tf-gpu

AMD Ryzen 7 3700X 8-Core testing with a MSI B450M MORTAR (MS-7B89) v1.0 (1.80 BIOS) and eVGA NVIDIA GeForce GTX 1080 Ti 11GB on Arch rolling via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1907316-HV-TFCIFAR1002.

tf-gpuProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionCPUCPU DDR4-2400MTsCPU DDR4-2666MTsCPU MKLCPU No-HTCPU No-HT,DDR4-2400MTsCPU+GPUCPU+GPU DDR4-2666MTsAMD Ryzen 7 3700X 8-Core @ 3.60GHz (8 Cores / 16 Threads)MSI B450M MORTAR (MS-7B89) v1.0 (1.80 BIOS)AMD Starship/Matisse16384MB256GB SAMSUNG MZVLW256HEHP-00000 + 240GB KINGSTON SA400S3eVGA NVIDIA GeForce GTX 1080 Ti 11GB (1480/5508MHz)NVIDIA GP102 HDMI AudioRealtek RTL8111/8168/8411 + Qualcomm Atheros AR9287Arch rolling5.2.1-arch1-1-ARCH (x86_64)X Server 1.20.5NVIDIA 430.344.6.0 NVIDIA 430.34GCC 9.1.0 + CUDA 10.1ext41920x108032768MB16384MB32768MBeVGA NVIDIA GeForce GTX 1080 Ti 11GB (1556/5726MHz)OpenBenchmarking.orgProcessor Details- Scaling Governor: acpi-cpufreq performancePython Details- Python 3.7.3Security Details- l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: always-on RSB filling

tf-gputensorflow: Cifar10DifferenceStandard ErrorStandard DeviationCPUCPU DDR4-2400MTsCPU DDR4-2666MTsCPU MKLCPU No-HTCPU No-HT,DDR4-2400MTsCPU+GPUCPU+GPU DDR4-2666MTs24.771.43x0.030.20%28.441.34x0.020.09%27.371.37x0.040.27%43.381.00x0.180.73%26.581.39x0.010.06%30.081.31x0.050.26%15.651.64x0.030.30%16.561.62x0.020.24%OpenBenchmarking.org

Tensorflow

Build: Cifar10

OpenBenchmarking.orgSeconds, Fewer Is BetterTensorflow 2017-02-03Build: Cifar10CPUCPU DDR4-2400MTsCPU DDR4-2666MTsCPU MKLCPU No-HTCPU No-HT,DDR4-2400MTsCPU+GPUCPU+GPU DDR4-2666MTs1020304050SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 324.7728.4427.3743.3826.5830.0815.6516.56

Phoronix Test Suite v10.8.4