Geekbench ML Score

1917
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AArch64

Result Information

Upload Date August 17 2024 03:31 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model SAMSUNG ELECTRONICS CO., LTD. Galaxy Book4 Edge
Motherboard SAMSUNG ELECTRONICS CO., LTD. NP960XMB-KB1US
Power PlanBalanced
CPU Information
Name Snapdragon(R) X Elite - X1E84100 - Qualcomm(R) Oryon(TM) CPU
Topology 1 Processor, 12 Cores
Identifier ARMv8 (64-bit) Family 8 Model 1 Revision 201
Base Frequency 3.80 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Snapdragon(R) X Elite - X1E84100 - Qualcomm(R) Adreno(TM) GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1037
194.1 IPS
 
Image Classification (F16)
100% 1103
206.4 IPS
 
Image Classification (I8)
100% 914
171.1 IPS
 
Image Segmentation (F32)
100% 1130
18.9 IPS
 
Image Segmentation (F16)
100% 1369
22.9 IPS
 
Image Segmentation (I8)
98% 1161
19.4 IPS
 
Pose Estimation (F32)
100% 6644
8.05 IPS
 
Pose Estimation (F16)
100% 6926
8.39 IPS
 
Pose Estimation (I8)
100% 5763
6.98 IPS
 
Object Detection (F32)
100% 959
71.6 IPS
 
Object Detection (F16)
100% 1006
75.1 IPS
 
Object Detection (I8)
71% 856
63.9 IPS
 
Face Detection (F32)
100% 1805
21.5 IPS
 
Face Detection (F16)
100% 1796
21.4 IPS
 
Face Detection (I8)
93% 1563
18.6 IPS
 
Depth Estimation (F32)
100% 4926
38.2 IPS
 
Depth Estimation (F16)
100% 5141
39.9 IPS
 
Depth Estimation (I8)
94% 4083
31.7 IPS
 
Style Transfer (F32)
100% 12742
16.8 IPS
 
Style Transfer (F16)
100% 12042
15.8 IPS
 
Style Transfer (I8)
98% 11316
14.9 IPS
 
Image Super-Resolution (F32)
100% 4017
143.5 IPS
 
Image Super-Resolution (F16)
100% 3688
131.7 IPS
 
Image Super-Resolution (I8)
99% 3299
117.8 IPS
 
Text Classification (F32)
100% 309
444.1 IPS
 
Text Classification (F16)
100% 328
470.9 IPS
 
Text Classification (I8)
98% 260
373.4 IPS
 
Machine Translation (F32)
100% 986
18.1 IPS
 
Machine Translation (F16)
100% 992
18.3 IPS
 
Machine Translation (I8)
65% 641
11.8 IPS
 

Compare

Set Baseline Geekbench 6 now available