RX 590 PlaidML Intel Core i9-9900K testing with a ASUS PRIME Z390-A (0602 BIOS) and Sapphire AMD Radeon RX 470/480/570/570X/580/580X 8GB on Ubuntu 18.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/1901306-SP-RX590PLAI91 .
RX 590 PlaidML Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL OpenCL Vulkan Compiler File-System Screen Resolution RX 590 Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads) ASUS PRIME Z390-A (0602 BIOS) Intel Cannon Lake PCH Shared SRAM 16384MB Samsung SSD 970 EVO 250GB + 2000GB SABRENT Sapphire AMD Radeon RX 470/480/570/570X/580/580X 8GB (1560/2100MHz) Realtek ALC1220 Acer B286HK Intel I219-V Ubuntu 18.10 5.0.0-050000rc4-generic (x86_64) 20190127 GNOME Shell 3.30.1 X Server 1.20.1 4.5 Mesa 19.0.0-devel padoka PPA (LLVM 9.0.0) OpenCL 2.1 AMD-APP (2783.0) 1.1.90 GCC 8.2.0 ext4 3840x2160 OpenBenchmarking.org - Scaling Governor: intel_pstate performance - 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
RX 590 PlaidML plaidml: No - Training - VGG16 - OpenCL plaidml: No - Training - VGG19 - OpenCL plaidml: No - Inference - VGG16 - OpenCL plaidml: No - Inference - VGG19 - OpenCL plaidml: Yes - Inference - VGG16 - OpenCL plaidml: Yes - Inference - VGG19 - OpenCL plaidml: No - Training - IMDB LSTM - OpenCL plaidml: No - Training - Mobilenet - OpenCL plaidml: No - Training - ResNet 50 - OpenCL plaidml: No - Inference - IMDB LSTM - OpenCL plaidml: No - Inference - Mobilenet - OpenCL plaidml: No - Inference - ResNet 50 - OpenCL plaidml: Yes - Inference - Mobilenet - OpenCL plaidml: Yes - Inference - ResNet 50 - OpenCL plaidml: No - Training - Inception V3 - OpenCL plaidml: No - Inference - DenseNet 201 - OpenCL plaidml: No - Inference - Inception V3 - OpenCL plaidml: No - Inference - NASNer Large - OpenCL RX 590 9.50 8.95 68.98 59.18 64.21 56.08 145 45.74 17.78 220 455 142.77 603.17 137 14.90 61.89 75.70 20.02 OpenBenchmarking.org
PlaidML FP16: No - Mode: Training - Network: VGG16 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Training - Network: VGG16 - Device: OpenCL RX 590 3 6 9 12 15 SE +/- 0.01, N = 3 9.50
PlaidML FP16: No - Mode: Training - Network: VGG19 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Training - Network: VGG19 - Device: OpenCL RX 590 3 6 9 12 15 SE +/- 0.00, N = 3 8.95
PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL RX 590 15 30 45 60 75 SE +/- 0.02, N = 3 68.98
PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL RX 590 13 26 39 52 65 SE +/- 0.01, N = 3 59.18
PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL RX 590 14 28 42 56 70 SE +/- 0.01, N = 3 64.21
PlaidML FP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCL RX 590 13 26 39 52 65 SE +/- 0.01, N = 3 56.08
PlaidML FP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Training - Network: IMDB LSTM - Device: OpenCL RX 590 30 60 90 120 150 SE +/- 0.02, N = 3 145
PlaidML FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Training - Network: Mobilenet - Device: OpenCL RX 590 10 20 30 40 50 SE +/- 0.01, N = 3 45.74
PlaidML FP16: No - Mode: Training - Network: ResNet 50 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Training - Network: ResNet 50 - Device: OpenCL RX 590 4 8 12 16 20 SE +/- 0.00, N = 3 17.78
PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: OpenCL RX 590 50 100 150 200 250 SE +/- 0.88, N = 3 220
PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL RX 590 100 200 300 400 500 SE +/- 0.37, N = 3 455
PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL RX 590 30 60 90 120 150 SE +/- 0.06, N = 3 142.77
PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL RX 590 130 260 390 520 650 SE +/- 1.63, N = 3 603.17
PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL RX 590 30 60 90 120 150 SE +/- 0.03, N = 3 137
PlaidML FP16: No - Mode: Training - Network: Inception V3 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Training - Network: Inception V3 - Device: OpenCL RX 590 4 8 12 16 20 SE +/- 0.00, N = 3 14.90
PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: OpenCL RX 590 14 28 42 56 70 SE +/- 0.08, N = 3 61.89
PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL RX 590 20 40 60 80 100 SE +/- 0.01, N = 3 75.70
PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL OpenBenchmarking.org Examples Per Second, More Is Better PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: OpenCL RX 590 5 10 15 20 25 SE +/- 0.01, N = 3 20.02
Phoronix Test Suite v10.8.4