Geekbench ML Score

2781
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 23 2024 09:23 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model ASUS System Product Name
Motherboard ASUSTeK COMPUTER INC. ROG STRIX B550-F GAMING
Power PlanBalanced
CPU Information
Name AMD Ryzen 7 5700G
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 25 Model 80 Stepping 0
Base Frequency 3.80 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 DirectML
Device AMD Radeon(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1278
239.2 IPS
 
Image Classification (F16)
100% 1276
238.7 IPS
 
Image Classification (I8)
99% 1050
196.5 IPS
 
Image Segmentation (F32)
100% 1392
23.3 IPS
 
Image Segmentation (F16)
100% 1386
23.1 IPS
 
Image Segmentation (I8)
98% 1182
19.7 IPS
 
Pose Estimation (F32)
100% 12322
14.9 IPS
 
Pose Estimation (F16)
100% 12319
14.9 IPS
 
Pose Estimation (I8)
100% 10103
12.2 IPS
 
Object Detection (F32)
100% 1204
89.9 IPS
 
Object Detection (F16)
100% 1231
91.9 IPS
 
Object Detection (I8)
67% 1037
77.4 IPS
 
Face Detection (F32)
100% 2535
30.1 IPS
 
Face Detection (F16)
100% 2615
31.1 IPS
 
Face Detection (I8)
89% 2013
23.9 IPS
 
Depth Estimation (F32)
100% 6812
52.8 IPS
 
Depth Estimation (F16)
100% 6953
53.9 IPS
 
Depth Estimation (I8)
94% 5295
41.1 IPS
 
Style Transfer (F32)
100% 21825
28.7 IPS
 
Style Transfer (F16)
100% 21754
28.6 IPS
 
Style Transfer (I8)
98% 16935
22.3 IPS
 
Image Super-Resolution (F32)
100% 4419
157.8 IPS
 
Image Super-Resolution (F16)
100% 4495
160.5 IPS
 
Image Super-Resolution (I8)
99% 3052
109.0 IPS
 
Text Classification (F32)
100% 966
1.39 KIPS
 
Text Classification (F16)
100% 960
1.38 KIPS
 
Text Classification (I8)
98% 653
939.0 IPS
 
Machine Translation (F32)
100% 1675
30.8 IPS
 
Machine Translation (F16)
100% 1685
31.0 IPS
 
Machine Translation (I8)
69% 833
15.3 IPS
 

Compare

Set Baseline Geekbench 6 now available