AMD Ryzen 5 5500U testing with a LENOVO LNVNB161216 (GLCN22WW BIOS) and AMD Lucienne 2GB on Ubuntu 21.10 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2203306-PTS-ONEDNN5567
onednn 5500U,
"oneDNN 2.6 - Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",14.4963,14.4974,14.5071
"B",11.3557,11.2056,11.4162
"C",11.4053,11.4424,11.3115
"oneDNN 2.6 - Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",4.55819,4.55498,4.54594
"B",3.59543,3.78304,3.78388,3.79637,3.81473
"C",3.78809,3.66693,3.8348
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",13.2734,13.3169,14.1219,13.9663,12.5843,13.2183,14.2704,13.0235,13.1835,13.9657,13.3796,14.2204,13.2684,14.2638,14.2763
"B",13.1143,13.8868,13.3068,12.7831,14.1699,13.9384,13.5919,14.2178,14.1646,13.9323,14.223,13.3206,12.6028,13.6931,13.6798
"C",12.6596,13.6622,14.1881,12.8889,13.8394,13.3579,14.0683,13.2599,12.2693,12.4068,13.9038,14.1861,12.7322,13.0721,13.3846
"oneDNN 2.6 - Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",3.65794,3.75518,3.77686
"B",3.74233,3.81175,3.83661
"C",3.73445,3.82653,3.82237
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",5.36111,5.60837,5.70217,5.71418,5.68907,5.69562
"B",5.37842,5.62105,5.72265,5.67275,5.7007
"C",5.35252,5.62782,6.26981,5.69737,5.69922,5.68067,5.67184,5.69595,5.69746,5.70786,5.68617,5.69092
"oneDNN 2.6 - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",7113.26,7140.96,7127.25
"B",7090.6,7068.23,7102.27
"C",7026.4,7032.8,7071.61
"oneDNN 2.6 - Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",34.4431,34.4464,34.4683
"B",34.1364,34.1125,34.1244
"C",34.1937,34.1838,34.0983
"oneDNN 2.6 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",7.92915,7.90397,7.88584
"B",7.86413,7.91521,7.89289
"C",7.84226,7.85347,7.86256
"oneDNN 2.6 - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",4696.48,4695.25,4669.45
"B",4664.55,4693.29,4692.44
"C",4654.74,4673.26,4658.06
"oneDNN 2.6 - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",4669.73,4705.11,4709.33
"B",4735.76,4665.79,4702.96
"C",4648.3,4681.33,4700.22
"oneDNN 2.6 - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",7131.94,7088.66,7077.25
"B",7090.67,7085.96,7118.18
"C",7068.84,7052.27,7079.21
"oneDNN 2.6 - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",7083.77,7070.38,7066.88
"B",7088.42,7045.39,7067.66
"C",7113.98,7097.18,7072.38
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",11.7444,11.7721,11.7506
"B",11.7112,11.7625,11.6818
"C",11.7221,11.7434,11.6959
"oneDNN 2.6 - Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",12.0737,12.0816,12.1609
"B",12.0418,12.0946,12.1265
"C",12.1228,12.0539,12.0826
"oneDNN 2.6 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",5.11809,5.11621,5.11941
"B",5.10554,5.11518,5.11861
"C",5.1071,5.12257,5.1216
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",8.03553,8.0137,8.04721
"B",8.0264,8.03385,8.02417
"C",8.01705,8.05853,8.01814
"oneDNN 2.6 - Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",4711.76,4663.73,4689.14
"B",4710.57,4689.86,4671.21
"C",4727.35,4696.38,4647.78
"oneDNN 2.6 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",
"oneDNN 2.6 - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",
"oneDNN 2.6 - Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",36.7568,34.8618,36.5713,34.7135,34.8137,51.2987,34.1807,34.0588,54.7304,33.8288,33.7189,33.72
"B",33.7213,33.809,33.6791
"C",33.7391,33.7225,33.7014
"oneDNN 2.6 - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",
"oneDNN 2.6 - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",