oneDNN Core i5 4670, "oneDNN 2.0 - Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU", Lower Results Are Better "1",11.1797,12.0056,11.1899,11.2202,11.2129,11.2475 "2",11.3371,11.3698,11.3309 "3",11.2961,11.1616,11.2167 "oneDNN 2.0 - Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU", Lower Results Are Better "1",16.5623,16.7445,16.5105 "2",16.3641,16.3023,16.3265 "3",16.2469,16.3288,16.1777 "oneDNN 2.0 - Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "1",6.33609,6.3463,6.35604 "2",6.24075,6.36848,6.26421 "3",6.34617,6.35706,6.38621 "oneDNN 2.0 - Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "1",5.63124,5.64703,5.63876 "2",5.49282,5.53779,5.50637 "3",5.50875,5.54051,5.5262 "oneDNN 2.0 - Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU", Lower Results Are Better "1",31.4355,31.4113,31.3405 "2",31.0587,31.4167,31.4034 "3",31.4124,31.4041,31.3705 "oneDNN 2.0 - Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU", Lower Results Are Better "1",12.6367,12.5711,12.5566 "2",12.6273,12.5888,12.5871 "3",12.5831,12.6361,12.6653 "oneDNN 2.0 - Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU", Lower Results Are Better "1",17.6835,17.547,17.7245 "2",18.0307,17.7038,18.1715 "3",17.722,17.7706,17.6385 "oneDNN 2.0 - Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "1",31.2185,31.2813,29.8798 "2",31.2001,31.2751,31.1143 "3",31.1397,31.2468,31.1622 "oneDNN 2.0 - Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "1",15.0978,15.1019,15.3867 "2",15.1555,15.1403,15.1833 "3",15.1395,15.1575,15.1399 "oneDNN 2.0 - Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "1",13.8157,13.8503,13.8474 "2",13.8072,13.8432,13.8305 "3",13.8691,14.0561,13.856 "oneDNN 2.0 - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU", Lower Results Are Better "1",8753.8,9000.64,9102.38 "2",8829.94,9092.28,9167.56 "3",8832.25,9015,9174.6 "oneDNN 2.0 - Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU", Lower Results Are Better "1",5462.03,5522.77,5540.06 "2",5558.84,5531.59,5525.84 "3",5600.53,5515.55,5571.99 "oneDNN 2.0 - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "1",9253.13,9396.15,9366.51 "2",9090.06,9175.54,9190.19 "3",9222.56,9337.27,9343.7 "oneDNN 2.0 - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "1",5450.21,5503.8,5596.55 "2",5550.51,5512.76,5660.41 "3",5542.95,5603.88,5600.61 "oneDNN 2.0 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU", Lower Results Are Better "1",7.8231,7.83673,7.8258 "2",8.94776,8.54874,8.25216,7.79631,7.79569,7.79517,8.51347,8.54175,8.27319,8.36446,8.59318,8.92645,8.46758,7.79646,7.78506 "3",7.95014,8.65104,8.26851,9.02696,8.21204,7.78691,7.79392,7.80487,7.93109,9.0258,9.06429,7.78947 "oneDNN 2.0 - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "1",9189.08,9197.98,9196.79 "2",9216.17,9646.85,9141.75 "3",9177.11,9229.43,9098.51 "oneDNN 2.0 - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU", Lower Results Are Better "1",5640.97,5639.62,5576.15 "2",5574.48,5571.49,5529.49 "3",5662.33,5544.5,5564.61 "oneDNN 2.0 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU", Lower Results Are Better "1",7.50177,7.54136,7.52057 "2",7.50458,7.52106,7.50815 "3",7.50603,7.51517,7.54809