Geekbench ML Score

2513
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User saiht
Upload Date August 18 2024 03:55 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model LENOVO 82JQ
Motherboard LENOVO LNVNB161216
Power PlanLegion Balance 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 16.00 GB
Inference Information
Framework ONNX
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1608
301.0 IPS
 
Image Classification (F16)
100% 1569
293.6 IPS
 
Image Classification (I8)
97% 2929
548.0 IPS
 
Image Segmentation (F32)
100% 1317
22.0 IPS
 
Image Segmentation (F16)
100% 1344
22.4 IPS
 
Image Segmentation (I8)
97% 1807
30.2 IPS
 
Pose Estimation (F32)
100% 3985
4.83 IPS
 
Pose Estimation (F16)
100% 3976
4.82 IPS
 
Pose Estimation (I8)
100% 9566
11.6 IPS
 
Object Detection (F32)
100% 1328
99.1 IPS
 
Object Detection (F16)
100% 1476
110.2 IPS
 
Object Detection (I8)
60% 1424
106.3 IPS
 
Face Detection (F32)
100% 1446
17.2 IPS
 
Face Detection (F16)
100% 1450
17.2 IPS
 
Face Detection (I8)
87% 2786
33.1 IPS
 
Depth Estimation (F32)
100% 5292
41.0 IPS
 
Depth Estimation (F16)
100% 5382
41.7 IPS
 
Depth Estimation (I8)
74% 8938
69.3 IPS
 
Style Transfer (F32)
100% 11276
14.8 IPS
 
Style Transfer (F16)
100% 11385
15.0 IPS
 
Style Transfer (I8)
85% 11538
15.2 IPS
 
Image Super-Resolution (F32)
100% 2350
83.9 IPS
 
Image Super-Resolution (F16)
100% 2303
82.3 IPS
 
Image Super-Resolution (I8)
97% 2603
92.9 IPS
 
Text Classification (F32)
100% 1452
2.09 KIPS
 
Text Classification (F16)
100% 1448
2.08 KIPS
 
Text Classification (I8)
94% 340
489.3 IPS
 
Machine Translation (F32)
100% 1615
29.7 IPS
 
Machine Translation (F16)
100% 1613
29.7 IPS
 
Machine Translation (I8)
67% 1771
32.6 IPS
 

Compare

Set Baseline Geekbench 6 now available