From c859c0e990994e55332d9ff923940e9b1a299a3f Mon Sep 17 00:00:00 2001 From: Kokkos Developers Date: Wed, 11 Jan 2023 02:37:39 +0000 Subject: [PATCH] Update from https://github.com/kokkos/kokkos/commit/57504c4b250a82edf2a153134a7ca44388ca1d18 --- ...ceTest_Benchmark_2023-01-11_T02-35-10.json | 646 ++++++++++++++++++ 1 file changed, 646 insertions(+) create mode 100644 ubuntu:latest-g++-OPENMP/KokkosCore_PerformanceTest_Benchmark_2023-01-11_T02-35-10.json diff --git a/ubuntu:latest-g++-OPENMP/KokkosCore_PerformanceTest_Benchmark_2023-01-11_T02-35-10.json b/ubuntu:latest-g++-OPENMP/KokkosCore_PerformanceTest_Benchmark_2023-01-11_T02-35-10.json new file mode 100644 index 00000000..c8701539 --- /dev/null +++ b/ubuntu:latest-g++-OPENMP/KokkosCore_PerformanceTest_Benchmark_2023-01-11_T02-35-10.json @@ -0,0 +1,646 @@ +{ + "context": { + "date": "2023-01-11T02:36:34+00:00", + "host_name": "15324f694b54", + "executable": "/__w/kokkos/kokkos/builddir/core/perf_test/KokkosCore_PerformanceTest_Benchmark", + "num_cpus": 2, + "mhz_per_cpu": 2095, + "cpu_scaling_enabled": false, + "caches": [ + { + "type": "Data", + "level": 1, + "size": 32768, + "num_sharing": 1 + }, + { + "type": "Instruction", + "level": 1, + "size": 32768, + "num_sharing": 1 + }, + { + "type": "Unified", + "level": 2, + "size": 1048576, + "num_sharing": 1 + }, + { + "type": "Unified", + "level": 3, + "size": 37486592, + "num_sharing": 2 + } + ], + "load_avg": [1.67285,0.805176,0.318359], + "library_build_type": "release", + "CPU architecture": "none", + "Default Device": "N6Kokkos6OpenMPE", + "GIT_BRANCH": "develop", + "GIT_CLEAN_STATUS": "CLEAN", + "GIT_COMMIT_DATE": "2023-01-10T21:33:21-05:00", + "GIT_COMMIT_DESCRIPTION": "Merge pull request #5698 from masterleinad/static_assert_reducer", + "GIT_COMMIT_HASH": "57504c4", + "GPU architecture": "none", + "KOKKOS_COMPILER_GNU": "1130", + "KOKKOS_ENABLE_ASM": "yes", + "KOKKOS_ENABLE_CXX17": "yes", + "KOKKOS_ENABLE_CXX20": "no", + "KOKKOS_ENABLE_CXX23": "no", + "KOKKOS_ENABLE_DEBUG_BOUNDS_CHECK": "no", + "KOKKOS_ENABLE_GNU_ATOMICS": "no", + "KOKKOS_ENABLE_HBWSPACE": "no", + "KOKKOS_ENABLE_HWLOC": "yes", + "KOKKOS_ENABLE_INTEL_ATOMICS": "no", + "KOKKOS_ENABLE_INTEL_MM_ALLOC": "no", + "KOKKOS_ENABLE_LIBDL": "yes", + "KOKKOS_ENABLE_LIBRT": "no", + "KOKKOS_ENABLE_OPENMP": "yes", + "KOKKOS_ENABLE_OPENMP_ATOMICS": "no", + "KOKKOS_ENABLE_PRAGMA_IVDEP": "no", + "KOKKOS_ENABLE_PRAGMA_LOOPCOUNT": "no", + "KOKKOS_ENABLE_PRAGMA_UNROLL": "no", + "KOKKOS_ENABLE_PRAGMA_VECTOR": "no", + "KOKKOS_ENABLE_WINDOWS_ATOMICS": "no", + "Kokkos": "OpenMP thread_pool_topology[ 1 x 2 x 1 ]", + "Kokkos Version": "3.7.99" + }, + "benchmarks": [ + { + "name": "ViewDeepCopy_Rank1/N:10/manual_time", + "family_index": 0, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank1/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.3834079299999994e-02, + "cpu_time": 7.2954030000000003e-02, + "time_unit": "s", + "FOM: GB/s": 2.1670209951409255e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank2/N:10/manual_time", + "family_index": 1, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank2/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.2254265200000015e-02, + "cpu_time": 7.2201139999999997e-02, + "time_unit": "s", + "FOM: GB/s": 2.2144021471551824e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank3/N:10/manual_time", + "family_index": 2, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank3/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.2513294300000003e-02, + "cpu_time": 7.2434110000000024e-02, + "time_unit": "s", + "FOM: GB/s": 2.2064919480564818e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank1/N:10/manual_time", + "family_index": 3, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank1/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.2456799399999994e-02, + "cpu_time": 7.2345980000000060e-02, + "time_unit": "s", + "FOM: GB/s": 2.2082123599845346e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank2/N:10/manual_time", + "family_index": 4, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank2/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 9, + "real_time": 7.2277169333333335e-02, + "cpu_time": 7.2241544444444486e-02, + "time_unit": "s", + "FOM: GB/s": 2.2137004184834609e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank3/N:10/manual_time", + "family_index": 5, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank3/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 9, + "real_time": 7.2496910444444451e-02, + "cpu_time": 7.2464066666666743e-02, + "time_unit": "s", + "FOM: GB/s": 2.2069906016561987e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank1/N:10/manual_time", + "family_index": 6, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank1/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 9, + "real_time": 7.2480298555555558e-02, + "cpu_time": 7.2449622222222246e-02, + "time_unit": "s", + "FOM: GB/s": 2.2074964257681874e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank2/N:10/manual_time", + "family_index": 7, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank2/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 2.8691352300000000e-01, + "cpu_time": 2.8400494999999992e-01, + "time_unit": "s", + "FOM: GB/s": 5.5765931952952945e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank3/N:10/manual_time", + "family_index": 8, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank3/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 3.4917799100000002e-01, + "cpu_time": 3.4775530000000021e-01, + "time_unit": "s", + "FOM: GB/s": 4.5821902904527567e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank1/N:10/manual_time", + "family_index": 9, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank1/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.2228760699999991e-02, + "cpu_time": 7.2202809999999923e-02, + "time_unit": "s", + "FOM: GB/s": 2.2151840686365261e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank2/N:10/manual_time", + "family_index": 10, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank2/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 2.8599699000000001e-01, + "cpu_time": 2.8587329999999866e-01, + "time_unit": "s", + "FOM: GB/s": 5.5944644732100155e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank3/N:10/manual_time", + "family_index": 11, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank3/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 2.7039284299999999e-01, + "cpu_time": 2.6758180000000031e-01, + "time_unit": "s", + "FOM: GB/s": 5.9173163839991139e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank4/N:10/manual_time", + "family_index": 12, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank4/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.1776876599999997e-02, + "cpu_time": 7.1747759999999869e-02, + "time_unit": "s", + "FOM: GB/s": 2.2291301541532945e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank5/N:10/manual_time", + "family_index": 13, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank5/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.3468862700000012e-02, + "cpu_time": 7.2680420000000009e-02, + "time_unit": "s", + "FOM: GB/s": 2.1777933415593758e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank4/N:10/manual_time", + "family_index": 14, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank4/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 9, + "real_time": 7.5009641333333335e-02, + "cpu_time": 7.1881122222222080e-02, + "time_unit": "s", + "FOM: GB/s": 2.1330591262125932e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank5/N:10/manual_time", + "family_index": 15, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank5/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 9, + "real_time": 7.4411384999999983e-02, + "cpu_time": 7.3223366666666900e-02, + "time_unit": "s", + "FOM: GB/s": 2.1502086004715547e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank4/N:10/manual_time", + "family_index": 16, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank4/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 3.4485665450000003e-01, + "cpu_time": 3.4479039999999905e-01, + "time_unit": "s", + "FOM: GB/s": 4.6396088900178087e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank5/N:10/manual_time", + "family_index": 17, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank5/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 3.5070291399999998e-01, + "cpu_time": 3.4858200000000039e-01, + "time_unit": "s", + "FOM: GB/s": 4.5622660551945122e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank4/N:10/manual_time", + "family_index": 18, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank4/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 3.5118120549999998e-01, + "cpu_time": 3.4963169999999977e-01, + "time_unit": "s", + "FOM: GB/s": 4.5560524735997019e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank5/N:10/manual_time", + "family_index": 19, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank5/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 3.4915155100000000e-01, + "cpu_time": 3.4737549999999828e-01, + "time_unit": "s", + "FOM: GB/s": 4.5825372833586524e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank6/N:10/manual_time", + "family_index": 20, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank6/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.3627496499999986e-02, + "cpu_time": 7.2175319999999488e-02, + "time_unit": "s", + "FOM: GB/s": 2.1731011864568831e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank6/N:10/manual_time", + "family_index": 21, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank6/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.1501684000000010e-02, + "cpu_time": 7.1487700000000126e-02, + "time_unit": "s", + "FOM: GB/s": 2.2377095342257952e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank6/N:10/manual_time", + "family_index": 22, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank6/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 3.6922782550000000e-01, + "cpu_time": 3.6423700000000281e-01, + "time_unit": "s", + "FOM: GB/s": 4.3333678815601617e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank6/N:10/manual_time", + "family_index": 23, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank6/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 2, + "real_time": 3.6605848200000002e-01, + "cpu_time": 3.6327070000000106e-01, + "time_unit": "s", + "FOM: GB/s": 4.3708862891476450e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank7/N:10/manual_time", + "family_index": 24, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank7/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.2849745200000010e-02, + "cpu_time": 7.2095399999999893e-02, + "time_unit": "s", + "FOM: GB/s": 2.1963014360687154e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank7/N:10/manual_time", + "family_index": 25, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank7/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.2211299499999992e-02, + "cpu_time": 7.2169299999999478e-02, + "time_unit": "s", + "FOM: GB/s": 2.2157197157212224e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank7/N:10/manual_time", + "family_index": 26, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank7/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 1, + "real_time": 5.4014887099999997e-01, + "cpu_time": 5.3986880000000070e-01, + "time_unit": "s", + "FOM: GB/s": 2.9621463376158759e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank7/N:10/manual_time", + "family_index": 27, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank7/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 1, + "real_time": 5.0056853000000001e-01, + "cpu_time": 5.0025279999999839e-01, + "time_unit": "s", + "FOM: GB/s": 3.1963655405984075e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank8/N:10/manual_time", + "family_index": 28, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank8/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.2960688199999998e-02, + "cpu_time": 7.2366390000000530e-02, + "time_unit": "s", + "FOM: GB/s": 2.1929617708841732e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank8/N:10/manual_time", + "family_index": 29, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank8/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 10, + "real_time": 7.4522200199999999e-02, + "cpu_time": 7.3112679999999847e-02, + "time_unit": "s", + "FOM: GB/s": 2.1470112204228776e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank8/N:10/manual_time", + "family_index": 30, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank8/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 1, + "real_time": 6.6370720200000000e-01, + "cpu_time": 6.3327539999999516e-01, + "time_unit": "s", + "FOM: GB/s": 2.4107015792183617e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Rank8/N:10/manual_time", + "family_index": 31, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Rank8/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 1, + "real_time": 6.5592244200000005e-01, + "cpu_time": 6.5424859999999541e-01, + "time_unit": "s", + "FOM: GB/s": 2.4393127869224513e+00, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Raw/N:10/manual_time", + "family_index": 32, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Raw/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 9, + "real_time": 7.7128109000000014e-02, + "cpu_time": 7.7057399999999471e-02, + "time_unit": "s", + "FOM: GB/s": 2.0744706706085584e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Raw/N:10/manual_time", + "family_index": 33, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Raw/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 9, + "real_time": 7.8779241111111106e-02, + "cpu_time": 7.7993300000000446e-02, + "time_unit": "s", + "FOM: GB/s": 2.0309918925765512e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Raw/N:10/manual_time", + "family_index": 34, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Raw/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 9, + "real_time": 7.9591110555555566e-02, + "cpu_time": 7.8859244444444698e-02, + "time_unit": "s", + "FOM: GB/s": 2.0102747515794249e+01, + "MB": 8.0000000000000000e+02 + }, + { + "name": "ViewDeepCopy_Raw/N:10/manual_time", + "family_index": 35, + "per_family_instance_index": 0, + "run_name": "ViewDeepCopy_Raw/N:10/manual_time", + "run_type": "iteration", + "repetitions": 1, + "repetition_index": 0, + "threads": 1, + "iterations": 8, + "real_time": 7.7342854249999995e-02, + "cpu_time": 7.7297074999999715e-02, + "time_unit": "s", + "FOM: GB/s": 2.0687108272836984e+01, + "MB": 8.0000000000000000e+02 + } + ] +}