PlaidML CPU + OpenCL Linux Benchmarks

Intel Core i9-9900K testing with a ASUS PRIME Z390-A (0602 BIOS) and NVIDIA GeForce GTX 1060 6GB on Ubuntu 18.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1901287-SP-PLAIDMLCP74.

PlaidML CPU + OpenCL Linux BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLVulkanCompilerFile-SystemScreen Resolution9900K + GTX 1060Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads)ASUS PRIME Z390-A (0602 BIOS)Intel Cannon Lake PCH Shared SRAM16384MBSamsung SSD 970 EVO 250GB + 2000GB SABRENTNVIDIA GeForce GTX 1060 6GB (1506/4006MHz)Realtek ALC1220Acer B286HKIntel I219-VUbuntu 18.104.20.3-042003-generic (x86_64)GNOME Shell 3.30.1X Server 1.20.1NVIDIA 415.274.6.0OpenCL 1.2 CUDA 10.0.1321.1.84GCC 8.2.0ext43840x2160OpenBenchmarking.org- Scaling Governor: intel_pstate performance- GPU Compute Cores: 1280- Python 2.7.15+ + Python 3.6.7- __user pointer sanitization + Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + SSB disabled via prctl and seccomp

PlaidML CPU + OpenCL Linux Benchmarksplaidml: No - Inference - VGG16 - CPUplaidml: No - Inference - VGG19 - CPUplaidml: No - Training - VGG16 - OpenCLplaidml: No - Training - VGG19 - OpenCLplaidml: No - Inference - VGG16 - OpenCLplaidml: No - Inference - VGG19 - OpenCLplaidml: No - Inference - IMDB LSTM - CPUplaidml: No - Inference - Mobilenet - CPUplaidml: No - Inference - ResNet 50 - CPUplaidml: No - Training - IMDB LSTM - OpenCLplaidml: No - Training - Mobilenet - OpenCLplaidml: No - Training - ResNet 50 - OpenCLplaidml: No - Inference - DenseNet 201 - CPUplaidml: No - Inference - IMDB LSTM - OpenCLplaidml: No - Inference - Mobilenet - OpenCLplaidml: No - Inference - NASNer Large - CPUplaidml: No - Inference - ResNet 50 - OpenCLplaidml: No - Training - DenseNet 201 - OpenCLplaidml: No - Training - Inception V3 - OpenCLplaidml: No - Training - NASNer Large - OpenCLplaidml: No - Inference - DenseNet 201 - OpenCLplaidml: No - Inference - Inception V3 - OpenCLplaidml: No - Inference - NASNer Large - OpenCL9900K + GTX 10604.383.722679.072688.1095.1079.591.7837.9310.3513687.251574.063.281835930.85196701.6322.45416.5264.0286.1818.44OpenBenchmarking.org

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPU9900K + GTX 10600.98551.9712.95653.9424.9275SE +/- 0.00, N = 34.38

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPU9900K + GTX 10600.8371.6742.5113.3484.185SE +/- 0.00, N = 33.72

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: VGG16 - Device: OpenCL9900K + GTX 10606001200180024003000SE +/- 13.17, N = 32679.07

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: VGG19 - Device: OpenCL9900K + GTX 10606001200180024003000SE +/- 7.68, N = 32688.10

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL9900K + GTX 106020406080100SE +/- 0.04, N = 395.10

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL9900K + GTX 106020406080100SE +/- 0.03, N = 379.59

PlaidML

FP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU9900K + GTX 10600.40050.8011.20151.6022.0025SE +/- 0.00, N = 31.78

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: CPU9900K + GTX 1060918273645SE +/- 0.06, N = 337.93

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU9900K + GTX 1060369121510.35

PlaidML

FP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCL9900K + GTX 1060306090120150SE +/- 0.07, N = 3136

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL9900K + GTX 106020406080100SE +/- 0.06, N = 387.25

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: ResNet 50 - Device: OpenCL9900K + GTX 1060300600900120015001574.06

PlaidML

FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU9900K + GTX 10600.7381.4762.2142.9523.69SE +/- 0.00, N = 33.28

PlaidML

FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL9900K + GTX 10604080120160200SE +/- 0.11, N = 3183

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL9900K + GTX 1060130260390520650SE +/- 0.90, N = 3593

PlaidML

FP16: No - Mode: Inference - Network: NASNer Large - Device: CPU

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: NASNer Large - Device: CPU9900K + GTX 10600.19130.38260.57390.76520.9565SE +/- 0.00, N = 30.85

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL9900K + GTX 10604080120160200SE +/- 0.10, N = 3196

PlaidML

FP16: No - Mode: Training - Network: DenseNet 201 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: DenseNet 201 - Device: OpenCL9900K + GTX 1060150300450600750SE +/- 7.34, N = 3701.63

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: Inception V3 - Device: OpenCL9900K + GTX 1060510152025SE +/- 0.02, N = 322.45

PlaidML

FP16: No - Mode: Training - Network: NASNer Large - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Training - Network: NASNer Large - Device: OpenCL9900K + GTX 106090180270360450SE +/- 3.12, N = 3416.52

PlaidML

FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL9900K + GTX 10601428425670SE +/- 0.01, N = 364.02

PlaidML

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

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL9900K + GTX 106020406080100SE +/- 0.09, N = 386.18

PlaidML

FP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL

OpenBenchmarking.orgExamples Per Second, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL9900K + GTX 1060510152025SE +/- 0.01, N = 318.44

Phoronix Test Suite v10.8.4