Geekbench ML Score

2935
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User chaton22
Upload Date August 16 2024 09:11 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Professionnel (64-bit)
Model SchenkerTechnologiesGmbH XMG APEX (Mid 2021)
Motherboard NB01 NHx0ERQ_EPS
Power PlanUtilisation normale
CPU Information
Name AMD Ryzen 9 5900HX
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 25 Model 80 Stepping 0
Base Frequency 3.30 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% 1585
296.6 IPS
 
Image Classification (F16)
100% 1514
283.3 IPS
 
Image Classification (I8)
97% 3266
611.2 IPS
 
Image Segmentation (F32)
100% 1384
23.1 IPS
 
Image Segmentation (F16)
100% 1425
23.8 IPS
 
Image Segmentation (I8)
97% 2489
41.6 IPS
 
Pose Estimation (F32)
100% 5013
6.07 IPS
 
Pose Estimation (F16)
100% 5098
6.17 IPS
 
Pose Estimation (I8)
100% 11581
14.0 IPS
 
Object Detection (F32)
100% 1444
107.8 IPS
 
Object Detection (F16)
100% 1491
111.3 IPS
 
Object Detection (I8)
60% 1626
121.4 IPS
 
Face Detection (F32)
100% 1919
22.8 IPS
 
Face Detection (F16)
100% 1925
22.9 IPS
 
Face Detection (I8)
87% 3479
41.4 IPS
 
Depth Estimation (F32)
100% 5942
46.1 IPS
 
Depth Estimation (F16)
100% 6092
47.2 IPS
 
Depth Estimation (I8)
74% 9401
72.9 IPS
 
Style Transfer (F32)
100% 11909
15.7 IPS
 
Style Transfer (F16)
100% 11468
15.1 IPS
 
Style Transfer (I8)
85% 13593
17.9 IPS
 
Image Super-Resolution (F32)
100% 2374
84.8 IPS
 
Image Super-Resolution (F16)
100% 2285
81.6 IPS
 
Image Super-Resolution (I8)
97% 2774
99.1 IPS
 
Text Classification (F32)
100% 1514
2.18 KIPS
 
Text Classification (F16)
100% 1607
2.31 KIPS
 
Text Classification (I8)
94% 1233
1.77 KIPS
 
Machine Translation (F32)
100% 1852
34.1 IPS
 
Machine Translation (F16)
100% 1836
33.8 IPS
 
Machine Translation (I8)
67% 2158
39.7 IPS
 

Compare

Set Baseline Geekbench 6 now available