Geekbench ML Score

3231
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 18 2024 05:37 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model ASUSTeK COMPUTER INC. ASUS Zenbook S 16 UM5606WA_UM5606WA
Motherboard ASUSTeK COMPUTER INC. UM5606WA
Power PlanEquilibrado
CPU Information
Name AMD Ryzen AI 9 HX 370 w/ Radeon 890M
Topology 1 Processor, 12 Cores, 24 Threads
Identifier AuthenticAMD Family 26 Model 36 Stepping 0
Base Frequency 2.00 GHz
Cluster 14 Cores
Cluster 28 Cores
L1 Instruction Cache32.0 KB x 12
L1 Data Cache48.0 KB x 12
L2 Cache1.00 MB x 12
L3 Cache5.33 MB x 3
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend CPU
Device Default

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% 3484
652.0 IPS
 
Image Segmentation (F32)
100% 872
14.6 IPS
 
Image Segmentation (F16)
100% 887
14.8 IPS
 
Image Segmentation (I8)
98% 2561
42.8 IPS
 
Pose Estimation (F32)
100% 6183
7.49 IPS
 
Pose Estimation (F16)
100% 6591
7.98 IPS
 
Pose Estimation (I8)
100% 23245
28.1 IPS
 
Object Detection (F32)
100% 1456
108.7 IPS
 
Object Detection (F16)
100% 1421
106.1 IPS
 
Object Detection (I8)
62% 1397
104.3 IPS
 
Face Detection (F32)
100% 3025
36.0 IPS
 
Face Detection (F16)
100% 3071
36.5 IPS
 
Face Detection (I8)
89% 4883
58.1 IPS
 
Depth Estimation (F32)
100% 6104
47.3 IPS
 
Depth Estimation (F16)
100% 5561
43.1 IPS
 
Depth Estimation (I8)
96% 14562
112.9 IPS
 
Style Transfer (F32)
100% 14532
19.1 IPS
 
Style Transfer (F16)
100% 14304
18.8 IPS
 
Style Transfer (I8)
98% 26384
34.7 IPS
 
Image Super-Resolution (F32)
100% 2511
89.7 IPS
 
Image Super-Resolution (F16)
100% 2589
92.5 IPS
 
Image Super-Resolution (I8)
99% 3930
140.4 IPS
 
Text Classification (F32)
100% 1302
1.87 KIPS
 
Text Classification (F16)
100% 1175
1.69 KIPS
 
Text Classification (I8)
98% 1089
1.57 KIPS
 
Machine Translation (F32)
100% 2066
38.0 IPS
 
Machine Translation (F16)
100% 2096
38.6 IPS
 
Machine Translation (I8)
67% 2754
50.7 IPS
 

Compare

Set Baseline Geekbench 6 now available