New Test

Intel Core i9-9900K testing with a ASUS PRIME Z390-A (0602 BIOS) and NVIDIA GeForce GTX 1070 8GB on Ubuntu 18.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1901114-SP-NEWTEST2730&grr.

New TestProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionNVIDIA GeForce GTX 1070Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads)ASUS PRIME Z390-A (0602 BIOS)Intel Cannon Lake PCH Shared SRAM16384MB2000GB SABRENT + Samsung SSD 970 EVO 250GBNVIDIA GeForce GTX 1070 8GB (1506/4006MHz)Realtek ALC1220Acer B286HKIntel I219-VUbuntu 18.044.20.0-042000-generic (x86_64)Xfce 4.12X Server 1.19.6NVIDIA 415.254.6.0OpenCL 1.2 CUDA 10.0.1321.1.84GCC 7.3.0 + LLVM 6.0.0 + CUDA 10.0ext43840x2160OpenBenchmarking.org- Scaling Governor: intel_pstate performance- GPU Compute Cores: 1920- Python 2.7.15rc1 + Python 3.6.7- __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp

New Testplaidml: Yes - Inference - VGG19 - CPUplaidml: Yes - Inference - VGG16 - CPUplaidml: No - Inference - VGG19 - CPUplaidml: No - Inference - VGG16 - CPUplaidml: No - Inference - ResNet 50 - CPUplaidml: No - Inference - Mobilenet - CPUplaidml: No - Inference - Inception V3 - OpenCLplaidml: Yes - Inference - Inception V3 - OpenCLplaidml: Yes - Inference - VGG19 - OpenCLplaidml: No - Inference - VGG19 - OpenCLplaidml: Yes - Inference - VGG16 - OpenCLplaidml: No - Inference - VGG16 - OpenCLplaidml: Yes - Inference - ResNet 50 - OpenCLplaidml: No - Inference - ResNet 50 - OpenCLplaidml: Yes - Inference - Mobilenet - OpenCLplaidml: No - Inference - Mobilenet - OpenCLNVIDIA GeForce GTX 10702.582.883.714.3910.3039.85113.60115.33108.09108.42126.31129.06234.66256.52654.58748.26OpenBenchmarking.org

PlaidML

FP16: Yes - Mode: Inference - Network: VGG19 - Device: CPU

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG19 - Device: CPUNVIDIA GeForce GTX 10700.58051.1611.74152.3222.9025SE +/- 0.00, N = 32.58

PlaidML

FP16: Yes - Mode: Inference - Network: VGG16 - Device: CPU

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG16 - Device: CPUNVIDIA GeForce GTX 10700.6481.2961.9442.5923.24SE +/- 0.01, N = 32.88

PlaidML

FP16: No - Mode: Inference - Network: VGG19 - Device: CPU

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUNVIDIA GeForce GTX 10700.83481.66962.50443.33924.174SE +/- 0.00, N = 33.71

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: CPU

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUNVIDIA GeForce GTX 10700.98781.97562.96343.95124.939SE +/- 0.02, N = 34.39

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUNVIDIA GeForce GTX 1070369121510.30

PlaidML

FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: CPUNVIDIA GeForce GTX 1070918273645SE +/- 0.06, N = 339.85

PlaidML

FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCLNVIDIA GeForce GTX 1070306090120150SE +/- 0.06, N = 3113.60

PlaidML

FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCLNVIDIA GeForce GTX 1070306090120150SE +/- 0.06, N = 3115.33

PlaidML

FP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCLNVIDIA GeForce GTX 107020406080100SE +/- 0.07, N = 3108.09

PlaidML

FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCLNVIDIA GeForce GTX 107020406080100SE +/- 0.10, N = 3108.42

PlaidML

FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCLNVIDIA GeForce GTX 1070306090120150SE +/- 0.15, N = 3126.31

PlaidML

FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCLNVIDIA GeForce GTX 1070306090120150SE +/- 0.12, N = 3129.06

PlaidML

FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCLNVIDIA GeForce GTX 107050100150200250SE +/- 0.26, N = 3234.66

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCLNVIDIA GeForce GTX 107060120180240300SE +/- 0.20, N = 3256.52

PlaidML

FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCLNVIDIA GeForce GTX 1070140280420560700SE +/- 0.92, N = 3654.58

PlaidML

FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCLNVIDIA GeForce GTX 1070160320480640800SE +/- 1.21, N = 3748.26

Phoronix Test Suite v10.8.5