Geekbench ML Score

9009
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 16 2024 03:49 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model LENOVO 82JQ
Motherboard LENOVO LNVNB161216
Power PlanLegion Performance Mode
CPU Information
Name AMD Ryzen 7 5800H
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 25 Model 80 Stepping 0
Base Frequency 3.20 GHz
Cluster 18 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache32.0 KB x 8
L2 Cache512 KB x 8
L3 Cache16.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 3060 Laptop GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4955
927.3 IPS
 
Image Classification (F16)
100% 4961
928.3 IPS
 
Image Classification (I8)
100% 3752
702.1 IPS
 
Image Segmentation (F32)
100% 6080
101.5 IPS
 
Image Segmentation (F16)
100% 6127
102.3 IPS
 
Image Segmentation (I8)
98% 4950
82.7 IPS
 
Pose Estimation (F32)
100% 54158
65.6 IPS
 
Pose Estimation (F16)
100% 54672
66.2 IPS
 
Pose Estimation (I8)
100% 53643
65.0 IPS
 
Object Detection (F32)
100% 3122
233.1 IPS
 
Object Detection (F16)
100% 3580
267.3 IPS
 
Object Detection (I8)
63% 2705
201.9 IPS
 
Face Detection (F32)
100% 12380
147.2 IPS
 
Face Detection (F16)
100% 12500
148.6 IPS
 
Face Detection (I8)
89% 9963
118.5 IPS
 
Depth Estimation (F32)
100% 24574
190.6 IPS
 
Depth Estimation (F16)
100% 30592
237.2 IPS
 
Depth Estimation (I8)
94% 18541
143.8 IPS
 
Style Transfer (F32)
100% 87528
115.1 IPS
 
Style Transfer (F16)
100% 89709
118.0 IPS
 
Style Transfer (I8)
98% 73579
96.8 IPS
 
Image Super-Resolution (F32)
100% 15819
565.0 IPS
 
Image Super-Resolution (F16)
100% 15273
545.4 IPS
 
Image Super-Resolution (I8)
99% 10427
372.4 IPS
 
Text Classification (F32)
100% 1595
2.29 KIPS
 
Text Classification (F16)
100% 1700
2.44 KIPS
 
Text Classification (I8)
98% 943
1.36 KIPS
 
Machine Translation (F32)
100% 2315
42.6 IPS
 
Machine Translation (F16)
100% 2294
42.2 IPS
 
Machine Translation (I8)
70% 1262
23.2 IPS
 

Compare

Set Baseline Geekbench 6 now available