AMD Ryzen 9 5900HX testing with a ASUS G513QY v1.0 (G513QY.311 BIOS) and ASUS AMD Cezanne 512MB 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 2203307-PTS-5900HXON51
5900HX oneDNN 2.6,
"oneDNN 2.6 - Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",3.73632,3.75804,3.82739
"B",3.8277,3.83476,3.83245
"C",3.75987,3.81337,3.80929
"oneDNN 2.6 - Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",15.631,15.6913,15.6456
"B",15.102,15.1601,15.0721
"C",14.2017,14.3571,14.4439
"oneDNN 2.6 - Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",1.27444,1.30878,1.31231
"B",1.27459,1.31098,1.30789
"C",1.2818,1.31184,1.31075
"oneDNN 2.6 - Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",3.59135,3.54426,3.53688
"B",3.53463,3.54429,3.55385
"C",3.37424,3.38674,3.39109
"oneDNN 2.6 - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",
"oneDNN 2.6 - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",
"oneDNN 2.6 - Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",31.3969,31.3313,31.264
"B",31.2759,31.2972,31.2906
"C",31.2523,31.2178,31.2061
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",8.3843,8.27914,8.64759
"B",9.00484,8.29741,9.14607,9.1656,8.32322,8.2573,8.67915,8.4153,8.02708,8.49424,8.59683,8.54126,8.45306,8.63956,8.41856
"C",9.25632,9.03621,7.10549,8.42785,9.02715,8.20649,8.17053,8.70923,8.74253,8.97214,8.97019,9.16506
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",6.42573,6.75867,6.48145,6.32493,6.57924,6.59974
"B",6.42113,6.41923,6.40671
"C",6.40219,6.48151,6.36845
"oneDNN 2.6 - Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",33.0737,32.891,32.8288
"B",32.5251,32.8197,32.821
"C",32.418,32.6487,32.4441
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",1.87655,1.89329,1.90004
"B",1.8768,1.89431,1.89493
"C",1.88496,1.89397,1.88786
"oneDNN 2.6 - Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",2.84606,2.79199,2.87126
"B",2.88816,3.12466,2.76462,3.05792,2.85797,3.07438,2.86599,2.82553,2.76959,2.86228,2.71298,2.80293,3.01662,2.69449,2.80443
"C",2.70864,3.3381,2.70361,2.70225,2.71363,3.31265,2.91848,3.08589,2.73078,2.85549,2.87702,3.17973,2.76616,2.801,2.8104
"oneDNN 2.6 - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",3958.84,3944.66,3957.32
"B",3928.83,3922,3934.8
"C",3933.57,3942.82,3942.87
"oneDNN 2.6 - Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",2805.2,3240.56,2875.03,2825.22,2816.65,2785.59,2812.6,2797.34,2813.62,2805.06,2779.45,2807.2,2837.55,2803.03,2825.76
"B",2809.04,2784.89,2812.31
"C",2987.39,2780.83,2784.05,2802.18,2803.04,2820.58,2826.48,2787.26
"oneDNN 2.6 - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",3943.48,4038.78,3938.76
"B",3944.7,3939.07,3942.05
"C",3932.42,3940.98,3950.35
"oneDNN 2.6 - Harness: Convolution Batch Shapes Auto - 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: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",
"oneDNN 2.6 - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",2826.48,2799.96,2821.12
"B",2829.95,2820.74,2808.6
"C",2794.25,2796.56,2813.04
"oneDNN 2.6 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU",
Lower Results Are Better
"A",6.3163,6.33737,6.32829
"B",6.30226,6.30448,6.30938
"C",6.27325,6.25899,6.25969
"oneDNN 2.6 - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",3929.64,3949.48,3942.54
"B",3921.79,3937.28,3919.14
"C",3935.6,3937.23,3932.47
"oneDNN 2.6 - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",2787.17,2799.87,2813.69
"B",2806.69,2830.38,2812.28
"C",2800.85,2799.84,2802.84
"oneDNN 2.6 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU",
Lower Results Are Better
"A",3.03288,2.37471,2.37869,2.3846,2.37747,2.38099,2.36319,2.40075,2.36685,2.38463,2.39552,2.36968,2.35991,2.38794
"B",2.36392,2.37461,2.37255
"C",2.35835,2.38327,2.35888
"oneDNN 2.6 - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU",
Lower Results Are Better
"A",
"B",
"C",