Geekbench ML Score

5580
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 15 2024 05:06 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model Acer Swift SF14-51T
Motherboard LNL Icefish_LNV
Power PlanAcer
CPU Information
Name Intel(R) Core(TM) Ultra 7 258V
Topology 1 Processor, 8 Cores
Identifier GenuineIntel Family 6 Model 189 Stepping 1
Base Frequency 2.20 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache64.0 KB x 4
L1 Data Cache48.0 KB x 4
L2 Cache2.50 MB x 1
L3 Cache12.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) 140V GPU (16GB)

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3719
695.9 IPS
 
Image Classification (F16)
100% 3133
586.3 IPS
 
Image Classification (I8)
100% 3140
587.5 IPS
 
Image Segmentation (F32)
100% 6162
102.9 IPS
 
Image Segmentation (F16)
100% 6120
102.2 IPS
 
Image Segmentation (I8)
98% 4617
77.1 IPS
 
Pose Estimation (F32)
100% 20135
24.4 IPS
 
Pose Estimation (F16)
100% 19603
23.7 IPS
 
Pose Estimation (I8)
100% 17001
20.6 IPS
 
Object Detection (F32)
100% 2971
221.8 IPS
 
Object Detection (F16)
100% 3059
228.4 IPS
 
Object Detection (I8)
61% 2613
195.1 IPS
 
Face Detection (F32)
100% 8532
101.4 IPS
 
Face Detection (F16)
100% 8290
98.6 IPS
 
Face Detection (I8)
89% 6010
71.5 IPS
 
Depth Estimation (F32)
100% 17915
138.9 IPS
 
Depth Estimation (F16)
100% 19256
149.3 IPS
 
Depth Estimation (I8)
94% 14437
112.0 IPS
 
Style Transfer (F32)
100% 50151
66.0 IPS
 
Style Transfer (F16)
100% 49263
64.8 IPS
 
Style Transfer (I8)
98% 39055
51.4 IPS
 
Image Super-Resolution (F32)
100% 7756
277.0 IPS
 
Image Super-Resolution (F16)
100% 7111
253.9 IPS
 
Image Super-Resolution (I8)
99% 5360
191.4 IPS
 
Text Classification (F32)
100% 651
935.0 IPS
 
Text Classification (F16)
100% 655
941.1 IPS
 
Text Classification (I8)
98% 474
681.8 IPS
 
Machine Translation (F32)
100% 1501
27.6 IPS
 
Machine Translation (F16)
100% 1518
27.9 IPS
 
Machine Translation (I8)
70% 892
16.4 IPS
 

Compare

Set Baseline Geekbench 6 now available