Geekbench ML Score

1408
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User paisarn
Upload Date September 01 2024 11:56 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 10 Home Single Language (64-bit)
Model ASUSTeK COMPUTER INC. ASUS TUF Gaming A15 FA506II_FA506II
Motherboard ASUSTeK COMPUTER INC. FA506II
Power PlanASUS Recommended
CPU Information
Name AMD Ryzen 5 4600H
Topology 1 Processor, 6 Cores, 12 Threads
Identifier AuthenticAMD Family 23 Model 96 Stepping 1
Base Frequency 3.00 GHz
Cluster 16 Cores
L1 Instruction Cache32.0 KB x 6
L1 Data Cache32.0 KB x 6
L2 Cache512 KB x 6
L3 Cache4.00 MB x 2
Memory Information
Size 8.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 535
100.1 IPS
 
Image Classification (F16)
100% 534
99.9 IPS
 
Image Classification (I8)
100% 470
88.0 IPS
 
Image Segmentation (F32)
100% 672
11.2 IPS
 
Image Segmentation (F16)
100% 662
11.1 IPS
 
Image Segmentation (I8)
98% 588
9.82 IPS
 
Pose Estimation (F32)
100% 6973
8.44 IPS
 
Pose Estimation (F16)
100% 6965
8.43 IPS
 
Pose Estimation (I8)
100% 5560
6.73 IPS
 
Object Detection (F32)
100% 549
41.0 IPS
 
Object Detection (F16)
100% 552
41.2 IPS
 
Object Detection (I8)
64% 494
36.9 IPS
 
Face Detection (F32)
100% 1053
12.5 IPS
 
Face Detection (F16)
100% 1053
12.5 IPS
 
Face Detection (I8)
89% 871
10.4 IPS
 
Depth Estimation (F32)
100% 3008
23.3 IPS
 
Depth Estimation (F16)
100% 3001
23.3 IPS
 
Depth Estimation (I8)
95% 2457
19.1 IPS
 
Style Transfer (F32)
100% 12397
16.3 IPS
 
Style Transfer (F16)
100% 12312
16.2 IPS
 
Style Transfer (I8)
98% 9245
12.2 IPS
 
Image Super-Resolution (F32)
100% 2851
101.8 IPS
 
Image Super-Resolution (F16)
100% 2828
101.0 IPS
 
Image Super-Resolution (I8)
99% 1828
65.3 IPS
 
Text Classification (F32)
100% 591
849.9 IPS
 
Text Classification (F16)
100% 587
844.0 IPS
 
Text Classification (I8)
98% 397
571.2 IPS
 
Machine Translation (F32)
100% 856
15.8 IPS
 
Machine Translation (F16)
100% 852
15.7 IPS
 
Machine Translation (I8)
69% 457
8.41 IPS
 

Compare

Set Baseline Geekbench 6 now available