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.


NVIDIA GeForce GTX 1070: 

	Processor: Intel Core i9-9900K @ 5.00GHz (8 Cores / 16 Threads), Motherboard: ASUS PRIME Z390-A (0602 BIOS), Chipset: Intel Cannon Lake PCH Shared SRAM, Memory: 16384MB, Disk: 2000GB SABRENT + Samsung SSD 970 EVO 250GB, Graphics: NVIDIA GeForce GTX 1070 8GB (1506/4006MHz), Audio: Realtek ALC1220, Monitor: Acer B286HK, Network: Intel I219-V

	OS: Ubuntu 18.04, Kernel: 4.20.0-042000-generic (x86_64), Desktop: Xfce 4.12, Display Server: X Server 1.19.6, Display Driver: NVIDIA 415.25, OpenGL: 4.6.0, OpenCL: OpenCL 1.2 CUDA 10.0.132, Vulkan: 1.1.84, Compiler: GCC 7.3.0 + LLVM 6.0.0 + CUDA 10.0, File-System: ext4, Screen Resolution: 3840x2160


PlaidML
FP16: Yes - Mode: Inference - Network: Inception V3 - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 115.33 |=============================================


PlaidML
FP16: No - Mode: Inference - Network: Inception V3 - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 113.60 |=============================================


PlaidML
FP16: Yes - Mode: Inference - Network: ResNet 50 - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 234.66 |=============================================


PlaidML
FP16: Yes - Mode: Inference - Network: Mobilenet - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 654.58 |=============================================


PlaidML
FP16: No - Mode: Inference - Network: ResNet 50 - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 256.52 |=============================================


PlaidML
FP16: No - Mode: Inference - Network: Mobilenet - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 748.26 |=============================================


PlaidML
FP16: Yes - Mode: Inference - Network: VGG19 - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 108.09 |=============================================


PlaidML
FP16: Yes - Mode: Inference - Network: VGG16 - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 126.31 |=============================================


PlaidML
FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 10.30 |==============================================


PlaidML
FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 39.85 |==============================================


PlaidML
FP16: No - Mode: Inference - Network: VGG19 - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 108.42 |=============================================


PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: OpenCL
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 129.06 |=============================================


PlaidML
FP16: Yes - Mode: Inference - Network: VGG19 - Device: CPU
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 2.58 |===============================================


PlaidML
FP16: Yes - Mode: Inference - Network: VGG16 - Device: CPU
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 2.88 |===============================================


PlaidML
FP16: No - Mode: Inference - Network: VGG19 - Device: CPU
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 3.71 |===============================================


PlaidML
FP16: No - Mode: Inference - Network: VGG16 - Device: CPU
Examples Per Second > Higher Is Better
NVIDIA GeForce GTX 1070 . 4.39 |===============================================