Geekbench ML Score

6095
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 17 2024 05:53 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 10 IoT Enterprise LTSC (64-bit)
Model HONOR HYM-WXX
Motherboard HONOR HYM-WXX-PCB
Power PlanBalanced
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 DirectML
Device NVIDIA GeForce RTX 3050 Laptop GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3362
629.1 IPS
 
Image Classification (F16)
100% 3354
627.6 IPS
 
Image Classification (I8)
100% 2664
498.6 IPS
 
Image Segmentation (F32)
100% 3836
64.1 IPS
 
Image Segmentation (F16)
100% 3841
64.2 IPS
 
Image Segmentation (I8)
98% 3274
54.7 IPS
 
Pose Estimation (F32)
100% 31422
38.1 IPS
 
Pose Estimation (F16)
100% 31004
37.5 IPS
 
Pose Estimation (I8)
100% 23638
28.6 IPS
 
Object Detection (F32)
100% 2540
189.6 IPS
 
Object Detection (F16)
100% 2245
167.6 IPS
 
Object Detection (I8)
61% 2405
179.6 IPS
 
Face Detection (F32)
100% 7871
93.6 IPS
 
Face Detection (F16)
100% 7893
93.8 IPS
 
Face Detection (I8)
89% 6238
74.2 IPS
 
Depth Estimation (F32)
100% 17617
136.6 IPS
 
Depth Estimation (F16)
100% 17630
136.7 IPS
 
Depth Estimation (I8)
95% 13770
106.8 IPS
 
Style Transfer (F32)
100% 51211
67.4 IPS
 
Style Transfer (F16)
100% 53533
70.4 IPS
 
Style Transfer (I8)
98% 48001
63.1 IPS
 
Image Super-Resolution (F32)
100% 8722
311.5 IPS
 
Image Super-Resolution (F16)
100% 8663
309.4 IPS
 
Image Super-Resolution (I8)
99% 5565
198.7 IPS
 
Text Classification (F32)
100% 1306
1.88 KIPS
 
Text Classification (F16)
100% 1302
1.87 KIPS
 
Text Classification (I8)
98% 981
1.41 KIPS
 
Machine Translation (F32)
100% 2083
38.3 IPS
 
Machine Translation (F16)
100% 2163
39.8 IPS
 
Machine Translation (I8)
70% 1125
20.7 IPS
 

Compare

Set Baseline Geekbench 6 now available