atomicrulez_ubuntu_2310_mkl-dnn
Intel Core i9-10850K testing with a ASUS ROG MAXIMUS XII APEX (2701 BIOS) and NVIDIA GeForce RTX 3090 Ti 24GB on Ubuntu 23.10 via the Phoronix Test Suite.


i9-10850K: 

	Processor: Intel Core i9-10850K @ 5.20GHz (10 Cores / 20 Threads), Motherboard: ASUS ROG MAXIMUS XII APEX (2701 BIOS), Chipset: Intel Comet Lake PCH, Memory: 64GB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: NVIDIA GeForce RTX 3090 Ti 24GB, Audio: Realtek ALC1220, Monitor: ROG PG259QN, Network: Intel I225-V + Intel Comet Lake PCH CNVi WiFi

	OS: Ubuntu 23.10, Kernel: 6.5.0-5-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.104.05, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.138, Compiler: GCC 13.2.0 + CUDA 12.0, File-System: ext4, Screen Resolution: 1920x1080


oneDNN MKL-DNN 1.3
Harness: IP Batch 1D - Data Type: f32
ms < Lower Is Better
i9-10850K . 2.93504 |==========================================================


oneDNN MKL-DNN 1.3
Harness: IP Batch All - Data Type: f32
ms < Lower Is Better
i9-10850K . 43.86 |============================================================


oneDNN MKL-DNN 1.3
Harness: IP Batch 1D - Data Type: u8s8f32
ms < Lower Is Better
i9-10850K . 1.23910 |==========================================================


oneDNN MKL-DNN 1.3
Harness: IP Batch All - Data Type: u8s8f32
ms < Lower Is Better
i9-10850K . 16.84 |============================================================


oneDNN MKL-DNN 1.3
Harness: IP Batch 1D - Data Type: bf16bf16bf16
ms < Lower Is Better


oneDNN MKL-DNN 1.3
Harness: IP Batch All - Data Type: bf16bf16bf16
ms < Lower Is Better


oneDNN MKL-DNN 1.3
Harness: Deconvolution Batch deconv_1d - Data Type: f32
ms < Lower Is Better
i9-10850K . 3.05229 |==========================================================


oneDNN MKL-DNN 1.3
Harness: Deconvolution Batch deconv_3d - Data Type: f32
ms < Lower Is Better
i9-10850K . 4.75091 |==========================================================


oneDNN MKL-DNN 1.3
Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32
ms < Lower Is Better
i9-10850K . 124.52 |===========================================================


oneDNN MKL-DNN 1.3
Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32
ms < Lower Is Better
i9-10850K . 2.18324 |==========================================================


oneDNN MKL-DNN 1.3
Harness: Recurrent Neural Network Training - Data Type: f32
ms < Lower Is Better
i9-10850K . 167.67 |===========================================================


oneDNN MKL-DNN 1.3
Harness: Recurrent Neural Network Inference - Data Type: f32
ms < Lower Is Better
i9-10850K . 25.75 |============================================================


oneDNN MKL-DNN 1.3
Harness: Recurrent Neural Network Training - Data Type: u8s8f32
ms < Lower Is Better


oneDNN MKL-DNN 1.3
Harness: Deconvolution Batch deconv_1d - Data Type: bf16bf16bf16
ms < Lower Is Better


oneDNN MKL-DNN 1.3
Harness: Deconvolution Batch deconv_3d - Data Type: bf16bf16bf16
ms < Lower Is Better


oneDNN MKL-DNN 1.3
Harness: Recurrent Neural Network Inference - Data Type: u8s8f32
ms < Lower Is Better


oneDNN MKL-DNN 1.3
Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16
ms < Lower Is Better


oneDNN MKL-DNN 1.3
Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16
ms < Lower Is Better