1,checking for dependencies,100,12012,2402400,2.1018,2.0965,2.1262,0.0499,0.0043,0.1186,"2.1008,2.0934,2.0951,2.0926,2.1016,2.0926,2.1017,2.0933,2.1016,2.0926,2.1009,2.0925,2.0934,2.1017,2.0925,2.1017,2.0934,2.1017,2.0933,2.0934,2.1017,2.0925,2.1009,2.0934,2.1016,2.0933,2.0934,2.1016,2.0925,2.1017,2.0934,2.1016,2.5963,2.1117,2.0934,2.0934,2.1016,2.0925,2.1017,2.0925,2.1016,2.0934,2.1017,2.0925,2.0926,2.1017,2.0925,2.1009,2.0934,2.1017,2.0925,2.0926,2.1009,2.0933,2.1017,2.0934,2.1017,2.0925,2.0926,2.1009,2.0933,2.1017,2.0926,2.1016,2.0926,2.1009,2.0925,2.0926,2.1017,2.0933,2.1016,2.0934,2.1017,2.0925,2.0926,2.1017,2.0925,2.1009,2.0926,2.1017,2.0925,2.0926,2.1017,2.0933,2.1017,2.0926,2.1016,2.0933,2.1017,2.0926,2.0933,2.1017,2.0926,2.1016,2.0926,2.1017,2.0933,2.0934,2.1017,2.0933"
+benchmark intrusive graph dependency handling with N nodes - 10,creating nodes,100,691,2487600,40.4515,40.3919,40.6910,0.5598,0.0591,1.3289,"40.4486,40.3184,40.3922,40.4645,40.3343,40.4501,40.3343,40.4501,40.3329,40.4501,40.4645,40.3343,40.4501,40.3343,40.4501,40.3329,40.4501,40.3343,40.4501,40.3343,40.4501,40.3343,40.4631,40.3343,40.4501,40.3343,40.4501,40.3343,40.4501,40.3329,40.4645,40.4501,40.3198,40.4501,40.3198,40.4501,40.3329,40.4356,40.3343,40.4501,40.3343,40.4501,40.3329,40.4501,45.9899,40.5065,40.3473,40.4501,40.4645,40.3343,40.4501,40.3198,40.4645,40.3329,40.4501,40.3343,40.4501,40.3343,40.4501,40.3329,40.4486,40.3343,40.4501,40.3343,40.4501,40.3343,40.4342,40.4486,40.3198,40.4501,40.3343,40.4501,40.3343,40.4486,40.3329,40.4356,40.3343,40.4501,40.3343,40.4501,40.3329,40.4501,40.3343,40.4501,40.3198,40.4645,40.4356,40.3329,40.4356,40.3343,40.4501,40.3343,40.4501,40.3184,40.4486,40.3343,40.4645,40.3343,40.4501,40.3343"
+benchmark intrusive graph dependency handling with N nodes - 10,creating and adding dependencies,100,90,2520000,280.8289,280.7118,280.9822,0.6809,0.5360,1.0741,"280.4000,281.2778,284.7444,281.4000,281.4000,280.5000,281.2889,280.4000,282.6222,281.4000,280.2889,281.1778,280.1778,281.4000,280.2778,281.2778,281.2778,280.1778,281.1778,280.2889,281.1778,281.1778,279.8444,281.0667,279.9444,281.1778,280.1778,280.9556,280.8444,279.9444,281.0556,280.1778,280.9556,281.2889,279.8444,281.2889,280.3889,281.3889,280.4000,280.8444,281.5111,280.4000,281.4000,280.1778,281.0556,279.6111,280.8444,280.9556,280.0667,280.9556,280.1667,281.5111,281.5111,280.1778,281.1778,280.1778,281.2889,280.3889,281.2778,281.2889,280.2889,280.9556,280.0667,281.0667,281.4000,279.9444,281.0667,280.0667,281.0667,280.1778,281.0667,281.1778,280.6111,281.1778,280.2889,281.0667,281.2889,279.7333,281.1778,280.1667,281.1778,280.2889,280.8444,281.5111,280.2889,281.1778,280.0556,280.9556,280.4000,280.9556,281.2889,280.2889,281.5111,280.3889,280.9444,281.4000,280.2889,281.1778,280.0667,281.1778"
+benchmark intrusive graph dependency handling with N nodes - 10,adding and removing dependencies,100,108,2516400,244.4057,244.2348,244.6105,0.9557,0.8234,1.0766,"243.7778,243.7778,245.9074,243.5926,243.8704,243.7778,244.5185,243.6759,243.8704,243.6852,243.7778,243.7778,243.7778,243.8704,243.6759,243.9630,243.6852,244.1481,244.3333,243.9630,243.8704,243.7778,244.5185,246.2778,246.0926,246.2870,246.1852,246.2870,246.2778,246.2778,246.8426,246.0000,246.1852,246.1019,246.2778,246.0926,246.1019,246.0000,246.2778,245.8148,246.3704,246.0000,246.1019,245.3519,243.5926,243.8704,244.1481,244.0463,244.2315,244.7037,243.7685,243.6852,244.1481,244.0556,243.7778,244.0556,244.0556,243.6852,244.0463,243.9537,243.8704,243.9630,243.7778,244.5185,244.1481,244.3333,243.9630,244.1481,243.9630,243.5833,244.1389,243.8704,243.7778,243.9630,244.4259,243.5926,243.7778,243.6852,243.7685,243.6759,243.8704,243.7778,243.9630,243.9630,243.9630,243.7778,243.7685,243.5833,243.8704,243.7778,244.0556,244.0556,243.4074,243.7778,244.4259,243.8611,243.7778,243.7778,243.7778,243.7778"
+benchmark intrusive graph dependency handling with N nodes - 10,checking for dependencies,100,505,2474500,40.5633,40.4072,41.1554,1.4213,0.2276,3.3481,"40.5485,40.5485,41.4792,40.6079,40.6079,40.5683,40.5663,40.5663,40.5485,40.5485,40.5485,40.5485,40.5663,40.7069,40.5683,40.5485,40.5485,40.0713,40.5683,40.5683,54.4950,40.5485,40.0713,40.0911,40.0733,40.0713,40.0713,40.0733,40.0713,40.0713,40.0733,40.0713,40.0713,40.0733,40.0713,40.0713,40.0931,40.0713,40.0713,40.0713,40.3485,40.5683,40.5485,40.5485,40.5683,40.5465,40.5485,40.5683,40.5683,40.5485,40.5465,40.5683,40.5485,40.5485,40.5683,40.5663,40.5465,40.5485,40.5683,40.5485,40.5465,40.5663,40.5485,40.5485,40.5683,40.5663,40.5465,40.5485,40.5683,40.5683,40.5465,40.5465,40.5683,40.5485,40.5485,40.5683,40.5465,40.0733,40.0713,40.0713,40.0733,40.0911,40.0713,40.0733,40.0713,40.0713,40.3307,40.5683,40.5485,40.5465,40.5485,40.0733,40.5267,40.5485,40.5683,40.5683,40.5485,40.5663,40.5683,40.5683"
+benchmark intrusive graph dependency handling with N nodes - 100,creating nodes,100,65,2535000,444.4885,443.5771,447.8448,7.6647,0.9656,17.4148,"442.4923,444.0462,468.4000,444.6462,442.5077,443.8769,443.8923,444.8154,443.7231,443.7385,442.4923,443.7385,443.7385,442.4923,443.7385,443.5846,442.4923,443.5846,443.5692,444.6615,446.0462,444.0462,442.4923,443.8923,443.8769,442.5077,443.8769,443.8923,442.4923,444.0308,444.0462,442.4923,443.8923,443.8769,442.4923,443.4308,443.7231,442.5077,443.5692,443.8923,442.4923,443.7385,443.8923,442.3385,443.8923,443.8769,442.5077,443.8769,443.8923,442.3385,443.8923,443.8923,442.4923,444.0462,443.8769,442.3538,516.1692,444.9692,442.5077,447.5846,443.7231,442.3538,443.7231,443.8923,442.4923,443.7231,443.8923,442.3385,443.5846,443.8769,442.5077,443.7231,443.8769,442.5077,443.7231,443.8923,442.4923,444.0462,444.0462,442.4923,443.8923,443.8769,442.5077,443.8769,444.0462,442.4923,443.8769,444.0462,442.4923,444.0462,444.0308,442.4923,443.8923,443.8769,442.5077,443.8769,443.8923,442.3385,444.0462,443.8923"
+benchmark intrusive graph dependency handling with N nodes - 100,creating and adding dependencies,100,6,2770200,4708.4483,4685.7933,4798.9933,193.5819,14.5926,448.9214,"4686.8333,4690.1667,5184.5000,4678.5000,4666.8333,4673.5000,4683.6667,4696.8333,4691.8333,4670.1667,4661.8333,4668.5000,4680.3333,4703.5000,4678.5000,4666.8333,4693.5000,4688.5000,4686.8333,4692.0000,4678.5000,4670.1667,4690.1667,4695.1667,4681.8333,4680.1667,4665.1667,4680.1667,4673.5000,4683.5000,4683.6667,4671.8333,4673.5000,4701.8333,4695.1667,4693.5000,4700.1667,4671.8333,4681.8333,4690.1667,4698.5000,4688.5000,4686.8333,4676.8333,4661.8333,4693.5000,4696.8333,4693.5000,4676.8333,4678.5000,4681.8333,4698.6667,4686.8333,4693.5000,4680.1667,4690.1667,4671.8333,4658.5000,4676.8333,4666.8333,4678.5000,4675.1667,4668.5000,4698.6667,4681.8333,6565.3333,4723.6667,4738.6667,4670.1667,4680.1667,4681.8333,4680.3333,4693.5000,4706.8333,4666.8333,4687.0000,4683.5000,4688.5000,4668.5000,4676.8333,4680.1667,4680.1667,4691.8333,4693.5000,4663.5000,4683.5000,4685.1667,4691.8333,4691.8333,4681.8333,4670.1667,4696.8333,4693.5000,4686.8333,4715.1667,4695.1667,4668.5000,4703.6667,4698.5000,4697.0000"
+benchmark intrusive graph dependency handling with N nodes - 100,adding and removing dependencies,100,6,2855400,4784.5000,4766.9917,4861.7700,157.6272,14.4764,370.2973,"4760.3333,4768.6667,5054.1667,4762.0000,4777.0000,4785.5000,4767.0000,4770.3333,4755.3333,4760.3333,4748.6667,4762.0000,4737.0000,4750.3333,4758.6667,4743.6667,4768.6667,4743.6667,4757.0000,4755.3333,4757.0000,4753.6667,4768.6667,4775.5000,4770.3333,4758.6667,4757.0000,4772.0000,4762.0000,4765.3333,4778.8333,4763.6667,4782.0000,4765.3333,4768.6667,4773.8333,4767.0000,4778.6667,4785.3333,4773.8333,4753.6667,4763.6667,4770.3333,4778.6667,4762.0000,4753.6667,4768.6667,4757.0000,4751.8333,4780.5000,4757.0000,4760.3333,4753.6667,4767.0000,4763.6667,4762.0000,4757.0000,4768.6667,4755.3333,4738.6667,4778.8333,4758.6667,4757.0000,4750.3333,4760.3333,4797.0000,4777.0000,4775.3333,4777.0000,4775.3333,4798.8333,4777.0000,4782.0000,4768.6667,4767.0000,4767.0000,4787.0000,4773.6667,4777.1667,6321.5000,4823.8333,4772.0000,4753.6667,4760.3333,4768.6667,4747.0000,4763.6667,4763.6667,4758.6667,4753.6667,4765.3333,4777.0000,4777.1667,4773.6667,4763.6667,4772.0000,4762.0000,4768.6667,4767.0000,4745.3333"
+benchmark intrusive graph dependency handling with N nodes - 100,checking for dependencies,100,13,2575300,2019.6800,2011.4562,2058.1169,76.3531,4.6897,181.0283,"2012.9231,2016.6923,2102.3077,2013.6154,2019.0769,2014.3846,2012.0769,2010.6154,2014.3846,2013.6923,2007.4615,2010.6154,2018.2308,2001.3077,2012.0769,2013.6923,2016.7692,2013.6154,2018.3077,2019.8462,2012.0769,2015.2308,2015.1538,2014.4615,2008.2308,2014.4615,2015.2308,2009.7692,2016.7692,2014.3846,2014.4615,2005.9231,2012.1538,2005.9231,2009.0769,2019.0000,2012.1538,2012.8462,2009.0769,2015.1538,2011.3077,2005.9231,2015.2308,2013.6923,2006.6923,2016.7692,2014.3846,2018.3077,2009.7692,2012.9231,2012.8462,2016.6923,2012.1538,2014.3846,2012.1538,2009.7692,2011.3846,2011.3077,2017.5385,2010.5385,2772.7692,2005.9231,2002.0769,1999.8462,2004.3846,2006.6923,2010.6154,2010.5385,2005.2308,2011.3077,2010.6154,2010.5385,2009.8462,2004.3846,2008.3077,2008.2308,2011.3077,2005.9231,2005.1538,2005.2308,2009.0000,2009.8462,2011.3077,2010.6154,2012.0769,2022.1538,2008.2308,2006.0000,2012.8462,2002.1538,2008.2308,2007.5385,2011.3077,2009.7692,2008.2308,2013.6923,2007.4615,2010.5385,2008.2308,2002.8462"
+generating large task graphs,soup topology,100,1,1024525700,10507581.2300,10298607.5500,10852982.2300,1344264.9500,923195.9127,1954560.4017,"9766853.0000,10620335.0000,11398757.0000,11474188.0000,10121433.0000,10270455.0000,10012838.0000,9735073.0000,9766653.0000,9761102.0000,9710185.0000,9790317.0000,10057142.0000,10544593.0000,9729131.0000,9705287.0000,10201094.0000,11092438.0000,9722228.0000,9886940.0000,11153043.0000,11402332.0000,10143484.0000,10561575.0000,10182819.0000,11453980.0000,9901687.0000,9863075.0000,11274301.0000,10755029.0000,14990143.0000,17286100.0000,16959373.0000,15702608.0000,9743418.0000,9884335.0000,9755792.0000,9730083.0000,9774407.0000,9738950.0000,9802510.0000,9871871.0000,9751635.0000,9687964.0000,9749360.0000,9695227.0000,9756393.0000,9657366.0000,9700647.0000,9732368.0000,9738269.0000,9785589.0000,10895835.0000,10401382.0000,9739481.0000,10755200.0000,11319858.0000,9728321.0000,10086898.0000,10755871.0000,9748218.0000,9857153.0000,11435967.0000,11423663.0000,9776831.0000,9944339.0000,9779386.0000,9724904.0000,9746414.0000,9764699.0000,9644651.0000,9706148.0000,9706549.0000,9752446.0000,9760099.0000,9766652.0000,10097979.0000,11440966.0000,11285232.0000,9729142.0000,10263051.0000,11431738.0000,10383608.0000,9737277.0000,10883301.0000,11348652.0000,9748388.0000,10874616.0000,11580960.0000,10350206.0000,9734682.0000,11368318.0000,11313285.0000,9677905.0000,10656163.0000,11499617.0000,10250938.0000,10750271.0000,11498745.0000,11079343.0000"
+generating large task graphs,chain topology,100,1,6724800,72003.6200,71568.9500,73541.5200,3597.9335,477.8841,8072.1606,"71603.0000,71693.0000,105217.0000,71303.0000,71874.0000,72004.0000,71844.0000,72065.0000,71353.0000,72284.0000,71373.0000,72105.0000,71573.0000,71513.0000,71714.0000,71914.0000,71834.0000,71653.0000,71673.0000,71123.0000,69850.0000,72034.0000,70692.0000,71182.0000,71884.0000,72095.0000,72034.0000,71443.0000,71894.0000,71874.0000,70862.0000,71122.0000,71163.0000,71894.0000,71563.0000,71994.0000,71182.0000,71042.0000,71813.0000,71804.0000,71433.0000,70932.0000,71223.0000,71002.0000,71774.0000,71864.0000,71633.0000,71082.0000,71704.0000,84317.0000,71022.0000,71864.0000,71764.0000,71774.0000,71353.0000,72024.0000,71293.0000,71463.0000,71824.0000,71964.0000,72044.0000,70892.0000,71864.0000,71834.0000,71603.0000,71723.0000,71694.0000,71814.0000,71753.0000,71584.0000,71022.0000,70602.0000,71172.0000,71493.0000,71884.0000,71654.0000,71363.0000,71824.0000,71834.0000,70912.0000,70150.0000,71624.0000,71703.0000,71043.0000,72114.0000,71473.0000,72004.0000,71733.0000,71594.0000,71693.0000,71714.0000,71092.0000,71814.0000,71974.0000,71654.0000,71403.0000,71062.0000,70842.0000,70842.0000,71824.0000"
+generating large task graphs,expanding tree topology,100,1,10914200,115293.3100,110933.3200,120996.4200,25135.6555,20447.4294,30887.8282,"102142.0000,102000.0000,152487.0000,119674.0000,125305.0000,119454.0000,119003.0000,119293.0000,119394.0000,118983.0000,123902.0000,162165.0000,197852.0000,173466.0000,167074.0000,153438.0000,150323.0000,153888.0000,153708.0000,159319.0000,169238.0000,163757.0000,163157.0000,198523.0000,167224.0000,201449.0000,157356.0000,124834.0000,102752.0000,102171.0000,102362.0000,102261.0000,124013.0000,102341.0000,102352.0000,102071.0000,102532.0000,102411.0000,102382.0000,102101.0000,101880.0000,102080.0000,102221.0000,102151.0000,102161.0000,102221.0000,102141.0000,102261.0000,102221.0000,101911.0000,102001.0000,101910.0000,102051.0000,101801.0000,102161.0000,102331.0000,101940.0000,102071.0000,102161.0000,101841.0000,102221.0000,102622.0000,102212.0000,102141.0000,102351.0000,101981.0000,102462.0000,102051.0000,102211.0000,102051.0000,102211.0000,111429.0000,102051.0000,101981.0000,102281.0000,102351.0000,102391.0000,102231.0000,102222.0000,102311.0000,102291.0000,102141.0000,102321.0000,102462.0000,102452.0000,102622.0000,102311.0000,102512.0000,102702.0000,101931.0000,102311.0000,102272.0000,102311.0000,101871.0000,102181.0000,102381.0000,102111.0000,102391.0000,102261.0000,102061.0000"
+generating large task graphs,contracting tree topology,100,1,17730700,182230.9200,181860.4000,182942.3300,2539.4524,1550.8924,4022.6552,"181631.0000,181651.0000,197902.0000,192542.0000,181682.0000,181481.0000,182232.0000,180900.0000,181732.0000,181501.0000,181601.0000,181301.0000,181421.0000,181441.0000,181270.0000,181972.0000,181441.0000,182002.0000,181752.0000,181691.0000,180850.0000,182213.0000,182022.0000,182393.0000,181721.0000,188795.0000,181110.0000,181161.0000,181401.0000,182122.0000,181611.0000,181852.0000,181401.0000,181561.0000,181802.0000,181741.0000,181831.0000,182132.0000,181691.0000,181301.0000,181942.0000,181601.0000,181711.0000,181662.0000,181681.0000,181752.0000,181972.0000,187763.0000,181150.0000,181451.0000,182243.0000,181942.0000,182302.0000,182213.0000,181501.0000,181080.0000,181782.0000,181551.0000,181501.0000,181711.0000,181632.0000,181751.0000,181511.0000,181141.0000,181431.0000,181150.0000,181351.0000,181651.0000,181582.0000,194004.0000,180930.0000,181582.0000,181391.0000,181541.0000,181851.0000,181270.0000,181962.0000,181621.0000,181461.0000,181921.0000,181722.0000,180569.0000,181762.0000,182132.0000,181121.0000,182362.0000,181892.0000,182323.0000,181982.0000,182022.0000,181461.0000,188093.0000,181150.0000,181982.0000,181812.0000,181791.0000,182183.0000,181711.0000,181351.0000,180569.0000"
+generating large task graphs,wave_sim topology,100,1,69614400,638478.6200,636386.2300,641393.0000,12501.5437,9641.9296,19158.0276,"628185.0000,639947.0000,709749.0000,645508.0000,628306.0000,667148.0000,626431.0000,637894.0000,628736.0000,641681.0000,625660.0000,656879.0000,627775.0000,640398.0000,628215.0000,638825.0000,625280.0000,658522.0000,629186.0000,638714.0000,626992.0000,639056.0000,630069.0000,640879.0000,650247.0000,640318.0000,627123.0000,642111.0000,626071.0000,640658.0000,644717.0000,638755.0000,626572.0000,640588.0000,628466.0000,638885.0000,655676.0000,639977.0000,628195.0000,641671.0000,629387.0000,642572.0000,639145.0000,641320.0000,629187.0000,640108.0000,628916.0000,641310.0000,630890.0000,655597.0000,628986.0000,643794.0000,627504.0000,641290.0000,629718.0000,672318.0000,627984.0000,638244.0000,628696.0000,641339.0000,628665.0000,653042.0000,629688.0000,640498.0000,629838.0000,647542.0000,635819.0000,636049.0000,659634.0000,641761.0000,623837.0000,638064.0000,625440.0000,639747.0000,647491.0000,641130.0000,625921.0000,639386.0000,624428.0000,639336.0000,645167.0000,638325.0000,626762.0000,640028.0000,630439.0000,641110.0000,649184.0000,641299.0000,630891.0000,639997.0000,630349.0000,640659.0000,629698.0000,670605.0000,626332.0000,639937.0000,628596.0000,639507.0000,627323.0000,655968.0000"
+generating large task graphs,jacobi topology,100,1,20776200,212303.9800,210013.7900,214961.3600,12507.5567,11255.6791,14395.1492,"229862.0000,229121.0000,252345.0000,204965.0000,204695.0000,203653.0000,203903.0000,204234.0000,203663.0000,203423.0000,203412.0000,203613.0000,203242.0000,203813.0000,203472.0000,203483.0000,203432.0000,217299.0000,203953.0000,203312.0000,204144.0000,203863.0000,203332.0000,203974.0000,203813.0000,203903.0000,203593.0000,203743.0000,203653.0000,203663.0000,203773.0000,203934.0000,203853.0000,204404.0000,203973.0000,203693.0000,222058.0000,204144.0000,204454.0000,204414.0000,203652.0000,204003.0000,204114.0000,204294.0000,204324.0000,203202.0000,203904.0000,203472.0000,203753.0000,203743.0000,204414.0000,204074.0000,204023.0000,203783.0000,204153.0000,204154.0000,236084.0000,204224.0000,204324.0000,204765.0000,205356.0000,204755.0000,205526.0000,204906.0000,204875.0000,204925.0000,205036.0000,205336.0000,204995.0000,205035.0000,204935.0000,204946.0000,204875.0000,204344.0000,205016.0000,228620.0000,230223.0000,230614.0000,229642.0000,230995.0000,230543.0000,230424.0000,230333.0000,229462.0000,230413.0000,230844.0000,230534.0000,230423.0000,230614.0000,230754.0000,230444.0000,230513.0000,235584.0000,229822.0000,229372.0000,229812.0000,229412.0000,229481.0000,229512.0000,229412.0000"
+generating large command graphs for N nodes - 1,soup topology,100,1,1863754300,18377377.1000,18163377.7200,18547512.7200,972728.9215,814206.2182,1121569.5742,"18937541.0000,18887285.0000,18100400.0000,16089750.0000,17903066.0000,18897074.0000,18333861.0000,19002744.0000,18958811.0000,19034745.0000,18948362.0000,18877007.0000,18956166.0000,18886135.0000,18958871.0000,18926601.0000,18952929.0000,18998436.0000,18947720.0000,18923705.0000,18949473.0000,18946749.0000,18927221.0000,18928304.0000,19018844.0000,17670818.0000,18987305.0000,18911352.0000,18190680.0000,16281784.0000,16222030.0000,16130868.0000,17037270.0000,18958401.0000,18884190.0000,18925849.0000,18990681.0000,19290148.0000,18690213.0000,16125728.0000,16867699.0000,16591579.0000,16163830.0000,16291291.0000,16149453.0000,16200700.0000,17832032.0000,18249362.0000,16218183.0000,17970223.0000,17914669.0000,16428691.0000,18817054.0000,18958641.0000,19002914.0000,18982997.0000,18952369.0000,18380469.0000,16112142.0000,17496038.0000,18875223.0000,18977657.0000,18910921.0000,18855577.0000,18877998.0000,18960945.0000,18988366.0000,18919106.0000,18999407.0000,18925058.0000,18884220.0000,18864714.0000,18867769.0000,18929527.0000,18894189.0000,18970414.0000,18886685.0000,18933013.0000,18936008.0000,18879842.0000,18088377.0000,18537625.0000,18866257.0000,18911412.0000,18886796.0000,18886805.0000,18910020.0000,18926991.0000,18968741.0000,18916481.0000,18905882.0000,18944424.0000,18968280.0000,18978438.0000,18488814.0000,16151076.0000,17172978.0000,18917262.0000,18946708.0000,18858251.0000"
+generating large command graphs for N nodes - 1,chain topology,100,1,27958100,281850.7400,281342.3400,282704.7200,3284.1878,2190.0756,4639.0691,"281009.0000,280639.0000,295636.0000,283013.0000,281530.0000,280999.0000,288663.0000,282953.0000,280528.0000,280038.0000,281530.0000,281230.0000,280688.0000,281781.0000,281360.0000,281229.0000,280699.0000,280167.0000,280508.0000,280628.0000,286981.0000,281239.0000,282051.0000,280297.0000,279907.0000,281179.0000,280338.0000,281440.0000,281751.0000,280067.0000,280508.0000,280488.0000,279987.0000,280358.0000,281199.0000,294745.0000,280578.0000,281680.0000,281280.0000,280618.0000,280418.0000,280147.0000,281059.0000,280819.0000,280338.0000,281089.0000,281279.0000,280859.0000,280238.0000,289305.0000,280818.0000,281189.0000,281410.0000,280428.0000,281149.0000,280508.0000,281420.0000,281279.0000,281240.0000,281460.0000,281009.0000,281971.0000,281039.0000,298081.0000,281550.0000,281560.0000,279897.0000,282011.0000,281029.0000,281450.0000,280688.0000,281510.0000,280619.0000,279977.0000,280989.0000,280619.0000,281029.0000,289154.0000,280799.0000,281009.0000,280248.0000,280378.0000,280418.0000,280698.0000,280288.0000,281520.0000,280198.0000,280899.0000,281440.0000,280688.0000,280849.0000,294905.0000,281349.0000,281120.0000,281279.0000,280879.0000,281440.0000,280689.0000,280618.0000,281210.0000"
+generating large command graphs for N nodes - 1,expanding tree topology,100,1,39594800,388210.8500,383968.1100,391926.3700,20299.9073,16808.2950,24876.9127,"395696.0000,402759.0000,461940.0000,397048.0000,396167.0000,394683.0000,394603.0000,396137.0000,407588.0000,396007.0000,395756.0000,394884.0000,386549.0000,348526.0000,346102.0000,347514.0000,346362.0000,346052.0000,345211.0000,354428.0000,346583.0000,345992.0000,345731.0000,344940.0000,345551.0000,345601.0000,345541.0000,345671.0000,344138.0000,343998.0000,379625.0000,397349.0000,395966.0000,396487.0000,395846.0000,396287.0000,395996.0000,396096.0000,396778.0000,394844.0000,400235.0000,395706.0000,395515.0000,395456.0000,394624.0000,395515.0000,395676.0000,395736.0000,396046.0000,396457.0000,399813.0000,395786.0000,394994.0000,394614.0000,395155.0000,394163.0000,394884.0000,394163.0000,395205.0000,395145.0000,405524.0000,396457.0000,395956.0000,395496.0000,395085.0000,395104.0000,394995.0000,395135.0000,394323.0000,394664.0000,401326.0000,396186.0000,395816.0000,394223.0000,394744.0000,395315.0000,395596.0000,395866.0000,395545.0000,393671.0000,395555.0000,408430.0000,395626.0000,394453.0000,395846.0000,395646.0000,395545.0000,396106.0000,396107.0000,394974.0000,395656.0000,401857.0000,396197.0000,395626.0000,396067.0000,395685.0000,395715.0000,396968.0000,395415.0000,394664.0000"
+generating large command graphs for N nodes - 1,contracting tree topology,100,1,47757000,554943.9000,522193.8900,595947.5000,186438.5486,155069.1633,215892.8454,"488952.0000,488721.0000,496035.0000,427636.0000,426714.0000,427185.0000,436704.0000,426494.0000,426213.0000,425262.0000,425021.0000,426104.0000,426203.0000,425332.0000,425151.0000,474765.0000,429059.0000,426834.0000,427535.0000,427085.0000,428528.0000,427756.0000,426604.0000,426594.0000,447102.0000,428197.0000,428277.0000,427777.0000,427516.0000,428648.0000,426374.0000,427436.0000,427576.0000,426273.0000,1107451.0000,947688.0000,939343.0000,932911.0000,958329.0000,933893.0000,929334.0000,928853.0000,936107.0000,928582.0000,929003.0000,928503.0000,936498.0000,933272.0000,930316.0000,929955.0000,950964.0000,931508.0000,642102.0000,489913.0000,488631.0000,488531.0000,488461.0000,494663.0000,489072.0000,488781.0000,488130.0000,489563.0000,489353.0000,489223.0000,490004.0000,497167.0000,489212.0000,491476.0000,490145.0000,489553.0000,488962.0000,488321.0000,489633.0000,490245.0000,504401.0000,489343.0000,488441.0000,488361.0000,487429.0000,488301.0000,489724.0000,489172.0000,493080.0000,488902.0000,489143.0000,490925.0000,488831.0000,490054.0000,490204.0000,490505.0000,501055.0000,491006.0000,488341.0000,489122.0000,490816.0000,489653.0000,490094.0000,489353.0000,497327.0000,489493.0000"
+generating large command graphs for N nodes - 1,wave_sim topology,100,1,225522700,2190300.2800,2166820.0400,2210805.7300,111627.8112,99978.5221,120279.9046,"2274516.0000,2256792.0000,2259798.0000,2249428.0000,2244348.0000,2254067.0000,2248016.0000,2257884.0000,2246813.0000,2244099.0000,2245772.0000,2238628.0000,2257674.0000,2242456.0000,2253997.0000,2263024.0000,2246153.0000,2254318.0000,2252224.0000,2262763.0000,2257935.0000,2272602.0000,2255350.0000,2261672.0000,2255650.0000,2249268.0000,2262523.0000,2249198.0000,2258506.0000,2250962.0000,2265859.0000,2266722.0000,2265148.0000,2273364.0000,2275668.0000,2292590.0000,2286028.0000,2287029.0000,2290316.0000,2285517.0000,2301527.0000,2285677.0000,2282831.0000,2280858.0000,2287650.0000,2304533.0000,2101289.0000,2018673.0000,2002632.0000,2022179.0000,2006129.0000,2017390.0000,2009034.0000,2015987.0000,2001960.0000,2017700.0000,2011038.0000,2031596.0000,2004786.0000,2016578.0000,2001910.0000,2084196.0000,2258666.0000,2265820.0000,2257934.0000,2268424.0000,2260329.0000,2265609.0000,2268434.0000,2254438.0000,2256251.0000,2255730.0000,2269506.0000,2256823.0000,2263004.0000,2260239.0000,2251463.0000,2269065.0000,2261371.0000,2257404.0000,2257103.0000,2268324.0000,2260369.0000,2251942.0000,2199433.0000,2002412.0000,2020556.0000,2009736.0000,2022410.0000,2010837.0000,2016097.0000,2004376.0000,2026207.0000,2007030.0000,2025796.0000,2010937.0000,2030404.0000,2011439.0000,2116117.0000,2257163.0000"
+generating large command graphs for N nodes - 1,jacobi topology,100,1,82599000,814585.6500,808453.1100,818988.3900,26328.0865,20437.2764,31963.4653,"821009.0000,821571.0000,752129.0000,745236.0000,767488.0000,743283.0000,743423.0000,741850.0000,740798.0000,747811.0000,742852.0000,742010.0000,742241.0000,742722.0000,769812.0000,826008.0000,825397.0000,823434.0000,823825.0000,830017.0000,825528.0000,823404.0000,823334.0000,823003.0000,830608.0000,823685.0000,823915.0000,824766.0000,824557.0000,835657.0000,823634.0000,823284.0000,824356.0000,823614.0000,829585.0000,822462.0000,823284.0000,822151.0000,822051.0000,836509.0000,822763.0000,822702.0000,822572.0000,830016.0000,821300.0000,821680.0000,823525.0000,823494.0000,830297.0000,823695.0000,822612.0000,822503.0000,823344.0000,835436.0000,822903.0000,823173.0000,822262.0000,822282.0000,827762.0000,821079.0000,819908.0000,821761.0000,821310.0000,837460.0000,821891.0000,822151.0000,821730.0000,822352.0000,828454.0000,824656.0000,820979.0000,822703.0000,822813.0000,829996.0000,823074.0000,821921.0000,822613.0000,834745.0000,823414.0000,821530.0000,822251.0000,822933.0000,828183.0000,823364.0000,820709.0000,822012.0000,823273.0000,842279.0000,822442.0000,822572.0000,821390.0000,822222.0000,830548.0000,823063.0000,823414.0000,822703.0000,822703.0000,828153.0000,820068.0000,821119.0000"
+generating large command graphs for N nodes - 4,soup topology,100,1,4205343300,42708788.4900,42402504.6700,42931269.5100,1317030.9096,1032972.4408,1666162.8130,"43474013.0000,43503369.0000,43364257.0000,42502518.0000,43209815.0000,43213661.0000,43234902.0000,43219754.0000,43303341.0000,41319532.0000,39408752.0000,43441162.0000,43354358.0000,43405144.0000,42855204.0000,43278224.0000,43342475.0000,42361101.0000,41881314.0000,43312498.0000,43353997.0000,43284857.0000,43455799.0000,39841700.0000,41361020.0000,43448054.0000,43453294.0000,43482680.0000,43407557.0000,42900750.0000,43344780.0000,43359568.0000,43386228.0000,41080020.0000,40193054.0000,43303452.0000,40827253.0000,43497658.0000,43412566.0000,43390365.0000,43428437.0000,42360149.0000,39518229.0000,43187632.0000,43462833.0000,43428127.0000,43439398.0000,43507617.0000,42625641.0000,43426544.0000,42998776.0000,43409051.0000,42973417.0000,43433808.0000,43319993.0000,43350640.0000,43389884.0000,40520282.0000,40502849.0000,43349538.0000,43322247.0000,43373413.0000,43320393.0000,42542283.0000,41308392.0000,38291010.0000,43354087.0000,43376049.0000,43336965.0000,43329020.0000,43521373.0000,43087864.0000,43372442.0000,43423609.0000,43394524.0000,43431372.0000,37693662.0000,43315334.0000,43480777.0000,42615842.0000,43246343.0000,41200067.0000,42185529.0000,43474164.0000,43512936.0000,43559785.0000,43176913.0000,43424350.0000,43485356.0000,42765043.0000,43293383.0000,43489223.0000,38500967.0000,41938963.0000,43421144.0000,42686365.0000,38435674.0000,43557652.0000,42836068.0000,43395375.0000"
+generating large command graphs for N nodes - 4,chain topology,100,1,333587400,3289545.3500,3260334.2600,3309269.1500,120696.7685,88377.7332,153249.8353,"3327716.0000,3326403.0000,3327927.0000,2985649.0000,2915797.0000,2925136.0000,2892143.0000,2911299.0000,2909245.0000,2913583.0000,2898565.0000,2912421.0000,3040774.0000,3332926.0000,3317427.0000,3334348.0000,3338656.0000,3331933.0000,3337524.0000,3330841.0000,3324399.0000,3338275.0000,3328247.0000,3334869.0000,3346291.0000,3334058.0000,3319841.0000,3333748.0000,3330962.0000,3323618.0000,3325752.0000,3324510.0000,3315584.0000,3329539.0000,3330101.0000,3325953.0000,3329780.0000,3328337.0000,3315944.0000,3329429.0000,3321324.0000,3323608.0000,3334067.0000,3335160.0000,3320162.0000,3339809.0000,3329760.0000,3335420.0000,3320772.0000,3320842.0000,3316785.0000,3328828.0000,3327355.0000,3329390.0000,3332154.0000,3323208.0000,3315844.0000,3339398.0000,3330982.0000,3334098.0000,3344057.0000,3325271.0000,3321064.0000,3327265.0000,3334259.0000,3328928.0000,3320112.0000,3330231.0000,3317346.0000,3323267.0000,3327936.0000,3340209.0000,3336162.0000,3327656.0000,3317537.0000,3329189.0000,3329790.0000,3332034.0000,3328367.0000,3337665.0000,3331032.0000,3329680.0000,3342754.0000,3339829.0000,3337454.0000,3337264.0000,3324129.0000,3340961.0000,3339398.0000,3332475.0000,3345219.0000,3329769.0000,3318408.0000,3334028.0000,3323268.0000,3324810.0000,3334789.0000,3321284.0000,3320322.0000,3330801.0000"
+generating large command graphs for N nodes - 4,expanding tree topology,100,1,650091500,6558322.4800,6508173.1900,6684085.9000,354070.3266,12323.5374,650680.8898,"6496543.0000,6506031.0000,6522422.0000,6507814.0000,6500580.0000,6513957.0000,6505761.0000,6493418.0000,6512314.0000,6500290.0000,6503517.0000,6501152.0000,6493778.0000,6517333.0000,6497907.0000,6511791.0000,6516732.0000,6495461.0000,6510530.0000,6502104.0000,6498467.0000,6496714.0000,6490021.0000,6514427.0000,6501794.0000,6480463.0000,6505410.0000,6505982.0000,6497065.0000,6508727.0000,6505731.0000,6509648.0000,6497596.0000,6495121.0000,6501303.0000,6505641.0000,6513264.0000,6508906.0000,6515078.0000,6515820.0000,6502164.0000,6512373.0000,6524076.0000,6515830.0000,6494189.0000,6516571.0000,6527011.0000,6521881.0000,6526210.0000,6494720.0000,6512434.0000,6504228.0000,6524205.0000,6527913.0000,6499710.0000,6525168.0000,6511482.0000,6514667.0000,6519006.0000,6524817.0000,6518795.0000,6514367.0000,6527462.0000,6503155.0000,6512474.0000,6519888.0000,6528634.0000,6541198.0000,6504017.0000,6502425.0000,6518104.0000,6492446.0000,6507434.0000,6510810.0000,6512975.0000,6497225.0000,6501052.0000,6543272.0000,6517302.0000,6503846.0000,6533132.0000,6505971.0000,8860551.0000,9198849.0000,6515650.0000,6492556.0000,6506443.0000,6490983.0000,6506342.0000,6510089.0000,6501353.0000,6496885.0000,6508646.0000,6483188.0000,6503657.0000,6472217.0000,6504458.0000,6495291.0000,6491654.0000,6502184.0000"
+generating large command graphs for N nodes - 4,contracting tree topology,100,1,368187800,3727709.3100,3726161.4300,3730788.3300,10797.2806,6508.8744,21107.4401,"3714927.0000,3728162.0000,3735376.0000,3735837.0000,3731309.0000,3725748.0000,3734425.0000,3726459.0000,3730968.0000,3725036.0000,3734214.0000,3737400.0000,3717913.0000,3729345.0000,3722041.0000,3732371.0000,3721721.0000,3725097.0000,3727211.0000,3724405.0000,3735516.0000,3728493.0000,3717002.0000,3727912.0000,3721861.0000,3727411.0000,3716831.0000,3705610.0000,3719006.0000,3728954.0000,3725097.0000,3731188.0000,3730167.0000,3731789.0000,3724014.0000,3732190.0000,3721741.0000,3728994.0000,3727842.0000,3726891.0000,3721639.0000,3719245.0000,3717392.0000,3735727.0000,3730537.0000,3727281.0000,3728714.0000,3723944.0000,3731969.0000,3724325.0000,3718945.0000,3730327.0000,3725117.0000,3727391.0000,3732161.0000,3719416.0000,3714337.0000,3729455.0000,3721209.0000,3732140.0000,3736409.0000,3728403.0000,3721560.0000,3731829.0000,3721691.0000,3730918.0000,3715669.0000,3723274.0000,3721038.0000,3733903.0000,3731259.0000,3725087.0000,3733402.0000,3720969.0000,3728964.0000,3811300.0000,3738031.0000,3738893.0000,3731249.0000,3732280.0000,3738301.0000,3724866.0000,3727902.0000,3744533.0000,3729656.0000,3739173.0000,3718493.0000,3717282.0000,3715799.0000,3728013.0000,3716190.0000,3728674.0000,3721921.0000,3723945.0000,3735827.0000,3712593.0000,3722151.0000,3732341.0000,3727572.0000,3729826.0000"
+generating large command graphs for N nodes - 4,wave_sim topology,100,1,1529845700,15267931.6100,15189638.4200,15296959.5600,219256.5916,66389.5991,439357.1011,"15291661.0000,15299988.0000,15400348.0000,15311709.0000,15327541.0000,15317191.0000,15287504.0000,15308304.0000,15325616.0000,15308054.0000,15286031.0000,15334454.0000,15347628.0000,15301240.0000,15319405.0000,15303524.0000,15288657.0000,15310597.0000,15290801.0000,15285740.0000,14869825.0000,15321358.0000,15305578.0000,15321018.0000,15298805.0000,15299007.0000,15302733.0000,15283347.0000,15298264.0000,15314636.0000,15310768.0000,15307092.0000,15272978.0000,15266644.0000,15310388.0000,15324714.0000,15346667.0000,15305297.0000,15329904.0000,15306530.0000,15325306.0000,15326388.0000,15314846.0000,15332159.0000,15286402.0000,15289669.0000,15288266.0000,15306039.0000,15284828.0000,15266324.0000,15268228.0000,15295739.0000,15312441.0000,15353689.0000,15291983.0000,15294177.0000,15294147.0000,15283186.0000,15304346.0000,15271514.0000,15266574.0000,15279700.0000,15293025.0000,15270072.0000,15259721.0000,15284129.0000,15279098.0000,15325336.0000,15311329.0000,15311720.0000,15298135.0000,15287264.0000,15295099.0000,15272065.0000,15288927.0000,15294948.0000,15274069.0000,15265914.0000,15292524.0000,15300750.0000,15291221.0000,15270823.0000,15271845.0000,15251617.0000,15272125.0000,15217452.0000,13468798.0000,14162197.0000,15350804.0000,15413121.0000,15341657.0000,15364259.0000,15332118.0000,15307181.0000,15301391.0000,15292925.0000,15287995.0000,15288397.0000,15310006.0000,15315607.0000"
+generating large command graphs for N nodes - 4,jacobi topology,100,1,507466100,5068313.0600,5011685.8200,5120000.4300,276244.4327,253797.8774,292471.9196,"5302939.0000,5278973.0000,5294493.0000,5258033.0000,5272461.0000,5281538.0000,5221665.0000,4669572.0000,4656376.0000,4653902.0000,4674440.0000,5289472.0000,5264686.0000,5275266.0000,5273332.0000,5274234.0000,5274885.0000,5290615.0000,5018681.0000,4649383.0000,4648221.0000,4665824.0000,4662276.0000,4672426.0000,4655104.0000,5003142.0000,5293651.0000,5284834.0000,5282199.0000,5315360.0000,4901289.0000,4911408.0000,5283010.0000,5104954.0000,4672337.0000,4678227.0000,4683146.0000,4679220.0000,4662428.0000,4736408.0000,5285987.0000,5295925.0000,5302588.0000,5297056.0000,4990428.0000,4666326.0000,4659783.0000,4680833.0000,5252002.0000,5292929.0000,5304070.0000,5285705.0000,5276798.0000,5295323.0000,4993153.0000,4678518.0000,4693607.0000,4681263.0000,4658331.0000,4695360.0000,4846025.0000,5272080.0000,5280736.0000,5266529.0000,5268613.0000,4871402.0000,4683377.0000,4658902.0000,4678368.0000,4693607.0000,4656797.0000,4640136.0000,5228868.0000,5269786.0000,5271840.0000,5276629.0000,5281928.0000,5268923.0000,5275156.0000,5267681.0000,5279894.0000,5285415.0000,5269064.0000,5266739.0000,5275646.0000,5291106.0000,5277550.0000,5268393.0000,5273944.0000,5265327.0000,5282118.0000,5283692.0000,5273653.0000,5276739.0000,5332635.0000,5291186.0000,5275706.0000,5287388.0000,5277631.0000,5283702.0000"
+generating large command graphs for N nodes - 16,soup topology,100,1,14519595300,140222187.1800,139337963.1400,141220725.3900,4792785.6426,4330820.7890,5189402.9447,"146560970.0000,147916240.0000,147799650.0000,147505906.0000,147476429.0000,147491578.0000,143766951.0000,148151535.0000,142198627.0000,143985944.0000,148440771.0000,148281840.0000,148205256.0000,143274299.0000,147161624.0000,148158698.0000,142565139.0000,148077856.0000,148284215.0000,148691415.0000,142840690.0000,142260793.0000,147887376.0000,144668444.0000,147525231.0000,147611425.0000,148374507.0000,148130014.0000,147810651.0000,147852520.0000,146508590.0000,148044784.0000,143079922.0000,138172519.0000,134677495.0000,137580270.0000,137498496.0000,136878625.0000,135384922.0000,136833730.0000,138324747.0000,135062362.0000,137933318.0000,139176597.0000,135210643.0000,136593416.0000,139408034.0000,135779848.0000,135957544.0000,136836274.0000,137184643.0000,136147393.0000,139653709.0000,136664890.0000,135685560.0000,138542980.0000,137079824.0000,134789176.0000,138426359.0000,136744189.0000,135923670.0000,137678155.0000,136872613.0000,136157622.0000,137632179.0000,136923299.0000,137730785.0000,135163163.0000,137469301.0000,137259483.0000,135542469.0000,137299349.0000,138446628.0000,136788614.0000,136619314.0000,137376536.0000,136993802.0000,136165006.0000,139252650.0000,134869599.0000,135466997.0000,138328194.0000,136949949.0000,135407545.0000,138374921.0000,137403927.0000,135585531.0000,137976639.0000,137401903.0000,136584679.0000,137830152.0000,136834781.0000,137480682.0000,135552459.0000,137045961.0000,139277517.0000,135523033.0000,137767685.0000,137277708.0000,145166765.0000"
+generating large command graphs for N nodes - 16,chain topology,100,1,39454798100,373793332.5700,371243441.1500,376278484.9900,12892767.9136,11826219.2512,14170899.8698,"383851446.0000,377578703.0000,370084604.0000,363116317.0000,369037345.0000,375579977.0000,363756748.0000,368058446.0000,362017321.0000,351930201.0000,360695553.0000,355927644.0000,367005325.0000,367086810.0000,376877420.0000,355171455.0000,347002329.0000,356982407.0000,354027894.0000,354474038.0000,361047689.0000,367080297.0000,359125557.0000,363907723.0000,361043250.0000,366557288.0000,355299557.0000,356981755.0000,367354625.0000,366915225.0000,360359538.0000,356757622.0000,354827745.0000,363649555.0000,352583926.0000,352834399.0000,364983314.0000,359439900.0000,351215109.0000,364013752.0000,380253488.0000,370328595.0000,362328328.0000,370095054.0000,347676151.0000,370511160.0000,369254074.0000,371509296.0000,373358390.0000,368226784.0000,368124611.0000,366207618.0000,370921474.0000,370281516.0000,368051642.0000,390491562.0000,380220004.0000,381926590.0000,391171788.0000,390774719.0000,381330132.0000,390054117.0000,383052768.0000,391280674.0000,391503014.0000,395478816.0000,385133379.0000,384406114.0000,391880648.0000,383270077.0000,386299252.0000,386873887.0000,385223910.0000,391925633.0000,385863349.0000,381515432.0000,379085411.0000,377013305.0000,386198932.0000,387456568.0000,378646351.0000,386773497.0000,392063313.0000,384146594.0000,385985238.0000,383825236.0000,385520851.0000,381232658.0000,377279107.0000,377294106.0000,376473095.0000,385304882.0000,391971700.0000,390852876.0000,386386186.0000,391927105.0000,385713694.0000,391763416.0000,386485042.0000,386890239.0000"
+generating large command graphs for N nodes - 16,expanding tree topology,100,1,41613130200,401174022.6700,399178140.5600,402962032.0200,9709571.3340,8526243.1784,11434333.3485,"399144321.0000,404176379.0000,413229447.0000,404525491.0000,412072691.0000,404551629.0000,407411143.0000,405866834.0000,401662259.0000,412839560.0000,413633741.0000,408198941.0000,407768628.0000,413209920.0000,412949077.0000,412799143.0000,414661904.0000,403914996.0000,409758478.0000,412969075.0000,415058993.0000,414180433.0000,413183701.0000,412720735.0000,413954346.0000,412069344.0000,401349879.0000,369379812.0000,399765285.0000,392737917.0000,402407789.0000,381240131.0000,392447218.0000,407257993.0000,392450564.0000,401848412.0000,410224138.0000,381199575.0000,389895676.0000,392544802.0000,395565841.0000,403622053.0000,391929128.0000,386325521.0000,407299552.0000,409599326.0000,407424979.0000,396780365.0000,409850020.0000,407046713.0000,412538982.0000,402387550.0000,407777244.0000,398760517.0000,402908354.0000,400486378.0000,404081360.0000,381505493.0000,386809044.0000,395192554.0000,398066636.0000,398099538.0000,400129754.0000,400449829.0000,396265111.0000,404480806.0000,405471086.0000,403905798.0000,411310551.0000,405845834.0000,405936666.0000,412466574.0000,403178284.0000,403220675.0000,410438742.0000,381536461.0000,392935620.0000,384470075.0000,394039196.0000,399686575.0000,398173738.0000,402169979.0000,396811154.0000,403572418.0000,398208494.0000,392195471.0000,389261207.0000,391409707.0000,392115821.0000,390575560.0000,384713414.0000,383490574.0000,406688295.0000,393204529.0000,402397969.0000,377737834.0000,404106106.0000,404175718.0000,404356410.0000,410952684.0000"
+generating large command graphs for N nodes - 16,contracting tree topology,100,1,12291806800,125188990.7500,124592592.4100,125737258.6500,2914371.8960,2628265.6051,3275022.2332,"127925927.0000,128173135.0000,127801752.0000,119143984.0000,128012731.0000,118773874.0000,119975645.0000,128641099.0000,122655528.0000,121770497.0000,119660170.0000,123004137.0000,121563737.0000,122701455.0000,126495726.0000,119314004.0000,121883560.0000,125314693.0000,121399145.0000,124270751.0000,126516114.0000,124997213.0000,124799390.0000,118082768.0000,127989327.0000,128316706.0000,128189755.0000,127990729.0000,123377022.0000,127977505.0000,127198924.0000,124667450.0000,124208062.0000,121137030.0000,127829194.0000,127960002.0000,123350231.0000,127788367.0000,126283474.0000,124667269.0000,122618298.0000,127750545.0000,127714888.0000,122971016.0000,127135313.0000,128228389.0000,124948531.0000,122714249.0000,127437996.0000,123070803.0000,122045035.0000,124773230.0000,121759275.0000,122731091.0000,122055926.0000,123134213.0000,127862527.0000,128092293.0000,127870071.0000,127867667.0000,127703257.0000,127986742.0000,127305174.0000,124060905.0000,127961464.0000,128101488.0000,128035193.0000,126914436.0000,123605663.0000,125909659.0000,125383833.0000,125316536.0000,123393013.0000,128122459.0000,128370768.0000,128237587.0000,128072735.0000,127852348.0000,123120829.0000,127832331.0000,128076632.0000,127871925.0000,128101038.0000,125301729.0000,125409121.0000,128061113.0000,122409614.0000,127984207.0000,123872189.0000,119940118.0000,122560039.0000,122810571.0000,123202852.0000,118177307.0000,122791226.0000,127981482.0000,122508731.0000,128074699.0000,127992894.0000,127895730.0000"
+generating large command graphs for N nodes - 16,wave_sim topology,100,1,12909611100,124911858.5900,124059661.5700,125772014.4200,4357252.1683,4034005.6219,4963302.6036,"129016888.0000,124141627.0000,129138469.0000,129161593.0000,129154388.0000,124106701.0000,129118521.0000,129133800.0000,129016478.0000,129039952.0000,129079807.0000,129138969.0000,129133729.0000,129275218.0000,129189615.0000,129177923.0000,129286909.0000,134103721.0000,128583249.0000,127436142.0000,128096741.0000,128037929.0000,119012054.0000,120416658.0000,122143251.0000,120282035.0000,119295750.0000,118590168.0000,120132271.0000,120324043.0000,119402311.0000,119123315.0000,119799302.0000,121914859.0000,119338060.0000,119266596.0000,120368457.0000,118545132.0000,121360521.0000,119515185.0000,119700555.0000,122285510.0000,119745260.0000,119412731.0000,119364800.0000,120878781.0000,119004240.0000,119169893.0000,120718248.0000,120104389.0000,120524862.0000,120908067.0000,119556573.0000,118242481.0000,121067578.0000,121062880.0000,119462345.0000,126444588.0000,124571620.0000,129379844.0000,124857610.0000,129038299.0000,129331483.0000,124419903.0000,124260020.0000,129404140.0000,123608749.0000,128144060.0000,124778349.0000,128633363.0000,121344681.0000,124717615.0000,125236375.0000,128193833.0000,128203421.0000,137453880.0000,127649345.0000,129197250.0000,129305775.0000,129062455.0000,129139921.0000,127851026.0000,121275350.0000,129060451.0000,129102120.0000,117436908.0000,129080289.0000,129079316.0000,125206839.0000,127811993.0000,129020084.0000,123923274.0000,129253255.0000,129223959.0000,123905931.0000,129229221.0000,124346664.0000,124706023.0000,124602948.0000,129086099.0000"
+generating large command graphs for N nodes - 16,jacobi topology,100,1,11943371300,120284391.5300,119738799.2500,120706359.8200,2434633.1347,1998057.0778,2972258.4227,"113216924.0000,114259764.0000,115719854.0000,121562894.0000,121765938.0000,121651181.0000,122005380.0000,121811585.0000,115443932.0000,116341759.0000,117660801.0000,119740020.0000,121702537.0000,121446313.0000,121517919.0000,118540964.0000,117715966.0000,119334744.0000,120248521.0000,121768993.0000,121943272.0000,121894821.0000,115746533.0000,121509383.0000,121476111.0000,121696667.0000,118195702.0000,116454622.0000,115610327.0000,121592269.0000,116284540.0000,116479498.0000,121647134.0000,121577973.0000,118882178.0000,118549841.0000,121738355.0000,121577130.0000,121577492.0000,121502329.0000,121455651.0000,121498002.0000,121588983.0000,121563575.0000,121486049.0000,120454460.0000,121716875.0000,121507269.0000,121660408.0000,121516326.0000,121728257.0000,121530683.0000,121528689.0000,121822234.0000,121767450.0000,120303113.0000,121656892.0000,121347466.0000,121656871.0000,121580318.0000,121658064.0000,121651221.0000,119746202.0000,121984871.0000,121618098.0000,121863381.0000,121735571.0000,121573143.0000,121510375.0000,121455391.0000,121457684.0000,121693701.0000,121533148.0000,121579284.0000,121648285.0000,121700394.0000,121529311.0000,121609682.0000,120090652.0000,121525063.0000,121489716.0000,121602699.0000,121495697.0000,121563055.0000,121590566.0000,121695484.0000,121682481.0000,121634158.0000,119997265.0000,121585818.0000,121470420.0000,121622927.0000,121646231.0000,121683212.0000,118395589.0000,117271476.0000,114421610.0000,112236011.0000,115548219.0000,111881261.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation,soup topology,100,1,1809866100,17141495.1700,16959788.4900,17342432.6600,974101.8427,882196.2962,1066676.3554,"16557574.0000,16164330.0000,19030557.0000,17075513.0000,18561511.0000,16794211.0000,17374588.0000,17184268.0000,16643326.0000,16146127.0000,17565889.0000,16283285.0000,17301921.0000,17791315.0000,16075192.0000,16749427.0000,18224153.0000,16883730.0000,17162277.0000,16154321.0000,18704871.0000,17219495.0000,18128873.0000,16219105.0000,16377895.0000,18506897.0000,16268116.0000,17592480.0000,18375489.0000,16287633.0000,16223333.0000,16249171.0000,16278476.0000,16301671.0000,16306218.0000,16221779.0000,16312121.0000,16248490.0000,16243952.0000,16287674.0000,16240474.0000,16238973.0000,16271303.0000,16321478.0000,16260072.0000,16272485.0000,16285700.0000,16289747.0000,17175240.0000,18812294.0000,16247238.0000,16282083.0000,16281313.0000,16255082.0000,16272095.0000,16678553.0000,18170973.0000,16282774.0000,16318143.0000,16202222.0000,17482181.0000,16151778.0000,16908988.0000,17359098.0000,16516106.0000,18846739.0000,16190881.0000,17652804.0000,17568043.0000,18418991.0000,17539209.0000,16289126.0000,19017983.0000,17363898.0000,18553796.0000,18539649.0000,16539670.0000,19021560.0000,17009137.0000,17405426.0000,18473835.0000,17460079.0000,16183787.0000,16776758.0000,17679664.0000,16141267.0000,18853122.0000,18942861.0000,17117803.0000,16173479.0000,18479174.0000,17641451.0000,18969591.0000,16724921.0000,16252457.0000,18492269.0000,18431785.0000,18877567.0000,17927112.0000,18939976.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation,chain topology,100,1,27574000,283813.4500,283350.6500,284579.1100,2970.9617,2007.1832,4241.3133,"283534.0000,283393.0000,294354.0000,284746.0000,284165.0000,285678.0000,284135.0000,283464.0000,283043.0000,297780.0000,284535.0000,285157.0000,284065.0000,285107.0000,283654.0000,283764.0000,283544.0000,283915.0000,282943.0000,283864.0000,283504.0000,283734.0000,283274.0000,290948.0000,283163.0000,284065.0000,282752.0000,283494.0000,283925.0000,282732.0000,282843.0000,282642.0000,282843.0000,283403.0000,283012.0000,282653.0000,283163.0000,283053.0000,289826.0000,283013.0000,282502.0000,282502.0000,282151.0000,283233.0000,282331.0000,282813.0000,282321.0000,281871.0000,282652.0000,282261.0000,281921.0000,282782.0000,294415.0000,282883.0000,281730.0000,282903.0000,282221.0000,282773.0000,282943.0000,281941.0000,282942.0000,282983.0000,281830.0000,282132.0000,281600.0000,282081.0000,289696.0000,282381.0000,282261.0000,282261.0000,282872.0000,283494.0000,282452.0000,282292.0000,280999.0000,282983.0000,282732.0000,282722.0000,282902.0000,282422.0000,287542.0000,283554.0000,282101.0000,282221.0000,282753.0000,283574.0000,283213.0000,282773.0000,282982.0000,283513.0000,282972.0000,283484.0000,283254.0000,283413.0000,298462.0000,283053.0000,282803.0000,283594.0000,282903.0000,283113.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation,expanding tree topology,100,1,39778000,380102.2800,374963.9500,384970.6900,25475.2635,23884.7917,26958.7632,"399283.0000,427686.0000,387791.0000,348687.0000,348757.0000,348447.0000,359748.0000,348176.0000,347615.0000,348026.0000,348216.0000,347465.0000,347344.0000,347245.0000,347384.0000,347525.0000,346894.0000,356812.0000,347485.0000,346283.0000,345901.0000,346102.0000,347554.0000,346553.0000,345821.0000,346152.0000,345681.0000,345160.0000,346533.0000,357003.0000,346763.0000,346382.0000,345862.0000,345611.0000,346232.0000,345601.0000,346834.0000,345571.0000,346853.0000,347264.0000,357924.0000,401156.0000,398911.0000,397809.0000,398842.0000,398712.0000,398711.0000,397900.0000,398011.0000,397840.0000,405053.0000,398551.0000,398992.0000,399142.0000,397559.0000,398752.0000,398301.0000,397639.0000,397058.0000,397399.0000,398261.0000,405103.0000,398010.0000,398120.0000,398241.0000,398431.0000,398201.0000,397779.0000,398410.0000,399182.0000,398752.0000,409752.0000,399373.0000,398301.0000,397810.0000,398621.0000,398732.0000,397870.0000,398992.0000,398471.0000,398882.0000,406145.0000,398701.0000,399754.0000,398661.0000,399483.0000,399283.0000,399864.0000,398801.0000,399743.0000,400064.0000,414091.0000,399974.0000,398190.0000,399363.0000,398912.0000,399433.0000,398962.0000,399654.0000,399292.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation,contracting tree topology,100,1,48722700,495239.0300,494550.5100,496226.3600,4144.9448,3157.7487,5296.5867,"493911.0000,493471.0000,509792.0000,495685.0000,495374.0000,495324.0000,495525.0000,494582.0000,511264.0000,496195.0000,493690.0000,496306.0000,495103.0000,494052.0000,495725.0000,494452.0000,505423.0000,492969.0000,494352.0000,493621.0000,492488.0000,493991.0000,493280.0000,496316.0000,508408.0000,494593.0000,494052.0000,493851.0000,493611.0000,493861.0000,493841.0000,492509.0000,502427.0000,493842.0000,493100.0000,491647.0000,492990.0000,494332.0000,493611.0000,493981.0000,508809.0000,492900.0000,492819.0000,493891.0000,492218.0000,492779.0000,492639.0000,492509.0000,499552.0000,494883.0000,495073.0000,494803.0000,491637.0000,494152.0000,493531.0000,492759.0000,501395.0000,494051.0000,494242.0000,492178.0000,492899.0000,492629.0000,493581.0000,493591.0000,504832.0000,493992.0000,492288.0000,492238.0000,492459.0000,493791.0000,493591.0000,493060.0000,501696.0000,493691.0000,494453.0000,493440.0000,492859.0000,494102.0000,493741.0000,495875.0000,493030.0000,503820.0000,495044.0000,494923.0000,493401.0000,495103.0000,493961.0000,493892.0000,493791.0000,507317.0000,494442.0000,493180.0000,494242.0000,493541.0000,492038.0000,491828.0000,493721.0000,501475.0000,492468.0000,493511.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation,wave_sim topology,100,1,209633900,2238254.6800,2217233.8800,2262611.6500,115236.8726,89917.1564,157789.7420,"2010316.0000,2023532.0000,2276559.0000,2260659.0000,2260960.0000,2267653.0000,2262553.0000,2254327.0000,2284584.0000,2255189.0000,2268584.0000,2256322.0000,2266160.0000,2269216.0000,2258596.0000,2262413.0000,2255429.0000,2264336.0000,2254878.0000,2269095.0000,2270158.0000,2265038.0000,2274085.0000,2263896.0000,2267823.0000,2255450.0000,2265850.0000,2273314.0000,2260970.0000,2320082.0000,2256982.0000,2271811.0000,2261180.0000,2266230.0000,2253797.0000,2260489.0000,2265219.0000,2261131.0000,2265659.0000,2258887.0000,2784119.0000,2556218.0000,2002862.0000,2026637.0000,2008153.0000,2068997.0000,2016448.0000,2031356.0000,2005928.0000,2122308.0000,2259116.0000,2275067.0000,2259317.0000,2263746.0000,2273824.0000,2259076.0000,2269115.0000,2258355.0000,2659864.0000,2225063.0000,2217478.0000,2240302.0000,2190257.0000,2211016.0000,2257403.0000,2268314.0000,2293631.0000,2396927.0000,2284996.0000,2382680.0000,2317758.0000,2251352.0000,2213079.0000,2250029.0000,2232747.0000,2228458.0000,2269216.0000,2288011.0000,2273614.0000,2278053.0000,2235061.0000,2225743.0000,2199844.0000,2208851.0000,2244359.0000,2227367.0000,2246753.0000,2241172.0000,2272481.0000,2282150.0000,2259066.0000,2235181.0000,2218480.0000,2234380.0000,2179376.0000,2103233.0000,2017280.0000,2027519.0000,2008834.0000,2068036.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation,jacobi topology,100,1,80084400,835094.9700,833928.6100,837145.5400,7675.0134,5030.4130,12606.4092,"835968.0000,834645.0000,857237.0000,833954.0000,830136.0000,831349.0000,838953.0000,830948.0000,834826.0000,831279.0000,833122.0000,840226.0000,829566.0000,833533.0000,830648.0000,830698.0000,845876.0000,829866.0000,831760.0000,832331.0000,831689.0000,839565.0000,833303.0000,833413.0000,834114.0000,831659.0000,846177.0000,830968.0000,830528.0000,831098.0000,836669.0000,833083.0000,832060.0000,833984.0000,830868.0000,836549.0000,834115.0000,831549.0000,834204.0000,831178.0000,843683.0000,834144.0000,832191.0000,830607.0000,832410.0000,838732.0000,832220.0000,831309.0000,831840.0000,833443.0000,845726.0000,833613.0000,832551.0000,832811.0000,867507.0000,832020.0000,833644.0000,832661.0000,833934.0000,837922.0000,831860.0000,831409.0000,830487.0000,832151.0000,844163.0000,833233.0000,832671.0000,833523.0000,834294.0000,838743.0000,830408.0000,833393.0000,830667.0000,831639.0000,844825.0000,834074.0000,833904.0000,830728.0000,838111.0000,831258.0000,831429.0000,831059.0000,830898.0000,843902.0000,831038.0000,830728.0000,831199.0000,831158.0000,837741.0000,832721.0000,831009.0000,831439.0000,833042.0000,838302.0000,831158.0000,832321.0000,832812.0000,884589.0000,852368.0000,832381.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread,soup topology,100,1,3505024300,36913587.0800,35979901.7700,37800784.6700,4635545.4118,4237519.3236,5105661.3160,"33318084.0000,38493362.0000,40018554.0000,43002643.0000,41977315.0000,42922912.0000,38445642.0000,41521674.0000,41582700.0000,42029393.0000,42821450.0000,37948753.0000,41619989.0000,42372302.0000,39911232.0000,42775534.0000,40433138.0000,34595808.0000,40663774.0000,40694070.0000,40304104.0000,40860776.0000,41736530.0000,40537886.0000,41349108.0000,40278224.0000,38133552.0000,40481067.0000,37745289.0000,37960815.0000,40749595.0000,39057628.0000,41982214.0000,40833324.0000,37041969.0000,34028185.0000,39989229.0000,41949654.0000,41988156.0000,41709109.0000,40705992.0000,41155612.0000,36648697.0000,40854954.0000,42652080.0000,41894939.0000,40584012.0000,41854663.0000,40778450.0000,42844614.0000,35044696.0000,41485886.0000,42544026.0000,41352614.0000,40886884.0000,38561912.0000,40680564.0000,40872047.0000,31289771.0000,33330567.0000,30736746.0000,34812847.0000,33146579.0000,34532809.0000,28555714.0000,33024207.0000,35508833.0000,35437108.0000,34194258.0000,34453940.0000,31692993.0000,32585689.0000,36356074.0000,35339983.0000,33298506.0000,30710055.0000,34551784.0000,34032873.0000,36694874.0000,31948706.0000,27903602.0000,27595721.0000,27728412.0000,27478189.0000,27783836.0000,30308156.0000,27940773.0000,31091216.0000,35015230.0000,33422341.0000,32786790.0000,33233894.0000,32745532.0000,31122175.0000,33517199.0000,33796778.0000,29278370.0000,30180815.0000,33566482.0000,31360896.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread,chain topology,100,1,87459400,816777.5400,790106.5700,847398.4600,145587.6314,124598.0146,174418.9846,"637994.0000,639226.0000,745446.0000,773179.0000,797715.0000,749865.0000,726401.0000,774261.0000,700893.0000,775243.0000,724667.0000,677158.0000,749995.0000,707114.0000,693528.0000,1157776.0000,1064139.0000,812593.0000,825097.0000,905018.0000,851376.0000,853901.0000,851697.0000,851527.0000,851106.0000,851678.0000,1015787.0000,743503.0000,798296.0000,798807.0000,773620.0000,823114.0000,774000.0000,773660.0000,797715.0000,799088.0000,774130.0000,774191.0000,822652.0000,797565.0000,798617.0000,843372.0000,855324.0000,822512.0000,749213.0000,750506.0000,788237.0000,798227.0000,798176.0000,798637.0000,798166.0000,825508.0000,798387.0000,797986.0000,798066.0000,798447.0000,808386.0000,831950.0000,870373.0000,851968.0000,871225.0000,1286218.0000,960683.0000,617575.0000,584603.0000,660085.0000,609269.0000,606735.0000,634216.0000,602677.0000,606264.0000,664203.0000,597296.0000,570016.0000,642702.0000,665596.0000,665085.0000,665426.0000,734015.0000,1094466.0000,1270839.0000,1090788.0000,979949.0000,1011148.0000,1037538.0000,985511.0000,993515.0000,1159910.0000,1042798.0000,987244.0000,988085.0000,915007.0000,940826.0000,959251.0000,1027049.0000,808856.0000,725308.0000,784461.0000,755005.0000,679532.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread,expanding tree topology,100,1,109045800,1114400.0700,1076767.2500,1157924.5800,207545.7674,184182.4897,229653.4982,"1330322.0000,1383913.0000,700622.0000,1309082.0000,1410263.0000,1410573.0000,1322908.0000,1532003.0000,1524057.0000,1524168.0000,1474825.0000,1450909.0000,1452252.0000,1499822.0000,1451912.0000,1499662.0000,1499912.0000,1500142.0000,1500654.0000,1450870.0000,1499962.0000,1451751.0000,1451891.0000,1444417.0000,1219402.0000,1219081.0000,1238728.0000,1218931.0000,1232487.0000,983687.0000,958409.0000,984589.0000,932109.0000,957317.0000,1015557.0000,987394.0000,987063.0000,1016478.0000,928843.0000,1015226.0000,987464.0000,986722.0000,900569.0000,928602.0000,1016037.0000,1016709.0000,986773.0000,1015737.0000,986743.0000,986773.0000,987915.0000,986291.0000,987113.0000,1132548.0000,929364.0000,1014925.0000,958980.0000,1015497.0000,987013.0000,987003.0000,980310.0000,1010107.0000,958790.0000,958620.0000,984158.0000,984548.0000,957648.0000,968068.0000,991060.0000,1004025.0000,985480.0000,984358.0000,957718.0000,1100858.0000,1044482.0000,987283.0000,987735.0000,986682.0000,985039.0000,957958.0000,957938.0000,957728.0000,958078.0000,958008.0000,957928.0000,987444.0000,928662.0000,986592.0000,987053.0000,1040764.0000,1010718.0000,1011329.0000,1011359.0000,1011059.0000,1011359.0000,1011409.0000,1010477.0000,1354688.0000,1357994.0000,1383522.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread,contracting tree topology,100,1,117350100,993383.0900,967383.5200,1012832.9100,113582.3011,89156.1114,135595.4861,"1036136.0000,1037739.0000,692156.0000,722262.0000,709760.0000,711612.0000,711271.0000,712293.0000,724086.0000,710701.0000,711062.0000,710110.0000,707465.0000,708758.0000,737802.0000,709950.0000,982545.0000,1037949.0000,1068066.0000,1038571.0000,1037799.0000,1036186.0000,1055662.0000,1033050.0000,1033421.0000,1032469.0000,1045824.0000,1036577.0000,1036036.0000,1036226.0000,1057616.0000,1034072.0000,1036756.0000,1032999.0000,1047437.0000,1035585.0000,1034413.0000,1036056.0000,1052908.0000,1034413.0000,1035645.0000,1054270.0000,1036276.0000,1032209.0000,1035735.0000,1045483.0000,1034683.0000,1039603.0000,1036166.0000,1050684.0000,1035475.0000,1035725.0000,1036046.0000,1048540.0000,1036396.0000,1032710.0000,1041375.0000,1055502.0000,1039231.0000,1034873.0000,1037809.0000,1044612.0000,1035495.0000,1033691.0000,1052196.0000,1040705.0000,1035775.0000,1036887.0000,1045253.0000,1035685.0000,1037979.0000,1033671.0000,1041416.0000,1036496.0000,1034784.0000,1033942.0000,1047658.0000,1036246.0000,1035385.0000,1035334.0000,1046766.0000,1039552.0000,1038671.0000,1037619.0000,1046015.0000,1036858.0000,1034693.0000,1034203.0000,1046786.0000,1041246.0000,1037579.0000,1045313.0000,1038570.0000,1037398.0000,1040705.0000,1048990.0000,1034522.0000,1039803.0000,1033681.0000,1045894.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread,wave_sim topology,100,1,662732000,6086953.7300,5781248.2000,6459758.7400,1723257.2006,1453189.0387,2042961.4407,"5063606.0000,5376497.0000,5029993.0000,5133477.0000,4067194.0000,6337924.0000,7997320.0000,9207535.0000,8986278.0000,4928371.0000,4788536.0000,4740265.0000,5008712.0000,4816378.0000,5228377.0000,5197059.0000,5245709.0000,5083945.0000,5061132.0000,4741417.0000,7585772.0000,6388449.0000,5928811.0000,6039660.0000,6348373.0000,5566696.0000,9206244.0000,6429106.0000,4936645.0000,4880008.0000,4871593.0000,5043739.0000,4798966.0000,4882644.0000,5046864.0000,4693476.0000,5011667.0000,4775652.0000,4841546.0000,4952746.0000,4822620.0000,7998672.0000,10711818.0000,10582635.0000,4781783.0000,4771073.0000,4764230.0000,4852778.0000,5516071.0000,5130012.0000,6299401.0000,7005225.0000,5186288.0000,4971492.0000,4784830.0000,4917920.0000,4859691.0000,4746066.0000,5978564.0000,4783757.0000,6752647.0000,9505910.0000,8205402.0000,7502123.0000,5183402.0000,4938449.0000,5137806.0000,4944681.0000,5243836.0000,5020765.0000,5077292.0000,4678038.0000,5772766.0000,8176067.0000,6927979.0000,6052164.0000,5174385.0000,4823332.0000,4850774.0000,4922169.0000,5880199.0000,7191737.0000,6242103.0000,4982593.0000,5674410.0000,7299380.0000,10400129.0000,11151660.0000,11306802.0000,9395241.0000,8898321.0000,7368882.0000,7905356.0000,8742617.0000,9065709.0000,6095105.0000,4875321.0000,4877634.0000,4862686.0000,5856193.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread,jacobi topology,100,1,202355400,2274749.2400,2196697.4800,2367838.0200,433541.9899,363248.8687,550665.6998,"2003524.0000,1902733.0000,2671866.0000,2399381.0000,2633624.0000,2593709.0000,2607566.0000,2337855.0000,1983506.0000,2163406.0000,2372210.0000,2851466.0000,2767267.0000,2367271.0000,2836628.0000,4044621.0000,3027428.0000,2045022.0000,2044932.0000,1978717.0000,1978086.0000,1921358.0000,2074468.0000,2356891.0000,2348095.0000,2422635.0000,2516012.0000,2516273.0000,2491245.0000,2629146.0000,3299603.0000,3251803.0000,2446812.0000,2265649.0000,2275106.0000,2298160.0000,2321625.0000,2447893.0000,2498299.0000,2519158.0000,1885701.0000,1889569.0000,2131586.0000,2062886.0000,2221255.0000,2270067.0000,2515511.0000,2422686.0000,2521753.0000,2325432.0000,2299192.0000,2491616.0000,2340280.0000,2379935.0000,2264767.0000,2273815.0000,2492547.0000,2197299.0000,1728724.0000,1704359.0000,1702766.0000,1756778.0000,1757058.0000,1736519.0000,1720739.0000,1719518.0000,1780011.0000,2188383.0000,2160069.0000,2264666.0000,2407967.0000,3180948.0000,3625789.0000,2129432.0000,2344548.0000,2794589.0000,3138899.0000,3019793.0000,2286448.0000,2416003.0000,2300304.0000,1931948.0000,1843351.0000,1992503.0000,2012751.0000,1645157.0000,1693698.0000,1877545.0000,1910678.0000,1984298.0000,1888406.0000,2006549.0000,1863659.0000,1896883.0000,1862147.0000,1916038.0000,1836257.0000,1916940.0000,2031266.0000,2003594.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task,soup topology,100,1,2119195500,21162705.4500,21027063.5000,21227552.0000,455990.4991,240668.9112,746766.0886,"21190458.0000,21179768.0000,21242366.0000,21244460.0000,21229161.0000,21223912.0000,21462342.0000,21276881.0000,21186110.0000,21195507.0000,21231596.0000,21227698.0000,21262564.0000,21222959.0000,21221767.0000,21309352.0000,21237657.0000,21343066.0000,21264799.0000,21261523.0000,21354789.0000,21264047.0000,21217288.0000,21215145.0000,21237938.0000,21216067.0000,21274577.0000,21242105.0000,21204715.0000,21265790.0000,21228029.0000,21296809.0000,21229793.0000,21277432.0000,21220665.0000,21212079.0000,21309754.0000,21272382.0000,21259779.0000,21261843.0000,21312098.0000,21230714.0000,21267062.0000,21272252.0000,21215495.0000,19920589.0000,21195226.0000,21262023.0000,21211537.0000,21226617.0000,21825227.0000,21217709.0000,21224432.0000,21229561.0000,21433928.0000,21265289.0000,21235172.0000,21233289.0000,21244641.0000,21304323.0000,21262304.0000,21250882.0000,21240172.0000,21252825.0000,21241273.0000,21210686.0000,21217680.0000,21256913.0000,21259699.0000,21245773.0000,21233910.0000,21311586.0000,21217339.0000,21235333.0000,21262253.0000,21258416.0000,21276089.0000,21217619.0000,21192993.0000,21219132.0000,21198122.0000,21258336.0000,21234441.0000,21211959.0000,21306497.0000,21229452.0000,20961826.0000,18569155.0000,21231816.0000,21245442.0000,21242166.0000,21198343.0000,21240222.0000,21222758.0000,19432846.0000,18305446.0000,21095338.0000,21259229.0000,21232658.0000,21329460.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task,chain topology,100,1,58182400,589640.8100,585383.9300,596817.9900,27401.2100,17239.4983,37889.5626,"580856.0000,581106.0000,589983.0000,582038.0000,582428.0000,582469.0000,580876.0000,593509.0000,583170.0000,583701.0000,581557.0000,582538.0000,583891.0000,582168.0000,588250.0000,581487.0000,582138.0000,581306.0000,581838.0000,580565.0000,582038.0000,596034.0000,581798.0000,581316.0000,581477.0000,581517.0000,581397.0000,580505.0000,588069.0000,582048.0000,582088.0000,581717.0000,581888.0000,582689.0000,586115.0000,582599.0000,581828.0000,580635.0000,588159.0000,693819.0000,693508.0000,703317.0000,695081.0000,708607.0000,687928.0000,588901.0000,581337.0000,583831.0000,582689.0000,580225.0000,581086.0000,581256.0000,580816.0000,580485.0000,589201.0000,581928.0000,581657.0000,581327.0000,580044.0000,580846.0000,581677.0000,593379.0000,581608.0000,580855.0000,579704.0000,580435.0000,580114.0000,580124.0000,586997.0000,581025.0000,581066.0000,581547.0000,581056.0000,579553.0000,580856.0000,588981.0000,581547.0000,581727.0000,580255.0000,580114.0000,580505.0000,594351.0000,581397.0000,581928.0000,581917.0000,581817.0000,581216.0000,579934.0000,587448.0000,580144.0000,580645.0000,580295.0000,582418.0000,582078.0000,581527.0000,593079.0000,581637.0000,580876.0000,580134.0000,580435.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task,expanding tree topology,100,1,71064600,711322.3600,710574.7100,712887.6700,5283.6440,3122.3238,10111.9029,"708987.0000,710040.0000,751668.0000,712143.0000,711192.0000,710842.0000,711623.0000,709679.0000,710811.0000,710380.0000,709528.0000,710761.0000,716592.0000,709809.0000,710110.0000,709669.0000,709279.0000,709007.0000,722112.0000,707946.0000,709158.0000,708487.0000,709068.0000,716322.0000,709088.0000,708617.0000,709578.0000,709168.0000,709379.0000,710530.0000,709558.0000,709588.0000,709268.0000,708907.0000,713706.0000,708967.0000,709209.0000,708516.0000,709398.0000,710040.0000,716352.0000,709889.0000,708146.0000,709138.0000,708857.0000,709960.0000,721752.0000,709559.0000,709509.0000,709619.0000,711562.0000,717685.0000,710049.0000,709608.0000,708667.0000,709118.0000,710300.0000,722183.0000,709528.0000,709739.0000,709208.0000,710400.0000,710200.0000,710741.0000,710781.0000,709549.0000,708738.0000,709258.0000,709759.0000,709219.0000,710200.0000,710230.0000,709028.0000,709669.0000,721111.0000,709078.0000,709028.0000,709919.0000,710040.0000,716723.0000,710400.0000,709258.0000,710460.0000,709519.0000,710000.0000,721832.0000,710611.0000,710130.0000,710100.0000,709969.0000,709339.0000,718025.0000,709248.0000,710721.0000,709228.0000,708847.0000,722974.0000,710540.0000,709429.0000,708777.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task,contracting tree topology,100,1,80689900,779665.3300,773299.2300,785746.6100,31784.8086,30062.3041,32858.4880,"804398.0000,805700.0000,813795.0000,807684.0000,814186.0000,808005.0000,806162.0000,805249.0000,805189.0000,816471.0000,758331.0000,740367.0000,740577.0000,739466.0000,744003.0000,741569.0000,740938.0000,739786.0000,739796.0000,738403.0000,774251.0000,740437.0000,740327.0000,739345.0000,739235.0000,743924.0000,740076.0000,740196.0000,740207.0000,739696.0000,746328.0000,740989.0000,741749.0000,741169.0000,740768.0000,740517.0000,784350.0000,739655.0000,740538.0000,740778.0000,738824.0000,747741.0000,740697.0000,740157.0000,739656.0000,738072.0000,739435.0000,745066.0000,739215.0000,741259.0000,740007.0000,740878.0000,793397.0000,808346.0000,805800.0000,805801.0000,806963.0000,813225.0000,806231.0000,806201.0000,806342.0000,804979.0000,811572.0000,805039.0000,807053.0000,804488.0000,806371.0000,809288.0000,804949.0000,803266.0000,804498.0000,803757.0000,804639.0000,804177.0000,805009.0000,803486.0000,804037.0000,805710.0000,805150.0000,803917.0000,803937.0000,805280.0000,814036.0000,806021.0000,802765.0000,805620.0000,805039.0000,810409.0000,804729.0000,804368.0000,803927.0000,803667.0000,814727.0000,806011.0000,802975.0000,804148.0000,803977.0000,807524.0000,804208.0000,803857.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task,wave_sim topology,100,1,431792000,4317302.6900,4303003.6800,4325843.1200,55169.5429,36693.1595,75815.2144,"4322355.0000,4331102.0000,4356249.0000,4332014.0000,4328817.0000,4333847.0000,4329950.0000,4328697.0000,4331182.0000,4330330.0000,4336082.0000,4340750.0000,4330371.0000,4326012.0000,4340158.0000,4332033.0000,4334668.0000,4322917.0000,4334999.0000,4324700.0000,4337193.0000,4321604.0000,4324129.0000,4328086.0000,4331422.0000,4324359.0000,4350498.0000,4239208.0000,4093122.0000,4080819.0000,4112469.0000,4117869.0000,4088714.0000,4152534.0000,4325221.0000,4323939.0000,4331031.0000,4318989.0000,4326684.0000,4324880.0000,4318318.0000,4323397.0000,4324449.0000,4329999.0000,4326233.0000,4323117.0000,4337574.0000,4320371.0000,4337233.0000,4329628.0000,4322165.0000,4333566.0000,4326343.0000,4319861.0000,4330550.0000,4327164.0000,4332845.0000,4325411.0000,4326834.0000,4329428.0000,4326963.0000,4321644.0000,4331223.0000,4324199.0000,4321083.0000,4326142.0000,4325712.0000,4332695.0000,4371859.0000,4339959.0000,4325090.0000,4327595.0000,4334518.0000,4332174.0000,4337484.0000,4329168.0000,4329429.0000,4327845.0000,4343795.0000,4342623.0000,4326403.0000,4333446.0000,4337504.0000,4322856.0000,4321494.0000,4331042.0000,4331082.0000,4334598.0000,4337404.0000,4339668.0000,4335260.0000,4387699.0000,4326263.0000,4339367.0000,4330961.0000,4322917.0000,4336242.0000,4330921.0000,4382940.0000,4326513.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task,jacobi topology,100,1,134745700,1353882.8700,1346894.2900,1369682.8100,50593.2702,20629.4500,87875.1242,"1343918.0000,1343467.0000,1334199.0000,1259248.0000,1300936.0000,1347605.0000,1345881.0000,1349789.0000,1344088.0000,1346272.0000,1351191.0000,1343907.0000,1344258.0000,1360078.0000,1346772.0000,1343938.0000,1351722.0000,1342815.0000,1344559.0000,1349248.0000,1343116.0000,1344088.0000,1358064.0000,1342815.0000,1657099.0000,1699509.0000,1515763.0000,1352273.0000,1343747.0000,1346833.0000,1348637.0000,1345670.0000,1346833.0000,1352764.0000,1344288.0000,1344639.0000,1351172.0000,1346081.0000,1342786.0000,1354277.0000,1343757.0000,1343306.0000,1351081.0000,1344228.0000,1342955.0000,1358985.0000,1343616.0000,1344939.0000,1352995.0000,1345881.0000,1343115.0000,1352003.0000,1344038.0000,1343406.0000,1355199.0000,1345962.0000,1343256.0000,1351091.0000,1343517.0000,1345170.0000,1351842.0000,1344528.0000,1344008.0000,1350550.0000,1344218.0000,1346483.0000,1346081.0000,1345050.0000,1341763.0000,1350840.0000,1343567.0000,1343617.0000,1354678.0000,1341373.0000,1343687.0000,1350189.0000,1344750.0000,1345670.0000,1356822.0000,1346042.0000,1345551.0000,1352313.0000,1345420.0000,1346011.0000,1359938.0000,1346462.0000,1345109.0000,1351943.0000,1341773.0000,1344258.0000,1349287.0000,1343748.0000,1344017.0000,1353536.0000,1343547.0000,1344829.0000,1349458.0000,1344329.0000,1342525.0000,1345630.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task,soup topology,100,1,2706887200,36455856.5600,34847254.1100,37851235.5700,7625407.3711,6643379.8876,8633333.9719,"34710284.0000,40122810.0000,21367592.0000,19644617.0000,19926680.0000,24454886.0000,39361913.0000,35534351.0000,40145554.0000,39600434.0000,37371121.0000,36548366.0000,40716253.0000,24870462.0000,17750267.0000,19839996.0000,25491605.0000,34474539.0000,39527386.0000,44643373.0000,43566248.0000,44524287.0000,43368734.0000,43254648.0000,35977749.0000,30542820.0000,41129142.0000,43043430.0000,41284056.0000,43820708.0000,42967726.0000,29533953.0000,18421306.0000,38865496.0000,36714531.0000,39278175.0000,39371662.0000,40156274.0000,42730458.0000,37005901.0000,39859243.0000,43692847.0000,41512086.0000,40385016.0000,44789449.0000,43141675.0000,41429159.0000,37086645.0000,26960430.0000,37996152.0000,35633227.0000,36790855.0000,36415216.0000,39585255.0000,39222810.0000,35483084.0000,40325634.0000,37114507.0000,44969539.0000,44877495.0000,43971733.0000,44759131.0000,28287758.0000,31862473.0000,38026671.0000,34174020.0000,22827440.0000,36782370.0000,25420591.0000,23204994.0000,32853094.0000,33639782.0000,39875333.0000,44869380.0000,38067737.0000,42020085.0000,42595484.0000,44341823.0000,44851105.0000,44392188.0000,43117219.0000,36597350.0000,22346853.0000,36525324.0000,24292740.0000,21897184.0000,25230442.0000,21235113.0000,39675095.0000,42069249.0000,40273456.0000,44113792.0000,42735337.0000,45059899.0000,41510483.0000,41980791.0000,38496638.0000,27479111.0000,32263231.0000,42933040.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task,chain topology,100,1,163798800,1640216.5900,1561962.5400,1728859.4700,425177.3541,371345.7963,509064.2089,"1711723.0000,1914987.0000,2025255.0000,1871895.0000,1975350.0000,2252614.0000,2222938.0000,2403419.0000,2478361.0000,2392730.0000,1756026.0000,1567139.0000,1859632.0000,1941787.0000,1655256.0000,1481036.0000,1397719.0000,2118070.0000,1697846.0000,2137767.0000,1510702.0000,1435370.0000,1327767.0000,1389804.0000,1358866.0000,1377791.0000,1459135.0000,1551560.0000,1497718.0000,1331464.0000,1354377.0000,1332746.0000,1268204.0000,1355028.0000,1238529.0000,1358244.0000,1396035.0000,1409310.0000,1702625.0000,2641399.0000,2613406.0000,2614618.0000,2242415.0000,2089757.0000,1802995.0000,2059369.0000,1716021.0000,1399192.0000,1417736.0000,1183624.0000,1059229.0000,1040203.0000,1043931.0000,1065902.0000,1021459.0000,1317557.0000,1369155.0000,1415122.0000,1616783.0000,1544176.0000,1504361.0000,1554015.0000,1540629.0000,2017891.0000,2254728.0000,2343045.0000,2178664.0000,2305224.0000,3113591.0000,1162805.0000,1045754.0000,1172814.0000,1152566.0000,1079237.0000,1380968.0000,1786213.0000,1746257.0000,1768971.0000,1808836.0000,1548454.0000,1520450.0000,1382991.0000,1219772.0000,1260891.0000,1353455.0000,1300125.0000,1226435.0000,1195006.0000,1461019.0000,1331223.0000,1536953.0000,1701473.0000,1653282.0000,1490314.0000,1364056.0000,1194716.0000,1854482.0000,1886492.0000,1943911.0000,1888716.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task,expanding tree topology,100,1,168253000,1965087.4000,1879893.6300,2060607.2500,458521.0302,412409.5759,546255.1597,"1454677.0000,1336423.0000,2623956.0000,1538375.0000,1599981.0000,1435951.0000,1545779.0000,1563162.0000,1462211.0000,1870051.0000,2218450.0000,2150311.0000,1768680.0000,1655927.0000,1767848.0000,1657209.0000,1654384.0000,1683088.0000,1565776.0000,1654063.0000,1658262.0000,1703898.0000,2235542.0000,1833452.0000,2319040.0000,2020817.0000,2313480.0000,2501535.0000,2034011.0000,2435289.0000,2756376.0000,2668089.0000,2387068.0000,2266099.0000,2027809.0000,1974910.0000,1774221.0000,1944964.0000,2583841.0000,2580925.0000,2656408.0000,2378031.0000,2374164.0000,2327586.0000,2315493.0000,2350750.0000,2474013.0000,2562450.0000,2520380.0000,2718515.0000,2700480.0000,2523306.0000,2553172.0000,2582097.0000,2733052.0000,2702485.0000,2700110.0000,2784590.0000,1862087.0000,1747349.0000,1739184.0000,1706272.0000,1574774.0000,1820548.0000,1858920.0000,2081992.0000,1916129.0000,2005207.0000,1677758.0000,1650977.0000,1574353.0000,1718355.0000,2384123.0000,1993816.0000,3555567.0000,1972895.0000,1400253.0000,1494141.0000,1508378.0000,1719627.0000,1708356.0000,1717824.0000,1729817.0000,1698968.0000,1707054.0000,1702285.0000,1599942.0000,1592357.0000,1426133.0000,1714518.0000,1699619.0000,1967025.0000,1425261.0000,1300725.0000,1474825.0000,1305715.0000,1372171.0000,1540268.0000,1300535.0000,1379625.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task,contracting tree topology,100,1,190977900,2038953.3700,1966820.9200,2110396.3500,365667.1313,325487.5723,411915.9144,"2092151.0000,1976282.0000,1904346.0000,2003634.0000,1992273.0000,2200256.0000,1994988.0000,1731289.0000,2104023.0000,2496806.0000,2395314.0000,2133389.0000,2091029.0000,2125844.0000,1971714.0000,2005087.0000,1966624.0000,1755254.0000,1974569.0000,1891151.0000,1666798.0000,1621733.0000,1700171.0000,2071182.0000,2105948.0000,2154178.0000,2336643.0000,2603717.0000,2581446.0000,2585694.0000,2582418.0000,2744744.0000,2703596.0000,2491145.0000,1943691.0000,1753511.0000,1708266.0000,1303009.0000,1354878.0000,1411034.0000,1399623.0000,1353496.0000,1349318.0000,1336965.0000,1346182.0000,1455418.0000,1484042.0000,1430170.0000,1551049.0000,1524268.0000,1526753.0000,1572610.0000,1741900.0000,2213300.0000,2570825.0000,2117078.0000,2521232.0000,2346141.0000,2366991.0000,2383502.0000,2285867.0000,2097562.0000,2272352.0000,2442784.0000,2680142.0000,2593749.0000,2342664.0000,2441431.0000,2697585.0000,2125754.0000,2254268.0000,2152295.0000,2574923.0000,2633975.0000,2612143.0000,2075580.0000,2042187.0000,2234590.0000,2148868.0000,2008042.0000,2063617.0000,2061514.0000,2058517.0000,1912331.0000,1954812.0000,2007802.0000,2026026.0000,1917622.0000,1998174.0000,1932740.0000,1960964.0000,1809958.0000,1970371.0000,1943200.0000,2017861.0000,1866365.0000,2021096.0000,1912912.0000,1949391.0000,1972615.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task,wave_sim topology,100,1,1248846100,11350992.5500,10928941.0700,11837249.6300,2318000.4244,1967247.1833,2721297.9920,"9427853.0000,12262238.0000,10815955.0000,10160156.0000,11539692.0000,11909381.0000,12309116.0000,11340797.0000,13099070.0000,10922165.0000,11624333.0000,10772482.0000,11580720.0000,10580169.0000,13577854.0000,15272255.0000,13280241.0000,11444192.0000,11990404.0000,11810624.0000,12927936.0000,12711296.0000,16974631.0000,17272185.0000,16208894.0000,17775345.0000,17451172.0000,15819941.0000,14600406.0000,10327633.0000,10850881.0000,9455284.0000,9633882.0000,9646194.0000,11693233.0000,10445975.0000,10059656.0000,11203397.0000,11272458.0000,15668123.0000,12083701.0000,10371495.0000,10601670.0000,11017837.0000,14354792.0000,11981788.0000,9298768.0000,8936614.0000,14289949.0000,11397855.0000,8807620.0000,9757255.0000,12903529.0000,8988452.0000,10568849.0000,11997717.0000,10054266.0000,9226681.0000,12918889.0000,13190792.0000,10404037.0000,8832867.0000,7561856.0000,6875429.0000,8067181.0000,7981749.0000,9839620.0000,9954307.0000,10085305.0000,10856703.0000,10388127.0000,10214569.0000,10690918.0000,14070645.0000,12132722.0000,8697322.0000,9350757.0000,11268740.0000,9811578.0000,11833367.0000,11309157.0000,11000313.0000,8768637.0000,10849197.0000,10949378.0000,9648549.0000,9397104.0000,9388989.0000,9258492.0000,9770420.0000,8807971.0000,10537688.0000,10981668.0000,8373489.0000,9631778.0000,16949354.0000,11884675.0000,11379700.0000,17075413.0000,9752746.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task,jacobi topology,100,1,352163700,3386860.1900,3274614.3500,3506706.7100,591689.4320,526442.0868,675670.1997,"5025333.0000,4452291.0000,2715850.0000,3510310.0000,3831077.0000,3782826.0000,3002622.0000,3204342.0000,3043649.0000,3323959.0000,3073345.0000,3498308.0000,4095266.0000,3920877.0000,3320753.0000,2770162.0000,2703036.0000,2661247.0000,2725768.0000,2833181.0000,2867266.0000,2882104.0000,2661928.0000,3151944.0000,3348605.0000,3005557.0000,3195205.0000,3466518.0000,2693898.0000,2607254.0000,2867897.0000,2848631.0000,3107440.0000,3421784.0000,3104744.0000,3268313.0000,3380886.0000,3013883.0000,2362993.0000,2695381.0000,3599750.0000,4490673.0000,2798526.0000,2595582.0000,2750155.0000,3095016.0000,3701332.0000,3566157.0000,3305213.0000,3280275.0000,3218219.0000,3091961.0000,2971222.0000,2526802.0000,3550727.0000,4142886.0000,3927960.0000,4047375.0000,3995177.0000,4298991.0000,4184835.0000,4175818.0000,3815027.0000,4587886.0000,4211146.0000,4268714.0000,3834474.0000,3243808.0000,4422535.0000,4606983.0000,4617243.0000,4409560.0000,4120314.0000,3835416.0000,3193462.0000,3062214.0000,3629797.0000,3627783.0000,2944723.0000,2955843.0000,2861445.0000,3065441.0000,3145612.0000,3221374.0000,3270428.0000,3750204.0000,3726430.0000,3854071.0000,3701132.0000,3351530.0000,3177522.0000,2885611.0000,2208921.0000,3416343.0000,2739154.0000,2265118.0000,3447572.0000,3293480.0000,3205454.0000,3951164.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation,soup topology,100,1,4397953200,43536383.1200,43132441.4500,43922530.5700,2002852.8828,1609362.5359,2558494.3628,"44634155.0000,43955874.0000,44174297.0000,44009775.0000,39657993.0000,42814026.0000,43960503.0000,43933592.0000,42974780.0000,39164710.0000,43984779.0000,44058918.0000,43914816.0000,43991030.0000,43941637.0000,47823752.0000,43559806.0000,43937038.0000,43980871.0000,38889611.0000,43891032.0000,43935114.0000,43973246.0000,43871815.0000,43957507.0000,44059610.0000,43917962.0000,43639065.0000,39044043.0000,40226658.0000,41409963.0000,44219201.0000,44254819.0000,45312117.0000,43971323.0000,44167864.0000,44286108.0000,45599048.0000,45133359.0000,44206517.0000,44113192.0000,44011619.0000,44029453.0000,43932970.0000,43912502.0000,43994648.0000,43954250.0000,44088904.0000,45508838.0000,43925616.0000,51251469.0000,38703440.0000,44165810.0000,43435800.0000,38834706.0000,44226184.0000,44063046.0000,44066131.0000,44220924.0000,43983496.0000,38191833.0000,44672668.0000,44264567.0000,44011419.0000,41423729.0000,41677750.0000,44008623.0000,44029323.0000,44010406.0000,43972505.0000,43979679.0000,43995879.0000,44031797.0000,44125434.0000,43955102.0000,44199856.0000,44068105.0000,44358384.0000,43250922.0000,39132079.0000,44111187.0000,44188523.0000,44090738.0000,43943871.0000,43446811.0000,50092950.0000,39445040.0000,44064328.0000,42542913.0000,43974598.0000,44109023.0000,44009775.0000,39773160.0000,42505103.0000,44119733.0000,43961755.0000,43709197.0000,39143972.0000,43956916.0000,44227327.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation,chain topology,100,1,342363000,3452317.0800,3395794.1600,3544350.5000,360511.7114,239166.2787,506248.8750,"3412465.0000,3425301.0000,3449266.0000,3437273.0000,3429639.0000,3506383.0000,3430249.0000,3417726.0000,3426762.0000,3429008.0000,3428606.0000,3418908.0000,3411564.0000,3410031.0000,3403490.0000,3446159.0000,3408158.0000,3422505.0000,4523165.0000,5000146.0000,5013291.0000,5038087.0000,4952737.0000,3153417.0000,2987072.0000,2971893.0000,3095917.0000,2993454.0000,2988054.0000,2979658.0000,3040994.0000,2993564.0000,3006840.0000,2981833.0000,3390855.0000,3424519.0000,3425982.0000,3422013.0000,3419780.0000,3423687.0000,3403519.0000,3419639.0000,3630287.0000,3424579.0000,3413658.0000,3411865.0000,3415942.0000,3398971.0000,3410252.0000,3425471.0000,3414309.0000,3409570.0000,3418868.0000,3418408.0000,3408939.0000,3422755.0000,3416995.0000,3419850.0000,3420842.0000,3413378.0000,3413568.0000,3410242.0000,3417706.0000,3412195.0000,3418627.0000,3412877.0000,3424348.0000,3415863.0000,3413328.0000,3415151.0000,3419450.0000,3415582.0000,3418617.0000,3415662.0000,3405803.0000,3418097.0000,3417416.0000,3412867.0000,3418828.0000,3508828.0000,3405543.0000,3407236.0000,3420882.0000,3414500.0000,3425541.0000,3418647.0000,3421984.0000,3421233.0000,3408108.0000,3410453.0000,3421122.0000,3420131.0000,3418257.0000,3431832.0000,3422044.0000,3409090.0000,3422936.0000,3418437.0000,3418417.0000,3431712.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation,expanding tree topology,100,1,639154500,6639552.7000,6556934.1200,6767814.1900,517593.6505,342045.7157,796655.6677,"6651757.0000,6649102.0000,5881502.0000,6271508.0000,6668317.0000,6667026.0000,6661656.0000,6658930.0000,6654662.0000,6662567.0000,6656947.0000,6670622.0000,6860141.0000,6658540.0000,6656296.0000,6636988.0000,6687133.0000,6654682.0000,6651286.0000,6649082.0000,6634224.0000,6649853.0000,6673638.0000,6650845.0000,6645936.0000,6665853.0000,6666715.0000,6651186.0000,6649523.0000,6668508.0000,6648341.0000,6662547.0000,6653890.0000,6654150.0000,6651947.0000,6646287.0000,7349334.0000,7159205.0000,6661094.0000,6646998.0000,6634704.0000,6663048.0000,6672156.0000,6637219.0000,6660423.0000,6673759.0000,6652128.0000,6669920.0000,6667897.0000,6665102.0000,5903102.0000,5772705.0000,5810568.0000,6023800.0000,6798143.0000,6318547.0000,6688837.0000,6660253.0000,6671152.0000,6659201.0000,6661135.0000,6688025.0000,6680992.0000,6683317.0000,7269494.0000,6671243.0000,6663729.0000,6673969.0000,6657899.0000,6669901.0000,6664511.0000,6658900.0000,6660272.0000,6634113.0000,6646968.0000,9192087.0000,9608383.0000,8087800.0000,5817190.0000,5977142.0000,5793124.0000,5901600.0000,5779188.0000,5854320.0000,5786852.0000,5972763.0000,6660553.0000,6665693.0000,6649772.0000,6661485.0000,6666715.0000,6647918.0000,6651767.0000,6652087.0000,6668789.0000,6647288.0000,6645625.0000,6665022.0000,6647418.0000,6668739.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation,contracting tree topology,100,1,355877300,3758447.0100,3722858.3200,3782475.6200,147103.6921,107902.1613,186524.7865,"3818373.0000,3804807.0000,3821810.0000,3813875.0000,3812963.0000,3806921.0000,3806671.0000,3806671.0000,3815258.0000,3838301.0000,3813874.0000,3795670.0000,3811350.0000,3798446.0000,3795730.0000,3804307.0000,3811310.0000,3804897.0000,3837620.0000,3816469.0000,3791482.0000,3799417.0000,3806190.0000,3801040.0000,3799016.0000,3811981.0000,3814115.0000,3804477.0000,3800589.0000,3807813.0000,3811940.0000,3808545.0000,3818403.0000,3800570.0000,3801682.0000,3782816.0000,3801881.0000,3806301.0000,3812351.0000,3804487.0000,3810568.0000,3798215.0000,3796691.0000,3805339.0000,3802643.0000,3798616.0000,3812562.0000,3795239.0000,3802323.0000,3809115.0000,3808034.0000,3811851.0000,3802493.0000,3800299.0000,3794999.0000,3794337.0000,3804045.0000,3810468.0000,3803215.0000,3811059.0000,3787665.0000,3807903.0000,3808033.0000,3803284.0000,3812803.0000,3807252.0000,3800760.0000,3810559.0000,3792083.0000,3800098.0000,3809516.0000,3800129.0000,3801431.0000,3803686.0000,3807102.0000,3794677.0000,3796311.0000,3391286.0000,3287921.0000,3286228.0000,3302739.0000,3298451.0000,3298420.0000,3311866.0000,3297810.0000,3306265.0000,3422626.0000,3808194.0000,3821128.0000,3808634.0000,3827981.0000,3807102.0000,3795851.0000,3802924.0000,3813053.0000,3873086.0000,3811671.0000,3820357.0000,3807012.0000,3808274.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation,wave_sim topology,100,1,1554790000,15552143.2900,15431804.8300,15711233.1000,698281.6858,470807.3152,1134587.3075,"15628389.0000,15608570.0000,15636333.0000,15657694.0000,15611005.0000,15589093.0000,15603351.0000,15585157.0000,15596517.0000,15585608.0000,13794773.0000,13719021.0000,14966778.0000,15635181.0000,15617589.0000,15606116.0000,15616416.0000,15648647.0000,15618780.0000,15644719.0000,15613431.0000,15603441.0000,15650900.0000,15601758.0000,15631995.0000,15616366.0000,15628028.0000,15644208.0000,15618980.0000,15596168.0000,15627055.0000,15622457.0000,15615504.0000,15618880.0000,15608852.0000,15605675.0000,15793429.0000,15616816.0000,15692970.0000,15626585.0000,15627257.0000,15631584.0000,15678122.0000,15685026.0000,15676549.0000,15653165.0000,15704343.0000,15667081.0000,15638167.0000,15660038.0000,15625232.0000,15617377.0000,15678243.0000,15642123.0000,15629009.0000,15634109.0000,15608180.0000,15639349.0000,15597070.0000,15588112.0000,15617909.0000,19936338.0000,18181993.0000,13975555.0000,15594836.0000,15589574.0000,15558456.0000,15571501.0000,15583914.0000,15561112.0000,15581029.0000,15594243.0000,15588393.0000,15557825.0000,13850008.0000,13759127.0000,15106752.0000,15701817.0000,15663515.0000,15664125.0000,15639329.0000,15668234.0000,15648546.0000,15667803.0000,15642785.0000,15657553.0000,15628108.0000,15735501.0000,15642224.0000,14836633.0000,13711105.0000,13976267.0000,15624892.0000,15635702.0000,15656652.0000,15619571.0000,15599964.0000,15622688.0000,15643216.0000,15636163.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation,jacobi topology,100,1,516668200,5407416.5800,5341498.2500,5517962.1700,427318.8774,273043.1982,655407.1199,"5368522.0000,5382338.0000,5407706.0000,5376117.0000,6967212.0000,7923620.0000,7303689.0000,4743571.0000,4732069.0000,4844883.0000,4740876.0000,4767026.0000,4967134.0000,5377208.0000,5382980.0000,5365847.0000,5380455.0000,5377359.0000,5363031.0000,5016146.0000,4736839.0000,4845734.0000,5374924.0000,6861883.0000,5378010.0000,5384051.0000,5400282.0000,5380073.0000,5113259.0000,4799687.0000,5402587.0000,5385964.0000,5392036.0000,5381146.0000,5387428.0000,5379933.0000,5382538.0000,5378090.0000,5390294.0000,5380264.0000,5379291.0000,5379903.0000,5373883.0000,5373822.0000,5392017.0000,5397226.0000,5378251.0000,5397096.0000,5381647.0000,5387096.0000,5391125.0000,5381788.0000,5409980.0000,5385834.0000,5370806.0000,5396765.0000,5383170.0000,5384482.0000,5373501.0000,5392808.0000,5381758.0000,5401524.0000,5387137.0000,5391355.0000,5452651.0000,5415250.0000,5419479.0000,5465204.0000,5466448.0000,5534566.0000,5547591.0000,5591683.0000,5498517.0000,5381577.0000,5374374.0000,5386075.0000,5383991.0000,5376488.0000,5389071.0000,5369274.0000,5382728.0000,5424588.0000,5367300.0000,5371468.0000,5379032.0000,5363181.0000,5385885.0000,5369885.0000,5372440.0000,5384882.0000,5372730.0000,5360407.0000,5380465.0000,5363602.0000,5360797.0000,5380585.0000,5373001.0000,5368242.0000,5365335.0000,5367790.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread,soup topology,100,1,7746524200,76309344.9500,75062805.2100,77347137.6400,5795827.2827,4925432.5139,6750392.9270,"79228161.0000,74223675.0000,75463799.0000,75255684.0000,78624882.0000,78810613.0000,82317148.0000,74676231.0000,79061397.0000,73738549.0000,63658241.0000,60707095.0000,62713917.0000,64469996.0000,74507883.0000,80815731.0000,79749406.0000,84264527.0000,80036418.0000,81138140.0000,78499775.0000,76027825.0000,80516585.0000,79982267.0000,79945046.0000,74607530.0000,78297552.0000,73874355.0000,69984986.0000,73808251.0000,76046058.0000,61941898.0000,79228402.0000,78320707.0000,81039453.0000,80975133.0000,81297601.0000,75924940.0000,72476294.0000,80826792.0000,77064803.0000,78584024.0000,74906496.0000,80552154.0000,73916866.0000,70198660.0000,74488576.0000,81136066.0000,80246486.0000,78970344.0000,81627335.0000,81643155.0000,79662461.0000,80449359.0000,81410595.0000,79836581.0000,80106973.0000,79941228.0000,75463698.0000,60487451.0000,65354907.0000,64191589.0000,63471069.0000,64469795.0000,79074260.0000,73082850.0000,79010050.0000,80108105.0000,79719830.0000,78994249.0000,77824770.0000,77088879.0000,83124884.0000,80384165.0000,78957209.0000,69845844.0000,73144446.0000,79934957.0000,68772124.0000,76708861.0000,73600858.0000,76119056.0000,74162380.0000,73695056.0000,82277955.0000,80276221.0000,78904540.0000,82802875.0000,73525325.0000,64579393.0000,64524348.0000,75991776.0000,76699783.0000,82333519.0000,83870061.0000,82896233.0000,82147197.0000,82369487.0000,81292522.0000,77826813.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread,chain topology,100,1,589548000,5695196.2100,5571544.5000,5852940.7300,710153.9898,587978.4143,940140.8601,"5511523.0000,5172221.0000,6341430.0000,8094443.0000,8851403.0000,7307897.0000,5305804.0000,5347051.0000,5282499.0000,5262431.0000,5303659.0000,5219100.0000,5390915.0000,5514166.0000,5226554.0000,5857927.0000,5500441.0000,5048156.0000,5033629.0000,5272651.0000,5948468.0000,5936585.0000,7056030.0000,5258064.0000,5483911.0000,5364564.0000,5317556.0000,6232104.0000,6145921.0000,5935573.0000,5648882.0000,6134269.0000,6170978.0000,5163304.0000,5736788.0000,5938308.0000,6923821.0000,5388309.0000,5448844.0000,5299873.0000,5880128.0000,5447191.0000,5503275.0000,6642780.0000,5665804.0000,5228848.0000,5200063.0000,5514748.0000,5304581.0000,5583709.0000,5491604.0000,5413116.0000,6733010.0000,6340338.0000,5167081.0000,5424667.0000,6557098.0000,6502374.0000,5071360.0000,4890839.0000,5123509.0000,5204342.0000,6369964.0000,6554052.0000,5757006.0000,5234199.0000,5076691.0000,5037636.0000,5115534.0000,5172352.0000,5155760.0000,5248826.0000,5729374.0000,6983203.0000,6319900.0000,5799796.0000,5569081.0000,6385403.0000,6458973.0000,5077402.0000,5091028.0000,5074647.0000,4929021.0000,5175307.0000,5023209.0000,5045292.0000,4985619.0000,4889347.0000,4956083.0000,5222656.0000,5297068.0000,5171570.0000,5150710.0000,6718282.0000,6871342.0000,5645876.0000,6898392.0000,6201305.0000,6409058.0000,5452140.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread,expanding tree topology,100,1,938220800,9105694.9600,9015991.7500,9304656.6700,647633.5477,367039.8785,1291577.9761,"8763076.0000,8687244.0000,14278147.0000,9406572.0000,8754911.0000,8733560.0000,8832707.0000,9289220.0000,9355635.0000,9070988.0000,8881550.0000,9972411.0000,9517361.0000,9456105.0000,9017647.0000,9096305.0000,9007778.0000,9634653.0000,8979354.0000,8725415.0000,8725124.0000,8639943.0000,8834792.0000,8873645.0000,8604406.0000,8669098.0000,8041011.0000,8022707.0000,8630917.0000,8915213.0000,9612942.0000,9156339.0000,8807620.0000,9005835.0000,9069595.0000,8647467.0000,8637599.0000,8817749.0000,9022877.0000,8845692.0000,9560713.0000,9687654.0000,9313847.0000,8697202.0000,8821907.0000,9779576.0000,10090164.0000,9080476.0000,9093471.0000,9599116.0000,9000214.0000,9154776.0000,10121612.0000,9086998.0000,9489549.0000,9131031.0000,9175616.0000,9042404.0000,9018558.0000,8933699.0000,9149084.0000,8925343.0000,9385612.0000,8980296.0000,9681822.0000,9265525.0000,9209270.0000,8831675.0000,8941012.0000,8840342.0000,8964045.0000,8898813.0000,9009472.0000,9155216.0000,8576794.0000,8656825.0000,9276576.0000,9100183.0000,9201143.0000,9066029.0000,9350436.0000,9444734.0000,9350877.0000,8975036.0000,10240939.0000,8777925.0000,9108078.0000,8787403.0000,8678015.0000,8645284.0000,8627750.0000,8950319.0000,8866451.0000,8600950.0000,8857624.0000,8731357.0000,8816247.0000,9681571.0000,9135971.0000,8907659.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread,contracting tree topology,100,1,672734600,6353015.3600,6195153.0200,6521853.6300,831660.3305,749636.5611,927374.7687,"5237835.0000,5611241.0000,8371115.0000,5721509.0000,5834502.0000,6149388.0000,6647288.0000,8015243.0000,6669290.0000,6812170.0000,6806810.0000,5785601.0000,5689559.0000,5932918.0000,7315240.0000,6399110.0000,7707632.0000,6110053.0000,7013461.0000,7471536.0000,5790459.0000,7436839.0000,5841306.0000,5673388.0000,5571605.0000,6962794.0000,6509709.0000,5855061.0000,5767355.0000,6644223.0000,6063866.0000,5595992.0000,5476716.0000,5300153.0000,5429798.0000,5331903.0000,5326913.0000,5449275.0000,5435790.0000,5495382.0000,5380825.0000,5302998.0000,5324539.0000,5163175.0000,5415451.0000,5360326.0000,5653351.0000,7537020.0000,6904335.0000,6271317.0000,5881441.0000,7414959.0000,6176819.0000,5538373.0000,5753740.0000,7219329.0000,6295563.0000,5728252.0000,6065920.0000,7467187.0000,6989154.0000,5795810.0000,5940704.0000,7502324.0000,6426542.0000,5887934.0000,5516512.0000,6261709.0000,7042416.0000,7713293.0000,6314830.0000,8042114.0000,6067093.0000,7088402.0000,6841504.0000,6673217.0000,7550205.0000,6555535.0000,8053816.0000,6510520.0000,7689498.0000,6657367.0000,5842628.0000,5657758.0000,6963496.0000,6213248.0000,5445487.0000,5568440.0000,6715156.0000,6601822.0000,5396144.0000,6433955.0000,7376515.0000,7998942.0000,6861403.0000,5698274.0000,5537341.0000,7626578.0000,7947645.0000,6181257.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread,wave_sim topology,100,1,2824514200,29848573.9300,29291494.3700,30436973.9600,2919235.3562,2621989.7254,3287785.8018,"24562910.0000,25437122.0000,27029781.0000,30562056.0000,29751313.0000,31674427.0000,32973583.0000,31707811.0000,26491353.0000,32258451.0000,28049528.0000,26433455.0000,36901664.0000,27307516.0000,26753590.0000,31545304.0000,26389852.0000,32025811.0000,24137987.0000,24033350.0000,28009273.0000,25243246.0000,25222015.0000,26659121.0000,25798705.0000,27659111.0000,31788443.0000,28236912.0000,28860209.0000,27951083.0000,29466977.0000,29327162.0000,34406519.0000,32879495.0000,29166489.0000,27672806.0000,34063682.0000,27075508.0000,29635195.0000,28352901.0000,28504458.0000,32385020.0000,29958134.0000,30659289.0000,33017626.0000,27548602.0000,27257612.0000,29256909.0000,29735805.0000,35086134.0000,33585108.0000,28433224.0000,34728598.0000,33372096.0000,30886258.0000,28679117.0000,31542819.0000,27554513.0000,32767873.0000,28591252.0000,28169655.0000,31935271.0000,31423723.0000,26287048.0000,26984405.0000,26438524.0000,28684438.0000,32177438.0000,28807140.0000,30214429.0000,28159295.0000,34735221.0000,28732589.0000,28527632.0000,32806426.0000,28949499.0000,34822465.0000,29071258.0000,30735935.0000,27642780.0000,27092470.0000,31869707.0000,29147604.0000,34217353.0000,31781860.0000,28626208.0000,34707659.0000,34596158.0000,27249707.0000,27500060.0000,34615254.0000,28657948.0000,30211784.0000,28155228.0000,33159634.0000,31548560.0000,28818410.0000,30846323.0000,36323021.0000,33375111.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread,jacobi topology,100,1,788031800,6650958.3900,6417356.6400,6945546.1200,1336018.6782,1085531.0511,1623595.0159,"5463431.0000,5368713.0000,10969375.0000,6578187.0000,6638582.0000,7389601.0000,9903731.0000,10493586.0000,5960551.0000,5334267.0000,5456278.0000,5544374.0000,5787013.0000,5526620.0000,5985899.0000,10307856.0000,7481053.0000,9922797.0000,10278119.0000,7755031.0000,10695789.0000,8029079.0000,6416813.0000,6767847.0000,6037546.0000,9897649.0000,9011536.0000,6312596.0000,6346279.0000,6551337.0000,6236722.0000,6203348.0000,6340479.0000,6366087.0000,7129149.0000,8602011.0000,6930213.0000,7151501.0000,6472107.0000,8361638.0000,6362711.0000,6683797.0000,6333005.0000,6564462.0000,6521290.0000,6626158.0000,6371488.0000,8207527.0000,7204421.0000,6194402.0000,6195004.0000,6120623.0000,6536088.0000,6843639.0000,6968075.0000,7169094.0000,5997431.0000,7391825.0000,6548481.0000,7240528.0000,6990176.0000,6899636.0000,7026204.0000,6783145.0000,6690981.0000,7157141.0000,6879707.0000,6965971.0000,6351911.0000,6486093.0000,6362741.0000,6809394.0000,5661435.0000,5669570.0000,5557119.0000,5848329.0000,5823552.0000,5722110.0000,5552490.0000,5858749.0000,6007419.0000,5798945.0000,5855363.0000,5962735.0000,5287249.0000,5518905.0000,5501303.0000,5214802.0000,5491314.0000,5141874.0000,5425299.0000,5320461.0000,5373842.0000,5125583.0000,5460124.0000,5667857.0000,5379062.0000,5278723.0000,5580652.0000,5523034.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task,soup topology,100,1,4536444200,45767725.3800,45524053.4700,45911410.7300,933872.8076,617894.9101,1354600.1347,"45934542.0000,46022719.0000,46369454.0000,46056333.0000,40914607.0000,46224190.0000,45178604.0000,42251513.0000,46170879.0000,46046354.0000,46127927.0000,46066081.0000,46079175.0000,46027809.0000,46076200.0000,46029923.0000,43907943.0000,42660948.0000,46027558.0000,43192741.0000,44244028.0000,46019032.0000,46038288.0000,46042376.0000,45987011.0000,46081721.0000,46160309.0000,46234709.0000,46312296.0000,46235160.0000,46014854.0000,46031335.0000,45976692.0000,46052054.0000,46013602.0000,46047015.0000,46041384.0000,45936155.0000,46066722.0000,46003673.0000,46074948.0000,46055471.0000,46020124.0000,46043158.0000,46047165.0000,46074677.0000,46068196.0000,46092520.0000,44647782.0000,45985379.0000,46054979.0000,46006518.0000,45978947.0000,46094234.0000,46116596.0000,46097290.0000,46031686.0000,46027638.0000,46108591.0000,46101819.0000,46098913.0000,46005676.0000,46106777.0000,46057464.0000,46030374.0000,46050662.0000,46032427.0000,45960421.0000,45998332.0000,45979336.0000,45992511.0000,46083844.0000,46004314.0000,45982432.0000,45999935.0000,46045021.0000,45966072.0000,45985348.0000,45984417.0000,46077703.0000,44714798.0000,46084075.0000,46054990.0000,46111907.0000,46059418.0000,45966332.0000,45970721.0000,45889698.0000,45972454.0000,45974889.0000,45976922.0000,41444930.0000,45236924.0000,46021997.0000,46029572.0000,46021637.0000,46041575.0000,46080097.0000,45983244.0000,46062745.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task,chain topology,100,1,372113600,3693096.0900,3662882.2800,3714088.8700,126866.1532,92937.7353,160294.7414,"3725388.0000,3737801.0000,3749974.0000,3715118.0000,3729435.0000,3721840.0000,3734865.0000,3727482.0000,3732911.0000,3723964.0000,3723373.0000,3726829.0000,3723423.0000,3731239.0000,3727351.0000,3727291.0000,3721390.0000,3733983.0000,3728874.0000,3729325.0000,3719587.0000,3717643.0000,3350840.0000,3302978.0000,3291457.0000,3303219.0000,3305403.0000,3291047.0000,3296738.0000,3314821.0000,3300113.0000,3386457.0000,3748511.0000,3744584.0000,3723604.0000,3740987.0000,3749142.0000,3739313.0000,3739473.0000,3741077.0000,3736518.0000,3733102.0000,3739684.0000,3742178.0000,3750164.0000,3742580.0000,3732541.0000,3734024.0000,3738903.0000,3733512.0000,3727091.0000,3734985.0000,3726630.0000,3743843.0000,3742019.0000,3756115.0000,3739554.0000,3741247.0000,3750555.0000,3737680.0000,3740897.0000,3746397.0000,3736859.0000,3748230.0000,3739273.0000,3728794.0000,3731309.0000,3748381.0000,3748460.0000,3729655.0000,3743321.0000,3733253.0000,3741217.0000,3731629.0000,3741908.0000,3733463.0000,3742450.0000,3729665.0000,3745926.0000,3726620.0000,3723533.0000,3732411.0000,3741588.0000,3732060.0000,3739945.0000,3751397.0000,3740786.0000,3745585.0000,3735165.0000,3730006.0000,3733372.0000,3728954.0000,3733402.0000,3737249.0000,3728383.0000,3719907.0000,3731208.0000,3728332.0000,3728312.0000,3738532.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task,expanding tree topology,100,1,696431900,6967677.0700,6965430.4200,6970030.8400,11736.3039,10178.3988,14843.4354,"6967022.0000,6979276.0000,6968355.0000,6967183.0000,6946794.0000,6987061.0000,6977101.0000,6950550.0000,6974647.0000,6968785.0000,6969727.0000,6946764.0000,6971632.0000,6980207.0000,6967964.0000,6977282.0000,6953166.0000,6961172.0000,6971140.0000,6961923.0000,6978484.0000,6972403.0000,6943849.0000,6968655.0000,6978725.0000,6970168.0000,6977231.0000,6960359.0000,6970189.0000,6963586.0000,6945321.0000,6967073.0000,6965981.0000,6972232.0000,6945702.0000,6961472.0000,6949880.0000,6963275.0000,6971050.0000,6964077.0000,6962463.0000,6955490.0000,6966792.0000,6983072.0000,6982691.0000,6960259.0000,6952554.0000,7014482.0000,6974456.0000,6962805.0000,6977101.0000,6969488.0000,6973965.0000,6962102.0000,6988293.0000,6976962.0000,6976250.0000,6970799.0000,6983494.0000,6971912.0000,6969006.0000,6948137.0000,6968596.0000,6962804.0000,6984716.0000,6964237.0000,6967312.0000,6961853.0000,6968155.0000,6955160.0000,6976921.0000,6959438.0000,6964448.0000,6956432.0000,6957213.0000,6977682.0000,6954669.0000,6973455.0000,6955811.0000,6985547.0000,6960850.0000,6970769.0000,6985929.0000,6953075.0000,6942436.0000,6971140.0000,6973925.0000,6972913.0000,6973445.0000,6974227.0000,6973344.0000,6971631.0000,6948758.0000,6965880.0000,6947306.0000,6961933.0000,6973755.0000,6986930.0000,6971211.0000,6973765.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task,contracting tree topology,100,1,411134100,4072027.2300,4038179.0800,4094291.0900,138554.8851,99791.9879,179657.9786,"4118149.0000,4108451.0000,4123750.0000,4126054.0000,4110635.0000,4107008.0000,4118791.0000,4108852.0000,4110495.0000,4117499.0000,4121245.0000,4109342.0000,4102069.0000,4108912.0000,4110355.0000,4117327.0000,4107809.0000,4120794.0000,4107460.0000,4115324.0000,4133238.0000,4107429.0000,4095527.0000,4101558.0000,4123720.0000,4111407.0000,4108562.0000,4116345.0000,4121887.0000,4117198.0000,4117278.0000,4122298.0000,4013541.0000,3609387.0000,3601634.0000,3593659.0000,3624436.0000,3623044.0000,3627972.0000,3619657.0000,3616371.0000,3834583.0000,4128099.0000,4120163.0000,4122167.0000,4103782.0000,4105516.0000,4118170.0000,4116937.0000,4109814.0000,4106387.0000,4111737.0000,4118099.0000,4115575.0000,4113180.0000,4102260.0000,4119982.0000,4187320.0000,4122497.0000,4117959.0000,4113621.0000,4128228.0000,4113280.0000,4107941.0000,4134330.0000,4113992.0000,4102119.0000,4113069.0000,4115755.0000,4127848.0000,4104193.0000,4123229.0000,4124662.0000,4112699.0000,4108692.0000,4110856.0000,4111517.0000,4111467.0000,4105265.0000,4112198.0000,4109042.0000,4120403.0000,4125944.0000,4120414.0000,4122447.0000,4121376.0000,4126335.0000,4121386.0000,4128208.0000,4111376.0000,4121746.0000,4120494.0000,4102911.0000,4120324.0000,4108882.0000,4109603.0000,4122117.0000,4113200.0000,4120484.0000,4110374.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task,wave_sim topology,100,1,1765580200,17586079.5300,17493505.8500,17635257.8200,333177.9500,204268.6981,508485.1123,"17670146.0000,17691446.0000,17652072.0000,17680727.0000,17612718.0000,17662141.0000,17652222.0000,17641472.0000,17630011.0000,17652823.0000,17656120.0000,17645439.0000,17633116.0000,17644348.0000,17612457.0000,17664806.0000,17658865.0000,17647503.0000,17593531.0000,17653124.0000,17656891.0000,17675496.0000,17670036.0000,17656250.0000,17685966.0000,17643957.0000,17639498.0000,17625302.0000,17625993.0000,17631463.0000,17630381.0000,17630802.0000,17643355.0000,17641734.0000,17104337.0000,15790995.0000,16756239.0000,17737064.0000,17743274.0000,17745398.0000,16071796.0000,15797408.0000,17460160.0000,17718166.0000,17719409.0000,17704652.0000,17690595.0000,17689743.0000,17699431.0000,17689283.0000,17108415.0000,17238350.0000,17368787.0000,17100410.0000,17701015.0000,17706935.0000,17678833.0000,17673613.0000,17670497.0000,17715742.0000,17764344.0000,17715181.0000,17707567.0000,17677681.0000,17667531.0000,17677901.0000,17666680.0000,17668232.0000,17686176.0000,17648064.0000,17691267.0000,17680305.0000,17698680.0000,17663945.0000,17670617.0000,17669996.0000,17696316.0000,17656079.0000,17699751.0000,17675096.0000,17720220.0000,17646471.0000,17675165.0000,17676408.0000,17681508.0000,17671348.0000,17696927.0000,17684794.0000,17674274.0000,17706484.0000,17693300.0000,17751049.0000,17720352.0000,17704030.0000,17726372.0000,17676398.0000,17685536.0000,17681117.0000,17696436.0000,17665597.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task,jacobi topology,100,1,585354000,5846439.6200,5807065.5300,5869499.9700,150370.7994,93620.3612,207362.8691,"5873616.0000,5880500.0000,5920505.0000,5877444.0000,5895758.0000,5877384.0000,5894917.0000,5893333.0000,5914062.0000,5888013.0000,5893653.0000,5873938.0000,5890959.0000,5880370.0000,5918781.0000,5900878.0000,5896681.0000,5885930.0000,5894084.0000,5872525.0000,5883064.0000,5890247.0000,5883375.0000,5892693.0000,5872134.0000,5882493.0000,5868557.0000,5857145.0000,5863087.0000,5902692.0000,5889175.0000,5895248.0000,5886180.0000,5886772.0000,5875089.0000,5876482.0000,5875791.0000,5871652.0000,5887252.0000,5875840.0000,5728502.0000,5222636.0000,5235741.0000,5244218.0000,5243285.0000,5238967.0000,5363823.0000,5881922.0000,5898604.0000,5886842.0000,5891359.0000,5885670.0000,5896490.0000,5876932.0000,5889767.0000,5899005.0000,5880580.0000,5889166.0000,5874698.0000,5888835.0000,5880118.0000,5907370.0000,5889105.0000,5934803.0000,5896970.0000,5881000.0000,5865250.0000,5885660.0000,5868437.0000,5882442.0000,5880469.0000,5872294.0000,5881021.0000,5884857.0000,5889407.0000,5877293.0000,5891169.0000,5884125.0000,5887944.0000,5877234.0000,5880549.0000,5871401.0000,5890849.0000,5882663.0000,5881562.0000,5885498.0000,5887974.0000,5884337.0000,5889757.0000,5873686.0000,5899205.0000,5888374.0000,5874007.0000,5891780.0000,5871873.0000,5880590.0000,5878987.0000,5885278.0000,5877404.0000,5895879.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task,soup topology,100,1,5638819600,53697878.1200,51723283.8800,55905882.8700,10651894.6469,9504379.4682,12105095.2060,"49297818.0000,72230819.0000,68584279.0000,56215118.0000,52644281.0000,43320894.0000,46903463.0000,73321280.0000,60167476.0000,59470930.0000,48192939.0000,38871065.0000,40944553.0000,42523286.0000,46885119.0000,44589541.0000,69365115.0000,55345855.0000,53466944.0000,67383762.0000,75042853.0000,62685714.0000,59768902.0000,42713405.0000,47596633.0000,42910619.0000,44039962.0000,45653401.0000,75531777.0000,65788576.0000,65245330.0000,41689881.0000,45554965.0000,63536723.0000,71046151.0000,46306506.0000,64126106.0000,39919777.0000,56941059.0000,59198445.0000,45311214.0000,68586153.0000,55578194.0000,59941690.0000,46344818.0000,55381972.0000,69025834.0000,58882729.0000,56562915.0000,46575934.0000,49123208.0000,68459594.0000,55709743.0000,56584525.0000,45336151.0000,44614839.0000,42024154.0000,78233893.0000,83292070.0000,51051160.0000,46182661.0000,46695009.0000,45221445.0000,35933315.0000,69338364.0000,61107112.0000,70625225.0000,74930019.0000,46335530.0000,41290727.0000,42731681.0000,42198984.0000,40782598.0000,65605962.0000,48642499.0000,56110560.0000,47730817.0000,44715328.0000,44420481.0000,53727768.0000,42852058.0000,44505773.0000,45926908.0000,50459763.0000,47967243.0000,62143348.0000,45783076.0000,53562024.0000,49519175.0000,61496527.0000,54334815.0000,46539345.0000,43247215.0000,52455233.0000,46230200.0000,45053457.0000,59410305.0000,41298562.0000,55625113.0000,55409475.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task,chain topology,100,1,630024900,6255082.6700,6089715.4100,6428464.9800,860749.8756,775589.6474,976819.5703,"5560235.0000,5353243.0000,7831356.0000,5473581.0000,4588889.0000,4592846.0000,5337314.0000,5323868.0000,7280214.0000,6746284.0000,5726729.0000,6563300.0000,5469893.0000,6327313.0000,6553501.0000,6782104.0000,7829201.0000,5333616.0000,5711100.0000,6886831.0000,5617311.0000,7429226.0000,6729003.0000,6533593.0000,6549553.0000,6808784.0000,7740825.0000,7470343.0000,7573980.0000,5555756.0000,6521791.0000,5219491.0000,6012499.0000,6888153.0000,5536158.0000,6148356.0000,6163133.0000,5716119.0000,5338515.0000,6526139.0000,7428705.0000,5155579.0000,5592736.0000,6804516.0000,7599978.0000,6855862.0000,5448673.0000,5521571.0000,6792242.0000,6788044.0000,6857325.0000,5819564.0000,5768046.0000,7339947.0000,7282058.0000,7003701.0000,7857235.0000,6353173.0000,6234057.0000,5685781.0000,5475154.0000,5357692.0000,7739843.0000,7624825.0000,7396624.0000,6732109.0000,7684619.0000,8640695.0000,7201735.0000,5995727.0000,5450667.0000,6088031.0000,6095646.0000,5667877.0000,5673499.0000,6053407.0000,6585751.0000,4794928.0000,6584620.0000,6026265.0000,5616660.0000,5634345.0000,6256410.0000,6095316.0000,5473640.0000,6675382.0000,5929693.0000,5193050.0000,4961453.0000,5452050.0000,6796671.0000,5198010.0000,6146031.0000,6131444.0000,5022638.0000,5435438.0000,5245869.0000,6789617.0000,7028108.0000,6017789.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task,expanding tree topology,100,1,910095500,8744404.0800,8564981.5700,8945470.3500,969594.7805,841179.4183,1149658.9853,"8103821.0000,8099121.0000,10696318.0000,9614545.0000,8858045.0000,7955520.0000,9031654.0000,8889184.0000,9138476.0000,8974716.0000,7998992.0000,7979285.0000,8631938.0000,8655062.0000,8789476.0000,7893683.0000,9149126.0000,9746454.0000,9410078.0000,7736246.0000,9579147.0000,8809183.0000,9759659.0000,8088501.0000,9233015.0000,8135140.0000,8083772.0000,8679990.0000,11021613.0000,10527891.0000,7648189.0000,8180856.0000,8810475.0000,9232442.0000,9104812.0000,8558369.0000,9755281.0000,8790858.0000,9151980.0000,8571524.0000,11128175.0000,11531187.0000,11825162.0000,8030392.0000,9417953.0000,9371195.0000,9266528.0000,7564431.0000,7569571.0000,9630795.0000,10407313.0000,10218407.0000,8533091.0000,8430988.0000,9986749.0000,8268582.0000,9733200.0000,9827106.0000,8405771.0000,8558570.0000,8597803.0000,9086547.0000,9273570.0000,8579449.0000,8894975.0000,8673125.0000,8366677.0000,7480422.0000,9364923.0000,10224939.0000,9804804.0000,9058245.0000,8074265.0000,8680671.0000,9610237.0000,9468528.0000,7395492.0000,7263422.0000,8035801.0000,8807179.0000,7980156.0000,7331300.0000,8118168.0000,8062332.0000,7418415.0000,8160518.0000,7334998.0000,7248734.0000,7898953.0000,7857194.0000,8592333.0000,7489650.0000,7650623.0000,7692874.0000,7692013.0000,7739692.0000,7751364.0000,8145750.0000,8365634.0000,8389030.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task,contracting tree topology,100,1,675876900,6118099.0300,5917053.1900,6332984.9100,1058305.1013,943077.1201,1199789.0829,"4496023.0000,5588919.0000,8387186.0000,5466557.0000,5002350.0000,5142014.0000,5980988.0000,6152874.0000,5164006.0000,6489690.0000,6646376.0000,6946714.0000,7920624.0000,5775340.0000,6557559.0000,5621791.0000,6193771.0000,6522161.0000,5556597.0000,4992401.0000,5084044.0000,5685070.0000,6442392.0000,5484572.0000,5831547.0000,6135982.0000,4873857.0000,6527382.0000,6259384.0000,6343885.0000,6489591.0000,8091486.0000,7223066.0000,7691452.0000,5458011.0000,5805076.0000,6559091.0000,8161520.0000,6214971.0000,5162412.0000,4279875.0000,4399100.0000,4551077.0000,4528885.0000,5542891.0000,6599588.0000,7934189.0000,5642149.0000,5208781.0000,5096959.0000,6045250.0000,6739422.0000,5487347.0000,4727250.0000,4284223.0000,4543192.0000,5697684.0000,5693026.0000,7306303.0000,6702773.0000,6055851.0000,5588608.0000,5582998.0000,5368251.0000,5380755.0000,5610109.0000,4493779.0000,5405231.0000,5405933.0000,7196757.0000,8869386.0000,7541037.0000,5037697.0000,6796150.0000,7209390.0000,7472067.0000,8417282.0000,7621679.0000,6712672.0000,5858127.0000,7219599.0000,6457370.0000,5781863.0000,4983394.0000,6457839.0000,7284693.0000,6800228.0000,7920103.0000,6217587.0000,6136543.0000,6901869.0000,7191606.0000,6624024.0000,5254296.0000,7189552.0000,7945241.0000,4471056.0000,5498207.0000,5658360.0000,5054018.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task,wave_sim topology,100,1,2805240800,29588274.6800,28894303.3200,30375459.5600,3760384.0474,3266404.9146,4523690.3330,"35552205.0000,30444533.0000,33911394.0000,26827439.0000,27895607.0000,28430047.0000,26179354.0000,26245730.0000,31939177.0000,30665952.0000,24760102.0000,30841193.0000,31507483.0000,32636586.0000,32472526.0000,31421901.0000,34578885.0000,26162623.0000,30137764.0000,24582137.0000,35912676.0000,30313106.0000,23671737.0000,26061582.0000,28763657.0000,42895089.0000,29242312.0000,31015402.0000,28506020.0000,28099092.0000,34642146.0000,27507234.0000,30589207.0000,27879928.0000,38343359.0000,25427203.0000,26832509.0000,27583227.0000,24737971.0000,26452280.0000,25185998.0000,33591841.0000,25247544.0000,23307919.0000,27004423.0000,27883795.0000,28020423.0000,30092128.0000,26221494.0000,28381515.0000,31120572.0000,31463920.0000,25830075.0000,34699303.0000,36686367.0000,27844841.0000,26286407.0000,31523562.0000,25106898.0000,24806210.0000,26395323.0000,30389910.0000,32316059.0000,25021206.0000,28075808.0000,28828190.0000,36482282.0000,32165285.0000,27795347.0000,34550733.0000,26322525.0000,25450628.0000,28618994.0000,29883664.0000,33205290.0000,28422533.0000,32791399.0000,30257630.0000,27615358.0000,25780861.0000,27341891.0000,26195835.0000,30738619.0000,30105073.0000,39185640.0000,26781362.0000,26671104.0000,30879415.0000,25315581.0000,30755021.0000,33407051.0000,30408585.0000,28420429.0000,38165893.0000,29064987.0000,30904202.0000,31197997.0000,35826603.0000,27373119.0000,27746426.0000"
+building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task,jacobi topology,100,1,940450100,11271631.2100,10970364.5300,11555363.5400,1498389.0743,1329226.3866,1698849.8864,"10172599.0000,11647287.0000,14700445.0000,12410799.0000,10344664.0000,12148664.0000,11578816.0000,8827027.0000,14116982.0000,11588635.0000,10118127.0000,11956681.0000,12708611.0000,11390130.0000,12137032.0000,8807670.0000,11755099.0000,10685830.0000,11168661.0000,11661182.0000,13188167.0000,11115250.0000,11611619.0000,12299078.0000,13677021.0000,12578335.0000,12798722.0000,8357890.0000,9003661.0000,11765920.0000,8481925.0000,12022234.0000,11657936.0000,12178149.0000,13165615.0000,12995322.0000,13281725.0000,13098658.0000,12197276.0000,7855270.0000,11800015.0000,11210009.0000,8078533.0000,7851723.0000,11426148.0000,10293067.0000,10567566.0000,9482035.0000,12068291.0000,10366436.0000,11224968.0000,11974495.0000,11683905.0000,12248482.0000,8684117.0000,11739230.0000,12984102.0000,11771210.0000,10133676.0000,11524244.0000,9175335.0000,8984926.0000,12031692.0000,12233203.0000,13612759.0000,9786580.0000,11771621.0000,12856040.0000,11058763.0000,12773133.0000,10076819.0000,12547908.0000,11516018.0000,10102126.0000,12286785.0000,10956912.0000,9201054.0000,9846113.0000,10042263.0000,9133897.0000,10746193.0000,11130369.0000,9624734.0000,11495950.0000,11542628.0000,9018489.0000,10828048.0000,10874075.0000,11716537.0000,9152442.0000,12041440.0000,12007857.0000,12030079.0000,8935181.0000,13258590.0000,13034738.0000,13606137.0000,11556825.0000,12721926.0000,11479970.0000"
diff --git a/ci/perf/gpuc1_bench.md b/ci/perf/gpuc1_bench.md
new file mode 100644
index 000000000..664cf0f4e
--- /dev/null
+++ b/ci/perf/gpuc1_bench.md
@@ -0,0 +1,95 @@
+# Benchmark Results
+
+| Metadata |                      |
+| :------- | :------------------- |
+| Created  | 2022-03-30T09:41:49Z |
+
+
+| Test case                                                                                                                                         | Benchmark name                   |            Min |           Mean |       Std dev |
+| :------------------------------------------------------------------------------------------------------------------------------------------------ | :------------------------------- | -------------: | -------------: | ------------: |
+| benchmark intrusive graph dependency handling with N nodes - 1                                                                                    | creating nodes                   |           4.47 |           4.72 |          0.18 |
+| benchmark intrusive graph dependency handling with N nodes - 1                                                                                    | creating and adding dependencies |          23.89 |          23.90 |          0.03 |
+| benchmark intrusive graph dependency handling with N nodes - 1                                                                                    | adding and removing dependencies |          20.52 |          20.58 |          0.41 |
+| benchmark intrusive graph dependency handling with N nodes - 1                                                                                    | checking for dependencies        |           2.09 |           2.10 |          0.05 |
+| benchmark intrusive graph dependency handling with N nodes - 10                                                                                   | creating nodes                   |          40.32 |          40.45 |          0.56 |
+| benchmark intrusive graph dependency handling with N nodes - 10                                                                                   | creating and adding dependencies |         279.61 |         280.83 |          0.68 |
+| benchmark intrusive graph dependency handling with N nodes - 10                                                                                   | adding and removing dependencies |         243.41 |         244.41 |          0.96 |
+| benchmark intrusive graph dependency handling with N nodes - 10                                                                                   | checking for dependencies        |          40.07 |          40.56 |          1.42 |
+| benchmark intrusive graph dependency handling with N nodes - 100                                                                                  | creating nodes                   |         442.34 |         444.49 |          7.66 |
+| benchmark intrusive graph dependency handling with N nodes - 100                                                                                  | creating and adding dependencies |       4'658.50 |       4'708.45 |        193.58 |
+| benchmark intrusive graph dependency handling with N nodes - 100                                                                                  | adding and removing dependencies |       4'737.00 |       4'784.50 |        157.63 |
+| benchmark intrusive graph dependency handling with N nodes - 100                                                                                  | checking for dependencies        |       1'999.85 |       2'019.68 |         76.35 |
+| generating large task graphs                                                                                                                      | soup topology                    |   9'644'651.00 |  10'507'581.23 |  1'344'264.95 |
+| generating large task graphs                                                                                                                      | chain topology                   |      69'850.00 |      72'003.62 |      3'597.93 |
+| generating large task graphs                                                                                                                      | expanding tree topology          |     101'801.00 |     115'293.31 |     25'135.66 |
+| generating large task graphs                                                                                                                      | contracting tree topology        |     180'569.00 |     182'230.92 |      2'539.45 |
+| generating large task graphs                                                                                                                      | wave\_sim topology                |     623'837.00 |     638'478.62 |     12'501.54 |
+| generating large task graphs                                                                                                                      | jacobi topology                  |     203'202.00 |     212'303.98 |     12'507.56 |
+| generating large command graphs for N nodes - 1                                                                                                   | soup topology                    |  16'089'750.00 |  18'377'377.10 |    972'728.92 |
+| generating large command graphs for N nodes - 1                                                                                                   | chain topology                   |     279'897.00 |     281'850.74 |      3'284.19 |
+| generating large command graphs for N nodes - 1                                                                                                   | expanding tree topology          |     343'998.00 |     388'210.85 |     20'299.91 |
+| generating large command graphs for N nodes - 1                                                                                                   | contracting tree topology        |     425'021.00 |     554'943.90 |    186'438.55 |
+| generating large command graphs for N nodes - 1                                                                                                   | wave\_sim topology                |   2'001'910.00 |   2'190'300.28 |    111'627.81 |
+| generating large command graphs for N nodes - 1                                                                                                   | jacobi topology                  |     740'798.00 |     814'585.65 |     26'328.09 |
+| generating large command graphs for N nodes - 4                                                                                                   | soup topology                    |  37'693'662.00 |  42'708'788.49 |  1'317'030.91 |
+| generating large command graphs for N nodes - 4                                                                                                   | chain topology                   |   2'892'143.00 |   3'289'545.35 |    120'696.77 |
+| generating large command graphs for N nodes - 4                                                                                                   | expanding tree topology          |   6'472'217.00 |   6'558'322.48 |    354'070.33 |
+| generating large command graphs for N nodes - 4                                                                                                   | contracting tree topology        |   3'705'610.00 |   3'727'709.31 |     10'797.28 |
+| generating large command graphs for N nodes - 4                                                                                                   | wave\_sim topology                |  13'468'798.00 |  15'267'931.61 |    219'256.59 |
+| generating large command graphs for N nodes - 4                                                                                                   | jacobi topology                  |   4'640'136.00 |   5'068'313.06 |    276'244.43 |
+| generating large command graphs for N nodes - 16                                                                                                  | soup topology                    | 134'677'495.00 | 140'222'187.18 |  4'792'785.64 |
+| generating large command graphs for N nodes - 16                                                                                                  | chain topology                   | 347'002'329.00 | 373'793'332.57 | 12'892'767.91 |
+| generating large command graphs for N nodes - 16                                                                                                  | expanding tree topology          | 369'379'812.00 | 401'174'022.67 |  9'709'571.33 |
+| generating large command graphs for N nodes - 16                                                                                                  | contracting tree topology        | 118'082'768.00 | 125'188'990.75 |  2'914'371.90 |
+| generating large command graphs for N nodes - 16                                                                                                  | wave\_sim topology                | 117'436'908.00 | 124'911'858.59 |  4'357'252.17 |
+| generating large command graphs for N nodes - 16                                                                                                  | jacobi topology                  | 111'881'261.00 | 120'284'391.53 |  2'434'633.13 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation                   | soup topology                    |  16'075'192.00 |  17'141'495.17 |    974'101.84 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation                   | chain topology                   |     280'999.00 |     283'813.45 |      2'970.96 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation                   | expanding tree topology          |     345'160.00 |     380'102.28 |     25'475.26 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation                   | contracting tree topology        |     491'637.00 |     495'239.03 |      4'144.94 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation                   | wave\_sim topology                |   2'002'862.00 |   2'238'254.68 |    115'236.87 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: single-threaded immediate graph generation                   | jacobi topology                  |     829'566.00 |     835'094.97 |      7'675.01 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread                              | soup topology                    |  27'478'189.00 |  36'913'587.08 |  4'635'545.41 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread                              | chain topology                   |     570'016.00 |     816'777.54 |    145'587.63 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread                              | expanding tree topology          |     700'622.00 |   1'114'400.07 |    207'545.77 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread                              | contracting tree topology        |     692'156.00 |     993'383.09 |    113'582.30 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread                              | wave\_sim topology                |   4'067'194.00 |   6'086'953.73 |  1'723'257.20 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > immediate submission to a scheduler thread                              | jacobi topology                  |   1'645'157.00 |   2'274'749.24 |    433'541.99 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task | soup topology                    |  18'305'446.00 |  21'162'705.45 |    455'990.50 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task | chain topology                   |     579'553.00 |     589'640.81 |     27'401.21 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task | expanding tree topology          |     707'946.00 |     711'322.36 |      5'283.64 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task | contracting tree topology        |     738'072.00 |     779'665.33 |     31'784.81 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task | wave\_sim topology                |   4'080'819.00 |   4'317'302.69 |     55'169.54 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > reference: throttled single-threaded graph generation at 10 us per task | jacobi topology                  |   1'259'248.00 |   1'353'882.87 |     50'593.27 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task            | soup topology                    |  17'750'267.00 |  36'455'856.56 |  7'625'407.37 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task            | chain topology                   |   1'021'459.00 |   1'640'216.59 |    425'177.35 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task            | expanding tree topology          |   1'300'535.00 |   1'965'087.40 |    458'521.03 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task            | contracting tree topology        |   1'303'009.00 |   2'038'953.37 |    365'667.13 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task            | wave\_sim topology                |   6'875'429.00 |  11'350'992.55 |  2'318'000.42 |
+| building command graphs in a dedicated scheduler thread for N nodes - 1 > throttled submission to a scheduler thread at 10 us per task            | jacobi topology                  |   2'208'921.00 |   3'386'860.19 |    591'689.43 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation                   | soup topology                    |  38'191'833.00 |  43'536'383.12 |  2'002'852.88 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation                   | chain topology                   |   2'971'893.00 |   3'452'317.08 |    360'511.71 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation                   | expanding tree topology          |   5'772'705.00 |   6'639'552.70 |    517'593.65 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation                   | contracting tree topology        |   3'286'228.00 |   3'758'447.01 |    147'103.69 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation                   | wave\_sim topology                |  13'711'105.00 |  15'552'143.29 |    698'281.69 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: single-threaded immediate graph generation                   | jacobi topology                  |   4'732'069.00 |   5'407'416.58 |    427'318.88 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread                              | soup topology                    |  60'487'451.00 |  76'309'344.95 |  5'795'827.28 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread                              | chain topology                   |   4'889'347.00 |   5'695'196.21 |    710'153.99 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread                              | expanding tree topology          |   8'022'707.00 |   9'105'694.96 |    647'633.55 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread                              | contracting tree topology        |   5'163'175.00 |   6'353'015.36 |    831'660.33 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread                              | wave\_sim topology                |  24'033'350.00 |  29'848'573.93 |  2'919'235.36 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > immediate submission to a scheduler thread                              | jacobi topology                  |   5'125'583.00 |   6'650'958.39 |  1'336'018.68 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task | soup topology                    |  40'914'607.00 |  45'767'725.38 |    933'872.81 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task | chain topology                   |   3'291'047.00 |   3'693'096.09 |    126'866.15 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task | expanding tree topology          |   6'942'436.00 |   6'967'677.07 |     11'736.30 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task | contracting tree topology        |   3'593'659.00 |   4'072'027.23 |    138'554.89 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task | wave\_sim topology                |  15'790'995.00 |  17'586'079.53 |    333'177.95 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > reference: throttled single-threaded graph generation at 10 us per task | jacobi topology                  |   5'222'636.00 |   5'846'439.62 |    150'370.80 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task            | soup topology                    |  35'933'315.00 |  53'697'878.12 | 10'651'894.65 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task            | chain topology                   |   4'588'889.00 |   6'255'082.67 |    860'749.88 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task            | expanding tree topology          |   7'248'734.00 |   8'744'404.08 |    969'594.78 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task            | contracting tree topology        |   4'279'875.00 |   6'118'099.03 |  1'058'305.10 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task            | wave\_sim topology                |  23'307'919.00 |  29'588'274.68 |  3'760'384.05 |
+| building command graphs in a dedicated scheduler thread for N nodes - 4 > throttled submission to a scheduler thread at 10 us per task            | jacobi topology                  |   7'851'723.00 |  11'271'631.21 |  1'498'389.07 |
+
+All numbers are in nanoseconds.
diff --git a/ci/perf/gpuc1_bench.txt b/ci/perf/gpuc1_bench.txt
deleted file mode 100644
index 5f0618b82..000000000
--- a/ci/perf/gpuc1_bench.txt
+++ /dev/null
@@ -1,520 +0,0 @@
-
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-benchmarks is a Catch v3.0.0-preview.4 host application.
-Run with -? for options
-
-Randomness seeded to: 983966020
-
--------------------------------------------------------------------------------
-benchmark intrusive graph dependency handling with N nodes - 1
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:17
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-creating nodes                                 100          5502     2.2008 ms 
-                                           4.77 ns    4.73913 ns    4.79881 ns 
-                                       0.152377 ns   0.138839 ns   0.167203 ns 
-                                                                               
-creating and adding dependencies               100          1065     2.4495 ms 
-                                        23.3573 ns    23.2772 ns     23.675 ns 
-                                       0.736352 ns  0.0987128 ns    1.74203 ns 
-                                                                               
-adding and removing dependencies               100          1559     2.4944 ms 
-                                         16.006 ns    15.9598 ns    16.2151 ns 
-                                       0.428661 ns  0.0498778 ns    1.01639 ns 
-                                                                               
-checking for dependencies                      100         20225     2.0225 ms 
-                                        1.23812 ns    1.23736 ns    1.23892 ns 
-                                     0.00399371 ns 0.00368628 ns 0.00436189 ns 
-                                                                               
-
--------------------------------------------------------------------------------
-benchmark intrusive graph dependency handling with N nodes - 10
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:17
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-creating nodes                                 100           634     2.4726 ms 
-                                        41.6619 ns    41.5964 ns    41.9192 ns 
-                                       0.610135 ns   0.068248 ns    1.44893 ns 
-                                                                               
-creating and adding dependencies               100           101     2.5048 ms 
-                                        237.222 ns    237.173 ns    237.452 ns 
-                                       0.464794 ns  0.0352424 ns    1.10688 ns 
-                                                                               
-adding and removing dependencies               100           124     2.5048 ms 
-                                        203.549 ns    201.573 ns    205.744 ns 
-                                         10.622 ns     9.7146 ns    13.8013 ns 
-                                                                               
-checking for dependencies                      100          1131     2.4882 ms 
-                                        22.8145 ns    22.7288 ns    23.1274 ns 
-                                       0.738047 ns   0.190773 ns    1.69136 ns 
-                                                                               
-
--------------------------------------------------------------------------------
-benchmark intrusive graph dependency handling with N nodes - 100
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:17
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-creating nodes                                 100            61     2.5254 ms 
-                                        403.776 ns     402.85 ns    407.736 ns 
-                                        7.98883 ns  0.0763468 ns    18.8193 ns 
-                                                                               
-creating and adding dependencies               100             6      2.529 ms 
-                                        4.11403 us    4.10222 us    4.15963 us 
-                                         104.03 ns    25.1029 ns    241.459 ns 
-                                                                               
-adding and removing dependencies               100             7     2.7888 ms 
-                                        4.55989 us    4.54751 us    4.58369 us 
-                                        84.5413 ns    54.1937 ns    157.457 ns 
-                                                                               
-checking for dependencies                      100            14      2.604 ms 
-                                        1.86798 us    1.86238 us    1.89361 us 
-                                        52.3931 ns     4.4915 ns    124.398 ns 
-                                                                               
-
--------------------------------------------------------------------------------
-generating large task graphs
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:352
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     1.06909 s 
-                                        11.2129 ms    11.1051 ms      11.31 ms 
-                                        519.906 us     470.22 us    571.551 us 
-                                                                               
-chain topology                                 100             1      6.611 ms 
-                                        60.6874 us    60.3085 us    61.3234 us 
-                                        2.43556 us     1.6868 us    3.58779 us 
-                                                                               
-expanding tree topology                        100             1    11.0109 ms
-                                        108.241 us    106.927 us    109.531 us 
-                                        6.65731 us    6.42674 us    7.23249 us 
-                                                                               
-contracting tree topology                      100             1    16.0505 ms
-                                         157.08 us     156.82 us    157.738 us 
-                                        1.95406 us    916.958 ns    3.81677 us 
-                                                                               
-wave_sim topology                              100             1    63.1047 ms 
-                                        622.136 us    617.472 us    627.936 us 
-                                        26.4859 us    22.0816 us    30.9328 us 
-                                                                               
-jacobi topology                                100             1    20.4853 ms 
-                                        201.036 us    200.051 us    202.688 us 
-                                        6.38163 us    4.22308 us    8.99984 us 
-                                                                               
-
--------------------------------------------------------------------------------
-generating large command graphs for N nodes - 1
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:356
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     1.75265 s 
-                                        19.3948 ms    19.2142 ms    19.5244 ms 
-                                        774.936 us    597.203 us    959.754 us 
-                                                                               
-chain topology                                 100             1    27.8444 ms 
-                                        280.785 us    280.256 us    281.982 us 
-                                        3.85864 us    2.11528 us    7.47205 us 
-                                                                               
-expanding tree topology                        100             1    39.2963 ms
-                                        392.809 us    392.318 us    393.637 us 
-                                        3.16984 us    2.17134 us    4.67992 us 
-                                                                               
-contracting tree topology                      100             1    48.8392 ms
-                                        489.535 us    489.061 us     490.21 us 
-                                        2.86475 us    2.16986 us    3.69985 us 
-                                                                               
-wave_sim topology                              100             1    222.626 ms 
-                                        2.18084 ms    2.15945 ms    2.19704 ms 
-                                        95.1228 us    76.7778 us    111.305 us 
-                                                                               
-jacobi topology                                100             1     79.945 ms 
-                                        815.411 us     814.43 us    817.619 us 
-                                        7.18611 us    4.04548 us    14.3051 us 
-                                                                               
-
--------------------------------------------------------------------------------
-generating large command graphs for N nodes - 4
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:356
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     4.54957 s 
-                                        45.1875 ms    44.9688 ms    45.3197 ms 
-                                         848.26 us    570.478 us    1.20771 ms 
-                                                                               
-chain topology                                 100             1    328.619 ms 
-                                        3.28591 ms    3.28431 ms    3.28754 ms 
-                                        8.23746 us    7.33804 us     9.3567 us 
-                                                                               
-expanding tree topology                        100             1    656.362 ms
-                                        6.52232 ms     6.4759 ms    6.54785 ms 
-                                        171.315 us     109.98 us    244.109 us 
-                                                                               
-contracting tree topology                      100             1    356.458 ms
-                                        3.65887 ms    3.62627 ms    3.68019 ms 
-                                        132.521 us      96.41 us    170.305 us 
-                                                                               
-wave_sim topology                              100             1      1.4972 s 
-                                        14.8607 ms    14.7559 ms    14.9237 ms 
-                                        405.842 us    269.065 us     560.71 us 
-                                                                               
-jacobi topology                                100             1    515.668 ms 
-                                        5.07844 ms    5.03069 ms    5.11216 ms 
-                                        202.028 us    155.415 us    247.241 us 
-                                                                               
-
--------------------------------------------------------------------------------
-generating large command graphs for N nodes - 16
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:356
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     15.5769 s 
-                                        154.942 ms    154.602 ms    155.189 ms 
-                                        1.46132 ms    1.12747 ms    1.80288 ms 
-                                                                               
-chain topology                                 100             1     41.3983 s 
-                                         416.63 ms    415.712 ms    417.346 ms 
-                                        4.10639 ms    3.40189 ms    5.32762 ms 
-                                                                               
-expanding tree topology                        100             1     43.6788 s
-                                         429.87 ms    427.493 ms    432.087 ms 
-                                        11.7664 ms    10.6778 ms    13.1724 ms 
-                                                                               
-contracting tree topology                      100             1     13.2692 s
-                                         129.55 ms    129.043 ms    130.003 ms 
-                                        2.45671 ms    2.19246 ms    2.87405 ms 
-                                                                               
-wave_sim topology                              100             1     12.8762 s 
-                                        127.215 ms    126.723 ms    127.656 ms 
-                                        2.37551 ms    2.15901 ms    2.73634 ms 
-                                                                               
-jacobi topology                                100             1     11.5795 s 
-                                        113.566 ms    112.829 ms    114.368 ms 
-                                          3.927 ms     3.4563 ms    4.59004 ms 
-                                                                               
-
--------------------------------------------------------------------------------
-building command graphs in a dedicated scheduler thread for N nodes - 1
-  reference: single-threaded immediate graph generation
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:361
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     1.81685 s 
-                                        18.3204 ms    18.1278 ms    18.5097 ms 
-                                        972.178 us     896.01 us    1.05263 ms 
-                                                                               
-chain topology                                 100             1    27.1377 ms 
-                                        259.042 us    255.742 us    262.504 us 
-                                         17.349 us    16.7269 us    18.0959 us 
-                                                                               
-expanding tree topology                        100             1      37.93 ms
-                                         381.45 us     377.08 us    385.155 us 
-                                        20.4583 us    17.6477 us    22.7529 us 
-                                                                               
-contracting tree topology                      100             1    47.2836 ms
-                                        477.091 us     471.59 us    481.674 us 
-                                        25.6995 us    21.7664 us    28.9349 us 
-                                                                               
-wave_sim topology                              100             1    211.621 ms 
-                                         2.1321 ms    2.10534 ms    2.16751 ms 
-                                        156.087 us    119.245 us    256.025 us 
-                                                                               
-jacobi topology                                100             1     74.359 ms 
-                                        740.786 us    732.271 us    750.484 us 
-                                         46.276 us    41.5718 us    49.6202 us 
-                                                                               
-
--------------------------------------------------------------------------------
-building command graphs in a dedicated scheduler thread for N nodes - 1
-  immediate submission to a scheduler thread
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:364
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     3.83597 s 
-                                        37.8145 ms    37.4335 ms      38.17 ms 
-                                        1.88512 ms    1.64422 ms    2.23124 ms 
-                                                                               
-chain topology                                 100             1    93.3715 ms 
-                                        945.146 us    920.734 us    971.394 us 
-                                        128.472 us    110.943 us    151.441 us 
-                                                                               
-expanding tree topology                        100             1    111.222 ms
-                                        1.26021 ms    1.21236 ms    1.31404 ms 
-                                        259.502 us    230.241 us    290.074 us 
-                                                                               
-contracting tree topology                      100             1    140.829 ms
-                                        1.29287 ms    1.24607 ms    1.34532 ms 
-                                        253.091 us    221.499 us    290.382 us 
-                                                                               
-wave_sim topology                              100             1    699.303 ms 
-                                         5.8711 ms    5.64876 ms    6.12988 ms 
-                                        1.22722 ms    1.04032 ms    1.44411 ms 
-                                                                               
-jacobi topology                                100             1    237.291 ms 
-                                        2.35772 ms    2.24384 ms    2.49738 ms 
-                                        642.373 us    545.267 us    757.761 us 
-                                                                               
-
--------------------------------------------------------------------------------
-building command graphs in a dedicated scheduler thread for N nodes - 1
-  reference: throttled single-threaded graph generation at 10 us per task
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:368
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     2.19705 s 
-                                        21.6897 ms    21.5013 ms    21.8862 ms 
-                                        977.968 us    761.873 us    1.45354 ms 
-                                                                               
-chain topology                                 100             1    57.5002 ms 
-                                        582.354 us    581.807 us    583.123 us 
-                                        3.29109 us    2.46418 us    4.33994 us 
-                                                                               
-expanding tree topology                        100             1    69.2673 ms
-                                        686.594 us    681.776 us    691.599 us 
-                                        24.9524 us    23.1709 us    30.0807 us 
-                                                                               
-contracting tree topology                      100             1    80.5997 ms
-                                        804.401 us    803.847 us    805.285 us 
-                                        3.51098 us    2.50605 us    5.47595 us 
-                                                                               
-wave_sim topology                              100             1    430.671 ms 
-                                        4.29362 ms    4.27516 ms    4.30955 ms 
-                                        87.1178 us    65.8922 us      117.3 us 
-                                                                               
-jacobi topology                                100             1    133.781 ms 
-                                        1.25763 ms    1.25029 ms    1.26754 ms 
-                                        43.0603 us    35.3056 us    59.4475 us 
-                                                                               
-
--------------------------------------------------------------------------------
-building command graphs in a dedicated scheduler thread for N nodes - 1
-  throttled submission to a scheduler thread at 10 us per task
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:371
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     3.26205 s 
-                                        27.9973 ms      26.68 ms    29.3975 ms 
-                                        6.94256 ms    6.27741 ms    7.78738 ms 
-                                                                               
-chain topology                                 100             1    166.051 ms 
-                                        1.58221 ms    1.50478 ms    1.67156 ms 
-                                        423.903 us     360.06 us     493.27 us 
-                                                                               
-expanding tree topology                        100             1    172.732 ms
-                                         2.2966 ms    2.21772 ms    2.37127 ms 
-                                        391.784 us    361.789 us    423.326 us 
-                                                                               
-contracting tree topology                      100             1    207.528 ms
-                                        1.98351 ms    1.89633 ms    2.06866 ms 
-                                        442.341 us    389.817 us    500.314 us 
-                                                                               
-wave_sim topology                              100             1    890.396 ms 
-                                        9.67753 ms    9.36573 ms    10.0498 ms 
-                                        1.73413 ms    1.43614 ms    2.24868 ms 
-                                                                               
-jacobi topology                                100             1    330.034 ms 
-                                        3.47443 ms     3.3248 ms    3.62412 ms 
-                                        765.306 us    695.358 us    844.144 us 
-                                                                               
-
--------------------------------------------------------------------------------
-building command graphs in a dedicated scheduler thread for N nodes - 4
-  reference: single-threaded immediate graph generation
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:361
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     4.24718 s 
-                                        43.7114 ms    43.3916 ms    44.0509 ms 
-                                         1.6887 ms    1.54398 ms    1.83716 ms 
-                                                                               
-chain topology                                 100             1    338.589 ms 
-                                        3.37986 ms    3.37852 ms    3.38126 ms 
-                                        6.99732 us    6.04976 us    8.44377 us 
-                                                                               
-expanding tree topology                        100             1    666.739 ms
-                                        6.60701 ms    6.54461 ms    6.65326 ms 
-                                        272.264 us    217.945 us    322.691 us 
-                                                                               
-contracting tree topology                      100             1    379.103 ms
-                                        3.75273 ms     3.7207 ms    3.77252 ms 
-                                        126.503 us    91.3047 us    165.895 us 
-                                                                               
-wave_sim topology                              100             1     1.53863 s 
-                                        15.3056 ms    15.2233 ms    15.3529 ms 
-                                        311.268 us    202.598 us    462.926 us 
-                                                                               
-jacobi topology                                100             1    527.785 ms 
-                                         5.1052 ms    5.04242 ms    5.15819 ms 
-                                        294.205 us    258.433 us    321.147 us 
-                                                                               
-
--------------------------------------------------------------------------------
-building command graphs in a dedicated scheduler thread for N nodes - 4
-  immediate submission to a scheduler thread
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:364
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     8.45884 s 
-                                        77.1768 ms    75.5613 ms    78.5701 ms 
-                                        7.62799 ms    6.64324 ms    8.63119 ms 
-                                                                               
-chain topology                                 100             1    592.978 ms 
-                                        4.44122 ms    4.27867 ms    4.64558 ms 
-                                        928.008 us    777.027 us    1.12323 ms 
-                                                                               
-expanding tree topology                        100             1    751.417 ms
-                                        7.99459 ms    7.75943 ms    8.28614 ms 
-                                        1.32757 ms     1.1046 ms    1.59387 ms 
-                                                                               
-contracting tree topology                      100             1    490.601 ms
-                                         4.3071 ms     4.1611 ms    4.50613 ms 
-                                        867.525 us    684.384 us    1.09668 ms 
-                                                                               
-wave_sim topology                              100             1     1.53225 s 
-                                        22.5137 ms    21.9437 ms     23.079 ms 
-                                          2.902 ms    2.60201 ms    3.28409 ms 
-                                                                               
-jacobi topology                                100             1    691.357 ms 
-                                        7.18509 ms    6.91521 ms    7.49879 ms 
-                                        1.48275 ms    1.27662 ms    1.73523 ms 
-                                                                               
-
--------------------------------------------------------------------------------
-building command graphs in a dedicated scheduler thread for N nodes - 4
-  reference: throttled single-threaded graph generation at 10 us per task
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:368
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     4.62436 s 
-                                        45.3529 ms    45.0657 ms    45.6217 ms 
-                                        1.41847 ms    1.30143 ms      1.551 ms 
-                                                                               
-chain topology                                 100             1    344.174 ms 
-                                        3.53857 ms    3.50006 ms      3.573 ms 
-                                        184.742 us    170.016 us    195.056 us 
-                                                                               
-expanding tree topology                        100             1    702.871 ms
-                                        6.58649 ms    6.51621 ms    6.65898 ms 
-                                        364.356 us    347.712 us    379.208 us 
-                                                                               
-contracting tree topology                      100             1    387.156 ms
-                                        3.92634 ms    3.88144 ms    3.96703 ms 
-                                        217.419 us    200.331 us    228.943 us 
-                                                                               
-wave_sim topology                              100             1     1.60086 s 
-                                        16.4787 ms    16.3312 ms    16.6997 ms 
-                                        901.575 us     665.21 us    1.56726 ms 
-                                                                               
-jacobi topology                                100             1    550.338 ms 
-                                        5.46266 ms    5.40198 ms    5.52237 ms 
-                                        307.221 us    293.166 us    320.337 us 
-                                                                               
-
--------------------------------------------------------------------------------
-building command graphs in a dedicated scheduler thread for N nodes - 4
-  throttled submission to a scheduler thread at 10 us per task
--------------------------------------------------------------------------------
-/software-local/fabian/code/celerity-runtime/test/benchmarks.cc:371
-...............................................................................
-
-benchmark name                       samples       iterations    estimated
-                                     mean          low mean      high mean
-                                     std dev       low std dev   high std dev
--------------------------------------------------------------------------------
-soup topology                                  100             1     7.04652 s 
-                                        67.4694 ms    64.6814 ms    70.1476 ms 
-                                        13.9298 ms    12.7374 ms    15.2983 ms 
-                                                                               
-chain topology                                 100             1    682.491 ms 
-                                        6.36963 ms    6.20825 ms     6.5369 ms 
-                                        836.193 us    747.527 us    948.434 us 
-                                                                               
-expanding tree topology                        100             1     970.99 ms
-                                        9.64736 ms    9.46017 ms    9.91348 ms 
-                                        1.12541 ms    836.098 us    1.65908 ms 
-                                                                               
-contracting tree topology                      100             1    680.713 ms
-                                        7.10584 ms    6.84426 ms    7.36677 ms 
-                                         1.3278 ms    1.20382 ms    1.49684 ms 
-                                                                               
-wave_sim topology                              100             1     3.46961 s 
-                                        26.2309 ms    25.1572 ms    27.4097 ms 
-                                        5.72653 ms    5.01215 ms    6.70009 ms 
-                                                                               
-jacobi topology                                100             1    758.439 ms 
-                                        8.10679 ms     7.7305 ms      8.514 ms 
-                                        1.99286 ms    1.82141 ms    2.16993 ms 
-                                                                               
-
-===============================================================================
-test cases: 9 | 9 passed
-assertions: - none -
-
diff --git a/test/CMakeLists.txt b/test/CMakeLists.txt
index 9dbbd911c..423716975 100644
--- a/test/CMakeLists.txt
+++ b/test/CMakeLists.txt
@@ -68,7 +68,7 @@ target_link_libraries(all_tests PRIVATE test_main)
 set_test_target_parameters(all_tests "")
 
 # Unit benchmark executable
-add_executable(benchmarks benchmarks.cc)
+add_executable(benchmarks benchmarks.cc benchmark_reporters.cc)
 target_link_libraries(benchmarks PRIVATE test_main)
 set_test_target_parameters(benchmarks benchmarks.cc)
 
diff --git a/test/benchmark_reporters.cc b/test/benchmark_reporters.cc
new file mode 100644
index 000000000..67894f4c6
--- /dev/null
+++ b/test/benchmark_reporters.cc
@@ -0,0 +1,253 @@
+#include <algorithm>
+#include <chrono>
+#include <ctime>
+#include <limits>
+#include <locale>
+#include <numeric>
+#include <ostream>
+#include <regex>
+#include <string>
+#include <unordered_set>
+#include <utility>
+#include <vector>
+
+#include <catch2/catch_test_case_info.hpp>
+#include <catch2/reporters/catch_reporter_registrars.hpp>
+#include <catch2/reporters/catch_reporter_streaming_base.hpp>
+#include <spdlog/fmt/chrono.h>
+#include <spdlog/fmt/fmt.h>
+#include <spdlog/fmt/ostr.h>
+
+// Escape according to RFC 4180 (w/o line break support)
+static std::string escape_csv(const std::string& str) {
+	assert(str.find_first_of("\r\n") == std::string::npos);
+	// Determine if we need escaping at all (string contains comma or quote).
+	if(str.find_first_of("\",") == std::string::npos) return str;
+
+	const std::regex re("\"");
+	// Prefix quotes with a another quote, wrap whole string in quotes.
+	return fmt::format("\"{}\"", std::regex_replace(str, re, "\"\""));
+}
+
+static std::string escape_md_partial(const std::string& str) {
+	// We only escape characters that
+	// - are likely to occur in a test case / benchmark name
+	// - have inline semantics (e.g. we don't expect a test case to start with a '-' or '>')
+	// - are likely not intended for formatting (e.g. using backticks to denote types/code is fine)
+	// - have a meaning in popular Markdown implementations (e.g. {} is reserved but not used)
+	if(str.find_first_of("*_|[]\\") == std::string::npos) return str;
+	const std::regex re(R"(([*_|[\]\\]))");
+	return std::regex_replace(str, re, "\\$1");
+}
+
+class benchmark_reporter_base : public Catch::StreamingReporterBase {
+  public:
+	using StreamingReporterBase::StreamingReporterBase;
+
+	void benchmarkPreparing(Catch::StringRef benchmarkName) override {
+		StreamingReporterBase::benchmarkPreparing(benchmarkName);
+		test_case_benchmark_combinations.insert(get_test_case_name() + ": " + benchmarkName);
+	}
+
+	// TODO: Do we want to somehow report this?
+	void benchmarkFailed(Catch::StringRef benchmarkName) override { StreamingReporterBase::benchmarkFailed(benchmarkName); }
+
+	void sectionStarting(Catch::SectionInfo const& sectionInfo) override {
+		StreamingReporterBase::sectionStarting(sectionInfo);
+		// Each test case has an implicit section with the name of the test case itself,
+		// so there is no need to capture that separately.
+		active_sections.push_back(sectionInfo.name);
+	}
+
+	void testCasePartialEnded(Catch::TestCaseStats const& testCaseStats, uint64_t partNumber) override {
+		StreamingReporterBase::testCasePartialEnded(testCaseStats, partNumber);
+		active_sections.clear();
+	}
+
+	void testRunEnded(Catch::TestRunStats const& testRunStats) override {
+		StreamingReporterBase::testRunEnded(testRunStats);
+		bool warning_printed = false;
+		for(auto it = test_case_benchmark_combinations.cbegin(); it != test_case_benchmark_combinations.cend(); ++it) {
+			const auto id = *it;
+			const auto count = test_case_benchmark_combinations.count(id);
+			if(count > 1) {
+				if(!warning_printed) {
+					fmt::print(stderr, "WARNING: Using generators will result in indistinguishable test cases. The following cases are ambiguous:\n");
+					warning_printed = true;
+				}
+				fmt::print(stderr, "\t{}\n", id);
+			}
+			// Same values are guaranteed to be contiguous; skip ahead.
+			std::advance(it, count - 1);
+		}
+		if(warning_printed) { fmt::print(stderr, "Consider naming benchmarks dynamically to avoid this.\n"); }
+	}
+
+  protected:
+	[[nodiscard]] std::string get_test_case_name() const { return fmt::format("{}", fmt::join(active_sections, " > ")); }
+
+  private:
+	std::vector<std::string> active_sections;
+	std::unordered_multiset<std::string> test_case_benchmark_combinations;
+};
+
+/**
+ * Prints benchmark results in CSV format.
+ * All timings are in nanoseconds.
+ *
+ * Note that unlike in some other reporters, sections that precede a BENCHMARK and are
+ * active in the current invocation will be printed as well (not just those directly
+ * surrounding a BENCHMARK).
+ */
+class benchmark_csv_reporter : public benchmark_reporter_base {
+  public:
+	using benchmark_reporter_base::benchmark_reporter_base;
+
+	static std::string getDescription() { return "Reporter for benchmarks in CSV format"; }
+
+	void testRunStarting(Catch::TestRunInfo const& testRunInfo) override {
+		benchmark_reporter_base::testRunStarting(testRunInfo);
+		fmt::print(m_stream, "test case,benchmark name,samples,iterations,estimated,mean,low mean,high mean,std dev,low std dev,high std dev,raw\n");
+	}
+
+	void benchmarkEnded(Catch::BenchmarkStats<> const& benchmarkStats) override {
+		benchmark_reporter_base::benchmarkEnded(benchmarkStats);
+		auto& info = benchmarkStats.info;
+		fmt::print(m_stream, "{},{},{},{},{},", escape_csv(get_test_case_name()), escape_csv(info.name), info.samples, info.iterations, info.estimatedDuration);
+		fmt::print(m_stream, "{:.4f},{:.4f},{:.4f},{:.4f},{:.4f},{:.4f},", benchmarkStats.mean.point.count(), benchmarkStats.mean.lower_bound.count(),
+		    benchmarkStats.mean.upper_bound.count(), benchmarkStats.standardDeviation.point.count(), benchmarkStats.standardDeviation.lower_bound.count(),
+		    benchmarkStats.standardDeviation.upper_bound.count());
+		// Finally print all raw values for custom analyses (as quoted comma-separated values).
+		std::vector<double> raw;
+		raw.reserve(benchmarkStats.samples.size());
+		std::transform(benchmarkStats.samples.cbegin(), benchmarkStats.samples.cend(), std::back_inserter(raw), [](auto& d) { return d.count(); });
+		fmt::print(m_stream, "\"{:.4f}\"\n", fmt::join(raw, ","));
+		// Flush so we can watch results come in when writing to file
+		m_stream.flush();
+	}
+};
+
+CATCH_REGISTER_REPORTER("celerity-benchmark-csv", benchmark_csv_reporter)
+
+enum class align : char { left = '<', right = '>', center = '^' };
+
+class markdown_table_printer {
+	struct column {
+		static constexpr size_t min_width = 3;
+		std::string header;
+		size_t width;
+		align alignment;
+	};
+
+  public:
+	markdown_table_printer(const std::vector<std::pair<std::string, align>>& columns) {
+		std::transform(columns.cbegin(), columns.end(), std::back_inserter(this->columns), [](const auto& c) {
+			const auto [name, alignment] = c;
+			return column{name, std::max(column::min_width, name.length()), alignment};
+		});
+	}
+
+	void add_row(std::vector<std::string> cells) {
+		if(cells.size() != columns.size()) { throw std::runtime_error("Column mismatch"); }
+		for(size_t i = 0; i < columns.size(); ++i) {
+			columns[i].width = std::max(columns[i].width, cells[i].length());
+		}
+		rows.push_back(std::move(cells));
+	}
+
+	void print(std::ostream& os) const {
+		// fmt does not allow to set alignment dynamically, so we need a helper function.
+		// Replaces 'A' in fmt_str with '<','>' or '^'.
+		constexpr auto align_fmt = [](std::string fmt_str, align a) {
+			std::replace(fmt_str.begin(), fmt_str.end(), 'A', static_cast<char>(a));
+			return fmt_str;
+		};
+
+		// Print column headers
+		fmt::print(os, "|");
+		for(const auto& [header, width, a] : columns) {
+			fmt::print(os, align_fmt(" {: A{}} |", a), header, width);
+		}
+		fmt::print(os, "\n");
+
+		// Print separators
+		fmt::print(os, "|");
+		for(const auto& [_, width, a] : columns) {
+			const char align_left = a != align::right ? ':' : '-';
+			const char align_right = a != align::left ? ':' : '-';
+			fmt::print(os, align_fmt(" {}{:-A{}}{} |", a), align_left, "", width - 2, align_right);
+		}
+		fmt::print(os, "\n");
+
+		// Print rows
+		for(const auto& r : rows) {
+			fmt::print(os, "|");
+			for(size_t i = 0; i < r.size(); ++i) {
+				fmt::print(os, align_fmt(" {: A{}} |", columns[i].alignment), r[i], columns[i].width);
+			}
+			fmt::print(os, "\n");
+		}
+	}
+
+  private:
+	std::vector<column> columns;
+	std::vector<std::vector<std::string>> rows;
+};
+
+class benchmark_md_reporter : public benchmark_reporter_base {
+  public:
+	using benchmark_reporter_base::benchmark_reporter_base;
+
+	static std::string getDescription() { return "Generates a Markdown report for benchmark results"; }
+
+	void testRunStarting(Catch::TestRunInfo const& testRunInfo) override {
+		benchmark_reporter_base::testRunStarting(testRunInfo);
+
+		fmt::print(m_stream, "# Benchmark Results\n\n");
+
+		markdown_table_printer meta_printer({{"Metadata", align::left}, {"", align::left}});
+		const auto now_gmt = fmt::gmtime(std::time(nullptr));
+		// TODO: It would be cool to also have celerity version, hostname, argv, ...
+		meta_printer.add_row({"Created", fmt::format("{:%FT%TZ}", now_gmt)});
+
+		meta_printer.print(m_stream);
+	}
+
+	void testRunEnded(Catch::TestRunStats const& testRunStats) override {
+		benchmark_reporter_base::testRunEnded(testRunStats);
+		fmt::print(m_stream, "\n\n");
+		results_printer.print(m_stream);
+		fmt::print(m_stream, "\nAll numbers are in nanoseconds.\n");
+	}
+
+	void benchmarkEnded(Catch::BenchmarkStats<> const& benchmarkStats) override {
+		benchmark_reporter_base::benchmarkEnded(benchmarkStats);
+
+		// Format numbers with ' as thousand separator and . as decimal separator.
+		constexpr auto format_result = [](std::chrono::duration<double, std::nano> ns) {
+			// fmt can only do thousands separators based on locale, so we need to do a character replacement afterwards.
+			// Also it only works on integral types, so we need to format the fractional part separately.
+			double integral;
+			const double fractional = std::modf(ns.count(), &integral);
+			auto integral_formatted = fmt::format(std::locale("en_US.UTF-8"), "{:L}", static_cast<int64_t>(integral));
+			std::replace(integral_formatted.begin(), integral_formatted.end(), ',', '\'');
+			const auto fractional_formatted = fmt::format("{:.2f}", fractional).substr(2);
+			return fmt::format("{}.{}", integral_formatted, fractional_formatted);
+		};
+
+		const auto min = std::reduce(benchmarkStats.samples.cbegin(), benchmarkStats.samples.cend(),
+		    std::chrono::duration<double, std::nano>(std::numeric_limits<double>::max()), [](auto& a, auto& b) { return std::min(a, b); });
+
+		results_printer.add_row({fmt::format("{}", escape_md_partial(get_test_case_name())), // Test case
+		    escape_md_partial(benchmarkStats.info.name),                                     // Benchmark name
+		    format_result(min),                                                              // Min
+		    format_result(benchmarkStats.mean.point),                                        // Mean
+		    format_result(benchmarkStats.standardDeviation.point)});                         // Std dev
+	}
+
+  private:
+	markdown_table_printer results_printer{
+	    {{"Test case", align::left}, {"Benchmark name", align::left}, {"Min", align::right}, {"Mean", align::right}, {"Std dev", align::right}}};
+};
+
+CATCH_REGISTER_REPORTER("celerity-benchmark-md", benchmark_md_reporter)