python Intel Core i9-7980XE testing with a ASRock X299 Taichi XE (P1.60 BIOS) and eVGA NVIDIA GeForce GTX 970 4GB on Gentoo/Linux via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/1911216-HV-PYTHON92677&grw&sro .
python Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Display Server Display Driver Vulkan Compiler File-System Screen Resolution LTO PGO STATIC LTO PGO LTO no SEMINTERPOS no SEMINTERPOS 2 Intel Core i9-7980XE @ 4.40GHz (18 Cores / 36 Threads) ASRock X299 Taichi XE (P1.60 BIOS) Intel Sky Lake-E DMI3 Registers 129024MB 960GB INTEL SSDPED1D960GAY + 2000GB Western Digital WD20EARS-00S + 2000GB Seagate ST2000DM001-1CH1 + 3 x 2000GB Seagate ST2000DM001-1ER1 + 2000GB Western Digital WD20EARS-00M + 250GB HITACHI HTS54322 eVGA NVIDIA GeForce GTX 970 4GB (135/324MHz) Realtek ALC1220 Intel I219-V + Intel I211 + Intel Dual Band-AC 3168NGW Gentoo/Linux 5.0.17-gentoo (x86_64) X Server 1.20.5 modesetting 1.20.5 1.1.119 GCC 9.2.0 + Clang 9.0.0 + LLVM 9.0.0 + CUDA 10.1 ext4 3840x1080 OpenBenchmarking.org Disk Details - NONE / noatime,rw Processor Details - Scaling Governor: intel_pstate performance Python Details - Python 3.6.9 Security Details - l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling
python compilebench: Compile compilebench: Initial Create compilebench: Read Compiled Tree cython-bench: numpy: pybench: Total For Average Test Times LTO PGO STATIC LTO PGO LTO no SEMINTERPOS no SEMINTERPOS 2 2389 549 2775 20.95 4809434 1050 2425 560 2795 21.30 4812236 1049 2408 558 2794 22.99 4826106 1212 22.46 5134657 1213 OpenBenchmarking.org
Compile Bench Test: Compile OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile LTO LTO PGO LTO PGO STATIC 500 1000 1500 2000 2500 SE +/- 7.39, N = 3 SE +/- 10.22, N = 3 SE +/- 12.80, N = 3 2408 2425 2389
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create LTO LTO PGO LTO PGO STATIC 120 240 360 480 600 SE +/- 1.69, N = 3 SE +/- 2.43, N = 3 SE +/- 2.49, N = 3 558 560 549
Compile Bench Test: Read Compiled Tree OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree LTO LTO PGO LTO PGO STATIC 600 1200 1800 2400 3000 SE +/- 16.47, N = 3 SE +/- 28.25, N = 3 SE +/- 18.44, N = 3 2794 2795 2775
Cython benchmark OpenBenchmarking.org Seconds, Fewer Is Better Cython benchmark 0.27 LTO LTO PGO LTO PGO STATIC no SEMINTERPOS 2 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 22.99 21.30 20.95 22.46
Numpy Benchmark OpenBenchmarking.org Nanoseconds, Fewer Is Better Numpy Benchmark LTO LTO PGO LTO PGO STATIC no SEMINTERPOS 2 1.1M 2.2M 3.3M 4.4M 5.5M 4826106 4812236 4809434 5134657
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times LTO LTO PGO LTO PGO STATIC no SEMINTERPOS 2 300 600 900 1200 1500 SE +/- 2.65, N = 3 SE +/- 1.15, N = 3 SE +/- 3.61, N = 3 1212 1049 1050 1213
Phoronix Test Suite v10.8.5