mkl-dnn-O3native
AMD Ryzen 7 2700 Eight-Core testing with a ASRock X470 Master SLI (P3.70 BIOS) and Zotac NVIDIA GeForce GTX 550 Ti 1GB on Mageia 9 via the Phoronix Test Suite.


mga9-O3native: 

	Processor: AMD Ryzen 7 2700 Eight-Core @ 4.05GHz (8 Cores / 16 Threads), Motherboard: ASRock X470 Master SLI (P3.70 BIOS), Chipset: AMD 17h, Memory: 16GB, Disk: Samsung SSD 970 EVO 250GB + 525GB Crucial CT525MX3 + 1000GB Seagate ST31000528AS + 512GB INTEL SSDSCKKW51, Graphics: Zotac NVIDIA GeForce GTX 550 Ti 1GB, Audio: NVIDIA GF116 HD Audio, Monitor: DELL U2412M, Network: Intel I211

	OS: Mageia 9, Kernel: 5.11.6-desktop-4.mga9 (x86_64), Desktop: KDE Plasma 5.21.2, Display Server: X Server 1.20.10, Display Driver: NVIDIA 390.141, OpenGL: 4.6.0, Compiler: GCC 10.2.1 20210313 + Clang 12.0.0 + LLVM 12.0.0, File-System: ext4, Screen Resolution: 1920x1200


oneDNN MKL-DNN 1.3
Harness: IP Batch 1D - Data Type: f32
ms < Lower Is Better
mga9-O3native . 7.53791 |======================================================


oneDNN MKL-DNN 1.3
Harness: IP Batch All - Data Type: f32
ms < Lower Is Better
mga9-O3native . 109.94 |=======================================================


oneDNN MKL-DNN 1.3
Harness: Deconvolution Batch deconv_1d - Data Type: f32
ms < Lower Is Better
mga9-O3native . 8.39442 |======================================================


oneDNN MKL-DNN 1.3
Harness: Deconvolution Batch deconv_3d - Data Type: f32
ms < Lower Is Better
mga9-O3native . 12.17 |========================================================


oneDNN MKL-DNN 1.3
Harness: Recurrent Neural Network Training - Data Type: f32
ms < Lower Is Better
mga9-O3native . 498.70 |=======================================================


oneDNN MKL-DNN 1.3
Harness: Recurrent Neural Network Inference - Data Type: f32
ms < Lower Is Better
mga9-O3native . 49.47 |========================================================